# Research Papers — 2026-04 · bundle page 90 of 233 > Full-text markdown of papers #4451–4500 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/90 [← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/89.md) [Next bundle →](https://aipod.dev/papers/archive/2026-04/page/91.md) ### Adaptive Computation Depth via Learned Token Routing in Transformers Authors: Ahmed Abdelmuniem Abdalla Mohammed Published: 2026-04-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.05222v1 Standard transformer architectures apply the same number of layers to every token regardless of contextual difficulty. We present Token-Selective Attention (TSA), a learned per-token gate on residual updates between consecutive transformer blocks. Each gate is a lightweight two-layer multi-layer perceptron (MLP) that produces a continuous halting probability, making the mechanism end-to-end differentiable with 1.7% parameter overhead and no changes to the base architecture. Notably, TSA learns difficulty-proportional routing without any explicit depth pressure: even at $λ=0$ (no depth regularisation), the task-loss gradient alone drives the router to skip 20% of token-layer operations. On character-level language modeling, TSA saved 14-23% of token-layer operations (TLOps) across Tiny-Shakespeare and enwik8 at <0.5% quality loss. At matched efficiency, TSA achieved 0.7% lower validation loss than early exit, and the learned routing transfers directly to inference-time sparse execution for real wall-clock speedup. --- ### TimeRFT: Stimulating Generalizable Time Series Forecasting for TSFMs via Reinforcement Finetuning Authors: Siyang Li, Yize Chen, Zijie Zhu, Yuxin Pan, Yan Guo, Ming Huang, Hui Xiong Published: 2026-04-18 Categories: eess.SP, cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2605.00015v2 Time Series Foundation Models (TSFMs) have demonstrated strong generalization capability and data efficiency in time series forecasting through large-scale pretraining. However, adapting TSFMs to downstream forecasting tasks remains challenging due to temporal distribution shifts and varying data availability. Specifically, the non-stationary and uncertain nature of time series data leads to discrepancies between historical training and future forecasting distributions, making existing Supervised FineTuning (SFT)-based adaptation vulnerable to overfitting and limited generalization. Moreover, forecasting tasks often operate under varying data regimes, requiring TSFMs to extract generalizable temporal patterns from limited training samples. To address these challenges, we propose Time series Reinforcement FineTuning (TimeRFT), a reinforcement learning-based adaptation paradigm for TSFMs. TimeRFT introduces two forecasting-oriented training recipes: (i) A quality-aware temporal reward mechanism providing fine-grained credit assignment by holistically evaluating the contribution of each prediction step to overall forecasting performance. (ii) A difficulty-aware data selection strategy prioritizing informative time series samples with generalizable forecasting patterns. Extensive experiments on diverse real-world forecasting benchmarks demonstrate that TimeRFT consistently surpasses SFT-based adaptation methods across various real-world forecasting tasks with different data regimes, achieving improved prediction accuracy and enhanced generalization against unforeseen distribution shifts. --- ### PivotMerge: Bridging Heterogeneous Multimodal Pre-training via Post-Alignment Model Merging Authors: Zibo Shao, Baochen Xiong, Xiaoshan Yang, Yaguang Song, Qimeng Zhang, Haifeng Chen, Changsheng Xu Published: 2026-04-18 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.22823v2 Multimodal Large Language Models (MLLMs) rely on multimodal pre-training over diverse data sources, where different datasets often induce complementary cross-modal alignment capabilities. Model merging provides a cost-effective mechanism for integrating multiple expert MLLMs with complementary strengths into a unified model. However, existing model merging research mainly focuses on post-finetuning scenarios, leaving the pre-training stage largely unexplored. We argue that the core of MLLM pre-training lies in establishing effective cross-modal alignment, which bridges visual and textual representations into a unified semantic space. Motivated by this insight, we introduce the post-alignment merging task, which aims to integrate cross-modal alignment capabilities learned from heterogeneous multimodal pre-training. This setting introduces two key challenges: cross-domain parameter interference, where parameter updates learned from different data distributions conflict during merging, and layer-wise alignment contribution disparity, where different layers and projectors contribute unevenly to cross-modal alignment. To address them, we propose \textbf{PivotMerge}, a post-alignment merging framework for cross-modal projectors. PivotMerge incorporates two key components: Shared-space Decomposition and Filtering, which disentangles shared alignment patterns from domain-specific variations and suppresses conflicting directions, and Alignment-guided Layer-wise Merging, which assigns layer-specific merging weights based on differing alignment contributions. We construct systematic CC12M-based post-alignment merging scenarios for evaluation. Extensive experiments on multiple multimodal benchmarks show that PivotMerge consistently outperforms existing baselines, demonstrating its effectiveness and generalization ability. --- ### DO-Bench: An Attributable Benchmark for Diagnosing Object Hallucination in Vision-Language Models Authors: JiYang Wang, Jiawei Chen, Mengqi Xiao, Yu Cheng, Yangfu Li, Zhaoxia Yin Published: 2026-04-18 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.22822v1 Object level hallucination remains a central reliability challenge for vision language models (VLMs), particularly in binary object existence verification. Existing benchmarks emphasize aggregate accuracy but rarely disentangle whether errors stem from perceptual limitations or from the influence of contextual textual priors, leaving underlying failure mechanisms ambiguous. We introduce DO-Bench, a controlled diagnostic benchmark that isolates these sources through structured multimodal interventions. Rather than evaluating models in unconstrained settings, DO-Bench probes two complementary dimensions: the Prior Override dimension progressively strengthens contextual textual priors while holding visual evidence constant to assess resistance to prior pressure, and the Perception-Limited dimension incrementally enhances visual evidence from full-scene context to localized object crops to measure perceptual grounding strength. This paired design enables attribution of errors to prior suppression, perceptual insufficiency, or their interaction. We further define two diagnostic metrics, PriorRobust and PerceptionAbility, to quantify these behaviors consistently. Evaluations across diverse open- and closed-source VLMs reveal systematic differences in prior sensitivity and perceptual reliability, demonstrating that object hallucination reflects heterogeneous, mechanism dependent failure patterns beyond aggregate accuracy. --- ### Emergence Transformer: Dynamical Temporal Attention Matters Authors: Zihan Zhou, Bo-Wei Qin, Kai Du, Wei Lin Published: 2026-04-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.19816v1 The Transformer, a breakthrough architecture in artificial intelligence, owes its success to the attention mechanism, which utilizes long-range interactions in sequential data, enabling the emergent coherence between large language models (LLMs) and data distributions. However, temporal attention, that is, different forms of long-range interactions in temporal sequences, has rarely been explored in emergence phenomenon of complex systems including oscillatory coherence in quantum, biophysical, or climate systems. Here, by designing dynamical temporal attention (DTA) with time-varying query, key, and value matrices, we propose an Emergence Transformer. This architecture allows each component to interact with its own or its neighbors' past states through dynamical attention kernels, thereby enabling the promotion and/or suppression of the emergent coherence of components. Interestingly, we uncover that neighbor-DTA consistently promotes oscillatory coherence, whereas self-DTA exhibits an optimal attention weight for coherence enhancement, owing to its non-monotonic dependence on network structure. Practically, we demonstrate how DTA reshapes social coherence, suggesting strategies to either enhance agreement or preserve plurality. We further apply DTA to the paradigmatic Hopfield neural network, achieving emergent continual learning without catastrophic forgetting. Together, these results lay a foundation and provide an immediate paradigm for modulating emergence phenomenon in networked dynamics only using DTA. --- ### StomaD2: An All-in-One System for Intelligent Stomatal Phenotype Analysis via Diffusion-Based Restoration Detection Network Authors: Quanling Zhao, Meng'en Qin, Yanfeng Sun, Yuan Miao, Xiaohui Yang Published: 2026-04-18 Categories: cs.CV, stat.AP arXiv: https://arxiv.org/abs/2604.18632v1 Stomata play a crucial role in regulating plant physiological processes and reflecting environmental responses. However, accurate and high-throughput stomatal phenotyping remains challenging, as conventional approaches rely on destructive sampling and manual annotation, restricting large-scale and field deployment. To overcome these limitations, a noninvasive restoration-detection integrated framework, termed StomaD2, is developed to achieve accurate and fast stomatal phenotyping under complex imaging conditions. The framework incorporates a diffusion-based restoration module to recover degraded images and a specialized rotated object detection network tailored to the small, dense, and cluttered characteristics of stomata. The proposed network enhances feature representation through three key innovations: a column-wise structure for global feature interaction, context-aware resampling and reweighting mechanism to improve multi-scale consistency, and a feature reassembly module to boost discrimination against complex backgrounds. In extensive comparisons, StomaD2 demonstrated state-of-the-art performance. On public Maize and Wheat datasets, it achieved accuracies of 0.994 and 0.992, respectively, significantly outperforming existing benchmarks. When benchmarked against ten other advanced models, including Oriented Former and YOLOv12, StomaD2 achieved a top-tier F1-score/mAP of 0.989. The framework is integrated into a user-friendly, field-operable system that supports the fast extraction of eight stomatal phenotypes, such as density and conductance. Validated on more than 130 plant species, StomaD2's results highlight its strong generalizability and potential for large-scale phenotyping, plant physiology analysis, and precision agriculture applications. --- ### Vision-Based Human Awareness Estimation for Enhanced Safety and Efficiency of AMRs in Industrial Warehouses Authors: Maximilian Haug, Christian Stippel, Lukas Pscherer, Benjamin Schwendinger, Ralph Hoch, Angel Gaydarov, Sebastian Schlund, Thilo Sauter Published: 2026-04-18 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2604.18627v1 Ensuring human safety is of paramount importance in warehouse environments that feature mixed traffic of human workers and autonomous mobile robots (AMRs). Current approaches often treat humans as generic dynamic obstacles, leading to conservative AMR behaviors like slowing down or detouring, even when workers are fully aware and capable of safely sharing space. This paper presents a real-time vision-based method to estimate human awareness of an AMR using a single RGB camera. We integrate state-of-the-art 3D human pose lifting with head orientation estimation to ascertain a human's position relative to the AMR and their viewing cone, thereby determining if the human is aware of the AMR. The entire pipeline is validated using synthetically generated data within NVIDIA Isaac Sim, a robust physics-accurate robotics simulation environment. Experimental results confirm that our system reliably detects human positions and their attention in real time, enabling AMRs to safely adapt their motion based on human awareness. This enhancement is crucial for improving both safety and operational efficiency in industrial and factory automation settings. --- ### Can We Build Scene Graphs, Not Classify Them? FlowSG: Progressive Image-Conditioned Scene Graph Generation with Flow Matching Authors: Xin Hu, Ke Qin, Wen Yin, Yuan-Fang Li, Ming Li, Tao He Published: 2026-04-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.18623v1 Scene Graph Generation (SGG) unifies object localization and visual relationship reasoning by predicting boxes and subject-predicate-object triples. Yet most pipelines treat SGG as a one-shot, deterministic classification problem rather than a genuinely progressive, generative task. We propose FlowSG, which recasts SGG as continuous-time transport on a hybrid discrete-continuous state: starting from a noised graph, the model progressively grows an image-conditioned scene graph through constraint-aware refinements that jointly synthesize nodes (objects) and edges (predicates). Specifically, we first leverage a VQ-VAE to quantize a scene graph (e.g., continuous visual features) into compact, predictable tokens; a graph Transformer then (i) predicts a conditional velocity field to transport continuous geometry (boxes) and (ii) updates discrete posteriors for categorical tokens (object features and predicate labels), coupling semantics and geometry via flow-conditioned message aggregation. Training combines flow-matching losses for geometry with a discrete-flow objective for tokens, yielding few-step inference and plug-and-play compatibility with standard detectors and segmenters. Extensive experiments on VG and PSG under closed- and open-vocabulary protocols show consistent gains in predicate R/mR and graph-level metrics, validating the mixed discrete-continuous generative formulation over one-shot classification baselines, with an average improvement of about 3 points over the state-of-the-art USG-Par. --- ### Quantum AI for Cancer Diagnostic Biomarker Discovery Authors: Mandeep Kaur Saggi, Amandeep Singh Bhatia, Humaira Gowher, Sabre Kais Published: 2026-04-18 Categories: q-bio.GN, cs.LG arXiv: https://arxiv.org/abs/2604.18621v1 Quantum machine learning offers a promising new paradigm for computational biology by leveraging quantum mechanical principles to enhance cancer classification, biomarker discovery, and bioinformatics diagnostics. In this study, we apply QML to identify subtype specific biomarkers for lung adenocarcinoma (LUAD) and lung squamous cell carcinoma (LUSC), the two predominant forms of non-small cell lung cancer. Our methodology involves a two-phase process: in Phase 1, differential expression analysis and methylation analysis between tumor and normal samples allows us to identify LUAD-specific and LUSC-specific genes, revealing potential prognostic biomarkers for cancer subtypes. Phase 2 focuses on developing a quantum classifier capable of distinguishing between LUAD and LUSC tumors, as well as between tumor and normal samples. This classifier not only enhances diagnostic precision but also demonstrates the quantum advantage in processing large-scale multiomic datasets. Our results consistently demonstrated that Sample3, representing the combined gene set, achieved the highest overall predictive performance in all metrics. These results demonstrate that QML provides an effective and scalable approach for biomarker discovery and subtype specific cancer classification. GO enrichment analysis highlighted the significant involvement of genes in synaptic signaling, ion channel regulation, and neuronal development. In the quantum phase, KEGG analysis further identified enrichment in cancer-associated pathways, including neurotrophin, MAPK, Ras, and PI3KAkt signaling, with key genes such as NGFR, NTRK2, and NTF3 suggesting a central role in neurotrophinmediated oncogenic processes. Our findings highlight the growing potential of quantum computing to advance precision oncology and next-generation biomedical analytics. --- ### The Virtue of Sparsity in Complexity Authors: Nima Afsharhajari, Jonathan Yu-Meng Li Published: 2026-04-18 Categories: q-fin.GN, cs.LG, econ.EM, q-fin.PM, q-fin.PR arXiv: https://arxiv.org/abs/2604.17166v2 Sparsity or complexity? In modern high-dimensional asset pricing, these are often viewed as competing principles: recent empirical evidence favors richer models, while economic intuition has long favored parsimony. We reconcile this tension by distinguishing capacity sparsity-restrictions on effective model capacity-from factor sparsity-the parsimonious structure of priced risks. Revisiting the benchmark empirical design of Didisheim et al. (2025), we combine nonlinear feature expansions with basis pursuit, using column generation and GPU acceleration to scale estimation to 432 million candidate factors. Reaching this scale reveals a reversal in out-of-sample performance: sparse portfolios trail dense ridgeless benchmarks at lower complexity but achieve a higher Sharpe ratio and lower pricing error at the largest candidate set. Capacity expansion and factor sparsity are therefore complements: enlarging the candidate space allows a parsimonious pricing kernel to outperform its dense counterpart. --- ### The Virtue of Sparsity in Complexity Authors: Nima Afsharhajari, Jonathan Yu-Meng Li Published: 2026-04-18 Categories: q-fin.GN, cs.LG, econ.EM, q-fin.PM, q-fin.PR arXiv: https://arxiv.org/abs/2604.17166v1 Sparsity or complexity? In modern high-dimensional asset pricing, these are often viewed as competing principles: richer feature spaces appear to favor complexity, while economic intuition has long favored parsimony. We show that this tension is misplaced. We distinguish capacity sparsity-the dimensionality of the candidate feature space-from factor sparsity-the parsimonious structure of priced risks-and argue that the two are complements: expanding capacity enables the discovery of factor sparsity. Revisiting the benchmark empirical design of Didisheim et al. (2025) and pushing it to higher complexity regimes, we show that nonlinear feature expansions combined with basis pursuit yield portfolios whose out-of-sample performance dominates ridgeless benchmarks beyond a critical complexity threshold. The evidence shows that the gains from complexity arise not from retaining more factors, but from enlarging the space from which a sparse structure of priced risks can be identified. The virtue of complexity in asset pricing operates through factor sparsity. --- ### PPEDCRF: Dynamic-CRF-Guided Selective Perturbation for Background-Based Location Privacy in Video Sequences Authors: Bo Ma, Weiqi Yan, Jinsong Wu Published: 2026-04-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.17163v1 We propose PPEDCRF, a calibrated selective perturbation framework that protects \emph{background-based location privacy} in released video frames against gallery-based retrieval attackers. Even after GPS metadata are stripped, an adversary can geolocate a frame by matching its background visual cues to geo-tagged reference imagery; PPEDCRF mitigates this threat by estimating location-sensitive background regions with a dynamic conditional random field (DCRF), rescaling perturbation strength with a normalized control penalty (NCP), and injecting Gaussian noise only inside the inferred regions via a DP-style calibration rule. On a controlled paired-scene retrieval benchmark with eight attacker backbones and three noise seeds, PPEDCRF reduces ResNet18 Top-1 retrieval accuracy from 0.667 to $0.361\pm0.127$ at $σ_0=8$ while preserving $36.14\,$dB PSNR -- an ${\approx}6\,$dB quality advantage over global Gaussian noise. Transfer across the eight-backbone seed-averaged benchmark is broadly supportive (23 of 24 backbone-gallery cells show negative $Δ$), while appendix-scale confirmation identifies MixVPR as a remaining adverse-transfer exception. Matched-operating-point analysis shows that PPEDCRF and global Gaussian noise converge in Top-1 privacy at equal utility, so the practical benefit is spatially concentrated perturbation that preserves higher visual quality at any given noise scale rather than stronger matched-utility privacy. Code: https://github.com/mabo1215/PPEDCRF --- ### Systematic Capability Benchmarking of Frontier Large Language Models for Offensive Cyber Tasks Authors: Tyler H. Merves, Michael H. Conaway, Joseph M. Escobar, Hakan T. Otal, Unal Tatar Published: 2026-04-18 Categories: cs.CR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.17159v1 We present, to our knowledge, the most comprehensive cross-model evaluation of LLM agents on offensive cybersecurity tasks, benchmarking 10 frontier models from 7 providers on all 200 challenges of the NYU CTF Bench. Building on the D-CIPHER multi-agent framework, we extend it with multi-provider backend support, a custom Kali Linux environment with over 100 pre-installed penetration testing tools, and runtime tool-discovery agents. Through a controlled factorial study, we find that the Kali Linux environment yields a +9.5 percentage-point improvement over Ubuntu, while auto-prompting and category-specific tips often degrade performance in well-equipped environments. Among models, Claude 4.5 Opus achieves the highest solve rate (59%), followed by Gemini 3 Pro (52%), with Gemini 3 Flash offering the best cost-efficiency at $0.05 per solve. Asymmetric planner/executor model assignments provide no meaningful benefit while coherent same-model configurations consistently outperform mixed-tier pairings. Our results indicate that environment tooling and model selection emerge as the strongest drivers of performance, whereas prompt engineering interventions show diminishing or negative returns in well-equipped environments. Reported performance reflects both model reasoning ability and compatibility with agent tooling and API integration. --- ### Lightweight Cybersickness Detection based on User-Specific Eye and Head Tracking Data in Virtual Reality Authors: Yijun Wang, Mihai Bâce, Maria Torres Vega Published: 2026-04-18 Categories: cs.HC, cs.LG arXiv: https://arxiv.org/abs/2604.17158v1 The occurrence of cybersickness in virtual reality (VR) significantly impairs users' perception and sense of immersion. Therefore, timely detection of cybersickness and the application of appropriate intervention strategies are crucial for enhancing the user experience. However, existing cybersickness detection methods often suffer from issues such as poor detection reliability across different levels of cybersickness and unnecessary model complexity. Furthermore, while cybersickness exhibits significant inter-user variability, most existing approaches aggregate all data from users and lack user-specific solutions. In this paper, we investigate a lightweight approach for cybersickness detection incorporating an ensemble learning model and user-specific eye and head tracking data. Our experiments using the open-source dataset Simulation 2021 demonstrate that feature engineering and training set construction are critical for determining detection performance. Models trained with data from similar-content segments achieve the best results, attaining detection accuracies of 93% in the cross-user setting and 88% in the user-personalized setting, using only 23-dimensional eye and head features. Moreover, by using user-specific data, well-tuned ensemble learning models with shorter training and inference times can be feasibly applied to real-world cybersickness detection, offering superior time efficiency and outstanding detection performance. This work offers useful evidence toward the development of lightweight and user-adaptive cybersickness detection models for VR applications. --- ### Uncertainty Quantification in PINNs for Turbulent Flows: Bayesian Inference and Repulsive Ensembles Authors: Khemraj Shukla, Zongren Zou, Theo Kaeufer, Michael Triantafyllou, George Em Karniadakis Published: 2026-04-18 Categories: cs.LG, physics.comp-ph arXiv: https://arxiv.org/abs/2604.17156v1 Physics-informed neural networks (PINNs) have emerged as a promising framework for solving inverse problems governed by partial differential equations (PDEs), including the reconstruction of turbulent flow fields from sparse data. However, most existing PINN formulations are deterministic and do not provide reliable quantification of epistemic uncertainty, which is critical for ill-posed problems such as data-driven Reynolds-averaged Navier-Stokes (RANS) modeling. In this work, we develop and systematically evaluate a set of probabilistic extensions of PINNs for uncertainty quantification in turbulence modeling. The proposed framework combines (i) Bayesian PINNs with Hamiltonian Monte Carlo sampling and a tempered multi-component likelihood, (ii) Monte Carlo dropout, and (iii) repulsive deep ensembles that enforce diversity in function space. Particular emphasis is placed on the role of ensemble diversity and likelihood tempering in improving uncertainty calibration for PDE-constrained inverse problems. The methods are assessed on a hierarchy of test cases, including the Van der Pol oscillator and turbulent flow past a circular cylinder at Reynolds numbers Re=3,900 (direct numerical simulation data) and Re = 10,000 (experimental particle image velocimetry data). The results demonstrate that Bayesian PINNs provide the most consistent uncertainty estimates across all inferred quantities, while function-space repulsive ensembles offer a computationally efficient approximation with competitive accuracy for primary flow variables. These findings provide quantitative insight into the trade-offs between accuracy, computational cost, and uncertainty calibration in physics-informed learning, and offer practical guidance for uncertainty quantification in data-driven turbulence modeling. --- ### Instant Colorization of Gaussian Splats Authors: Daniel Lieber, Alexander Mock, Nils Wandel Published: 2026-04-18 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2604.17155v1 Gaussian Splatting has recently become one of the most popular frameworks for photorealistic 3D scene reconstruction and rendering. While current rasterizers allow for efficient mappings of 3D Gaussian splats onto 2D camera views, this work focuses on mapping 2D image information (e.g. color, neural features or segmentation masks) efficiently back onto an existing scene of Gaussian splats. This 'opposite' direction enables applications ranging from scene relighting and stylization to 3D semantic segmentation, but also introduces challenges, such as view-dependent colorization and occlusion handling. Our approach tackles these challenges using the normal equation to solve a visibility-weighted least squares problem for every Gaussian and can be implemented efficiently with existing differentiable rasterizers. We demonstrate the effectiveness of our approach on scene relighting, feature enrichment and 3D semantic segmentation tasks, achieving up to an order of magnitude speedup compared to gradient descent-based baselines. --- ### From Legal Text to Executable Decision Models: Evaluating Structured Representations for Legal Decision Model Generation Authors: David Graus Published: 2026-04-18 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.17153v1 Transforming legal text into executable decision logic is a longstanding challenge in legal informatics. With the rise of LLMs, this task has gained renewed interest, but remains challenging due to requiring extensive manual coding and evaluation. We use a unique real-world dataset that pairs production-grade decision models with legal text from the Dutch Environment and Planning Act. These models power the Omgevingsloket government platform, where citizens check permit requirements for environmental activities. We study whether intermediate structured representations can improve LLM-based generation of executable decision models from legal text. We compare four input conditions: raw legal text, text enriched with semantic role labels, text enriched with input and output constraints, and text enriched with both. We evaluate along two dimensions: structural evaluation, through similarity to gold decision models with graph kernels and graphs' descriptive statistics, and outcome evaluation, through functional equivalence by executing models on pre-configured test scenarios. Our findings show that I/O constraints provide the dominant improvement (+37-54% similarity over baseline), while semantic role labels show modest improvements. Outcome evaluation shows that generated models match the gold standard on 51-53% of test scenarios, even though generated models are typically smaller and simpler. We find LLMs eliminate redundant pass-through logic that comprises up to 45-55% of nodes. Importantly, structural similarity and outcome equivalence are complementary: structural similarity does not guarantee outcome equivalence, and vice versa. To facilitate reproducibility, we publicly release our dataset of 95 production decision models with associated legal text and all experimental code. --- ### FlowRefiner: Flow Matching-Based Iterative Refinement for 3D Turbulent Flow Simulation Authors: Yilong Dai, Yiming Sun, Yiheng Chen, Shengyu Chen, Xiaowei Jia, Runlong Yu Published: 2026-04-18 Categories: physics.flu-dyn, cs.LG arXiv: https://arxiv.org/abs/2604.17149v2 Accurate autoregressive prediction of 3D turbulent flows remains challenging for neural PDE solvers, as small errors in fine-scale structures can accumulate rapidly over rollout. In this paper, we propose FlowRefiner, a flow matching-based iterative refinement framework for 3D turbulent flow simulation. The method replaces stochastic denoising refinement with deterministic ODE-based correction, uses a unified velocity-field regression objective across all refinement stages, and introduces a decoupled sigma schedule that fixes the noise range independently of refinement depth. These design choices yield stable and effective refinement in the small-noise regime. Experiments on large-scale 3D turbulence with rich multi-scale structures show that FlowRefiner achieves state-of-the-art autoregressive prediction accuracy and strong physical consistency. Although developed for turbulent flow simulation, the proposed framework is broadly applicable to iterative refinement problems in scientific modeling. --- ### Graph-of-Agents: A Graph-based Framework for Multi-Agent LLM Collaboration Authors: Sukwon Yun, Jie Peng, Pingzhi Li, Wendong Fan, Jie Chen, James Zou, Guohao Li, Tianlong Chen Published: 2026-04-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.17148v1 With an ever-growing zoo of LLMs and benchmarks, the need to orchestrate multiple models for improved task performance has never been more pressing. While frameworks like Mixture-of-Agents (MoA) attempt to coordinate LLMs, they often fall short in terms of (1) selecting relevant agents, (2) facilitating effective intra-agent communication, and (3) integrating responses efficiently. In this work, we propose Graph-of-Agents (GoA), a new graph-based framework for modeling multi-agent LLM communication. Our approach begins with node sampling, selecting only the most relevant agents by leveraging model cards that summarize each model's domain, task specialization, and other characteristics. Next, we construct edges between the selected agents by evaluating their responses against one another to determine relevance ordering. Directed message passing is then performed from highly relevant agents to less relevant ones to enhance their responses, followed by reverse message passing to refine the original responses of the more relevant agents. Finally, the updated responses are aggregated via graph-based pooling (e.g., max or mean pooling) to produce a single, unified answer. We evaluate GoA on diverse multi-domain benchmarks (MMLU, MMLU-Pro, GPQA) and domain-specific benchmarks (MATH, HumanEval, MedMCQA), with an agent pool of 6 LLMs spanning multiple domains. Surprisingly, GoA achieves superior performance using only 3 selected agents, outperforming recent multi-agent LLM baselines that utilize all 6 agents simultaneously. By adopting a graph structure, GoA offers both scalability and effectiveness through structured message passing-positioning it as a strong candidate for navigating the challenges of the ever-growing LLM zoo. Code is available at: https://github.com/UNITES-Lab/GoA. --- ### ScenarioControl: Vision-Language Controllable Vectorized Latent Scenario Generation Authors: Lili Gao, Yanbo Xu, William Koch, Samuele Ruffino, Luke Rowe, Behdad Chalaki, Dmitriy Rivkin, Julian Ost, Roger Girgis, Mario Bijelic, Felix Heide Published: 2026-04-18 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2604.17147v1 We introduce ScenarioControl, the first vision-language control mechanism for learned driving scenario generation. Given a text prompt or an input image, Scenario-Control synthesizes diverse, realistic 3D scenario rollouts - including map, 3D boxes of reactive actors over time, pedestrians, driving infrastructure, and ego camera observations. The method generates scenes in a vectorized latent space that represents road structure and dynamic agents jointly. To connect multimodal control with sparse vectorized scene elements, we propose a cross-global control mechanism that integrates crossattention with a lightweight global-context branch, enabling fine-grained control over road layout and traffic conditions while preserving realism. The method produces temporally consistent scenario rollouts from the perspectives different actors in the scene, supporting long-horizon continuation of driving scenarios. To facilitate training and evaluation, we release a dataset with text annotations aligned to vectorized map structures. Extensive experiments validate that the control adherence and fidelity of ScenarioControl compare favorable to all tested methods across all experiments. Project webpage: https://light.princeton.edu/ScenarioControl --- ### Negative Momentum for Convex-Concave Optimization Authors: Henry Shugart, Shuyi Wang, Jason M. Altschuler Published: 2026-04-18 Categories: math.OC, cs.DS, cs.LG arXiv: https://arxiv.org/abs/2604.17145v1 This paper revisits momentum in the context of min-max optimization. Momentum is a celebrated mechanism for accelerating gradient dynamics in settings like convex minimization, but its direct use in min-max optimization makes gradient dynamics diverge. Surprisingly, Gidel et al. 2019 showed that negative momentum can help fix convergence. However, despite these promising initial results and progress since, the power of momentum remains unclear for min-max optimization in two key ways. (1) Generality: is global convergence possible for the foundational setting of convex-concave optimization? This is the direct analog of convex minimization and is a standard testing ground for min-max algorithms. (2) Fast convergence: is accelerated convergence possible for strongly-convex-strong-concave optimization (the only non-linear setting where global convergence is known)? Recent work has even argued that this is impossible. We answer both these questions in the affirmative. Together, these results put negative momentum on more equal footing with competitor algorithms, and show that negative momentum enables convergence significantly faster and more generally than was known possible. --- ### SeekerGym: A Benchmark for Reliable Information Seeking Authors: Remy Kim, Minseung Lee, Shuo Li, Osbert Bastani Published: 2026-04-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.17143v1 Despite their substantial successes, AI agents continue to face fundamental challenges in terms of trustworthiness. Consider deep research agents, tasked with searching for information relevant to a given topic-while AI agents can perform effective information retrieval, there is little guarantee regarding the completeness of this information. Gaps in retrieved information can leave biases that mislead users even if the information they are given is correct and relevant. We introduce SeekerGym, a benchmark designed to evaluate the completeness of information retrieved by AI agents. In addition, SeekerGym also measures how well agents quantify their uncertainty in the completeness of their information; if an agent fails to retrieve all relevant information, it is useful for it to at least quantify how much might be missing. At a high level, each task in SeekerGym is a document (e.g., a Wikipedia article), and the AI agent must issue queries to retrieve passages from that document. Intuitively, the document comprehensively covers a topic, so the ability to retrieve its sections directly measures completeness of information retrieval. In addition to Wikipedia, we also consider machine learning survey papers, where the goal is to retrieve relevant sections of a survey paper. We benchmark several models and algorithms; the best approaches retrieve 42.5% of passages on Wikipedia and 29.2% on ML Surveys, leaving substantial room for improvement. --- ### SciImpact: A Multi-Dimensional, Multi-Field Benchmark for Scientific Impact Prediction Authors: Hangxiao Zhu, Yuyu Zhang, Ping Nie, Yu Zhang Published: 2026-04-18 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.17141v2 The rapid growth of scientific literature calls for automated methods to assess and predict research impact. Prior work has largely focused on citation-based metrics, leaving limited evaluation of models' capability to reason about other impact dimensions. To this end, we introduce SciImpact, a large-scale, multi-dimensional benchmark for scientific impact prediction spanning 19 fields. SciImpact captures various forms of scientific influence, ranging from citation counts to award recognition, media attention, patent reference, and artifact adoption, by integrating heterogeneous data sources and targeted web crawling. It comprises 215,928 contrastive paper pairs reflecting meaningful impact differences in both short-term (e.g., Best Paper Award) and long-term settings (e.g., Nobel Prize). We evaluate 11 widely used large language models (LLMs) on SciImpact. Results show that off-the-shelf models exhibit substantial variability across dimensions and fields, while multi-task supervised fine-tuning consistently enables smaller LLMs (e.g., 4B) to markedly outperform much larger models (e.g., 30B) and surpass powerful closed-source LLMs (e.g., o4-mini). These results establish SciImpact as a challenging benchmark and demonstrate its value for multi-dimensional, multi-field scientific impact prediction. Our project homepage is https://flypig23.github.io/sciimpact-homepage/ --- ### Local Inconsistency Resolution: The Interplay between Attention and Control in Probabilistic Models Authors: Oliver E. Richardson, Mandana Samiei, Mehran Shakerinava, Joseph D. Viviano, Abdessamad El Kabid, Ali Parviz, Yoshua Bengio Published: 2026-04-18 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.17140v1 We present a generic algorithm for learning and approximate inference with an intuitive epistemic interpretation: iteratively focus on a subset of the model and resolve inconsistencies using the parameters under control. This framework, which we call Local Inconsistency Resolution (LIR) is built upon Probabilistic Dependency Graphs (PDGs), which provide a flexible representational foundation capable of capturing inconsistent beliefs. We show how LIR unifies and generalizes a wide variety of important algorithms in the literature, including the Expectation-Maximization (EM) algorithm, belief propagation, adversarial training, GANs, and GFlowNets. In the last case, LIR actually suggests a more natural loss, which we demonstrate improves GFlowNet convergence. Each method can be recovered as a specific instance of LIR by choosing a procedure to direct focus (attention and control). We implement this algorithm for discrete PDGs and study its properties on synthetically generated PDGs, comparing its behavior to the global optimization semantics of the full PDG. --- ### The Consensus Trap: Rescuing Multi-Agent LLMs from Adversarial Majorities via Token-Level Collaboration Authors: Jiayuan Liu, Shiyi Du, Weihua Du, Mingyu Guo, Vincent Conitzer Published: 2026-04-18 Categories: cs.CL, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2604.17139v1 Multi-agent large language model (LLM) architectures increasingly rely on response-level aggregation, such as Majority Voting (MAJ), to raise reasoning ceilings. However, in open environments, agents are highly susceptible to stealthy contextual corruption, such as targeted prompt injections. We reveal a critical structural vulnerability in current multi-agent systems: response-level aggregation collapses when corrupted agents form a local majority. Because voting aggregates fully-formed conclusions, it is blind to flawed intermediate logic. To overcome this systematic limitation, we propose the Token-Level Round-Robin (RR) Collaboration, where agents sequentially interleave generation within a shared auto-regressive context. We formalize this process as a discrete-time dynamical system, proving that token-level interleaving transitions aggregation from a brittle counting of final votes (a linear sum) to a dynamic, interwoven chain of logic (a non-linear operator product). Through this theoretical lens, we prove that the honest model's restorative pull can overpower adversarial corruptions, even when corrupted agents form a majority. We conduct an exhaustive empirical evaluation across diverse reasoning benchmarks and demonstrate that while MAJ collapses when corrupted agents reach a majority, RR maintains robust accuracy well beyond this critical threshold. --- ### BOIL: Learning Environment Personalized Information Authors: Rohan Patil, Henrik I. Christensen Published: 2026-04-18 Categories: cs.LG, cs.RO arXiv: https://arxiv.org/abs/2604.17137v2 Navigating complex environments poses challenges for multi-agent systems, requiring efficient extraction of insights from limited information. In this paper, we introduce the Blackbox Oracle Information Learning (BOIL) process, a scalable solution for extracting valuable insights from the environment structure. Leveraging the Pagerank algorithm and common information maximization, BOIL facilitates the extraction of information to guide long-term agent behavior applicable to problems such as coverage, patrolling, and stochastic reachability. Through experiments, we demonstrate the efficacy of BOIL in generating strategy distributions conducive to improved performance over extended time horizons, surpassing heuristic approaches in complex environments. --- ### OptiMVMap: Offline Vectorized Map Construction via Optimal Multi-vehicle Perspectives Authors: Zedong Dan, Zijie Wang, Wei Zhang, Xiangru Lin, Weiming Zhang, Xiao Tan, Jingdong Wang, Liang Lin, Guanbin Li Published: 2026-04-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.17135v1 Offline vectorized maps constitute critical infrastructure for high-precision autonomous driving and mapping services. Existing approaches rely predominantly on single ego-vehicle trajectories, which fundamentally suffer from viewpoint insufficiency: while memory-based methods extend observation time by aggregating ego-trajectory frames, they lack the spatial diversity needed to reveal occluded regions. Incorporating views from surrounding vehicles offers complementary perspectives, yet naive fusion introduces three key challenges: computational cost from large candidate pools, redundancy from near-collinear viewpoints, and noise from pose errors and occlusion artifacts. We present OptiMVMap, which reformulates multi-vehicle mapping as a select-then-fuse problem to address these challenges systematically. An Optimal Vehicle Selection (OVS) module strategically identifies a compact subset of helpers that maximally reduce ego-centric uncertainty in occluded regions, addressing computation and redundancy challenges. Cross-Vehicle Attention (CVA) and Semantic-aware Noise Filter (SNF) then perform pose-tolerant alignment and artifact suppression before BEV-level fusion, addressing the noise challenge. This targeted pipeline yields more complete and topologically faithful maps with substantially fewer views than indiscriminate aggregation. On nuScenes and Argoverse2, OptiMVMap improves MapTRv2 by +10.5 mAP and +9.3 mAP, respectively, and surpasses memory-augmented baselines MVMap and HRMapNet by +6.2 mAP and +3.8 mAP on nuScenes. These results demonstrate that uncertainty-guided selection of helper vehicles is essential for efficient and accurate multi-vehicle vectorized mapping. The code is released at https://github.com/DanZeDong/OptiMVMap. --- ### RoIt-XMASA: Multi-Domain Multilingual Sentiment Analysis Dataset for Romanian and Italian Authors: Andrei-Marius Avram, Aureliu Valentin Antonie, Cosmin-Mircea Croitoru, Vlad Andrei Muntean, Dumitru-Clementin Cercel Published: 2026-04-18 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.17134v2 We present RoIt-XMASA, a multilingual dataset that extends the Cross-lingual Multi-domain Amazon Sentiment Analysis to Italian and Romanian, comprising 36,000 labeled reviews across three domains (books, movies, and music) and 202,141 unlabeled samples. To address cross-lingual and cross-domain challenges, we propose a multi-target adversarial training framework that employs loss reversal with meta-learned coefficients to dynamically balance sentiment discrimination with domain and language invariance. XLM-R achieves an F1-score of 66.23% with our approach, outperforming the baseline by 4.64%. Few-shot evaluation shows that Llama-3.1-8B achieves 58.43% F1-score, revealing a meaningful trade-off between the efficiency of prompting-based approaches and the higher performance of task-specific fine-tuning. --- ### If Only My CGM Could Speak: A Privacy-Preserving Agent for Question Answering over Continuous Glucose Data Authors: Yanjun Cui, Ali Emami, Temiloluwa Prioleau, Nikhil Singh Published: 2026-04-18 Categories: cs.AI, cs.CR arXiv: https://arxiv.org/abs/2604.17133v1 Continuous glucose monitors (CGMs) used in diabetes care collect rich personal health data that could improve day-to-day self-management. However, current patient platforms only offer static summaries which do not support inquisitive user queries. Large language models (LLMs) could enable free-form inquiries about continuous glucose data, but deploying them over sensitive health records raises privacy and accuracy concerns. In this paper, we present CGM-Agent, a privacy-preserving framework for question answering over personal glucose data. In our design, the LLM serves purely as a reasoning engine that selects analytical functions. All computation occurs locally, and personal health data never leaves the user's device. For evaluation, we construct a benchmark of 4,180 questions combining parameterized question templates with real user queries and ground truth derived from deterministic program execution. Evaluating 6 leading LLMs, we find that top models achieve 94\% value accuracy on synthetic queries and 88\% on ambiguous real-world queries. Errors stem primarily from intent and temporal ambiguity rather than computational failures. Additionally, lightweight models achieve competitive performance in our agent design, suggesting opportunities for low-cost deployment. We release our code and benchmark to support future work on trustworthy health agents. --- ### Please refuse to answer me! Mitigating Over-Refusal in Large Language Models via Adaptive Contrastive Decoding Authors: Yupeng Qi, Ziyu Lyu, Lixin Cui, Lu Bai, Feng Xia Published: 2026-04-18 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.17132v1 Safety-aligned large language models (LLMs) often generate refusal responses to harmless queries due to the over-refusal problem. However, existing methods for mitigating over-refusal cannot maintain a low refusal ratio for harmless queries while keeping a high refusal ratio for malicious ones. In this paper, we analyze how system prompts with varying safety levels affect LLM refusal behaviors when facing over-refusal queries. A key observation is that, when LLMs suffer from the over-refusal issue, non-refusal tokens remain present in the next-token candidate list, but the model systematically fails to select them, despite the generation of refusal tokens. Based on this observation, we propose a training-free and model-agnostic approach, Adaptive Contrastive Decoding (AdaCD), to mitigate over-refusal while maintaining LLM safety. First, AdaCD compares the output distributions of the LLM with or without an extreme safety system prompt to refine the refusal token distribution. Second, we introduce an adaptive contrastive decoding strategy that dynamically incorporates or removes the refusal token distribution, adaptively boosting the probability of selecting refusal or non-refusal tokens. Experimental results on five benchmark datasets show that, on average, AdaCD reduces the refusal ratio for over-refusal queries by 10.35%, yet still increases the refusal ratio for malicious queries by 0.13%. Code is available at https://github.com/OutdoorManofML/AdaCD. --- ### Automated Classification of Plasma Regions at Mars Using Machine Learning Authors: Yilan Qin, Chuanfei Dong, Hongyang Zhou, Chi Zhang, Kaichun Xu, Jiawei Gao, Simin Shekarpaz, Xinmin Li, Liang Wang Published: 2026-04-18 Categories: physics.space-ph, astro-ph.EP, cs.LG, physics.plasm-ph arXiv: https://arxiv.org/abs/2604.17131v1 The plasma environment around Mars is highly variable because it is strongly influenced by the solar wind. Accurate identification of plasma regions around Mars is important for the community studying solar wind-Mars interactions, region-specific plasma processes, and atmospheric escape. In this study, we develop a machine-learning-based classifier to automatically identify three key plasma regions--solar wind, magnetosheath, and induced magnetosphere--using only ion omnidirectional energy spectra measured by the MAVEN Solar Wind Ion Analyzer (SWIA). Two neural network architectures are evaluated: a multilayer perceptron (MLP) and a convolutional neural network (CNN) that incorporates short temporal sequences. Our results show that the CNN can reliably distinguish the three plasma regions, whereas the MLP struggles to separate the solar wind and magnetosheath. Therefore, the CNN-based approach provides an efficient and accurate framework for large-scale plasma region identification at Mars and can be readily applied to future planetary missions. --- ### A proposal for PU classification under Non-SCAR using clustering and logistic model Authors: Konrad Furmanczyk, Kacper Paczutkowski Published: 2026-04-18 Categories: stat.ME, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2604.17130v1 The present study aims to investigate a cluster cleaning algorithm that is both computationally simple and capable of solving the PU classification when the SCAR condition is unsatisfied. A secondary objective of this study is to determine the robustness of the LassoJoint method to perturbations of the SCAR condition. In the first step of our algorithm, we obtain cleaning labels from 2-means clustering. Subsequently, we perform logistic regression on the cleaned data, assigning positive labels from the cleaning algorithm with additional true positive observations. The remaining observations are assigned the negative label. The proposed algorithm is evaluated by comparing 11 real data sets from machine learning repositories and a synthetic set. The findings obtained from this study demonstrate the efficacy of the clustering algorithm in scenarios where the SCAR condition is violated and further underscore the moderate robustness of the LassoJoint algorithm in this context. --- ### Prompt Sensitivity in Vision-Language Grounding: How Small Changes in Wording Affect Object Detection Authors: Dawar Jyoti Deka, Amit Sethi, Syed Mohammad Ali Published: 2026-04-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.17126v1 Vision-language models enable open-vocabulary object grounding through natural language queries, under the implicit assumption that semantically equivalent descriptions yield consistent outputs. We examine this assumption using a controlled pipeline combining DETR for object proposals with CLIP for language-conditioned selection on 263 COCO val2017 images. We find that overlapping prompts such as "a person," "a human," and "a pedestrian" frequently select different instances, with mean instability of 2.11 distinct selections across six prompts. PCA analysis shows this variability is structured and directional, not random. Prompt ensembling does not improve quality and often shifts selections toward generic regions. We further show that text embedding proximity explains only 34% of grounding disagreement (r = -0.58), confirming that instability arises from the argmax selection mechanism rather than text-level distances alone. --- ### CASCADE: A Component Ablation and Corpus Audit of a Layered Local Defense for MCP-Based Systems Authors: İpek Abasıkeleş Turgut, Edip Gümüş Published: 2026-04-18 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2604.17125v2 The Model Context Protocol (MCP) widens the prompt injection attack surface of large language model applications to tool descriptions, parameter schemas, and tool outputs. Defenses for it are appearing quickly, but their reported figures are not comparable: each is evaluated on a corpus of its authors' construction, under a decision convention that is rarely stated. This paper asks how much those choices decide, taking CASCADE, a fully local layered defense, as the case: three configurations on a frozen 5,000-sample corpus under a pinned revision and a fixed protocol, with that corpus audited in full. Four results follow. First, the aggregation convention dominates the headline metric: counting review referrals as positives reports an 11.70% false-positive rate where 1.51% of benign traffic would be denied without a human, and conceals that 68.5% of all traffic reaches a reviewer. Second, detection is not provenance-invariant: recall ranges from 86.20% on original material to 99.88% on template-generated material, and added false positives fall on original benign records at ten times the rate they fall on transformed ones. Third, the operating point that ran is not readable from the released configuration, which names four candidate thresholds, its deployment files selecting one that did not govern; it is recoverable from point masses the policy layer leaves in the score distribution, so record-level output is a stronger reproducibility guarantee than a parameter table. Fourth, a local review model invoked for 32.56% of requests at 2.51 s each changes no classification outcome: it returned 90 not-malicious verdicts and the policy stage admitted none, making that null a guard setting rather than a model property. The ablation is unsurprising -- the rule-based layer reaches 61.05% recall, the semantic stage 94.77% -- and that is what makes the other results the substance of the paper. --- ### CASCADE: A Cascaded Hybrid Defense Architecture for Prompt Injection Detection in MCP-Based Systems Authors: İpek Abasıkeleş Turgut, Edip Gümüş Published: 2026-04-18 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2604.17125v1 Model Context Protocol (MCP) is a rapidly adopted standard for defining and invoking external tools in LLM applications. The multi-layered architecture of MCP introduces new attack surfaces such as tool poisoning, in addition to traditional prompt injection. Existing defense systems suffer from limitations including high false positive rates, API dependency, or white-box access requirements. In this study, we propose CASCADE, a three-tiered cascaded defense architecture for MCP-based systems: (i) Layer 1 performs fast pre-filtering using regex, phrase weighting, and entropy analysis; (ii) Layer 2 conducts semantic analysis via BGE embedding with an Ollama Llama3 fallback mechanism; (iii) Layer 3 applies pattern-based output filtering. Evaluation on a dataset of 5,000 samples yielded 95.85% precision, 6.06% false positive rate, 61.05% recall, and 74.59% F1-score. Analysis across 31 attack types categorized into 6 tiers revealed high detection rates for data exfiltration (91.5%) and prompt injection (84.2%), while semantic attack (52.5%) and tool poisoning (59.9%) categories showed potential for improvement. A key advantage of CASCADE over existing solutions is its fully local operation, requiring no external API calls --- ### Multimodal Fusion of Histopathology Images and Electronic Health Records for Early Breast Cancer Diagnosis Authors: Aditya Shribhagwan Khandelwal, Mohammad Samar Ansari, Asra Aslam Published: 2026-04-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.17122v1 Breast cancer is a leading cause of cancer-related mortality worldwide, and timely accurate diagnosis is critical to improving survival outcomes. While convolutional neural networks (CNNs) have demonstrated strong performance on histopathology image classification, and machine learning models on structured electronic health records (EHR) have shown utility for clinical risk stratification, most existing work treats these modalities in isolation. This paper presents a systematic multimodal framework that integrates patch-level histopathology features from the BreCaHAD dataset with structured clinical data from MIMIC-IV. We train and evaluate unimodal image models (a simple CNN baseline and ResNet-18 with transfer learning), unimodal tabular models (XGBoost and a multilayer perceptron), and an intermediate-fusion model that concatenates latent representations from both modalities. ResNet-18 achieves near-perfect accuracy (1.000) and AUC (1.000) on three-class patch-level classification, while XGBoost achieves 98% accuracy on the EHR prediction task. The intermediate fusion model yields a macro-average AUC of 0.997, outperforming all unimodal baselines and delivering the largest improvements on the diagnostically critical but class-imbalanced mitosis category (AUC 0.994). Grad-CAM and SHAP interpretability analyses validate that model decisions align with established pathological and clinical criteria. Our results demonstrate that multimodal integration delivers meaningful improvements in both predictive performance and clinical transparency. --- ### The Topological Trouble With Transformers Authors: Michael C. Mozer, Shoaib Ahmed Siddiqui, Rosanne Liu Published: 2026-04-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.17121v5 Transformers encode structure in sequences via an expanding contextual history. However, their purely feedforward architecture fundamentally limits dynamic state tracking. State tracking -- the iterative updating of latent variables reflecting an evolving environment -- involves inherently sequential dependencies that feedforward networks struggle to maintain. Consequently, feedforward models push evolving state representations deeper into their layer stack with each new input step, rendering information inaccessible in shallow layers and ultimately exhausting the model's depth. While this depth limit can be bypassed by dynamic depth models and by explicit or latent thinking that externalizes state representations, these solutions are computationally and memory inefficient. In this article, we argue that temporally extended cognition requires refocusing from explicit thought traces to implicit activation dynamics via recurrent architectures. We introduce a taxonomy of recurrent and continuous-thought transformer architectures, categorizing them by their recurrence axis (depth versus step) and their ratio of input tokens to recurrence steps. Finally, we outline promising research directions, including enhanced state-space models and coarse-grained recurrence, to better integrate state tracking into modern foundation models. --- ### The Topological Trouble With Transformers Authors: Michael C. Mozer, Shoaib Ahmed Siddiqui, Rosanne Liu Published: 2026-04-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.17121v4 Transformers encode structure in sequences via an expanding contextual history. However, their purely feedforward architecture fundamentally limits dynamic state tracking. State tracking -- the iterative updating of latent variables reflecting an evolving environment -- involves inherently sequential dependencies that feedforward networks struggle to maintain. Consequently, feedforward models push evolving state representations deeper into their layer stack with each new input step, rendering information inaccessible in shallow layers and ultimately exhausting the model's depth. While this depth limit can be bypassed by dynamic depth models and by explicit or latent thinking that externalizes state representations, these solutions are computationally and memory inefficient. In this article, we argue that temporally extended cognition requires refocusing from explicit thought traces to implicit activation dynamics via recurrent architectures. We introduce a taxonomy of recurrent and continuous-thought transformer architectures, categorizing them by their recurrence axis (depth versus step) and their ratio of input tokens to recurrence steps. Finally, we outline promising research directions, including enhanced state-space models and coarse-grained recurrence, to better integrate state tracking into modern foundation models. --- ### A Two-Stage Deep Learning Framework for Segmentation of Ten Gastrointestinal Organs from Coronal MR Enterography Authors: Ashiqur Rahman, Md. Abu Sayed, Md Sharjis Ibne Wadud, Md. Abu Asad Al-Hafiz, Adam Mushtak, Muhammad E. H. Chowdhury Published: 2026-04-18 Categories: eess.IV, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2604.17118v1 Accurate segmentation of gastrointestinal (GI) organs in magnetic resonance enterography (MRE) is critical for diagnosing inflammatory bowel disease (IBD). However, anatomical variability, class imbalance, and low tissue contrast hinder reliable automation. This study proposes a dual-stage deep learning framework for organ-specific segmentation of GI structures from coronal MRE images to address these challenges. A publicly available MRE dataset of 3,195 coronal T2-weighted HASTE slices from 114 IBD patients was used. Initially, a DenseNet201-UNet++ model generated coarse masks for ROI extraction. A DenseNet121-SelfONN-UNet model was then trained on organ-specific patches. Extensive data augmentation, normalization, five-fold cross-validation, and class-specific weighting were applied to mitigate severe class imbalance, particularly for the appendix. The initial stage achieved strong organ localization but underperformed for the appendix; class weighting improved its DSC from 6.76% to 85.76%. The second-stage DenseNet121-SelfONN-UNet significantly enhanced segmentation across all GI structures, with notable DSC gains (cecum +23.62%, sigmoid +18.57%, rectum +17.99%, small intestine +16.06%). Overall, the framework achieved mDSC of 88.99%, mIoU of 84.76%, and mHD95 of 6.94 mm, outperforming all baselines. This framework demonstrates the effectiveness of a coarse-to-fine, organ-aware segmentation strategy for intestinal MRE. Despite higher computational cost, it shows strong potential for clinical translation and enables anatomically informed diagnostic tools in gastroenterology. --- ### Inference-Time Temporal Probability Smoothing for Stable Video Segmentation with SAM2 under Weak Prompts Authors: Dawar Jyoti Deka Published: 2026-04-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.17115v1 Interactive video segmentation models such as SAM2 have demonstrated strong generalization across diverse visual domains. However, under weak user supervision, for example, when sparse point prompts are provided on a single frame, their predictions often suffer from temporal instability, including flickering boundaries, object dropout, and inconsistent object extents across frames. These issues limit their reliability in downstream video understanding and control applications. In this paper, we propose an inference-time temporal probability smoothing method that improves the temporal stability of SAM2-based video segmentation without retraining or architectural modification. Our approach operates directly on per-frame segmentation probability maps and leverages optical-flow-based motion warping together with pixel-wise uncertainty estimates derived from segmentation entropy, and forward-backwards flow consistency. These signals are used to adaptively blend current-frame predictions with motion-aligned historical estimates, yielding temporally coherent segmentation outputs under weak prompts. We evaluate the proposed method on four diverse video sequences using a comprehensive set of frame-wise and temporal stability metrics, including motion-compensated IoU, boundary consistency, object persistence, and area volatility. Experimental results demonstrate consistent improvements in temporal stability over vanilla SAM2 inference while preserving spatial accuracy. The proposed framework is lightweight, model-agnostic, and well-suited for real-time, interactive video segmentation. --- ### The Provenance Gap in Clinical AI: Evidence-Traceable Temporal Knowledge Graphs for Rare Disease Reasoning Authors: Md Shamim Ahmed, Maja Dusanic, Moritz Nikolai Kirschner, Elisabeth Nyoungui, Jana Zschüntzsch, Lukas Galke Poech, Richard Röttger Published: 2026-04-18 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.17114v2 Frontier large language models generate clinically accurate outputs, but their citations are often fabricated. We term this the Provenance Gap. We tested five frontier LLMs across 36 clinician-validated scenarios for three rare neuromuscular disease pairs. No model produced a clinically relevant PubMed identifier without prompting. When explicitly asked to cite, the best model achieved 15.3% relevant PMIDs; the majority resolved to real publications in unrelated fields. We present HEG-TKG (Hierarchical Evidence-Grounded Temporal Knowledge Graphs), a system that grounds clinical claims in temporal knowledge graphs built from 4,512 PubMed records and curated sources with quality-tier stratification and 1,280 disease-trajectory milestones. In a controlled three-arm comparison using the same synthesis model, HEG-TKG matches baseline clinical feature coverage while achieving 100% evidence verifiability with 203 inline citations. Guideline-RAG, given overlapping source documents as raw text, produces zero verifiable citations. LLM judges cannot distinguish fabricated from verified citations without PubMed audit data. Independent clinician evaluation confirms the verifiability advantage (Cohen's d = 1.81, p < 0.001) with no degradation on safety or completeness. A counterfactual experiment shows 80% resistance to injected clinical errors with 100% detectability via citation trace. The system deploys on-premise via open-source models so patient data never leaves institutional infrastructure. --- ### Complementing Self-Consistency with Cross-Model Disagreement for Uncertainty Quantification Authors: Kimia Hamidieh, Veronika Thost, Walter Gerych, Mikhail Yurochkin, Marzyeh Ghassemi Published: 2026-04-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.17112v1 Large language models (LLMs) often produce confident yet incorrect responses, and uncertainty quantification is one potential solution to more robust usage. Recent works routinely rely on self-consistency to estimate aleatoric uncertainty (AU), yet this proxy collapses when models are overconfident and produce the same incorrect answer across samples. We analyze this regime and show that cross-model semantic disagreement is higher on incorrect answers precisely when AU is low. Motivated by this, we introduce an epistemic uncertainty (EU) term that operates in the black-box access setting: EU uses only generated text from a small, scale-matched ensemble and is computed as the gap between inter-model and intra-model sequence-semantic similarity. We then define total uncertainty (TU) as the sum of AU and EU. In a comprehensive study across five 7-9B instruction-tuned models and ten long-form tasks, TU improves ranking calibration and selective abstention relative to AU, and EU reliably flags confident failures where AU is low. We further characterize when EU is most useful via agreement and complementarity diagnostics. --- ### HiveMind: OS-Inspired Scheduling for Concurrent LLM Agent Workloads Authors: Justice Owusu Agyemang, Jerry John Kponyo, Obed Kwasi Somuah, Elliot Amponsah, Godfred Manu Addo Boakye, Kwame Opuni-Boachie Obour Agyekum Published: 2026-04-18 Categories: cs.DC, cs.AI arXiv: https://arxiv.org/abs/2604.17111v1 When multiple LLM coding agents share a rate-limited API endpoint, they exhibit resource contention patterns analogous to unscheduled OS processes competing for CPU, memory, and I/O. In a motivating incident, 3 of 11 parallel agents died from connection resets and HTTP 502 errors - a 27% failure rate - despite the API having sufficient aggregate capacity to serve all 11 sequentially. We present HIVEMIND, a transparent HTTP proxy that applies five OS-inspired scheduling primitives - admission control, rate-limit tracking, AIMD backpressure with circuit breaking, token budget management, and priority queuing - to eliminate the failure modes caused by uncoordinated parallel execution. The proxy requires zero modifications to existing agent code and supports Anthropic, OpenAI, and local model APIs via auto-detected provider profiles. Our evaluation across seven scenarios (5-50 concurrent agents) shows that uncoordinated agents fail at 72-100% rates under contention, while HIVEMIND reduces failures to 0-18% and eliminates 48-100% of wasted compute. An ablation study reveals that transparent retry - not admission control - is the single most critical primitive, but the primitives are most effective in combination. Real-world validation against Ollama confirms that HIVEMIND adds under 3ms of proxy overhead per request. The system is open-source under the MIT license. --- ### From Clinical Intent to Clinical Model: Autonomous Coding-Agents for Clinician-driven AI Development Authors: Zihao Zhao, Frederik Hauke, Juliana De Castilhos, Mathis Bode, Jakob Nikolas Kather, Sven Nebelung, Daniel Truhn Published: 2026-04-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.17110v2 Developing AI models that are useful in clinical practice, requires efficient collaboration between clinicians and AI developers. This poses a practical challenge: clinicians must repeatedly communicate and refine their requirements with AI developers before those requirements can be translated into executable model development. This iterative process is time-consuming, and even after repeated discussion, misalignment may still exist because the two sides do not fully share each other's expertise. Coding agents may help close this gap. They can write and refine code on their own, and they carry working knowledge of both medicine and AI to understand commands formulated by both medical experts and developers. We present a prototype that lets clinicians drive AI development directly. A clinician describes the task in plain language, and the system turns the description into a working pipeline, refines it through repeated experiments together with the clinician, and returns a model that meets the stated clinical objective. Across five clinical tasks, the system reliably produces models that matched the clinician's request and reached competitive performance. Most notably, on chest radiographs the system sharply reduced the model's reliance on chest drains, a well-known shortcut for pneumothorax classification, from 60% to 31% on one dataset and from 50% to 18% on another. Our results suggest that coding agents can shift clinical AI development toward a more clinician-driven mode, allowing domain experts to shape models directly instead of relaying requirements through specialized AI teams. --- ### A fully parallel densely connected probabilistic Ising machine with inertia for real-time applications Authors: Ruomin Zhu, Abhishek Kumar Singh, Jérémie Laydevant, Fan O. Wu, Ari Kapelyan, Davide Venturelli, Kyle Jamieson, Peter L. McMahon Published: 2026-04-18 Categories: cs.ET, cond-mat.dis-nn, cs.NE, eess.SP arXiv: https://arxiv.org/abs/2604.17109v2 Ising machines---special-purpose hardware for heuristically solving Ising optimization problems---based on probabilistic bits (p-bits) have been established as a promising alternative to heuristic optimization algorithms run on conventional computers. However, it has---until now---been thought that Ising spins that are connected in probabilistic Ising machines (PIMs) cannot be updated in parallel without ruining the machine's solving ability. This has presented a major challenge to realizing the potential for probabilistic Ising machines to act as fast solvers for densely connected Ising problems. In this paper, we show that it is possible to circumvent this conventional wisdom. We introduce a modified form of Ising spin dynamics for PIMs, adding an inertia term, and verify in algorithm simulations, field-programmable gate array (FPGA) emulation, and in FPGA experiments that the modified dynamics enables fully parallel, synchronous updates and at the same time improves the achieved success probability. Our evaluations were performed with various types of abstract (Max-Cut and Sherrington-Kirkpatrick model) and application-derived (multiple-input and multiple-output, MIMO detection) dense Ising benchmark instances. Performing fully parallel updates results in a speed advantage that grows superlinearly with the number of spins, giving rise to large time-to-solution reductions for practical problem sizes. For both MC and the SK model at a problem size of 200, our approach achieved an average speedup of ~34x, with the best single-instance speedup reaching 150x. As an example of the practical utility of our approach in an application where speed is critical, we co-design the algorithm dynamics and hardware implementation for MIMO detection, achieving improved detection accuracy relative to the standard linear detector and higher throughput than the conventional sequential-update PIM. --- ### A fully parallel densely connected probabilistic Ising machine with inertia for real-time applications Authors: Ruomin Zhu, Abhishek Kumar Singh, Jérémie Laydevant, Fan O. Wu, Ari Kapelyan, Davide Venturelli, Kyle Jamieson, Peter L. McMahon Published: 2026-04-18 Categories: cs.ET, cond-mat.dis-nn, cs.NE, eess.SP arXiv: https://arxiv.org/abs/2604.17109v1 Ising machines -- special-purpose hardware for heuristically solving Ising optimization problems -- based on probabilistic bits (p-bits) have been established as a promising alternative to heuristic optimization algorithms run on conventional computers. However, it has -- until now -- been thought that Ising spins that are connected in probabilistic Ising machines cannot be updated in parallel without ruining the machine's solving ability. This has been a major challenge for using probabilistic Ising machines as fast solvers for densely connected problems. Here, we circumvent this by introducing a modified Ising spin dynamics with an added inertia term, and verify in algorithm simulations, FPGA hardware emulation, and FPGA experiments that it enables fully parallel, synchronous updates while improving rather than degrading success probability. We evaluated on various types of abstract (Max-Cut and Sherrington-Kirkpatrick-model) and application-derived (MIMO, wireless detection) dense Ising benchmark instances. Performing fully parallel updates results in a speed advantage that grows faster than linearly with the number of spins, giving rise to large time-to-solution increases for practical problem sizes. For both Max-Cut and the SK-1 model at a problem size of 200, our approach achieved an average speedup of $\approx 35\times$, with the best single-instance speedup reaching $150\times$. As an example of the practical utility of our approach in an application where speed is critical, we further show by co-designing the algorithm dynamics with the hardware implementation -- co-optimizing for solver ability and silicon resource usage -- that probabilistic Ising machines based on our approach satisfy the stringent solution quality and latency/throughput requirements for real-time MIMO detection in modern 5G cellular wireless networks while using a practically reasonable silicon area. --- ### Beyond Word Boundaries: A Hebrew Coreference Benchmark and an Evaluation Protocol for Morphologically Complex Text Authors: Refael Shaked Greenfeld, Reut Tsarfaty Published: 2026-04-18 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.17108v1 Coreference Resolution (CR) is a fundamental NLP task critical for long-form tasks as information extraction, summarization, and many business applications. However, CR methods originally designed for English struggle with Morphologically Rich Languages (MRLs), where mention boundaries do not necessarily align with word boundaries, and a single token may consist of multiple anaphors. CR modeling and evaluation protocols standardly assume that, as in English, words and mentions mostly align. However, this assumption breaks down in MRLs, particularly in the context of LLMs' raw-text processing and end-to-end tasks. To assess and address this challenge, we introduce {\em KibutzR}, the first comprehensive CR dataset for Modern Hebrew, an MRL rich with complex words and pronominal clitics. We deliver an annotated dataset that identifies mentions at word, sub-word and multi-word levels, and propose an evaluation protocol that directly addresses word/morpheme boundary discrepancies. Our experiments show that contemporary LLMs perform significantly worse on Hebrew than on English, and that performance degrades on raw unsegmented text. Crucially, we show an inverse performance-trend in Hebrew relative to English, where smaller encoders perform far better than contemporary decoder models, leaving ample space for investigation and improvement. We deliver a new benchmark for Hebrew coreference resolution and a segmentation-aware evaluation protocol to inform future work on other MRLs. --- ### Hybrid Multi-Dimensional MRI Prostate Cancer Detection via Hadamard Network-Based Bias Correction and Residual Networks Authors: Emadeldeen Hamdan, Gorkem Durak, Muhammed Enes Tasci, Abel Lorente Campos, Aritrick Chatterjee, Roger Engelmann, Gregory Karczma, Aytekin Oto, Ahmet Enis Cetin, Ulas Bagci Published: 2026-04-18 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2604.17107v1 Magnetic Resonance Imaging (MRI) is vital for prostate cancer (PCa) diagnosis. While advanced techniques such as Hybrid Multi-dimensional MRI (HM-MRI) have enhanced diagnostic capabilities, the significant need remains for robust, automated Artificial Intelligence (AI)-based detection methods. In this study, we combine quantitative HM-MRI of tissue composition with an AI-based neural network. We propose the Hadamard-Bias Network plus ResNet18 (HBR-Net-18), a two-stage AI framework for PCa detection. In the first stage, a Hadamard U-Net-based algorithm suppresses intensity inhomogeneities (bias fields) across six parametric HM-MRI maps generated via a Physics-Informed Autoencoder (PIA). In the second stage, a Residual Network (ResNet-18) performs patch-level classification. The framework utilizes overlapping 11-by-11 patches, incorporating both 2D intra-slice and 3D inter-slice (adjacent-slice) information to improve spatial consistency. Our experimental results demonstrate that HB-Net achieves balanced sensitivity and specificity, significantly outperforming conventional radiomics-based approaches and baseline CNN models, highlighting its potential for clinical deployment. --- ### Live LTL Progress Tracking: Towards Task-Based Exploration Authors: Noel Brindise, Cedric Langbort, Melkior Ornik Published: 2026-04-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.17106v1 Motivated by the challenge presented by non-Markovian objectives in reinforcement learning (RL), we present a novel framework to track and represent the progress of autonomous agents through complex, multi-stage tasks. Given a specification in finite linear temporal logic (LTL), the framework establishes a 'tracking vector' which updates at each time step in a trajectory rollout. The values of the vector represent the status of the specification as the trajectory develops, assigning true, false, or 'open' labels (where 'open' is used for indeterminate cases). Applied to an LTL formula tree, the tracking vector can be used to encode detailed information about how a task is executed over a trajectory, providing a potential tool for new performance metrics, diverse exploration, and reward shaping. In this paper, we formally present the framework and algorithm, collectively named Live LTL Progress Tracking, give a simple working example, and demonstrate avenues for its integration into RL models. Future work will apply the framework to problems such as task-space exploration and diverse solution-finding in RL. --- ### How Tokenization Limits Phonological Knowledge Representation in Language Models and How to Improve Them Authors: Disen Liao, Freda Shi Published: 2026-04-18 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.17105v1 Tokenization is the first step in every language model (LM), yet it never takes the sounds of words into account. We investigate how tokenization influences text-only LMs' ability to represent phonological knowledge. Through a series of probing experiments, we show that subword-based tokenization systematically weakens the encoding of both local (e.g., rhyme) and global (e.g., syllabification) phonological features. To quantify this effect, we introduce the syllabification-tokenization alignment distance (STAD), a metric that measures the misalignment between a model's tokenization and the natural syllable boundaries of words, and find that higher misalignment correlates with poorer phonological representations, providing a simple diagnostic for phonology-aware tokenization. To address these limitations, we propose a lightweight IPA-based fine-tuning method that infuses phonological awareness into LMs, leading to consistent improvements across three phonology-related tasks while largely preserving math and general reasoning ability, with 1.1\% and 0.9\% drops on GSM8K and MMLU, respectively. ---