# Research Papers — 2026-04 · bundle page 170 of 233 > Full-text markdown of papers #8451–8500 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/170 [← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/169.md) [Next bundle →](https://aipod.dev/papers/archive/2026-04/page/171.md) ### When Should a Language Model Trust Itself? Same-Model Self-Verification as a Conditional Confidence Signal Authors: Aditya Ajay Phalod Published: 2026-04-08 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2605.02915v1 Same-model self-verification, prompting a model to audit its own predicted answer, is a plausible confidence signal for selective prediction, but its practical value remains unclear once strong likelihood-based baselines are taken seriously. We evaluate self-verification against two such baselines, LL-AVG and LL-SUM, on ARC-Challenge and TruthfulQA-MC across multiple model families, scales, and prompt variants. We measure not only correctness ranking, but also abstention quality through AURC and operating-point analyses. The results are sharply task- and model-dependent. On ARC-Challenge, self-verification substantially improves over LL-AVG for Phi-2 and the Qwen models, with the largest gains appearing in Qwen-7B. On TruthfulQA-MC, however, the signal is less reliable: smaller models can become prompt-sensitive, DeepSeek-R1-Distill-8B degrades relative to LL-AVG, and LL-SUM often remains the stronger practical baseline. We therefore do not treat self-verification as a general-purpose uncertainty estimator. In this setting, it is better understood as a conditional confidence signal whose value depends on task type, model family, prompt formulation, and, crucially, the baseline it must beat. --- ### When Safety Geometry Collapses: Fine-Tuning Vulnerabilities in Agentic Guard Models Authors: Ismail Hossain, Sai Puppala, Jannatul Ferdaus, Md Jahangir Alam, Yoonpyo Lee, Syed Bahauddin Alam, Sajedul Talukder Published: 2026-04-08 Categories: cs.LG, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2605.02914v1 A guard model fine-tuned on entirely benign data can lose all safety alignment -- not through adversarial manipulation, but through standard domain specialization. We demonstrate this failure across three purpose-built safety classifiers -- LlamaGuard, WildGuard, and Granite Guardian -- deployed as protection layers in agentic AI pipelines, and show that it originates in the destruction of latent safety geometry: the structured harmful -- benign representational boundary that guides classification. We extract per-layer safety subspaces via SVD on class-conditional activation differences and track how this boundary evolves under benign fine-tuning. Granite Guardian undergoes complete collapse -- refusal rate drops from 85\% to 0\%, CKA falls to zero, and 100\% of outputs become ambiguous -- a severity exceeding prior findings on general-purpose LLMs, explained by the specialization hypothesis: concentrated safety representations are efficient but catastrophically brittle. To mitigate this, we propose Fisher-Weighted Safety Subspace Regularization (FW-SSR), a training-time penalty combining (i) curvature-aware direction weights derived from diagonal Fisher information and (ii) an adaptive $λ_t$ that scales with task-safety gradient conflict. FW-SSR recovers 75\% refusal on Granite Guardian (CKA = 0.983) and reduces WildGuard's Attack Success Rate to 3.6\% -- below the unmodified baseline -- by actively sharpening the safety subspace rather than merely anchoring it. Across all three models, structural representational geometry (CKA, Fisher score) predicts safety behavior more reliably than absolute displacement metrics, establishing geometry-based monitoring as a necessary component of guard model evaluation in agentic deployments. --- ### Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning Authors: Rohan Surana, Gagan Mundada, Xunyi Jiang, Chuhan Wang, Zhenwei Tang, Difan Jiao, Zihan Huang, Yuxin Xiong, Junda Wu, Sheldon Yu, Xintong Li, Raghav Jain et al. Published: 2026-04-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.02913v1 Reinforcement learning (RL) has become a central post-training tool for improving the reasoning abilities of large language models (LLMs). In these systems, the rollout, the trajectory sampled from a prompt to termination, including intermediate reasoning steps and optional tool or environment interactions, determines the data the optimizer learns from, yet rollout design is often underreported. This survey provides an optimizer-agnostic view of rollout strategies for RL-based post-training of reasoning LLMs. We formalize rollout pipelines with unified notation and introduce Generate-Filter-Control-Replay (GFCR), a lifecycle taxonomy that decomposes rollout pipelines into four modular stages: Generate proposes candidate trajectories and topologies; Filter constructs intermediate signals via verifiers, judges, critics; Control allocates compute and makes continuation/branching/stopping decisions under budgets; and Replay retains and reuses artifacts across rollouts without weight updates, including self-evolving curricula that autonomously generate new training tasks. We complement GFCR with a criterion taxonomy of reliability, coverage, and cost sensitivity that characterizes rollout trade-offs. Using this framework, we synthesize methods spanning RL with verifiable rewards, process supervision, judge-based gating, guided and tree/segment rollouts, adaptive compute allocation, early-exit and partial rollouts, throughput optimization, and replay/recomposition for self-improvement. We ground the framework with case studies in math, code/SQL, multimodal reasoning, tool-using agents, and agentic skill benchmarks that evaluate skill induction, reuse, and cross-task transfer. Finally, we provide a diagnostic index that maps common rollout pathologies to GFCR modules and mitigation levers, alongside open challenges for building reproducible, compute-efficient, and trustworthy rollout pipelines. --- ### Prism: An Evolutionary Memory Substrate for Multi-Agent Open-Ended Discovery Authors: Suyash Mishra Published: 2026-04-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.19795v1 We introduce \prism{} (\textbf{P}robabilistic \textbf{R}etrieval with \textbf{I}nformation-\textbf{S}tratified \textbf{M}emory), an evolutionary memory substrate for multi-agent AI systems engaged in open-ended discovery. \prism{} unifies four independently developed paradigms -- layered file-based persistence, vector-augmented semantic memory, graph-structured relational memory, and multi-agent evolutionary search -- under a single decision-theoretic framework with eight interconnected subsystems. We make five contributions: (1)~an \emph{entropy-gated stratification} mechanism that assigns memories to a tri-partite hub (skills/notes/attempts) based on Shannon information content, with formal context-window utilization bounds; (2)~a \emph{causal memory graph} $\mathcal{G} = (V, E_r, E_c)$ with interventional edges and agent-attributed provenance; (3)~a \emph{Value-of-Information retrieval} policy with self-evolving strategy selection; (4)~a \emph{heartbeat-driven consolidation} controller with stagnation detection via optimal stopping theory; and (5)~a \emph{replicator-decay dynamics} framework that interprets memory confidence as evolutionary fitness, proving convergence to an Evolutionary Stable Memory Set (ESMS). On the LOCOMO benchmark, \prism{} achieves 88.1 LLM-as-a-Judge score (31.2\% over Mem0). On CORAL-style evolutionary optimization tasks, 4-agent \prism{} achieves 2.8$\times$ higher improvement rate than single-agent baselines.% --- ### Healthcare AI for Automation or Allocation? A Transaction Cost Economics Framework Authors: Ari Ercole Published: 2026-04-08 Categories: cs.AI, econ.GN arXiv: https://arxiv.org/abs/2604.16465v1 Healthcare productivity is shaped not only by clinical complexity but by the costs of coordinating work under uncertainty. Transaction-cost economics offers a theory of these coordination frictions, yet has rarely been operationalised at task level across health occupations. Using task statements and frequency weights from the O*NET occupational database, we characterised healthcare work at task granularity and coded each unique task using a constrained large language model into one dominant transaction-cost category (information search, decision and bargaining, monitoring and enforcement, or adaptation and coordination) together with an overall transaction-cost intensity score. Aggregating to the occupation level, clinician roles exhibited substantially higher transaction-cost intensity than non-clinician roles, driven primarily by greater burdens of information search and decision-related coordination, while dispersion of transaction costs within occupations did not differ. These findings demonstrate systematic heterogeneity in the nature of coordination work across healthcare roles and suggest that the opportunities for digital and AI interventions are unevenly distributed, shaped less by technical task complexity than by underlying coordination structure. --- ### Horizon-Aware Forecasting of Passenger Assistance Demand for Rail Station Workforce Planning Authors: Michael Sheehan, Irina Timoshenko Published: 2026-04-08 Categories: stat.AP, cs.LG arXiv: https://arxiv.org/abs/2604.16464v1 Passenger assistance services are essential for accessible rail travel, yet demand varies substantially across stations and over time, creating challenges for workforce planning and staff rostering. This paper presents a data-driven decision support framework for forecasting station-level passenger assistance demand and translating forecasts into workforce plans. The forecasting component applies a horizon-aware Prophet modelling approach using multi-source operational data, while the planning component maps demand forecasts to staffing requirements under service and operational constraints through an interpretable red-amber-green risk framework. The approach has been implemented within a production-grade system to support routine planning and staffing decisions across LNER-managed stations. Results demonstrate improved forecast accuracy relative to year-on-year baseline methods, with absolute error reduced by up to 76.9%, and show that forecast-informed staffing is associated with an approximate 50% reduction in failed passenger assistance deliveries attributable to staff availability. These findings highlight the value of integrating interpretable forecasting with operational work. --- ### MLE-Toolbox: An Open-Source Toolbox for Comprehensive EEG and MEG Data Analysis Authors: Xiaobo Liu Published: 2026-04-08 Categories: q-bio.NC, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2604.16463v1 MLE-Toolbox is a comprehensive open-source MATLAB toolbox for end-to-end analysis of magnetoencephalography (MEG) and electroencephalography (EEG) data. Inspired by widely used neuroimaging platforms such as Brainstorm and FieldTrip, it integrates the full analysis pipeline within a unified and user-friendly graphical interface (GUI), covering raw data import, preprocessing, source localization, functional connectivity, oscillatory analysis, and machine learning-based classification. The toolbox includes automated artifact rejection methods, including independent component analysis (ICA), signal-space projection (SSP), and signal-space separation (SSS); multiple source localization approaches, including minimum norm estimation (MNE), dynamic statistical parametric mapping (dSPM), standardized low-resolution brain electromagnetic tomography (sLORETA), and beamforming; multi-atlas parcellation with anatomical visualization; spectral power analysis with frequency-band brain mapping; phase-amplitude coupling (PAC); graph-theoretic brain network analysis; and integrated machine learning and deep learning classifiers. MLE-Toolbox also provides native interoperability with Brainstorm, FieldTrip, EEGLAB, and FreeSurfer, allowing researchers to build on established workflows while benefiting from additional automation, interactive visualization, and one-click academic report generation. Freely available for non-commercial use, MLE-Toolbox is designed to lower the barrier to rigorous, reproducible MEG/EEG research. --- ### From Inheritance to Saturation: Disentangling the Evolution of Visual Redundancy for Architecture-Aware MLLM Inference Acceleration Authors: Jiaqi Shi, Yuechan Li, Xulong Zhang, Xiaoyang Qu, Jianzong Wang Published: 2026-04-08 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.16462v1 High-resolution Multimodal Large Language Models (MLLMs) face prohibitive computational costs during inference due to the explosion of visual tokens. Existing acceleration strategies, such as token pruning or layer sparsity, suffer from severe "backbone dependency", performing well on Vicuna or Mistral architectures (e.g., LLaVA) but causing significant performance degradation when transferred to architectures like Qwen. To address this, we leverage truncated matrix entropy to uncover a universal three-stage inference lifecycle, decoupling visual redundancy into universal Intrinsic Visual Redundancy (IVR) and architecture-dependent Secondary Saturation Redundancy (SSR). Guided by this insight, we propose HalfV, a framework that first mitigates IVR via a unified pruning strategy and then adaptively handles SSR based on its specific manifestation. Experiments demonstrate that HalfV achieves superior efficiency-performance trade-offs across diverse backbones. Notably, on Qwen25-VL, it retains 96.8\% performance at a 4.1$\times$ FLOPs speedup, significantly outperforming state-of-the-art baselines. Our code is available at https://github.com/civilizwa/HalfV. --- ### Modelling Gas-Phase Reaction Kinetics with Guided Particle Diffusion Sampling Authors: Andrew Millard, Zheng Zhao, Henrik Pedersen Published: 2026-04-08 Categories: physics.comp-ph, cs.LG arXiv: https://arxiv.org/abs/2604.16461v2 Physics-guided sampling with diffusion priors has recently shown strong performance in solving complex systems of partial differential equations (PDEs) from sparse observations. However, these methods are typically evaluated on benchmark problems that do not fully demonstrate their ability to generate temporally consistent solutions of time-dependent PDEs, often focusing instead on reconstructing a single snapshot. In this work, we apply these methods to gas-phase reaction kinetics problems governed by the advection-reaction-diffusion (ARD) equation, providing a setting that more closely reflects realistic laboratory experiments. We demonstrate that guided sampling can be used to reconstruct full spatiotemporal trajectories, rather than isolated states. Furthermore, we show that these methods generalise to previously unseen parameter regimes, highlighting their potential for real-world applications. --- ### Deep Hierarchical Knowledge Loss for Fault Intensity Diagnosis Authors: Yu Sha, Shuiping Gou, Bo Liu, Haofan Lu, Ningtao Liu, Jiahui Fu, Horst Stoecker, Domagoj Vnucec, Nadine Wetzstein, Andreas Widl, Kai Zhou Published: 2026-04-08 Categories: eess.AS, cs.AI, cs.CV, cs.LG, cs.SD, eess.SP arXiv: https://arxiv.org/abs/2604.16459v1 Fault intensity diagnosis (FID) plays a pivotal role in intelligent manufacturing while neglecting dependencies among target classes hinders its practical deployment. This paper introduces a novel and general framework with deep hierarchical knowledge loss (DHK) to achieve hierarchical consistent representation and prediction. We develop a novel hierarchical tree loss to enable a holistic mapping of same-attribute classes, leveraging tree-based positive and negative hierarchical knowledge constraints. We further design a focal hierarchical tree loss to enhance its extensibility and devise two adaptive weighting schemes based on tree height. In addition, we propose a group tree triplet loss with hierarchical dynamic margin by incorporating hierarchical group concepts and tree distance to model boundary structural knowledge across classes. The joint two losses significantly improve the recognition of subtle faults. Extensive experiments are performed on four real-world datasets from various industrial domains (three cavitation datasets from SAMSON AG and one publicly available dataset) for FID, all showing superior results and outperforming recent state-of-the-art FID methods. --- ### EchoChain: A Full-Duplex Benchmark for State-Update Reasoning Under Interruptions Authors: Smit Nautambhai Modi, Gandharv Mahajan, Marc Wetter, Randall Welles Published: 2026-04-08 Categories: cs.CL, cs.AI, cs.LG, cs.SD arXiv: https://arxiv.org/abs/2604.16456v1 Real-time voice assistants must revise task state when users interrupt mid-response, but existing spoken-dialog benchmarks largely evaluate turn-based interaction and miss this failure mode. We introduce EchoChain, a controlled benchmark for evaluating full-duplex state-update reasoning under mid-speech interruptions. EchoChain identifies three recurring failure patterns in post-interruption continuations: contextual inertia, interruption amnesia, and objective displacement. The benchmark generates scenario-driven conversations and injects interruptions at a standardized point relative to assistant speech onset, enabling controlled cross-model comparison. In a paired half-duplex control, total failures drop by 40.2% relative to interrupted runs, indicating that many errors are driven by state-update reasoning under interruption rather than task difficulty alone. Across evaluated real-time voice models, no system exceeds a 50% pass rate, showing substantial room for improvement in mid-generation state revision. EchoChain provides a reproducible benchmark for diagnosing state-update reasoning failures in full-duplex voice interaction. --- ### CROP: Token-Efficient Reasoning in Large Language Models via Regularized Prompt Optimization Authors: Deep Shah, Sanket Badhe, Nehal Kathrotia, Priyanka Tiwari Published: 2026-04-08 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.14214v1 Large Language Models utilizing reasoning techniques improve task performance but incur significant latency and token costs due to verbose generation. Existing automatic prompt optimization(APO) frameworks target task accuracy exclusively at the expense of generating long reasoning traces. We propose Cost-Regularized Optimization of Prompts (CROP), an APO method that introduces regularization on response length by generating textual feedback in addition to standard accuracy feedback. This forces the optimization process to produce prompts that elicit concise responses containing only critical information and reasoning. We evaluate our approach on complex reasoning datasets, specifically GSM8K, LogiQA and BIG-Bench Hard. We achieved an 80.6\% reduction in token consumption while maintaining competitive accuracy, seeing only a nominal decline in performance. This presents a pragmatic solution for deploying token-efficient and cost-effective agentic AI systems in production pipelines. --- ### ConfigSpec: Profiling-Based Configuration Selection for Distributed Edge--Cloud Speculative LLM Serving Authors: Xiangchen Li, Saeid Ghafouri, Jiakun Fan, Babar Ali, Hans Vandierendonck, Dimitrios S. Nikolopoulos Published: 2026-04-08 Categories: cs.DC, cs.AI arXiv: https://arxiv.org/abs/2604.09722v1 Speculative decoding enables collaborative Large Language Model (LLM) inference across cloud and edge by separating lightweight token drafting from heavyweight verification. While prior systems show performance and cost benefits, practical deployment requires navigating a large configuration space spanning draft model variants, quantisation levels, speculative lengths, and heterogeneous edge devices. This paper presents ConfigSpec, a configurationselection framework for distributed speculative LLM serving. ConfigSpec profiles edge devices and draft-target alignment, and models drafting throughput, acceptance rate, and power to evaluate goodput, verification cost efficiency, and energy efficiency across the joint configuration space. Our analysis across three edge platforms and two LLM families reveals structurally conflicting optima. Firstly, goodput is maximised by the smallest, fastest draft model at device-dependent speculative lengths (K*=2-10). Secondly, both cost and energy efficiency converge to K=2 due to a dominant bonus-token effect-with cost favouring the largest drafter for its high acceptance rate and energy favouring the smallest for its low power draw. These conflicts confirm that no single fixed configuration can simultaneously optimise all objectives, underscoring the need for profiling-based configuration selection in disaggregated edge-cloud LLM inference. --- ### Agentic Compilation: Mitigating the LLM Rerun Crisis for Minimized-Inference-Cost Web Automation Authors: Jagadeesh Chundru Published: 2026-04-08 Categories: cs.DC, cs.AI, cs.PL arXiv: https://arxiv.org/abs/2604.09718v2 LLM-driven web agents operating through continuous inference loops -- repeatedly querying a model to evaluate browser state and select actions -- exhibit a fundamental scalability constraint for repetitive tasks. We characterize this as the Rerun Crisis: the linear growth of token expenditure and API latency relative to execution frequency. For a 5-step workflow over 500 iterations, a continuous agent incurs approximately 150.00 USD in inference costs; even with aggressive caching, this remains near 15.00 USD. We propose a Compile-and-Execute architecture that decouples LLM reasoning from browser execution, reducing per-workflow inference cost to under 0.10 USD. A one-shot LLM invocation processes a token-efficient semantic representation from a DOM Sanitization Module (DSM) and emits a deterministic JSON workflow blueprint. A lightweight runtime then drives the browser without further model queries. We formalize this cost reduction from O(M x N) to amortized O(1) inference scaling, where M is the number of reruns and N is the sequential actions. Empirical evaluation across data extraction, form filling, and fingerprinting tasks yields zero-shot compilation success rates of 80-94%. Crucially, the modularity of the JSON intermediate representation allows minimal Human-in-the-Loop (HITL) patching to elevate execution reliability to near-100%. At per-compilation costs between 0.002 USD and 0.092 USD across five frontier models, these results establish deterministic compilation as a paradigm enabling economically viable automation at scales previously infeasible under continuous architectures. --- ### Multi-Head Attention based interaction-aware architecture for Bangla Handwritten Character Recognition: Introducing a Primary Dataset Authors: Mirza Raquib, Asif Pervez Polok, Kedar Nath Biswas, Farida Siddiqi Prity, Saydul Akbar Murad, Nick Rahimi Published: 2026-04-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.09717v1 Character recognition is the fundamental part of an optical character recognition (OCR) system. Word recognition, sentence transcription, document digitization, and language processing are some of the higher-order activities that can be done accurately through character recognition. Nonetheless, recognizing handwritten Bangla characters is not an easy task because they are written in different styles with inconsistent stroke patterns and a high degree of visual character resemblance. The datasets available are usually limited in intra-class and inequitable in class distribution. We have constructed a new balanced dataset of Bangla written characters to overcome those problems. This consists of 78 classes and each class has approximately 650 samples. It contains the basic characters, composite (Juktobarno) characters and numerals. The samples were a diverse group comprising a large age range and socioeconomic groups. Elementary and high school students, university students, and professionals are the contributing factors. The sample also has right and left-handed writers. We have further proposed an interaction-aware hybrid deep learning architecture that integrates EfficientNetB3, Vision Transformer, and Conformer modules in parallel. A multi-head cross-attention fusion mechanism enables effective feature interaction across these components. The proposed model achieves 98.84% accuracy on the constructed dataset and 96.49% on the external CHBCR benchmark, demonstrating strong generalization capability. Grad-CAM visualizations further provide interpretability by highlighting discriminative regions. The dataset and source code of this research is publicly available at: https://huggingface.co/MIRZARAQUIB/Bangla_Handwritten_Character_Recognition. --- ### Training Deep Visual Networks Beyond Loss and Accuracy Through a Dynamical Systems Approach Authors: Hai La Quang, Hassan Ugail, Newton Howard, Cong Tran Tien, Nam Vu Hoai, Hung Nguyen Viet Published: 2026-04-08 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.09716v1 Deep visual recognition models are usually trained and evaluated using metrics such as loss and accuracy. While these measures show whether a model is improving, they reveal very little about how its internal representations change during training. This paper introduces a complementary way to study that process by examining training through the lens of dynamical systems. Drawing on ideas from signal analysis originally used to study biological neural activity, we define three measures from layer activations collected across training epochs: an integration score that reflects long-range coordination across layers, a metastability score that captures how flexibly the network shifts between more and less synchronised states, and a combined dynamical stability index. We apply this framework to nine combinations of model architecture and dataset, including several ResNet variants, DenseNet-121, MobileNetV2, VGG-16, and a pretrained Vision Transformer on CIFAR-10 and CIFAR-100. The results suggest three main patterns. First, the integration measure consistently distinguishes the easier CIFAR-10 setting from the more difficult CIFAR-100 setting. Second, changes in the volatility of the stability index may provide an early sign of convergence before accuracy fully plateaus. Third, the relationship between integration and metastability appears to reflect different styles of training behaviour. Overall, this study offers an exploratory but promising new way to understand deep visual training beyond loss and accuracy. --- ### MuPPet: Multi-person 2D-to-3D Pose Lifting Authors: Thomas Markhorst, Zhi-Yi Lin, Jouh Yeong Chew, Jan van Gemert, Xucong Zhang Published: 2026-04-08 Categories: cs.CV, eess.IV arXiv: https://arxiv.org/abs/2604.09715v1 Multi-person social interactions are inherently built on coherence and relationships among all individuals within the group, making multi-person localization and body pose estimation essential to understanding these social dynamics. One promising approach is 2D-to-3D pose lifting which provides a 3D human pose consisting of rich spatial details by building on the significant advances in 2D pose estimation. However, the existing 2D-to-3D pose lifting methods often neglect inter-person relationships or cannot handle varying group sizes, limiting their effectiveness in multi-person settings. We propose MuPPet, a novel multi-person 2D-to-3D pose lifting framework that explicitly models inter-person correlations. To leverage these inter-person dependencies, our approach introduces Person Encoding to structure individual representations, Permutation Augmentation to enhance training diversity, and Dynamic Multi-Person Attention to adaptively model correlations between individuals. Extensive experiments on group interaction datasets demonstrate MuPPet significantly outperforms state-of-the-art single- and multi-person 2D-to-3D pose lifting methods, and improves robustness in occlusion scenarios. Our findings highlight the importance of modeling inter-person correlations, paving the way for accurate and socially-aware 3D pose estimation. Our code is available at: https://github.com/Thomas-Markhorst/MuPPet --- ### Zero-Shot Synthetic-to-Real Handwritten Text Recognition via Task Analogies Authors: Carlos Garrido-Munoz, Aniello Panariello, Silvia Cascianelli, Angelo Porrello, Simone Calderara, Jorge Calvo-Zaragoza, Rita Cucchiara Published: 2026-04-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.09713v1 Handwritten Text Recognition (HTR) models trained on synthetic handwriting often struggle to generalize to real text, and existing adaptation methods still require real samples from the target domain. In this work, we tackle the fully zero-shot synthetic-to-real generalization setting, where no real data from the target language is available. Our approach learns how model parameters change when moving from synthetic to real handwriting in one or more source languages and transfers this learned correction to new target languages. When using multiple sources, we rely on linguistic similarity to weigh their contrubition when combining them. Experiments across five languages and six architectures show consistent improvements over synthetic-only baselines and reveal that the transferred corrections benefit even languages unrelated to the sources. --- ### LAST: Leveraging Tools as Hints to Enhance Spatial Reasoning for Multimodal Large Language Models Authors: Shi-Yu Tian, Zhi Zhou, Kun-Yang Yu, Ming Yang, Yang Chen, Ziqiao Shang, Lan-Zhe Guo, Yu-Feng Li Published: 2026-04-08 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.09712v1 Spatial reasoning is a cornerstone capability for intelligent systems to perceive and interact with the physical world. However, multimodal large language models (MLLMs) frequently suffer from hallucinations and imprecision when parsing complex geometric layouts. As data-driven scaling struggles to internalize structured geometric priors and spatial constraints, integrating mature, specialized vision models presents a compelling alternative. Despite its promise, applying this paradigm to spatial reasoning is hindered by two key challenges: The difficulty of invoking heterogeneous, parameter-rich tools, as well as the challenge of understanding and effectively leveraging their diverse low-level outputs (e.g., segmentation masks, depth maps) in high-level reasoning. To address these challenges, we propose LAST, a unified framework for tool-augmented spatial reasoning. LAST features an extensible interactive sandbox, termed LAST-Box, which abstracts heterogeneous tool invocations into atomic instructions and reusable spatial skills, returning multimodal hints (e.g., annotated images and textual descriptions) that can be directly consumed by LLMs. We further design a three-stage progressive training strategy that guides models from understanding tool outputs to proficient and adaptive tool invocation. Experiments on four datasets show that LAST-7B achieves around 20\% performance gains over its backbone and outperforms strong proprietary closed-source LLMs, substantially enhancing reasoning on complex spatial tasks. --- ### Head-wise Modality Specialization within MLLMs for Robust Fake News Detection under Missing Modality Authors: Kai Qian, Weijie Shi, Jiaqi Wang, Mengze Li, Hao Chen, Yue Cui, Hanghui Guo, Ziyi Liu, Jia Zhu, Jiajie Xu Published: 2026-04-08 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2604.09711v1 Multimodal fake news detection (MFND) aims to verify news credibility by jointly exploiting textual and visual evidence. However, real-world news dissemination frequently suffers from missing modality due to deleted images, corrupted screenshots, and similar issues. Thus, robust detection in this scenario requires preserving strong verification ability for each modality, which is challenging in MFND due to insufficient learning of the low-contribution modality and scarce unimodal annotations. To address this issue, we propose Head-wise Modality Specialization within Multimodal Large Language Models (MLLMs) for robust MFND under missing modality. Specifically, we first systematically study attention heads in MLLMs and their relationship with performance under missing modality, showing that modality-critical heads serve as key carriers of unimodal verification ability through their modality specialization. Based on this observation, to better preserve verification ability for the low-contribution modality, we introduce a head-wise specialization mechanism that explicitly allocates these heads to different modalities and preserves their specialization through lower-bound attention constraints. Furthermore, to better exploit scarce unimodal annotations, we propose a Unimodal Knowledge Retention strategy that prevents these heads from drifting away from the unimodal knowledge learned from limited supervision. Experiments show that our method improves robustness under missing modality while preserving performance with full multimodal input. --- ### Robust Fair Disease Diagnosis in CT Images Authors: Justin Li, Daniel Ding, Asmita Yuki Pritha, Aryana Hou, Xin Wang, Shu Hu Published: 2026-04-08 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2604.09710v1 Automated diagnosis from chest CT has improved considerably with deep learning, but models trained on skewed datasets tend to perform unevenly across patient demographics. However, the situation is worse than simple demographic bias. In clinical data, class imbalance and group underrepresentation often coincide, creating compound failure modes that neither standard rebalancing nor fairness corrections can fix alone. We introduce a two-level objective that targets both axes of this problem. Logit-adjusted cross-entropy loss operates at the sample level, shifting decision margins by class frequency with provable consistency guarantees. Conditional Value at Risk aggregation operates at the group level, directing optimization pressure toward whichever demographic group currently has the higher loss. We evaluate on the Fair Disease Diagnosis benchmark using a 3D ResNet-18 pretrained on Kinetics-400, classifying CT volumes into Adenocarcinoma, Squamous Cell Carcinoma, COVID-19, and Normal groups with patient sex annotations. The training set illustrates the compound problem concretely: squamous cell carcinoma has 84 samples total, 5 of them female. The combined loss reaches a gender-averaged macro F1 of 0.8403 with a fairness gap of 0.0239, a 13.3% improvement in score and 78% reduction in demographic disparity over the baseline. Ablations show that each component alone falls short. The code is publicly available at https://github.com/Purdue-M2/Fair-Disease-Diagnosis. --- ### Orthogonal Quadratic Complements for Vision Transformer Feed-Forward Networks Authors: Wang Zixian Published: 2026-04-08 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.09709v1 Recent bilinear feed-forward replacements for vision transformers can substantially improve accuracy, but they often conflate two effects: stronger second-order interactions and increased redundancy relative to the main branch. We study a complementary design principle in which auxiliary quadratic features contribute only information not already captured by the dominant hidden representation. To this end, we propose Orthogonal Quadratic Complements (OQC), which construct a low-rank quadratic auxiliary branch and explicitly project it onto the orthogonal complement of the main branch before injection. We further study an efficient low-rank realization (OQC-LR) and gated extensions (OQC-static and OQC-dynamic). Under a parameter-matched Deep-ViT and CIFAR-100 protocol with a fixed penultimate residual readout, full OQC improves an AFBO baseline from 64.25 +/- 0.22 to 65.59 +/- 0.22, while OQC-LR reaches 65.52 +/- 0.25 with a substantially better speed-accuracy tradeoff. On TinyImageNet, the gated extension OQC-dynamic achieves 51.88 +/- 0.32, improving the baseline (50.45 +/- 0.21) by 1.43 points and outperforming all ungated variants. Mechanism analyses show near-zero post-projection auxiliary-main overlap together with improved representation geometry and class separation. The full family, including both ungated and gated variants, generalizes consistently across both datasets. --- ### A Semi-Automated Framework for 3D Reconstruction of Medieval Manuscript Miniatures Authors: Riccardo Pallotto, Pierluigi Feliciati, Tiberio Uricchio Published: 2026-04-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.08610v1 This paper presents a semi-automated framework for transforming two-dimensional miniatures from medieval manuscripts into three-dimensional digital models suitable for extended reality (XR), tactile 3D~printing, and web-based visualization. We evaluate seven image-to-3D methods (TripoSR, SF3D, SPAR3D, TRELLIS, Wonder3D, SAM~3D, Hi3DGen) on 69~manuscript figures from two collections using rendering-based metrics (Silhouette IoU, LPIPS, CLIP~Score) and volumetric measures (Depth Range Ratio, watertight percentage), revealing a trade-off between volumetric expansion and geometric fidelity. Hi3DGen balances topological quality with rich surface detail through its normal bridging approach, making it a good starting point for expert refinement. Our pipeline combines SAM segmentation, Hi3DGen mesh generation, expert refinement in ZBrush, and AI-assisted texturing. Two case studies on Gothic illuminations from the Decretum Gratiani (Vatican Library) and Renaissance miniatures by Giulio Clovio demonstrate applicability across artistic traditions. The resulting models can support WebXR visualization, AR overlay on physical manuscripts, and tactile 3D~prints for visually impaired users. --- ### Detection of Hate and Threat in Digital Forensics: A Case-Driven Multimodal Approach Authors: Ponkoj Chandra Shill Published: 2026-04-08 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.08609v1 Digital forensic investigations increasingly rely on heterogeneous evidence such as images, scanned documents, and contextual reports. These artifacts may contain explicit or implicit expressions of harm, hate, threat, violence, or intimidation, yet existing automated approaches often assume clean text input or apply vision models without forensic justification. This paper presents a case-driven multimodal approach for hate and threat detection in forensic analysis. The proposed framework explicitly determines the presence and source of textual evidence, distinguishing between embedded text, associated contextual text, and image-only evidence. Based on the identified evidence configuration, the framework selectively applies text analysis, multimodal fusion, or image-only semantic reasoning using vision language models with vision transformer backbones (ViT). By conditioning inference on evidence availability, the approach mirrors forensic decision-making, improves evidentiary traceability, and avoids unjustified modality assumptions. Experimental evaluation on forensic-style image evidence demonstrates consistent and interpretable behavior across heterogeneous evidence scenarios. --- ### Semantic Intent Fragmentation: A Single-Shot Compositional Attack on Multi-Agent AI Pipelines Authors: Tanzim Ahad, Ismail Hossain, Md Jahangir Alam, Sai Puppala, Yoonpyo Lee, Syed Bahauddin Alam, Sajedul Talukder Published: 2026-04-08 Categories: cs.CR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.08608v2 We introduce Semantic Intent Fragmentation (SIF), an attack class against LLM orchestration systems where a single, legitimately phrased request causes an orchestrator to decompose a task into subtasks that are individually benign but jointly violate security policy. Current safety mechanisms operate at the subtask level, so each step clears existing classifiers -- the violation only emerges at the composed plan. SIF exploits OWASP LLM06:2025 through four mechanisms: bulk scope escalation, silent data exfiltration, embedded trigger deployment, and quasi-identifier aggregation, requiring no injected content, no system modification, and no attacker interaction after the initial request. We construct a three-stage red-teaming pipeline grounded in OWASP, MITRE ATLAS, and NIST frameworks to generate realistic enterprise scenarios. Across 14 scenarios spanning financial reporting, information security, and HR analytics, a GPT-20B orchestrator produces policy-violating plans in 71% of cases (10/14) while every subtask appears benign. Three independent signals validate this: deterministic taint analysis, chain-of-thought evaluation, and a cross-model compliance judge with 0% false positives. Stronger orchestrators increase SIF success rates. Plan-level information-flow tracking combined with compliance evaluation detects all attacks before execution, showing the compositional safety gap is closable. --- ### Joint Interference Detection and Identification via Adversarial Multi-task Learning Authors: H. Xu, L. Hu, B. He, S. Wang Published: 2026-04-08 Categories: cs.LG, cs.AI, cs.CR, cs.IT arXiv: https://arxiv.org/abs/2604.08607v2 Precise interference detection and identification are crucial for enhancing the survivability of communication systems in non-cooperative wireless environments. While deep learning (DL) has advanced this field, existing single-task learning (STL) approaches neglect inherent task correlations. Furthermore, emerging multi-task learning (MTL) methods often lack a theoretical foundation for quantifying and modeling task relationships. To bridge this gap, we establish a theoretically grounded MTL framework for joint interference detection, modulation identification, and interference identification. First, we derive an upper bound for the weighted expected loss in MTL frameworks. This bound explicitly connects MTL performance to task similarity, quantified by the Wasserstein distance and learnable task relation coefficients. Guided by this theory, we present the adversarial multi-task interference detection and identification network (AMTIDIN), which integrates adversarial training to minimize distributional discrepancies across tasks and uses adaptive coefficients to model task correlations dynamically. Crucially, we conducted a quantitative analysis of task similarity to reveal intrinsic task relationships, specifically that modulation identification and interference identification share a substantial feature overlap distinct from interference detection. Experiments demonstrate that AMTIDIN outperforms its independently trained single-task counterparts and MTL baselines under the evaluated conditions of limited training data, short signal lengths, and low signal-to-noise ratios (SNRs) --- ### Joint Interference Detection and Identification via Adversarial Multi-task Learning Authors: H. Xu, B. He, S. Wang Published: 2026-04-08 Categories: cs.LG, cs.AI, cs.CR, cs.IT arXiv: https://arxiv.org/abs/2604.08607v1 Precise interference detection and identification are crucial for enhancing the survivability of communication systems in non-cooperative wireless environments. While deep learning (DL) has advanced this field, existing single-task learning (STL) approaches neglect inherent task correlations. Furthermore, emerging multi-task learning (MTL) methods often lack a theoretical foundation for quantifying and modeling task relationships. To bridge this gap, we establish a theoretically grounded MTL framework for joint interference detection, modulation identification, and interference identification. First, we derive an upper bound for the weighted expected loss in MTL frameworks. This bound explicitly connects MTL performance to task similarity, quantified by the Wasserstein distance and learnable task relation coefficients. Guided by this theory, we present the adversarial multi-task interference detection and identification network (AMTIDIN), which integrates adversarial training to minimize distributional discrepancies across tasks and uses adaptive coefficients to model task correlations dynamically. Crucially, we conducted a quantitative analysis of task similarity to reveal intrinsic task relationships, specifically that modulation identification and interference identification share a substantial feature overlap distinct from interference detection. Extensive comparative experiments demonstrate that AMTIDIN significantly outperforms both its task-specific STL baseline and state-of-the-art MTL baselines in robustness and generalization, particularly under challenging conditions with limited training data, short signal lengths, and low signal-to-noise ratios (SNRs). --- ### Extrapolating Volition with Recursive Information Markets Authors: Abhimanyu Pallavi Sudhir, Long Tran-Thanh Published: 2026-04-08 Categories: cs.GT, cs.AI, econ.TH arXiv: https://arxiv.org/abs/2604.08606v1 One of the impediments to the efficiency of information markets is the inherent information asymmetry present in them, exacerbated by the "buyer's inspection paradox" (the buyer cannot mitigate the asymmetry by "inspecting" the information, because in doing so the buyer obtains the information without paying for it). Previous work has suggested that using Large Language Model (LLM) buyers to inspect and purchase information could overcome this information asymmetry, as an LLM buyer can simply "forget" the information it inspects. In this work, we analyze this mechanism formally through a "value-of-information" paradigm, i.e. whether it incentivizes information to be priced and provided in accordance with its "true value". We focus in particular on our new recursive version of the mechanism, which we believe has a range of applications including in AI alignment research, where it is related to Extrapolated Volition and Scalable Oversight. --- ### From Business Events to Auditable Decisions: Ontology-Governed Graph Simulation for Enterprise AI Authors: Hongyin Zhu, Jinming Liang, Mengjun Hou, Ruifan Tang, Xianbin Zhu, Jingyuan Yang, Yuanman Mao, Feng Wu Published: 2026-04-08 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.08603v1 Existing LLM-based agent systems share a common architectural failure: they answer from the unrestricted knowledge space without first simulating how active business scenarios reshape that space for the event at hand -- producing decisions that are fluent but ungrounded and carrying no audit trail. We present LOM-action, which equips enterprise AI with \emph{event-driven ontology simulation}: business events trigger scenario conditions encoded in the enterprise ontology~(EO), which drive deterministic graph mutations in an isolated sandbox, evolving a working copy of the subgraph into the scenario-valid simulation graph $G_{\text{sim}}$; all decisions are derived exclusively from this evolved graph. The core pipeline is \emph{event $\to$ simulation $\to$ decision}, realized through a dual-mode architecture -- \emph{skill mode} and \emph{reasoning mode}. Every decision produces a fully traceable audit log. LOM-action achieves 93.82% accuracy and 98.74% tool-chain F1 against frontier baselines Doubao-1.8 and DeepSeek-V3.2, which reach only 24--36% F1 despite 80% accuracy -- exposing the \emph{illusive accuracy} phenomenon. The four-fold F1 advantage confirms that ontology-governed, event-driven simulation, not model scale, is the architectural prerequisite for trustworthy enterprise decision intelligence. --- ### TiAb Review Plugin: A Browser-Based Tool for AI-Assisted Study Selection in Systematic Reviews Authors: Yuki Kataoka, Masahiro Banno, Michihito Kyo, Shuri Nakao, Tomoo Sato, Shunsuke Taito, Tomohiro Takayama, Takahiro Tsuge, Yasushi Tsujimoto, Ryuhei So, Toshi A. Furukawa Published: 2026-04-08 Categories: cs.DL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.08602v2 Server-based screening tools impose subscription costs, while open-source alternatives require coding skills, and full-text screening has remained outside the scope of no-code open-source tools. We developed TiAb Review Plugin, an open-source Chrome browser extension that provides no-code, serverless artificial intelligence (AI)-assisted study selection covering both title and abstract (T&A) screening and full-text screening. It uses Google Sheets as a shared database and Google Drive as a PDF store, and users supply their own large language model (LLM) API key. For T&A screening, it offers manual review, LLM batch screening, and machine learning (ML) active learning. For full-text screening, it retrieves open-access PDFs from PubMed Central, Europe PMC, Unpaywall, OpenAlex, and publisher pages, supports blinded dual review with structured exclusion reasons and adjudication, optionally obtains an LLM judgment with page-anchored evidence, and computes PRISMA 2020 flow counts. We re-implemented the default ASReview algorithm (TF-IDF with Naive Bayes) in TypeScript and compared it with the Python original using 10-fold cross-validation on six datasets. For LLM T&A screening, we compared 16 parameter configurations on a benchmark dataset, validated the best (Gemini 3.0 Flash, low thinking budget, TopP 0.95) on five public datasets (1,038 to 5,628 records; 0.5% to 2.0% prevalence), and benchmarked nine further models from four developers. The TypeScript classifier produced top-100 rankings identical to ASReview on all six datasets. LLM T&A screening achieved recall of 94% to 100% with precision of 2% to 15%, and work saved over sampling at 95% recall (WSS@95) of 46.3% to 89.3%. No additional model exceeded the 96.1% recall of the reference configuration; the most recent models traded recall for precision. The classification accuracy of the full-text stage has not yet been evaluated. --- ### TiAb Review Plugin: A Browser-Based Tool for AI-Assisted Title and Abstract Screening Authors: Yuki Kataoka, Masahiro Banno, Michihito Kyo, Shuri Nakao, Tomoo Sato, Shunsuke Taito, Tomohiro Takayama, Takahiro Tsuge, Yasushi Tsujimoto, Ryuhei So, Toshi A. Furukawa Published: 2026-04-08 Categories: cs.DL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.08602v1 Background: Server-based screening tools impose subscription costs, while open-source alternatives require coding skills. Objectives: We developed a browser extension that provides no-code, serverless artificial intelligence (AI)-assisted title and abstract screening and examined its functionality. Methods: TiAb Review Plugin is an open-source Chrome browser extension (available at https://chromewebstore.google.com/detail/tiab-review-plugin/alejlnlfflogpnabpbplmnojgoeeabij). It uses Google Sheets as a shared database, requiring no dedicated server and enabling multi-reviewer collaboration. Users supply their own Gemini API key, stored locally and encrypted. The tool offers three screening modes: manual review, large language model (LLM) batch screening, and machine learning (ML) active learning. For ML evaluation, we re-implemented the default ASReview active learning algorithm (TF-IDF with Naive Bayes) in TypeScript to enable in-browser execution, and verified equivalence against the original Python implementation using 10-fold cross-validation on six datasets. For LLM evaluation, we compared 16 parameter configurations across two model families on a benchmark dataset, then validated the optimal configuration (Gemini 3.0 Flash, low thinking budget, TopP=0.95) with a sensitivity-oriented prompt on five public datasets (1,038 to 5,628 records, 0.5 to 2.0 percent prevalence). Results: The TypeScript classifier produced top-100 rankings 100 percent identical to the original ASReview across all six datasets. For LLM screening, recall was 94 to 100 percent with precision of 2 to 15 percent, and Work Saved over Sampling at 95 percent recall (WSS@95) ranged from 48.7 to 87.3 percent. Conclusions: We developed a functional browser extension that integrates LLM screening and ML active learning into a no-code, serverless environment, ready for practical use in systematic review screening. --- ### Efficient and Effective Internal Memory Retrieval for LLM-Based Healthcare Prediction Authors: Mingchen Li, Jiatan Huang, Zonghai Yao, Hong yu Published: 2026-04-08 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.07659v1 Large language models (LLMs) hold significant promise for healthcare, yet their reliability in high-stakes clinical settings is often compromised by hallucinations and a lack of granular medical context. While Retrieval Augmented Generation (RAG) can mitigate these issues, standard supervised pipelines require computationally intensive searches over massive external knowledge bases, leading to high latency that is impractical for time-sensitive care. To address this, we introduce Keys to Knowledge (K2K), a novel framework that replaces external retrieval with internal, key-based knowledge access. By encoding essential clinical information directly into the model's parameter space, K2K enables rapid retrieval from internal key-value memory without inference-time overhead. We further enhance retrieval quality through activation-guided probe construction and cross-attention reranking. Experimental results demonstrate that K2K achieves state-of-the-art performance across four benchmark healthcare outcome prediction datasets. --- ### Optimal Decay Spectra for Linear Recurrences Authors: Yang Cao Published: 2026-04-08 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.07658v1 Linear recurrent models offer linear-time sequence processing but often suffer from suboptimal long-range memory. We trace this to the decay spectrum: for $N$ channels, random initialization collapses the minimum spectral gap to $O(N^{-2})$, yielding sub-exponential error $\exp(-Ω(N/\log N))$; linear spacing avoids collapse but degrades to $\exp(-O(N/\sqrt{T}))$, practically algebraic over long contexts. We introduce Position-Adaptive Spectral Tapering (PoST), an architecture-agnostic framework combining two mechanisms: (1) Spectral Reparameterization, which structurally enforces geometrically spaced log-decay rates, proven minimax optimal at rate $O(\exp(-cN/\log T))$; and (2) Position-Adaptive Scaling, the provably unique mechanism that eliminates the scale mismatch of static spectra (where only $N\log t/\log T$ of $N$ channels are effective at position $t$) by stretching the spectrum to the actual dependency range, sharpening the rate to $O(\exp(-cN/\log t))$. This scaling natively induces fractional invariance: the impulse response becomes scale-free, with channels interpolating between relative and absolute temporal coordinates. PoST integrates into any diagonal linear recurrence without overhead. We instantiate it across Mamba-2, RWKV-7, Gated DeltaNet, Gated Linear Attention, and RetNet. Pre-training at 180M-440M scales shows consistent zero-shot language modeling improvements, significant long-context retrieval gains for Mamba-2 (MQAR and NIAH), and competitive or improved performance across other architectures. Code: https://github.com/SiLifen/PoST. --- ### MVOS_HSI: A Python Library for Preprocessing Agricultural Crop Hyperspectral Data Authors: Rishik Aggarwal, Krisha Joshi, Pappu Kumar Yadav, Jianwei Qin, Thomas F. Burks, Moon S. Kim Published: 2026-04-08 Categories: cs.SE, cs.CV arXiv: https://arxiv.org/abs/2604.07656v3 Hyperspectral imaging (HSI) allows researchers to study plant traits non-destructively. By capturing hundreds of narrow spectral bands per pixel, it reveals details about plant biochemistry and stress that standard cameras miss. However, processing this data is often challenging. Many labs still rely on loosely organized collections of lab-specific MATLAB or Python scripts, which makes workflows difficult to share and results difficult to reproduce. MVOS_HSI is an open-source Python library that provides an end-to-end workflow for processing leaf-level HSI data. The software handles everything from calibrating raw ENVI files to detecting and clipping individual leaves based on multiple vegetation indices (NDVI, CIRedEdge and GCI). It also includes tools for data augmentation to create training-time variations for machine learning and utilities to visualize spectral profiles. MVOS_HSI can be used as an importable Python library or run directly from the command line. The code and documentation are available on GitHub. By consolidating these common tasks into a single package, MVOS_HSI helps researchers produce consistent and reproducible results in plant phenotyping --- ### Guardian-as-an-Advisor: Advancing Next-Generation Guardian Models for Trustworthy LLMs Authors: Yue Huang, Haomin Zhuang, Jiayi Ye, Han Bao, Yanbo Wang, Hang Hua, Siyuan Wu, Pin-Yu Chen, Xiangliang Zhang Published: 2026-04-08 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2604.07655v1 Hard-gated safety checkers often over-refuse and misalign with a vendor's model spec; prevailing taxonomies also neglect robustness and honesty, yielding safer-on-paper yet less useful systems. This work introduces Guardian-as-an-Advisor (GaaA), a soft-gating pipeline where a guardian predicts a binary risk label plus a concise explanation and prepends this advice to the original query for re-inference, keeping the base model operating under its original spec. To support training and evaluation, GuardSet is constructed, a 208k+ multi-domain dataset unifying harmful and harmless cases with targeted robustness and honesty slices. GuardAdvisor is trained via SFT followed by RL to enforce label-explanation consistency. GuardAdvisor attains competitive detection accuracy while enabling the advisory workflow; when used to augment inputs, responses improve over unaugmented prompts. A latency study shows advisor inference uses below 5% of base-model compute and adds only 2-10% end-to-end overhead under realistic harmful-input rates. Overall, GaaA steers models to comply with the model spec, maintaining safety while reducing over-refusal. --- ### Bridging Natural Language and Interactive What-If Interfaces via LLM-Generated Declarative Specification Authors: Sneha Gathani, Sirui Zeng, Diya Patel, Ryan Rossi, Dan Marshall, Cagatay Demiralp, Steven Drucker, Zhicheng Liu Published: 2026-04-08 Categories: cs.AI, cs.HC arXiv: https://arxiv.org/abs/2604.07652v1 What-if analysis (WIA) is an iterative, multi-step process where users explore and compare hypothetical scenarios by adjusting parameters, applying constraints, and scoping data through interactive interfaces. Current tools fall short of supporting effective interactive WIA: spreadsheet and BI tools require time-consuming and laborious setup, while LLM-based chatbot interfaces are semantically fragile, frequently misinterpret intent, and produce inconsistent results as conversations progress. To address these limitations, we present a two-stage workflow that translates natural language (NL) WIA questions into interactive visual interfaces via an intermediate representation, powered by the Praxa Specification Language (PSL): first, LLMs generate PSL specifications from NL questions capturing analytical intent and logic, enabling validation and repair of erroneous specifications; and second, the specifications are compiled into interactive visual interfaces with parameter controls and linked visualizations. We benchmark this workflow with 405 WIA questions spanning 11 WIA types, 5 datasets, and 3 state-of-the-art LLMs. The results show that across models, half of specifications (52.42%) are generated correctly without intervention. We perform an analysis of the failure cases and derive an error taxonomy spanning non-functional errors (specifications fail to compile) and functional errors (specifications compile but misrepresent intent). Based on the taxonomy, we apply targeted repairs on the failure cases using few-shot prompts and improve the success rate to 80.42%. Finally, we show how undetected functional errors propagate through compilation into plausible but misleading interfaces, demonstrating that the intermediate specification is critical for reliably bridging NL and interactive WIA interface in LLM-powered WIA systems. --- ### Cognitive-Causal Multi-Task Learning with Psychological State Conditioning for Assistive Driving Perception Authors: Keito Inoshita, Nobuhiro Hayashida, Akira Imanishi Published: 2026-04-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.07651v1 Multi-task learning for advanced driver assistance systems requires modeling the complex interplay between driver internal states and external traffic environments. However, existing methods treat recognition tasks as flat and independent objectives, failing to exploit the cognitive causal structure underlying driving behavior. In this paper, we propose CauPsi, a cognitive science-grounded causal multi-task learning framework that explicitly models the hierarchical dependencies among Traffic Context Recognition (TCR), Vehicle Context Recognition (VCR), Driver Emotion Recognition (DER), and Driver Behavior Recognition (DBR). The proposed framework introduces two key mechanisms. First, a Causal Task Chain propagates upstream task predictions to downstream tasks via learnable prototype embeddings, realizing the cognitive cascade from environmental perception to behavioral regulation in a differentiable manner. Second, Cross-Task Psychological Conditioning (CTPC) estimates a psychological state signal from driver facial expressions and body posture and injects it as a conditioning input to all tasks including environmental recognition, thereby modeling the modulatory effect of driver internal states on cognitive and decision-making processes. Evaluated on the AIDE dataset, CauPsi achieves a mean accuracy of 82.71% with only 5.05M parameters, surpassing prior work by +1.0% overall, with notable improvements on DER (+3.65%) and DBR (+7.53%). Ablation studies validate the independent contribution of each component, and analysis of the psychological state signal confirms that it acquires systematic task-label-dependent patterns in a self-supervised manner without explicit psychological annotations. --- ### A Statistical Framework for Auditing Behavioral Dependence and Induced Bias in LLM Judges Authors: Chenchen Kuai, Jiwan Jiang, Zihao Zhu, Hao Wang, Keshu Wu, Zihao Li, Yunlong Zhang, Chenxi Liu, Zhengzhong Tu, Zhiwen Fan, Yang Zhou Published: 2026-04-08 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.07650v2 The rapid growth of the large language model (LLM) ecosystem raises a critical question: are seemingly diverse models truly independent? Shared pretraining data, distillation, and alignment pipelines can induce hidden behavioral dependencies, or latent entanglement, that undermine multi-model systems such as LLM-as-a-judge pipelines and ensemble verification, which implicitly assume independent signals. In practice, this manifests as correlated reasoning patterns and synchronized failures, where apparent agreement reflects shared error modes rather than independent validation. To address this, we develop a statistical framework for auditing behavioral entanglement among black-box LLMs. Our approach introduces a multi-resolution hierarchy that characterizes the joint failure manifold through two information-theoretic metrics: (i) a Difficulty-Weighted Behavioral Entanglement Index (BEI), which amplifies synchronized failures on easy tasks, and (ii) a Cumulative Information Gain (CIG) metric, which captures directional alignment in erroneous responses. Through experiments on 18 LLMs from six model families, we identify statistically significant behavioral entanglement. Such behavioral dependence is associated with judge over-endorsement bias on a disjoint MMLU-Pro evaluation set (rho = 0.508 for BEI and rho = 0.520 for CIG; p < 0.01). The association further transfers to the MATH-500 benchmark (rho = 0.441 for BEI and rho = 0.457 for CIG; p < 0.05), providing cross-benchmark evidence that the identified dependency structure generalizes beyond the data and response format used for its estimation. Finally, we demonstrate a practical use case of entanglement through de-entangled verifier ensemble reweighting, achieving 3.5 and 2.6 percentage-point gains in accuracy and precision, respectively, over majority voting. --- ### How Independent are Large Language Models? A Statistical Framework for Auditing Behavioral Entanglement and Reweighting Verifier Ensembles Authors: Chenchen Kuai, Jiwan Jiang, Zihao Zhu, Hao Wang, Keshu Wu, Zihao Li, Yunlong Zhang, Chenxi Liu, Zhengzhong Tu, Zhiwen Fan, Yang Zhou Published: 2026-04-08 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.07650v1 The rapid growth of the large language model (LLM) ecosystem raises a critical question: are seemingly diverse models truly independent? Shared pretraining data, distillation, and alignment pipelines can induce hidden behavioral dependencies, latent entanglement, that undermine multi-model systems such as LLM-as-a-judge pipelines and ensemble verification, which implicitly assume independent signals. In practice, this manifests as correlated reasoning patterns and synchronized failures, where apparent agreement reflects shared error modes rather than independent validation. To address this, we develop a statistical framework for auditing behavioral entanglement among black-box LLMs. Our approach introduces a multi-resolution hierarchy that characterizes the joint failure manifold through two information-theoretic metrics: (i) a Difficulty-Weighted Behavioral Entanglement Index, which amplifies synchronized failures on easy tasks, and (ii) a Cumulative Information Gain (CIG) metric, which captures directional alignment in erroneous responses. Through extensive experiments on 18 LLMs from six model families, we identify widespread behavioral entanglement and analyze its impact on LLM-as-a-judge evaluation. We find that CIG exhibits a statistically significant association with degradation in judge precision, with Spearman coefficient of 0.64 (p < 0.001) for GPT-4o-mini and 0.71 (p < 0.01) for Llama3-based judges, indicating that stronger dependency corresponds to increased over-endorsement bias. Finally, we demonstrate a practical use case of entanglement through de-entangled verifier ensemble reweighting. By adjusting model contributions based on inferred independence, the proposed method mitigates correlated bias and improves verification performance, achieving up to a 4.5% accuracy gain over majority voting. --- ### PRIME: Training Free Proactive Reasoning via Iterative Memory Evolution for User-Centric Agent Authors: Prince Zizhuang Wang, Shuli Jiang Published: 2026-04-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.07645v1 The development of autonomous tool-use agents for complex, long-horizon tasks in collaboration with human users has become the frontier of agentic research. During multi-turn Human-AI interactions, the dynamic and uncertain nature of user demands poses a significant challenge; agents must not only invoke tools but also iteratively refine their understanding of user intent through effective communication. While recent advances in reinforcement learning offer a path to more capable tool-use agents, existing approaches require expensive training costs and struggle with turn-level credit assignment across extended interaction horizons. To this end, we introduce PRIME (Proactive Reasoning via Iterative Memory Evolution), a gradient-free learning framework that enables continuous agent evolvement through explicit experience accumulation rather than expensive parameter optimization. PRIME distills multi-turn interaction trajectories into structured, human-readable experiences organized across three semantic zones: successful strategies, failure patterns, and user preferences. These experiences evolve through meta-level operations and guide future agent behavior via retrieval-augmented generation. Our experiments across several diverse user-centric environments demonstrate that PRIME achieves competitive performance with gradient-based methods while offering cost-efficiency and interpretability. Together, PRIME presents a practical paradigm for building proactive, collaborative agents that learn from Human-AI interaction without the computational burden of gradient-based training. --- ### Safe Large-Scale Robust Nonlinear MPC in Milliseconds via Reachability-Constrained System Level Synthesis on the GPU Authors: Jeffrey Fang, Glen Chou Published: 2026-04-08 Categories: cs.RO, cs.AI, eess.SY, math.OC arXiv: https://arxiv.org/abs/2604.07644v1 We present GPU-SLS, a GPU-parallelized framework for safe, robust nonlinear model predictive control (MPC) that scales to high-dimensional uncertain robotic systems and long planning horizons. Our method jointly optimizes an inequality-constrained, dynamically-feasible nominal trajectory, a tracking controller, and a closed-loop reachable set under disturbance, all in real-time. To efficiently compute nominal trajectories, we develop a sequential quadratic programming procedure with a novel GPU-accelerated quadratic program (QP) solver that uses parallel associative scans and adaptive caching within an alternating direction method of multipliers (ADMM) framework. The same GPU QP backend is used to optimize robust tracking controllers and closed-loop reachable sets via system level synthesis (SLS), enabling reachability-constrained control in both fixed- and receding-horizon settings. We achieve substantial performance gains, reducing nominal trajectory solve times by 97.7% relative to state-of-the-art CPU solvers and 71.8% compared to GPU solvers, while accelerating SLS-based control and reachability by 237x. Despite large problem scales, our method achieves 100% empirical safety, unlike high-dimensional learning-based reachability baselines. We validate our approach on complex nonlinear systems, including whole-body quadrupeds (61D) and humanoids (75D), synthesizing robust control policies online on the GPU in 20 milliseconds on average and scaling to problems with 2 x 10^5 decision variables and 8 x 10^4 constraints. The implementation of our method is available at https://github.com/Jeff300fang/gpu_sls. --- ### Narrix: Remixing Narrative Strategies from Examples for Story Writing Authors: Chao Zhang, Shunan Guo, Abe Davis, Eunyee Koh Published: 2026-04-08 Categories: cs.HC, cs.CL arXiv: https://arxiv.org/abs/2604.07643v1 Experienced storytellers decompose stories into local narrative strategies and how these strategies shape higher-level arcs. This decomposition helps writers recognize patterns in others' work and adapt those patterns to tell new stories. Novices, however, struggle to identify these strategies or to reuse them effectively. We present Narrix, a novel writing tool that helps novice writers recognize narrative strategies in example stories and repurpose these strategies in their own writing. Narrix analyzes strategies in example stories, highlights them with color-coded lexical cues and explanations, and situates them on an interactive story arc for exploration by emotional shifts and turning points. Writers then drag strategies onto multi-dimensional tracks and apply block-scoped edits to revise or continue their drafts through controlled generation steered by specified strategies. Through a within-subjects study (N=12), Narrix showed improved participants' retention, confidence, and creative adaptation of narrative strategies compared to a baseline chat-based writing interface. --- ### Exponential quantum advantage in processing massive classical data Authors: Haimeng Zhao, Alexander Zlokapa, Hartmut Neven, Ryan Babbush, John Preskill, Jarrod R. McClean, Hsin-Yuan Huang Published: 2026-04-08 Categories: quant-ph, cs.AI, cs.CC, cs.IT, cs.LG arXiv: https://arxiv.org/abs/2604.07639v1 Broadly applicable quantum advantage, particularly in classical data processing and machine learning, has been a fundamental open problem. In this work, we prove that a small quantum computer of polylogarithmic size can perform large-scale classification and dimension reduction on massive classical data by processing samples on the fly, whereas any classical machine achieving the same prediction performance requires exponentially larger size. Furthermore, classical machines that are exponentially larger yet below the required size need superpolynomially more samples and time. We validate these quantum advantages in real-world applications, including single-cell RNA sequencing and movie review sentiment analysis, demonstrating four to six orders of magnitude reduction in size with fewer than 60 logical qubits. These quantum advantages are enabled by quantum oracle sketching, an algorithm for accessing the classical world in quantum superposition using only random classical data samples. Combined with classical shadows, our algorithm circumvents the data loading and readout bottleneck to construct succinct classical models from massive classical data, a task provably impossible for any classical machine that is not exponentially larger than the quantum machine. These quantum advantages persist even when classical machines are granted unlimited time or if BPP=BQP, and rely only on the correctness of quantum mechanics. Together, our results establish machine learning on classical data as a broad and natural domain of quantum advantage and a fundamental test of quantum mechanics at the complexity frontier. --- ### Variational Approximated Restricted Maximum Likelihood Estimation for Spatial Data Authors: Debjoy Thakur Published: 2026-04-08 Categories: stat.ML, cs.LG, stat.AP arXiv: https://arxiv.org/abs/2604.07635v2 This research considers a scalable inference for spatial data modeled through Gaussian intrinsic conditional autoregressive (ICAR) structures. The classical estimation method, restricted maximum likelihood (REML), requires repeated inversion and factorization of large, sparse precision matrices, which makes this computation costly. To sort this problem out, we propose a variational restricted maximum likelihood (VREML) framework that approximates the intractable marginal likelihood using a Gaussian variational distribution. By constructing an evidence lower bound (ELBO) on the restricted likelihood, we derive a computationally efficient coordinate-ascent algorithm for jointly estimating the spatial random effects and variance components. In this article, we theoretically establish the monotone convergence of ELBO and mathematically exhibit that the variational family is exact under Gaussian ICAR settings, which is an indication of nullifying approximation error at the posterior level. We empirically establish the supremacy of our VREML over MLE and INLA. --- ### VSAS-Bench: Real-Time Evaluation of Visual Streaming Assistant Models Authors: Pavan Kumar Anasosalu Vasu, Cem Koc, Fartash Faghri, Chun-Liang Li, Bo Feng, Zhengfeng Lai, Meng Cao, Oncel Tuzel, Hadi Pouransari Published: 2026-04-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.07634v2 Streaming vision-language models (VLMs) continuously generate responses given an instruction prompt and an online stream of input frames. This is a core mechanism for real-time visual assistants. Existing VLM frameworks predominantly assess models in offline settings. In contrast, the performance of a streaming VLM depends on additional metrics beyond pure video understanding, including proactiveness, which reflects the timeliness of the model's responses, and consistency, which captures the robustness of its responses over time. To address this limitation, we propose VSAS-Bench, a new framework and benchmark for Visual Streaming Assistants. In contrast to prior benchmarks that primarily employ single-turn question answering on video inputs, VSAS-Bench features temporally dense annotations with over 18,000 annotations across diverse input domains and task types. We introduce standardized synchronous and asynchronous evaluation protocols, along with metrics that isolate and measure distinct capabilities of streaming VLMs. Using this framework, we conduct large-scale evaluations of recent video and streaming VLMs, analyzing the accuracy-latency trade-off under key design factors such as memory buffer length, memory access policy, and input resolution, yielding several practical insights. Finally, we show empirically that conventional VLMs can be adapted to streaming settings without additional training, and demonstrate that these adapted models outperform recent streaming VLMs. For example, Qwen3-VL-4B surpasses Dispider, the best streaming VLM on our benchmark, by 3% under the asynchronous protocol. The benchmark and code will be available at https://github.com/apple/ml-vsas-bench. --- ### Sheaf-Laplacian Obstruction and Projection Hardness for Cross-Modal Compatibility on a Modality-Independent Site Authors: Tibor Sloboda Published: 2026-04-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.07632v2 Cross-modal representations vary in how easily they can be aligned, and compatibility is generally non-transitive: two modalities may align through an intermediate modality at lower complexity than through a direct map. We introduce a reference formalism that evaluates all modalities on a fixed neighborhood site and defines two directed invariants. Projection hardness \(H_{a\to b}(\varepsilon)\) is the minimum complexity within a nested Lipschitz-controlled family required to reach error \(\varepsilon\). For a declared local projection family, sheaf-Laplacian obstruction \(C_{a\to b}(\varepsilon)\) is the minimum variation of locally fitted projection parameters required to reach the same error. Under identity restrictions, obstruction is the graph Dirichlet energy of a vector-valued parameter field; the sheaf formulation identifies zero energy with successful gluing and extends to edge-dependent transports and heterogeneous parameter spaces. We relate obstruction to the site spectral gap and excess global-map error, and construct ReLU examples showing non-transitive compatibility and a quadratic separation between staged and direct width. Controlled synthetic calibrations recover the predicted hardness separation, cut-induced obstruction scaling, and sensitivity to the fixed site graph. --- ### Trilinear Compute-in-Memory Architecture for Energy-Efficient Transformer Acceleration Authors: Md Zesun Ahmed Mia, Jiahui Duan, Kai Ni, Abhronil Sengupta Published: 2026-04-08 Categories: cs.AR, cs.ET, cs.NE arXiv: https://arxiv.org/abs/2604.07628v1 Self-attention in Transformers generates dynamic operands that force conventional Compute-in-Memory (CIM) accelerators into costly non-volatile memory (NVM) reprogramming cycles, degrading throughput and stressing device endurance. Existing solutions either reduce but retain NVM writes through matrix decomposition or sparsity, or move attention computation to digital CMOS at the expense of NVM density. We present TrilinearCIM, a Double-Gate FeFET (DG-FeFET)-based architecture that uses back-gate modulation to realize a three-operand multiply-accumulate primitive for in-memory attention computation without dynamic ferroelectric reprogramming. Evaluated on BERT-base (GLUE) and ViT-base (ImageNet and CIFAR), TrilinearCIM outperforms conventional CIM on seven of nine GLUE tasks while achieving up to 46.6\% energy reduction and 20.4\% latency improvement over conventional FeFET CIM at 37.3\% area overhead. To our knowledge, this is the first architecture to perform complete Transformer attention computation exclusively in NVM cores without runtime reprogramming. --- ### DIVERSED: Relaxed Speculative Decoding via Dynamic Ensemble Verification Authors: Ziyi Wang, Siva Rajesh Kasa, Ankith M S, Santhosh Kumar Kasa, Jiaru Zou, Sumit Negi, Ruqi Zhang, Nan Jiang, Qifan Song Published: 2026-04-08 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.07622v1 Speculative decoding is an effective technique for accelerating large language model inference by drafting multiple tokens in parallel. In practice, its speedup is often bottlenecked by a rigid verification step that strictly enforces the accepted token distribution to exactly match the target model. This constraint leads to the rejection of many plausible tokens, lowering the acceptance rate and limiting overall time speedup. To overcome this limitation, we propose Dynamic Verification Relaxed Speculative Decoding (DIVERSED), a relaxed verification framework that improves time efficiency while preserving generation quality. DIVERSED learns an ensemble-based verifier that blends the draft and target model distributions with a task-dependent and context-dependent weight. We provide theoretical justification for our approach and demonstrate empirically that DIVERSED achieves substantially higher inference efficiency compared to standard speculative decoding methods. Code is available at: https://github.com/comeusr/diversed. --- ### ADAG: Automatically Describing Attribution Graphs Authors: Aryaman Arora, Zhengxuan Wu, Jacob Steinhardt, Sarah Schwettmann Published: 2026-04-08 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.07615v1 In language model interpretability research, \textbf{circuit tracing} aims to identify which internal features causally contributed to a particular output and how they affected each other, with the goal of explaining the computations underlying some behaviour. However, all prior circuit tracing work has relied on ad-hoc human interpretation of the role that each feature in the circuit plays, via manual inspection of data artifacts such as the dataset examples the component activates on. We introduce \textbf{ADAG}, an end-to-end pipeline for describing these attribution graphs which is fully automated. To achieve this, we introduce \textit{attribution profiles} which quantify the functional role of a feature via its input and output gradient effects. We then introduce a novel clustering algorithm for grouping features, and an LLM explainer--simulator setup which generates and scores natural-language explanations of the functional role of these feature groups. We run our system on known human-analysed circuit-tracing tasks and recover interpretable circuits, and further show ADAG can find steerable clusters which are responsible for a harmful advice jailbreak in Llama 3.1 8B Instruct. --- ### Towards Real-Time Human-AI Musical Co-Performance: Accompaniment Generation with Latent Diffusion Models and MAX/MSP Authors: Tornike Karchkhadze, Shlomo Dubnov Published: 2026-04-08 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2604.07612v1 We present a framework for real-time human-AI musical co-performance, in which a latent diffusion model generates instrumental accompaniment in response to a live stream of context audio. The system combines a MAX/MSP front-end-handling real-time audio input, buffering, and playback-with a Python inference server running the generative model, communicating via OSC/UDP messages. This allows musicians to perform in MAX/MSP - a well-established, real-time capable environment - while interacting with a large-scale Python-based generative model, overcoming the fundamental disconnect between real-time music tools and state-of-the-art AI models. We formulate accompaniment generation as a sliding-window look-ahead protocol, training the model to predict future audio from partial context, where system latency is a critical constraint. To reduce latency, we apply consistency distillation to our diffusion model, achieving a 5.4x reduction in sampling time, with both models achieving real-time operation. Evaluated on musical coherence, beat alignment, and audio quality, both models achieve strong performance in the Retrospective regime and degrade gracefully as look-ahead increases. These results demonstrate the feasibility of diffusion-based real-time accompaniment and expose the fundamental trade-off between model latency, look-ahead depth, and generation quality that any such system must navigate. ---