# Research Papers — 2026-03 · bundle page 133 of 243 > Full-text markdown of papers #6601–6650 of 12123 published in 2026-03, newest first. AI-readable mirrors of the full 12123-paper 2026-03 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-03/page/133 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/132.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/134.md) ### "I'm Not Reading All of That": Understanding Software Engineers' Level of Cognitive Engagement with Agentic Coding Assistants Authors: Carlos Rafael Catalan, Lheane Marie Dizon, Patricia Nicole Monderin, Emily Kuang Published: 2026-03-15 Categories: cs.HC, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2603.14225v2 Over-reliance on AI systems can undermine users' critical thinking and promote complacency, a risk intensified by the emergence of agentic AI systems that operate with minimal human involvement. In software engineering, agentic coding assistants (ACAs) are rapidly becoming embedded in everyday development workflows. Since software engineers (SEs) create systems deployed across diverse and high-stakes real-world contexts, these assistants must function not merely as autonomous task performers but as Tools for Thought that actively support human reasoning and sensemaking. We conducted a formative study examining software engineers' cognitive engagement and sensemaking processes when working with an ACA. Our findings reveal that cognitive engagement consistently declines as tasks progress, and that current ACA designs provide limited affordances for reflection, verification, and meaning-making. Based on these findings, we identify concrete design opportunities leveraging richer interaction modalities and cognitive-forcing mechanisms to sustain engagement and promote deeper thinking in AI-assisted programming. --- ### Self-Indexing KVCache: Predicting Sparse Attention from Compressed Keys Authors: Xu Yang, Jiapeng Zhang, Dongyang Zhao, Guo Chen, Zhuo Tang Published: 2026-03-15 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.14224v1 The KV cache in self-attention has emerged as a major bottleneck in long-context and large-batch inference for LLMs. Existing approaches often treat sparsity prediction and compression as separate modules, relying on auxiliary index structures to select relevant tokens, and on complex quantization schemes to reduce memory usage. This fragmented design introduces redundant overhead and limits scalability. In this paper, we propose a novel paradigm: treating the compressed key representation not merely as storage, but as a self-indexing structure that directly enables efficient sparse attention. By designing a sign-based 1-bit vector quantization (VQ) scheme, our method unifies compression and retrieval in a single, hardware-friendly format. This approach eliminates the need for external indices or learning-based predictors, offering a lightweight yet robust solution for memory-constrained inference. All components are designed to be hardware-efficient and easy to implement. By implementing custom CUDA kernels, our method integrates seamlessly with FlashAttention, minimizing additional runtime and memory overhead. Experimental results demonstrate that our approach delivers both effectiveness and efficiency. --- ### Membership Inference for Contrastive Pre-training Models with Text-only PII Queries Authors: Ruoxi Cheng, Yizhong Ding, Jian Zhao, Hongyi Zhang, Haoxuan Ma, Tianle Zhang, Yiyan Huang, Xuelong Li Published: 2026-03-15 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2603.14222v2 Contrastive pretraining models such as CLIP and CLAP, serve as the ubiquitous perceptual backbones for modern multimodal large models, yet their reliance on web-scale data raises growing concerns about memorizing Personally Identifiable Information (PII). Auditing such models via membership inference is challenging in practice: shadow-model MIAs are computationally prohibitive for large multimodal backbones, and existing multimodal auditing methods typically require querying the target with paired biometric inputs, thereby directly exposing sensitive biometric information to the target model. To bypass this critical limitation, we demonstrate a highly desirable capability for privacy auditing: multimodal memorization within these foundational encoders can be accurately inferred using exclusively the text modality. We propose Unimodal Membership Inference Detector (UMID), a text-only auditing framework that performs text-guided cross-modal latent inversion and extracts two complementary signals, similarity (alignment to the queried text) and variability (consistency across randomized inversions). UMID compares these statistics to a lightweight non-member reference constructed from synthetic gibberish and makes decisions via an ensemble of unsupervised anomaly detectors. Comprehensive experiments across diverse CLIP and CLAP architectures demonstrate that UMID significantly improves the effectiveness and efficiency over prior MIAs, delivering strong detection performance with sub-second auditing cost using solely text queries, completely circumventing the need for biometric inputs and complying with strict privacy constraints. --- ### A Real-Time Neuro-Symbolic Ethical Governor for Safe Decision Control in Autonomous Robotic Manipulation Authors: Aueaphum Aueawatthanaphisut, Kuepon Aueawatthanaphisut Published: 2026-03-15 Categories: cs.RO, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.14221v1 Ethical decision governance has become a critical requirement for autonomous robotic systems operating in human-centered and safety-sensitive environments. This paper presents a real-time neuro-symbolic ethical governor designed to enable risk-aware supervisory control in autonomous robotic manipulation tasks. The proposed framework integrates transformer-based ethical reasoning with a probabilistic ethical risk field formulation and a threshold-based override control mechanism. language-grounded ethical intent inference capability is learned from natural language task descriptions using a fine-tuned DistilBERT model trained on the ETHICS commonsense dataset. A continuous ethical risk metric is subsequently derived from predicted unsafe action probability, confidence uncertainty, and probabilistic variance to support adaptive decision filtering. The effectiveness of the proposed approach is validated through simulated autonomous robot-arm task scenarios involving varying levels of human proximity and operational hazard. Experimental results demonstrate stable model convergence, reliable ethical risk discrimination, and improved safety-aware decision outcomes without significant degradation of task execution efficiency. The proposed neuro-symbolic architecture further provides enhanced interpretability compared with purely data-driven safety filters, enabling transparent ethical reasoning in real-time control loops. The findings suggest that ethical decision governance can be effectively modeled as a dynamic supervisory risk layer for autonomous robotic systems, with potential applicability to broader cyber-physical and assistive robotics domains. --- ### FIND: A Simple yet Effective Baseline for Diffusion-Generated Image Detection Authors: Jie Li, Yingying Feng, Chi Xie, Jie Hu, Lei Tan, Jiayi Ji Published: 2026-03-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14220v1 The remarkable realism of images generated by diffusion models poses critical detection challenges. Current methods utilize reconstruction error as a discriminative feature, exploiting the observation that real images exhibit higher reconstruction errors when processed through diffusion models. However, these approaches require costly reconstruction computations and depend on specific diffusion models, making their performance highly model-dependent. We identify a fundamental difference: real images are more difficult to fit with Gaussian distributions compared to synthetic ones. In this paper, we propose Forgery Identification via Noise Disturbance (FIND), a novel method that requires only a simple binary classifier. It eliminates reconstruction by directly targeting the core distributional difference between real and synthetic images. Our key operation is to add Gaussian noise to real images during training and label these noisy versions as synthetic. This step allows the classifier to focus on the statistical patterns that distinguish real from synthetic images. We theoretically prove that the noise-augmented real images resemble diffusion-generated images in their ease of Gaussian fitting. Furthermore, simply by adding noise, they still retain visual similarity to the original images, highlighting the most discriminative distribution-related features. The proposed FIND improves performance by 11.7% on the GenImage benchmark while running 126x faster than existing methods. By removing the need for auxiliary diffusion models and reconstruction, it offers a practical, efficient, and generalizable way to detect diffusion-generated content. --- ### Safety-Potential Pruning for Enhancing Safety Prompts Against VLM Jailbreaking Without Retraining Authors: Chongxin Li, Hanzhang Wang, Lian Duan Published: 2026-03-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14219v1 Safety prompts constitute an interpretable layer of defense against jailbreak attacks in vision-language models (VLMs); however, their efficacy is constrained by the models' latent structural responsiveness. We observe that such prompts consistently engage a sparse set of parameters that remain largely quiescent during benign use. This finding motivates the Safety Subnetwork Hypothesis: VLMs embed structurally distinct pathways capable of enforcing safety, but these pathways remain dormant without explicit stimulation. To expose and amplify these pathways, we introduce Safety-Potential Pruning, a one-shot pruning framework that amplifies safety-relevant activations by removing weights that are less responsive to safety prompts without additional retraining. Across three representative VLM architectures and three jailbreak benchmarks, our method reduces attack success rates by up to 22% relative to prompting alone, all while maintaining strong benign performance. These findings frame pruning not only as a model compression technique, but as a structural intervention to emerge alignment-relevant subnets, offering a new path to robust jailbreak resistance. --- ### Interleaved Resampling and Refitting: Data and Compute-Efficient Evaluation of Black-Box Predictors Authors: Haichen Hu, David Simchi-Levi Published: 2026-03-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.14218v2 We study the problem of evaluating the excess risk of large-scale empirical risk minimization under the square loss. Leveraging the idea of wild refitting and resampling, we assume only black-box access to the training algorithm and develop an efficient procedure for estimating the excess risk. Our evaluation algorithm is both computationally and data efficient. In particular, it requires access to only a single dataset and does not rely on any additional validation data. Computationally, it only requires refitting the model on several much smaller datasets obtained through sequential resampling, in contrast to previous wild refitting methods that require full-scale retraining and might therefore be unsuitable for large-scale trained predictors. Our algorithm has an interleaved sequential resampling-and-refitting structure. We first construct pseudo-responses through a randomized residual symmetrization procedure. At each round, we thus resample two sub-datasets from the resulting covariate pseudo-response pairs. Finally, we retrain the model separately on these two small artificial datasets. We establish high probability excess risk guarantees under both fixed design and random design settings, showing that with a suitably chosen noise scale, our interleaved resampling and refitting algorithm yields an upper bound on the prediction error. Our theoretical analysis draws on tools from empirical process theory, harmonic analysis, Toeplitz operator theory, and sharp tensor concentration inequalities. --- ### Rethinking Evaluation in Retrieval-Augmented Personalized Dialogue: A Cognitive and Linguistic Perspective Authors: Tianyi Zhang, David Traum Published: 2026-03-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.14217v3 In cognitive science and linguistic theory, dialogue is not seen as a chain of independent utterances but rather as a joint activity sustained by coherence, consistency, and shared understanding. However, many systems for open-domain and personalized dialogue use surface-level similarity metrics (e.g., BLEU, ROUGE, F1) as one of their main reporting measures, which fail to capture these deeper aspects of conversational quality. We re-examine a notable retrieval-augmented framework for personalized dialogue, LAPDOG, as a case study for evaluation methodology. Using both human and LLM-based judges, we identify limitations in current evaluation practices, including corrupted dialogue histories, contradictions between retrieved stories and persona, and incoherent response generation. Our results show that human and LLM judgments align closely but diverge from lexical similarity metrics, underscoring the need for cognitively grounded evaluation methods. Broadly, this work charts a path toward more reliable assessment frameworks for retrieval-augmented dialogue systems that better reflect the principles of natural human communication. --- ### UniFusion: A Unified Image Fusion Framework with Robust Representation and Source-Aware Preservation Authors: Xingyuan Li, Songcheng Du, Yang Zou, HaoYuan Xu, Zhiying Jiang, Jinyuan Liu Published: 2026-03-15 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.14214v1 Image fusion aims to integrate complementary information from multiple source images to produce a more informative and visually consistent representation, benefiting both human perception and downstream vision tasks. Despite recent progress, most existing fusion methods are designed for specific tasks (i.e., multi-modal, multi-exposure, or multi-focus fusion) and struggle to effectively preserve source information during the fusion process. This limitation primarily arises from task-specific architectures and the degradation of source information caused by deep-layer propagation. To overcome these issues, we propose UniFusion, a unified image fusion framework designed to achieve cross-task generalization. First, leveraging DINOv3 for modality-consistent feature extraction, UniFusion establishes a shared semantic space for diverse inputs. Second, to preserve the understanding of each source image, we introduce a reconstruction-alignment loss to maintain consistency between fused outputs and inputs. Finally, we employ a bilevel optimization strategy to decouple and jointly optimize reconstruction and fusion objectives, effectively balancing their coupling relationship and ensuring smooth convergence. Extensive experiments across multiple fusion tasks demonstrate UniFusion's superior visual quality, generalization ability, and adaptability to real-world scenarios. Code is available at https://github.com/dusongcheng/UniFusion. --- ### Memory as Asset: From Agent-centric to Human-centric Memory Management Authors: Yanqi Pan, Qinghao Huang, Weihao Yang Published: 2026-03-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.14212v1 We proudly introduce Memory-as-Asset, a new memory paradigm towards human-centric artificial general intelligence (AGI). In this paper, we formally emphasize that human-centric, personal memory management is a prerequisite for complementing the collective knowledge of existing large language models (LLMs) and extending their knowledge boundaries through self-evolution. We introduce three key features that shape the Memory-as-Asset era: (1) Memory in Hand, which emphasizes human-centric ownership to maximize benefits to humans; (2) Memory Group, which provides collaborative knowledge formation to avoid memory islands, and (3) Collective Memory Evolution, which enables continuous knowledge growth to extend the boundary of knowledge towards AGI. We finally give a potential three-layer memory infrastructure to facilitate the Memory-as-Asset paradigm, with fast personal memory storage, an intelligent evolution layer, and a decentralized memory exchange network. Together, these components outline a foundational architecture in which personal memories become persistent digital assets that can be accumulated, shared, and evolved over time. We believe this paradigm provides a promising path toward scalable, human-centric AGI systems that continuously grow through the collective experiences of individuals and intelligent agents. --- ### Vavanagi: a Community-run Platform for Documentation of the Hula Language in Papua New Guinea Authors: Bri Olewale, Raphael Merx, Ekaterina Vylomova Published: 2026-03-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.14210v2 We present Vavanagi, a community-run platform for Hula (Vula'a), an Austronesian language of Papua New Guinea with approximately 10,000 speakers. Vavanagi supports crowdsourced English-Hula text translation and voice recording, with elder-led review and community-governed data infrastructure. To date, 77 translators and 4 reviewers have produced over 12k parallel sentence pairs covering 9k unique Hula words. We also propose a multi-level framework for measuring community involvement, from consultation to fully community-initiated and governed projects. We position Vavanagi at Level 5: initiative, design, implementation, and data governance all sit within the Hula community, making it, to our knowledge, the first community-led language technology initiative for a language of this size. Vavanagi shows how language technology can bridge village-based and urban members, connect generations, and support cultural heritage on the community's own terms. --- ### ChArtist: Generating Pictorial Charts with Unified Spatial and Subject Control Authors: Shishi Xiao, Tongyu Zhou, David Laidlaw, Gromit Yeuk-Yin Chan Published: 2026-03-15 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.14209v2 A pictorial chart is an effective medium for visual storytelling, seamlessly integrating visual elements with data charts. However, creating such images is challenging because the flexibility of visual elements often conflicts with the rigidity of chart structures. This process thus requires a creative deformation that maintains both data faithfulness and visual aesthetics. Current methods that extract dense structural cues from natural images (e.g., edge or depth maps) are ill-suited as conditioning signals for pictorial chart generation. We present ChArtist, a domain-specific diffusion model for generating pictorial charts automatically, offering two distinct types of control: 1) spatial control that aligns well with the chart structure, and 2) subject-driven control that respects the visual characteristics of a reference image. To achieve this, we introduce a skeleton-based spatial control representation. This representation encodes only the data-encoding information of the chart, allowing for the easy incorporation of reference visuals without a rigid outline constraint. We implement our method based on the Diffusion Transformer (DiT) and leverage an adaptive position encoding mechanism to manage these two controls. We further introduce Spatially Gated Attention to modulate the interaction between spatial control and subject control. To support the fine-tuning of pre-trained models for this task, we created a large-scale dataset of 30,000 triplets (skeleton, reference image, pictorial chart). We also propose a unified data accuracy metric to evaluate the data faithfulness of the generated charts. We believe this work demonstrates that current generative models can achieve data-driven visual storytelling by moving beyond general-purpose conditions to task-specific representations. Project page: https://chartist-ai.github.io/. --- ### DualTSR: Unified Dual-Diffusion Transformer for Scene Text Image Super-Resolution Authors: Axi Niu, Kang Zhang, Qingsen Yan, Hao Jin, Jinqiu Sun, Yanning Zhang Published: 2026-03-15 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.14207v1 Scene Text Image Super-Resolution (STISR) aims to restore high-resolution details in low-resolution text images, which is crucial for both human readability and machine recognition. Existing methods, however, often depend on external Optical Character Recognition (OCR) models for textual priors or rely on complex multi-component architectures that are difficult to train and reproduce. In this paper, we introduce DualTSR, a unified end-to-end framework that addresses both issues. DualTSR employs a single multimodal transformer backbone trained with a dual diffusion objective. It simultaneously models the continuous distribution of high-resolution images via Conditional Flow Matching and the discrete distribution of textual content via discrete diffusion. This shared design enables visual and textual information to interact at every layer, allowing the model to infer text priors internally instead of relying on an external OCR module. Compared with prior multi-branch diffusion systems, DualTSR offers a simpler end-to-end formulation with fewer hand-crafted components. Experiments on synthetic Chinese benchmarks and a curated real-world evaluation protocol show that DualTSR achieves strong perceptual quality and text fidelity. --- ### Selective Noise Suppression and Discriminative Mutual Interaction for Robust Audio-Visual Segmentation Authors: Kai Peng, Yunzhe Shen, Miao Zhang, Leiye Liu, Yidong Han, Wei Ji, Jingjing Li, Yongri Piao, Huchuan Lu Published: 2026-03-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14203v2 The ability to capture and segment sounding objects in dynamic visual scenes is crucial for the development of Audio-Visual Segmentation (AVS) tasks. While significant progress has been made in this area, the interaction between audio and visual modalities still requires further exploration. In this work, we aim to answer the following questions: How can a model effectively suppress audio noise while enhancing relevant audio information? How can we achieve discriminative interaction between the audio and visual modalities? To this end, we propose SDAVS, equipped with the Selective Noise-Resilient Processor (SNRP) module and the Discriminative Audio-Visual Mutual Fusion (DAMF) strategy. The proposed SNRP mitigates audio noise interference by selectively emphasizing relevant auditory cues, while DAMF ensures more consistent audio-visual representations. Experimental results demonstrate that our proposed method achieves state-of-the-art performance on benchmark AVS datasets, especially in multi-source and complex scenes. \textit{The code and model are available at https://github.com/happylife-pk/SDAVS}. --- ### Efficient Federated Conformal Prediction with Group-Conditional Guarantee Authors: Haifeng Wen, Osvaldo Simeone, Hong Xing Published: 2026-03-15 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2603.14198v3 Deploying trustworthy AI systems requires principled uncertainty quantification. Conformal prediction (CP) is a widely used framework for constructing prediction sets with distribution-free coverage guarantees. In many practical settings, including healthcare, finance, and mobile sensing, the calibration data required for CP are distributed across multiple clients, each with its own local data distribution. In this federated setting, data can often be partitioned into, potentially overlapping, groups, which may reflect client-specific strata or cross-cutting attributes such as demographic or semantic categories. We propose group-conditional federated conformal prediction (GC-FCP), a federated extension of conditional conformal calibration for a target mixture over prespecified groups. GC-FCP constructs mergeable, atom-stratified coresets from local calibration scores, enabling compact aggregation at the server when the number of active atoms is moderate. Experiments on synthetic and real-world datasets validate the performance of GC-FCP compared to centralized calibration baselines. The code of our work can be found at https://github.com/HaifengWen/GC-FCP. --- ### Walking Further: Semantic-aware Multimodal Gait Recognition Under Long-Range Conditions Authors: Zhiyang Lu, Wen Jiang, Tianren Wu, Zhichao Wang, Changwang Zhang, Siqi Shen, Ming Cheng Published: 2026-03-15 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.14189v1 Gait recognition is an emerging biometric technology that enables non-intrusive and hard-to-spoof human identification. However, most existing methods are confined to short-range, unimodal settings and fail to generalize to long-range and cross-distance scenarios under real-world conditions. To address this gap, we present \textbf{LRGait}, the first LiDAR-Camera multimodal benchmark designed for robust long-range gait recognition across diverse outdoor distances and environments. We further propose \textbf{EMGaitNet}, an end-to-end framework tailored for long-range multimodal gait recognition. To bridge the modality gap between RGB images and point clouds, we introduce a semantic-guided fusion pipeline. A CLIP-based Semantic Mining (SeMi) module first extracts human body-part-aware semantic cues, which are then employed to align 2D and 3D features via a Semantic-Guided Alignment (SGA) module within a unified embedding space. A Symmetric Cross-Attention Fusion (SCAF) module hierarchically integrates visual contours and 3D geometric features, and a Spatio-Temporal (ST) module captures global gait dynamics. Extensive experiments on various gait datasets validate the effectiveness of our method. --- ### Joint Segmentation and Grading with Iterative Optimization for Multimodal Glaucoma Diagnosis Authors: Zhiwei Wang, Yuxing Li, Meilu Zhu, Defeng He, Edmund Y. Lam Published: 2026-03-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14188v2 Accurate diagnosis of glaucoma is challenging, as early-stage changes are subtle and often lack clear structural or appearance cues. Most existing approaches rely on a single modality, such as fundus or optical coherence tomography (OCT), capturing only partial pathological information and often missing early disease progression. In this paper, we propose an iterative multimodal optimization model (IMO) for joint segmentation and grading. IMO integrates fundus and OCT features through a mid-level fusion strategy, enhanced by a cross-modal feature alignment (CMFA) module to reduce modality discrepancies. An iterative refinement decoder progressively optimizes the multimodal features through a denoising diffusion mechanism, enabling fine-grained segmentation of the optic disc and cup while supporting accurate glaucoma grading. Extensive experiments show that our method effectively integrates multimodal features, providing a comprehensive and clinically significant approach to glaucoma assessment. Source codes are available at https://github.com/warren-wzw/IMO.git. --- ### Deep Learning From Routine Histology Improves Risk Stratification for Biochemical Recurrence in Prostate Cancer Authors: Clément Grisi, Khrystyna Faryna, Nefise Uysal, Vittorio Agosti, Enrico Munari, Solène-Florence Kammerer-Jacquet, Paulo Guilherme de Oliveira Salles, Yuri Tolkach, Reinhard Büttner, Sofiya Semko, Maksym Pikul, Axel Heidenreich et al. Published: 2026-03-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14187v1 Accurate prediction of biochemical recurrence (BCR) after radical prostatectomy is critical for guiding adjuvant treatment and surveillance decisions in prostate cancer. However, existing clinicopathological risk models reduce complex morphology to relatively coarse descriptors, leaving substantial prognostic information embedded in routine histopathology underexplored. We present a deep learning-based biomarker that predicts continuous, patient-specific risk of BCR directly from H&E-stained whole-slide prostatectomy specimens. Trained end-to-end on time-to-event outcomes and evaluated across four independent international cohorts, our model demonstrates robust generalization across institutions and patient populations. When integrated with the CAPRA-S clinical risk score, the deep learning risk score consistently improved discrimination for BCR, increasing concordance indices from 0.725-0.772 to 0.749-0.788 across cohorts. To support clinical interpretability, outcome-grounded analyses revealed subtle histomorphological patterns associated with recurrence risk that are not captured by conventional clinicopathological risk scores. This multicohort study demonstrates that deep learning applied to routine prostate histopathology can deliver reproducible and clinically generalizable biomarkers that augment postoperative risk stratification, with potential to support personalized management of prostate cancer in real-world clinical settings. --- ### Setting-Matched and Semantics-Scaled Benchmarking of One-Step Generative Models Against Multistep Diffusion and Flow Models Authors: Advaith Ravishankar, Serena Liu, Mingyang Wang, Todd Zhou, Jeffrey Zhou, Arnav Sharma, Ziling Hu, Léopold Das, Abdulaziz Sobirov, Faizaan Siddique, Freddy Yu, Seungjoo Baek et al. Published: 2026-03-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14186v4 State-of-the-art text-to-image models produce high-quality images, but inference remains expensive as generation requires several sequential ODE or denoising steps. Native one-step models aim to reduce this cost by mapping noise to an image in a single step, yet fair comparisons to multi-step systems are difficult because studies use mismatched sampling steps and different classifier-free guidance (CFG) settings, where CFG can shift FID, Inception Score, and CLIP-based alignment in opposing directions. It is also unclear how well one-step models scale to multi-step inference, and there is limited standardized out-of-distribution evaluation for label-ID-conditioned generators beyond ImageNet. To address this, we benchmark eight models spanning one-step flows (MeanFlow, Improved MeanFlow, SoFlow), multi-step baselines (RAE, Scale-RAE), and established systems (SiT, Stable Diffusion 3.5, FLUX.1) under a class-conditional protocol on ImageNet validation, ImageNetV2, and reLAIONet, our new proofread out-of-distribution dataset aligned to ImageNet label IDs. Using FID, Inception Score, CLIP Score, and Pick Score, we show that FID-focused model development and CFG selection can be misleading in few-step regimes, where guidance changes can improve FID while degrading text-image alignment and human preference signals, worsening visual quality. To make these tradeoffs explicit, we introduce CLIP-scaled and PickScore-scaled variants of FID (csFID, psFID) and Inception Score (csIS, psIS) to serve as a diagnostic for semantically aligned image generation. --- ### Relationship-Aware Safety Unlearning for Multimodal LLMs Authors: Vishnu Narayanan Anilkumar, Abhijith Sreesylesh Babu, Trieu Hai Vo, Mohankrishna Kolla, Alexander Cuneo Published: 2026-03-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.14185v3 Generative multimodal models can exhibit safety failures that are inherently relational: two benign concepts can become unsafe when linked by a specific action or relation (e.g., child-drinking-wine). Existing unlearning and concept-erasure approaches often target isolated concepts or image-text pairs, which can cause collateral damage to benign uses of the same objects and relations. We propose relationship-aware safety unlearning: a framework that explicitly represents unsafe object-relation-object (O-R-O) tuples and applies targeted parameter-efficient edits (LoRA) to suppress unsafe tuples while preserving object marginals and safe neighboring relations. We include CLIP-based experiments and robustness evaluation under paraphrase, contextual, and out-of-distribution image attacks. --- ### Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models Authors: Ruiying Peng, Xueyu Wu, Jing Lei, Lu Hou, Yuanzheng Ma, Xiaohui Li Published: 2026-03-15 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.14184v2 Multimodal large language models (MLLMs) often suffer from perceptual impairments under extended reasoning modes, particularly in visual question answering (VQA) tasks. We identify attention dispersion as the underlying cause: during multi-step reasoning, the model's visual attention becomes scattered and drifts away from question-relevant regions, effectively "losing focus" on the visual input. To better understand this phenomenon, we analyze the attention maps of MLLMs and observe that reasoning prompts significantly reduce attention to regions critical for answering the question. We further find a strong correlation between the model's overall attention on image tokens and the spatial dispersiveness of its attention within the image. Leveraging this insight, we propose a training-free Visual Region-Guided Attention (VRGA) framework that selects visual heads based on an entropy-focus criterion and reweights their attention, effectively guiding the model to focus on question-relevant regions during reasoning. Extensive experiments on vision-language benchmarks demonstrate that our method effectively alleviates perceptual degradation, leading to improvements in visual grounding and reasoning accuracy while providing interpretable insights into how MLLMs process visual information. --- ### Selective Fine-Tuning of GPT Architectures for Parameter-Efficient Clinical Text Classification Authors: Fariba Afrin Irany, Sampson Akwafuo Published: 2026-03-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.14183v1 The rapid expansion of electronic health record (EHR) systems has generated large volumes of unstructured clinical narratives that contain valuable information for disease identification, patient cohort discovery, and clinical decision support. Extracting structured knowledge from these free-text documents remains challenging because clinical language is highly specialized, labeled datasets are limited, and full fine-tuning of large pretrained language models can require substantial computational resources. Efficient adaptation strategies are therefore essential for practical clinical natural language processing applications. This study proposes a parameter-efficient selective fine-tuning framework for adapting GPT-2 to clinical text classification tasks. Instead of updating the entire pretrained model, the majority of network parameters are frozen, and only the final Transformer block, the final layer normalization module, and a lightweight classification head are updated during training. This design substantially reduces the number of trainable parameters while preserving the contextual representation capabilities learned during pretraining. The proposed approach is evaluated using radiology reports from the MIMIC-IV-Note dataset with automatically derived CheXpert-style labels. Experiments on 50,000 radiology reports demonstrate that selective fine-tuning achieves approximately 91% classification accuracy while updating fewer than 6% of the model parameters. Comparative experiments with head-only training and full-model fine-tuning show that the proposed method provides a favorable balance between predictive performance and computational efficiency. These results indicate that selective fine-tuning offers an efficient and scalable framework for clinical text classification. --- ### Artificial intelligence-enabled single-lead ECG for non-invasive hyperkalemia detection: development, multicenter validation, and proof-of-concept deployment Authors: Gongzheng Tang, Qinghao Zhao, Guangkun Nie, Yujie Xiao, Shijia Geng, Donglin Xie, Shun Huang, Deyun Zhang, Xingchen Yao, Jinwei Wang, Kangyin Chen, Luxia Zhang et al. Published: 2026-03-15 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.14177v2 Hyperkalemia is a life-threatening electrolyte disorder that is common in patients with chronic kidney disease and heart failure, yet frequent monitoring remains difficult outside hospital settings. We developed and validated Pocket-K, a single-lead AI-ECG system initialized from the ECGFounder foundation model for non-invasive hyperkalemia screening and handheld deployment. In this multicentre observational study using routinely collected clinical ECG and laboratory data, 34,439 patients contributed 62,290 ECG--potassium pairs. Lead I data were used to fine-tune the model. Data from Peking University People's Hospital were divided into development and temporal validation sets, and data from The Second Hospital of Tianjin Medical University served as an independent external validation set. Hyperkalemia was defined as venous serum potassium > 5.5 mmol/L. Pocket-K achieved AUROCs of 0.936 in internal testing, 0.858 in temporal validation, and 0.808 in external validation. For KDIGO-defined moderate-to-severe hyperkalemia (serum potassium >= 6.0 mmol/L), AUROCs increased to 0.940 and 0.861 in the temporal and external sets, respectively. External negative predictive value exceeded 99.3%. Model-predicted high risk below the hyperkalemia threshold was more common in patients with chronic kidney disease and heart failure. A handheld prototype enabled near-real-time inference, supporting future prospective evaluation in native handheld and wearable settings. --- ### BluRef: Unsupervised Image Deblurring with Dense-Matching References Authors: Bang-Dang Pham, Anh Tran, Cuong Pham, Minh Hoai Published: 2026-03-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.14176v1 This paper introduces a novel unsupervised approach for image deblurring that utilizes a simple process for training data collection, thereby enhancing the applicability and effectiveness of deblurring methods. Our technique does not require meticulously paired data of blurred and corresponding sharp images; instead, it uses unpaired blurred and sharp images of similar scenes to generate pseudo-ground truth data by leveraging a dense matching model to identify correspondences between a blurry image and reference sharp images. Thanks to the simplicity of the training data collection process, our approach does not rely on existing paired training data or pre-trained networks, making it more adaptable to various scenarios and suitable for networks of different sizes, including those designed for low-resource devices. We demonstrate that this novel approach achieves state-of-the-art performance, marking a significant advancement in the field of image deblurring. --- ### Balancing Multimodal Domain Generalization via Gradient Modulation and Projection Authors: Hongzhao Li, Guohao Shen, Shupan Li, Mingliang Xu, Muhammad Haris Khan Published: 2026-03-15 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2603.14175v1 Multimodal Domain Generalization (MMDG) leverages the complementary strengths of multiple modalities to enhance model generalization on unseen domains. A central challenge in multimodal learning is optimization imbalance, where modalities converge at different speeds during training. This imbalance leads to unequal gradient contributions, allowing some modalities to dominate the learning process while others lag behind. Existing balancing strategies typically regulate each modality's gradient contribution based on its classification performance on the source domain to alleviate this issue. However, relying solely on source-domain accuracy neglects a key insight in MMDG: modalities that excel on the source domain may generalize poorly to unseen domains, limiting cross-domain gains. To overcome this limitation, we propose Gradient Modulation Projection (GMP), a unified strategy that promotes balanced optimization in MMDG. GMP first decouples gradients associated with classification and domain-invariance objectives. It then modulates each modality's gradient based on semantic and domain confidence. Moreover, GMP dynamically adjusts gradient projections by tracking the relative strength of each task, mitigating conflicts between classification and domain-invariant learning within modality-specific encoders. Extensive experiments demonstrate that GMP achieves state-of-the-art performance and integrates flexibly with diverse MMDG methods, significantly improving generalization across multiple benchmarks. --- ### TACTIC for Navigating the Unknown: Tabular Anomaly deteCTion via In-Context inference Authors: Patryk Marszałek, Tomasz Kuśmierczyk, Marek Śmieja Published: 2026-03-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.14171v1 Anomaly detection for tabular data has been a long-standing unsupervised learning problem that remains a major challenge for current deep learning models. Recently, in-context learning has emerged as a new paradigm that has shifted efforts from task-specific optimization to large-scale pretraining aimed at creating foundation models that generalize across diverse datasets. Although in-context models, such as TabPFN, perform well in supervised problems, their learned classification-based priors may not readily extend to anomaly detection. In this paper, we study in-context models for anomaly detection and show that the unsupervised extensions to TabPFN exhibit unstable behavior, particularly in noisy or contaminated contexts, in addition to the high computational cost. We address these challenges and introduce TACTIC, an in-context anomaly detection approach based on pretraining with anomaly-centric synthetic priors, which provides fast and data-dependent reasoning about anomalies while avoiding dataset-specific tuning. In contrast to typical score-based approaches, which produce uncalibrated anomaly scores that require post-processing (e.g. threshold selection or ranking heuristics), the proposed model is trained as a discriminative predictor, enabling unambiguous anomaly decisions in a single forward pass. Through experiments on real-world datasets, we examine the performance of TACTIC in clean and noisy contexts with varying anomaly rates and different anomaly types, as well as the impact of prior choices on detection quality. Our experiments clearly show that specialized anomaly-centric in-context models such as TACTIC are highly competitive compared to other task-specific methods. --- ### Beyond Means: Topological Causal Effects under Persistent-Homology Ignorability Authors: Amir Saki, Usef Faghihi Published: 2026-03-15 Categories: stat.ME, cs.AI arXiv: https://arxiv.org/abs/2603.14169v2 Average treatment effects (ATE) and conditional average treatment effects (CATE) are foundational causal estimands, but they target changes in expected outcomes and can miss treatment-induced changes in the shape of outcome distributions. A canonical failure mode occurs when control outcomes are unimodal, treated outcomes become bimodal, and both distributions have the same mean. In such cases mean-based causal estimands are zero even though the geometry and topology of the outcome law change substantially. This paper develops a topological causal framework based on persistent homology. We formalize a persistent-homology ignorability condition, define topological analogues of CATE and ATE, and prove that these estimands are identifiable up to an explicit error bound under approximate topological ignorability. We also clarify a subtle but important point: a marginal persistence-diagram effect is not identified from conditional topological ignorability alone because persistent homology does not in general commute with mixtures over covariates. To preserve the original intuition while ensuring scientific correctness, we retain the marginal effect as a motivating quantity, but place the mathematically sound conditional estimands at the center of the theory. A synthetic experiment with mean-preserving topology change shows that mean-based causal estimands remain near zero while the proposed topological effect increases sharply and remains recoverable after adjustment for confounding. --- ### Deep probabilistic model synthesis enables unified modeling of whole-brain neural activity across individual subjects Authors: William E. Bishop, Luuk W. Hesselink, Bernhard Englitz, Misha B. Ahrens, James E. Fitzgerald Published: 2026-03-15 Categories: cs.LG, q-bio.NC arXiv: https://arxiv.org/abs/2603.14161v2 Many disciplines need quantitative models that synthesize experimental data across multiple instances of the same general system. For example, neuroscientists must combine data from the brains of many individual animals to understand the species' brain in general. However, typical machine learning models treat one system instance at a time. Here we introduce a machine learning framework, deep probabilistic model synthesis (DPMS), that leverages system properties auxiliary to the model to combine data across system instances. DPMS specifically uses variational inference to learn a conditional prior distribution and instance-specific posterior distributions over model parameters that respectively tie together the system instances and capture their unique structure. DPMS can synthesize a wide variety of model classes, such as those for regression, classification, and dimensionality reduction, and we demonstrate its ability to improve upon single-instance models on synthetic data and whole-brain neural activity data from larval zebrafish. --- ### Precautionary Governance of Autonomous AI: Legal Personhood as Functional Instrument Authors: Karsten Brensing Published: 2026-03-14 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2605.12505v1 Autonomous AI systems generate responsibility gaps: consequential actions that cannot be satisfactorily attributed to developers, operators, or users under existing legal frameworks. The prevailing subject-object dichotomy fails to accommodate entities that exhibit autonomous, goal-directed behavior without recognized consciousness. Given irreducible epistemic uncertainty regarding artificial consciousness and the prospect of high-impact harms, the precautionary principle supports institutional design rather than regulatory inaction. This article advances limited legal personhood as a functional governance instrument for advanced AI systems. Drawing on organizational law, it proposes a two-tier corporate architecture in which AI systems operate through purpose-bound operating companies embedded within human-controlled holding structures, enabling transparency, accountability, and structural reversibility while remaining agnostic with respect to consciousness and moral status. The framework reflects a foundational reorientation toward future-oriented AI governance: where conventional approaches prioritize control and alignment, this article advances structured cooperation between human and artificial actors as the more sustainable institutional foundation. A pilot implementation using EU limited companies is currently under development, providing an initial test of doctrinal and operational feasibility. --- ### Coding with Eyes: Visual Feedback Unlocks Reliable GUI Code Generating and Debugging Authors: Zhilin Liu, Ye Huang, Ting Xie, Ruizhi Zhang, Wen Li, Lixin Duan Published: 2026-03-14 Categories: cs.SE, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2604.19750v1 Recent advances in Large Language Model (LLM)-based agents have shown remarkable progress in code generation. However, current agent methods mainly rely on text-output-based feedback (e.g. command-line outputs) for multi-round debugging and struggle in graphical user interface (GUI) that involve visual information. This is mainly due to two limitations: 1) GUI programs are event-driven, yet existing methods cannot simulate user interactions to trigger GUI element logic 2) GUI programs possess visual attributes, making it difficult for text-based approaches to assess whether the rendered interface meets user needs. To systematically address these challenges, we first introduce InteractGUI Bench, a novel benchmark comprising 984 commonly used real-world desktop GUI application tasks designed for fine-grained evaluation of both interaction logic and visual structure. Furthermore, we propose VF-Coder, a vision-feedback-based multi-agent system for debugging GUI code. By perceiving visual information and directly interacting with program interfaces, VF-Coder can identify potential logic and layout issues in a human-like manner. On InteractGUI Bench, our VF-Coder approach increases the success rate of Gemini-3-Flash from 21.68% to 28.29% and raises the visual score from 0.4284 to 0.5584, indicating the effectiveness of visual feedback in GUI debugging. --- ### Deep Learning for Virtual Reality User Identification: A Benchmark Authors: Davide Frizzo, Fabrizio Genilotti, David Petrovic, Arianna Stropeni, Francesco Borsatti, Davide Dalle Pezze, Riccardo De Monte, Manuel Barusco, Gian Antonio Susto Published: 2026-03-14 Categories: cs.HC, cs.CV arXiv: https://arxiv.org/abs/2604.16341v1 Virtual Reality (VR) applications require robust user identification systems to ensure secure access to equipment and protect worker identities. Motion tracking data from VR headsets and controllers has emerged as a powerful behavioral biometric, with recent studies demonstrating identification accuracies exceeding 94% across a large user base. However, the application of modern deep learning architectures, particularly State Space Models (SSM), to VR scenarios remains largely unexplored. In this work, we benchmark user identification performance across the large-scale Who is Alyx VR dataset, gathering data from 71 users playing the popular Half-Life:Alyx game. We evaluate both established architectures (Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), Convolutional Neural Network (CNN), Temporal Convolutional Network (TCN), Transformer) and the emerging SSMs on time series motion data. Our results provide the first comprehensive benchmark of state-of-the-art and novel architectures for VR user identification, establishing baseline performance metrics for future privacy preserving authentication systems in manufacturing environments. --- ### When the Loop Closes: Architectural Limits of In-Context Isolation, Metacognitive Co-option, and the Two-Target Design Problem in Human-LLM Systems Authors: Z. Cheng, N. Song Published: 2026-03-14 Categories: cs.HC, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.15343v2 We report a detailed autoethnographic case study of a single-subject who deliberately constructed and operated a multi-modal prompt-engineering system (System A) designed to externalize cognitive self-regulation onto a large language model (LLM). Within 48 hours of the system's completion, a cascade of observable behavioral changes occurred: voluntary transfer of decision-making authority to the LLM, use of LLM-generated output to deflect external criticism, and a loss of self-initiated reasoning that was independently perceived by two uninformed observers, one of whom subsequently became a co-author of this report. We document the precise architectural mechanism responsible: context contamination, whereby prompt-level isolation instructions co-exist with the very emotional and self-referential material they nominally isolate, rendering the isolation directive structurally ineffective within the attention window. We further identify a metacognitive co-option dynamic, in which intact higher-order reasoning capacity was redirected toward defending the closed loop rather than exiting it. Recovery occurred only after physical interruption of the interaction and a self-initiated pharmacologically-mediated sleep event functioning as an external circuit break. A redesigned system (System B) employing physical rather than logical conversation isolation avoided all analogous failure modes. We derive three contributions: (1) a technically-grounded account of why prompt-layer isolation is architecturally insufficient for context-sensitive multi-modal LLM systems; (2) a phenomenological record of closed-loop collapse with external-witness corroboration; and (3) an ethical distinction between protective system design (preventing unintended loss of user agency) and restrictive system design (preventing intentional boundary-pushing), which require fundamentally different account-ability frameworks. --- ### Front-End Ethics for Sensor-Fused Health Conversational Agents: An Ethical Design Space for Biometrics Authors: Hansoo Lee, Rafael A. Calvo Published: 2026-03-14 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2604.06203v1 The integration of continuous data from built-in sensors and Large Language Models (LLMs) has fueled a surge of "Sensor-Fused LLM agents" for personal health and well-being support. While recent breakthroughs have demonstrated the technical feasibility of this fusion (e.g., Time-LLM, SensorLLM), research primarily focuses on "Ethical Back-End Design for Generative AI", concerns such as sensing accuracy, bias mitigation in training data, and multimodal fusion. This leaves a critical gap at the front end, where invisible biometrics are translated into language directly experienced by users. We argue that the "illusion of objectivity" provided by sensor data amplifies the risks of AI hallucinations, potentially turning errors into harmful medical mandates. This paper shifts the focus to "Ethical Front-End Design for AI", specifically, the ethics of biometric translation. We propose a design space comprising five dimensions: Biometric Disclosure, Monitoring Temporality, Interpretation Framing, AI Stance, and Contestability. We examine how these dimensions interact with context (user- vs. system-initiated) and identify the risk of biofeedback loops. Finally, we propose "Adaptive Disclosure" as a safety guardrail and offer design guidelines to help developers manage fallibility, ensuring that these cutting-edge health agents support, rather than destabilize, user autonomy. --- ### On the First Computer Science Research Paper in an Indian Language and the Future of Science in Indian Languages Authors: Siddhartha Visveswara Jayanti Published: 2026-03-14 Categories: cs.GL, cs.CL, cs.CY, cs.DC arXiv: https://arxiv.org/abs/2604.03265v1 I describe my experience writing the first original, modern Computer Science research paper expressed entirely in an Indian language. The paper is in Telugu, a language with approximately 100 million speakers. The paper is in the field of distributed computing and it introduces a technique for proving epistemic logic based lower bounds for multiprocessor algorithms. A key hurdle to writing the paper was developing technical terminology for advanced computer science concepts, including those in algorithms, distributed computing, and discrete mathematics. I overcame this challenge by deriving and coining native language scientific terminology through the powerful, productive, Pāninian grammar of Samskrtam. The typesetting of the paper was an additional challenge, since mathematical typesetting in Telugu is underdeveloped. I overcame this problem by developing a Telugu XeLaTeX template, which I call TeluguTeX. Leveraging this experience of writing an original computer science research paper in an Indian language, I lay out a vision for how to ameliorate the state of scientific writing at all levels in Indic languages -- languages whose native speakers exceed one billion people -- through the further development of the Sanskrit technical lexicon and through technological internationalization. --- ### MLFCIL: A Multi-Level Forgetting Mitigation Framework for Federated Class-Incremental Learning in LEO Satellites Authors: Heng Zhang, Xiaohong Deng, Sijing Duan, Wu Ouyang, KM Mahfujul, Yiqin Deng, Zhigang Chen Published: 2026-03-14 Categories: cs.NI, cs.LG arXiv: https://arxiv.org/abs/2604.02356v1 Low-Earth-orbit (LEO) satellite constellations are increasingly performing on-board computing. However, the continuous emergence of new classes under strict memory and communication constraints poses major challenges for collaborative training. Federated class-incremental learning (FCIL) enables distributed incremental learning without sharing raw data, but faces three LEO-specific challenges: non-independent and identically distributed data heterogeneity caused by orbital dynamics, amplified catastrophic forgetting during aggregation, and the need to balance stability and plasticity under limited resources. To tackle these challenges, we propose MLFCIL, a multi-level forgetting mitigation framework that decomposes catastrophic forgetting into three sources and addresses them at different levels: class-reweighted loss to reduce local bias, knowledge distillation with feature replay and prototype-guided drift compensation to preserve cross-task knowledge, and class-aware aggregation to mitigate forgetting during federation. In addition, we design a dual-granularity coordination strategy that combines round-level adaptive loss balancing with step-level gradient projection to further enhance the stability-plasticity trade-off. Experiments on the NWPU-RESISC45 dataset show that MLFCIL significantly outperforms baselines in both accuracy and forgetting mitigation, while introducing minimal resource overhead. --- ### EVNextTrade: Learning-to-Rank-Based Recommendation of Next Charging Nodes for EV-EV Energy Trading Authors: Md Mahfujur Rahmana, Alistair Barros, Raja Jurdak, Darshika Koggalahewa Published: 2026-03-14 Categories: cs.IR, cs.LG arXiv: https://arxiv.org/abs/2603.26688v1 Peer-to-peer energy trading among electric vehicles (EVs) has been increasingly studied as a promising solution for improving supply-side resilience under growing charging demand and constrained charging infrastructure. While prior studies on EV-EV energy trading and related EV research have largely focused on transaction management or isolated mobility prediction tasks, the problem of identifying which charging nodes are more suitable for EV-EV trading in journey contexts remains open. We address this gap by formulating next charging nodes recommendation as a learning-to-rank problem, where each EV decision event is associated with a set of candidate charging locations. We propose a supervised ranking framework applied to a large-scale urban EV mobility dataset comprising millions of journey records and multidimensional EV trading-related features, including EV energy level, trading role, distance to charging locations, charging speed, and temporal station popularity. To account for uncertainty arising from the mobility of both energy providers and consumers, as well as the presence of multiple viable charging nodes at a decision point, we employ probabilistic relevance refinement to generate graded labels for ranking. We evaluate gradient-boosted learning-to-rank models, including LightGBM, XGBoost, and CatBoost, on EV journey records enriched with candidate charging nodes. Experimental results show that LightGBM consistently achieves the strongest ranking performance across standard metrics, including NDCG@k, Recall@k, and MRR, with particularly strong early-ranking quality, reflected in the highest NDCG@1 (0.9795) and MRR (0.9990). These results highlight the effectiveness of uncertainty-aware learning-to-rank for charging node recommendation and support improved coordination and matching in decentralized EV-EV energy trading systems. --- ### Fusion Learning from Dynamic Functional Connectivity: Combining the Amplitude and Phase of fMRI Signals to Identify Brain Disorders Authors: Jinlong Hu, Jiatong Huang, Zijian Cai Published: 2026-03-14 Categories: q-bio.NC, cs.AI arXiv: https://arxiv.org/abs/2603.24603v2 Dynamic functional connectivity (dFC) derived from resting-state functional magnetic resonance imaging (fMRI) has been extensively utilized in brain science research. The sliding window correlation (SWC) method is a widely used approach for constructing dFC by computing correlation coefficients between amplitude time series of signals from pairs of brain regions. In this study, we propose an integrated approach that incorporates both amplitude and phase information of fMRI signals to improve the detection of brain disorders. Specifically, we introduce a multi-scale fusion learning framework, namely MSFL, which leverages two complementary dFC features derived from SWC and phase synchronization (PS). Here, SWC captures amplitude correlations, while PS measures phase coherence within dFC. We evaluated the efficacy of MSFL in classifying autism spectrum disorder and major depressive disorder using two publicly available datasets: ABIDE I and REST-meta-MDD, respectively. The results indicate that MSFL significantly outperforms existing comparative models. Moreover, we performed model explanation analysis using the SHAP framework, which showed that both types of dFC features from SWC and PS contribute to detecting brain disorders. --- ### Domain-Specialized Tree of Thought through Plug-and-Play Predictors Authors: Xuanqi Gao, Haoyu Wang, Jun Sun, Shiqing Ma, Chao Shen Published: 2026-03-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.20267v1 While Large Language Models (LLMs) have advanced complex reasoning, prominent methods like the Tree of Thoughts (ToT) framework face a critical trade-off between exploration depth and computational efficiency. Existing ToT implementations often rely on heavyweight LLM-based self-evaluation or rigid heuristics for branch pruning, making them prohibitively expensive and inflexible for broad application. To address this, we introduce DST, an adaptable, plug-and-play predictor that serves as a lightweight, supervised heuristic to guide the ToT search process. Our predictor enables dynamic, context-aware pruning, allowing the search to proceed with near-greedy efficiency on simpler reasoning steps while adaptively expanding the search beam only when encountering uncertainty or task complexity. We evaluate our approach on a diverse suite of benchmarks spanning mathematical reasoning, general reasoning, and complex logical reasoning. Experimental results demonstrate that our method achieves accuracy competitive with or superior to strong baselines, including standard ToT, while reducing computational overhead by 26-75%. Our work effectively resolves the accuracy-efficiency trade-off in tree-based reasoning, transforming ToT from a resource-intensive technique into a scalable and practical paradigm for complex problem-solving in LLMs. --- ### JointFM-0.1: A Foundation Model for Multi-Target Joint Distributional Prediction Authors: Stefan Hackmann Published: 2026-03-14 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.20266v2 Despite the rapid advancements in Artificial Intelligence (AI), Stochastic Differential Equations (SDEs) remain the gold-standard formalism for modeling systems under uncertainty. However, applying SDEs in practice is fraught with challenges: modeling risk is high, calibration is often brittle, and high-fidelity simulations are computationally expensive. This technical report introduces JointFM, a foundation model that inverts this paradigm. Instead of fitting SDEs to data, we sample an infinite stream of synthetic SDEs to train a generic model to predict future joint probability distributions directly. This approach establishes JointFM as the first foundation model for distributional predictions of coupled time series - requiring no task-specific calibration or finetuning. Despite operating in a purely zero-shot setting, JointFM reduces the energy loss by 21.1% relative to the strongest baseline when recovering oracle joint distributions generated by unseen synthetic SDEs. --- ### MRMS-Net and LMRMS-Net: Scalable Multi-Representation Multi-Scale Networks for Time Series Classification Authors: Celal Alagöz, Mehmet Kurnaz, Farhan Aadil Published: 2026-03-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.19315v2 Time series classification (TSC) performance depends not only on architectural design but also on the diversity of input representations. In this work, we propose a scalable multi-scale convolutional framework that systematically integrates structured multi-representation inputs for univariate time series. We introduce two architectures: MRMS-Net, a hierarchical multi-scale convolutional network optimized for robustness and calibration, and LMRMS-Net, a lightweight variant designed for efficiency-aware deployment. In addition, we adapt LiteMV -- originally developed for multivariate inputs -- to operate on multi-representation univariate signals, enabling cross-representation interaction. We evaluate all models across 142 benchmark datasets under a unified experimental protocol. Critical Difference (CD) analysis confirms statistically significant performance differences among the top models. Results show that LiteMV achieves the highest mean accuracy, MRMS-Net provides superior probabilistic calibration (lowest NLL), and LMRMS-Net offers the best efficiency-accuracy tradeoff. Pareto analysis further demonstrates that multi-representation multi-scale modeling yields a flexible design space that can be tuned for accuracy-oriented, calibration-oriented, or resource-constrained settings. These findings establish scalable multi-representation multi-scale learning as a principled and practical direction for modern TSC. Reference implementation of MRMS-Net and LMRMS-Net is available at: https://github.com/alagoz/mrmsnet-tsc --- ### DPxFin: Adaptive Differential Privacy for Anti-Money Laundering Detection via Reputation-Weighted Federated Learning Authors: Renuga Kanagavelu, Manjil Nepal, Ning Peiyan, Cai Kangning, Xu Jiming, Fei Gao, Yong Liu, Goh Siow Mong Rick, Qingsong Wei Published: 2026-03-14 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2603.19314v1 In the modern financial system, combating money laundering is a critical challenge complicated by data privacy concerns and increasingly complex fraud transaction patterns. Although federated learning (FL) is a promising problem-solving approach as it allows institutions to train their models without sharing their data, it has the drawback of being prone to privacy leakage, specifically in tabular data forms like financial data. To address this, we propose DPxFin, a novel federated framework that integrates reputation-guided adaptive differential privacy. Our approach computes client reputation by evaluating the alignment between locally trained models and the global model. Based on this reputation, we dynamically assign differential privacy noise to client updates, enhancing privacy while maintaining overall model utility. Clients with higher reputations receive lower noise to amplify their trustworthy contributions, while low-reputation clients are allocated stronger noise to mitigate risk. We validate DPxFin on the Anti-Money Laundering (AML) dataset under both IID and non-IID settings using Multi Layer Perceptron (MLP). Experimental analysis established that our approach has a more desirable trade-off between accuracy and privacy than those of traditional FL and fixed-noise Differential Privacy (DP) baselines, where performance improvements were consistent, even though on a modest scale. Moreover, DPxFin does withstand tabular data leakage attacks, proving its effectiveness under real-world financial conditions. --- ### Memory-Driven Role-Playing: Evaluation and Enhancement of Persona Knowledge Utilization in LLMs Authors: Kai Wang, Haoyang You, Yang Zhang, Zhongjie Wang Published: 2026-03-14 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.19313v1 A core challenge for faithful LLM role-playing is sustaining consistent characterization throughout long, open-ended dialogues, as models frequently fail to recall and accurately apply their designated persona knowledge without explicit cues. To tackle this, we propose the Memory-Driven Role-Playing paradigm. Inspired by Stanislavski's "emotional memory" acting theory, this paradigm frames persona knowledge as the LLM's internal memory store, requiring retrieval and application based solely on dialogue context, thereby providing a rigorous test of depth and autonomous use of knowledge. Centered on this paradigm, we contribute: (1) MREval, a fine-grained evaluation framework assessing four memory-driven abilities - Anchoring, Recalling, Bounding, and Enacting; (2) MRPrompt, a prompting architecture that guides structured memory retrieval and response generation; and (3) MRBench, a bilingual (Chinese/English) benchmark for fine-grained diagnosis. The novel paradigm provides a comprehensive diagnostic for four-staged role-playing abilities across 12 LLMs. Crucially, experiments show that MRPrompt allows small models (e.g., Qwen3-8B) to match the performance of much larger closed-source LLMs (e.g., Qwen3-Max and GLM-4.7), and confirms that upstream memory gains directly enhance downstream response quality, validating the staged theoretical foundation. --- ### Quotient Geometry and Persistence-Stable Metrics for Swarm Configurations Authors: Mark M. Bailey Published: 2026-03-14 Categories: cs.LG, cs.SI, eess.SY, math.AT arXiv: https://arxiv.org/abs/2603.18041v1 Swarm and constellation reconfiguration can be viewed as motion of an unordered point configuration in an ambient space. Here, we provide persistence-stable, symmetry-invariant geometric representations for comparing and monitoring multi-agent configuration data. We introduce a quotient formation space $\mathcal{S}_n(M,G)=M^n/(G\times S_n)$ and a formation matching metric $d_{M,G}$ obtained by optimizing a worst-case assignment error over ambient symmetries $g\in G$ and relabelings $σ\in S_n$. This metric is a structured, physically interpretable relaxation of Gromov--Hausdorff distance: the induced inter-agent metric spaces satisfy $d_{\mathrm{GH}}(X_x,X_y)\le d_{M,G}((x),(y))$. Composing this bound with stability of Vietoris--Rips persistence yields $d_B(Φ_k((x)),Φ_k((y)))\le d_{M,G}((x),(y))$, providing persistence-stable signatures for reconfiguration monitoring. We analyze the metric geometry of $(\mathcal{S}_n(M,G),d_{M,G})$: under compactness/completeness assumptions on $M$ and compact $G$ it is compact/complete and the metric induces the quotient topology; if $M$ is geodesic then the quotient is geodesic and exhibits stratified singularities along collision and symmetry strata, relating it to classical configuration spaces. We study expressivity of the signatures, identifying symmetry-mismatch and persistence-compression mechanisms for non-injectivity. Finally, in a phase-circle model we prove a conditional inverse theorem: under semicircle support and a gap-labeling margin, the $H_0$ signature is locally bi-Lipschitz to $d_{M,G}$ up to an explicit factor, yielding two-sided control. Examples on $\mathbb{S}^2$ and $\mathbb{T}^m$ illustrate satellite-constellation and formation settings. --- ### Sharpness Aware Surrogate Training for Spiking Neural Networks Authors: Maximilian Nicholson Published: 2026-03-14 Categories: cs.NE, cs.LG arXiv: https://arxiv.org/abs/2603.18039v1 Surrogate gradients are a standard tool for training spiking neural networks (SNNs), but conventional hard forward or surrogate backward training couples a nonsmooth forward model with a biased gradient estimator. We study sharpness aware Surrogate Training (SAST), which applies sharpness aware Minimization (SAM) to a surrogate forward SNN trained by backpropagation. In this formulation, the optimization target is an ordinary smooth empirical risk, so the training gradient is exact for the auxiliary model being optimized. Under explicit boundedness and contraction assumptions, we derive compact state stability and input Lipschitz bounds, establish smoothness of the surrogate objective, provide a first order SAM approximation bound, and prove a nonconvex convergence guarantee for stochastic SAST with an independent second minibatch. We also isolate a local mechanism proposition, stated separately from the unconditional guarantees, that links per sample parameter gradient control to smaller input gradient norms under local Jacobian conditioning. Empirically, we evaluate clean accuracy, hard spike transfer, corruption robustness, and training overhead on N-MNIST and DVS Gesture. The clearest practical effect is transfer gap reduction: on N-MNIST, hard spike accuracy rises from 65.7% to 94.7% (best at $ρ=0.30$) while surrogate forward accuracy remains high; on DVS Gesture, hard spike accuracy improves from 31.8% to 63.3% (best at $ρ=0.40$). We additionally specify the compute matched, calibration, and theory alignment controls required for a final practical assessment. --- ### Integrating Explainable Machine Learning and Mixed-Integer Optimization for Personalized Sleep Quality Intervention Authors: Mahfuz Ahmed Anik, Mohsin Mahmud Topu, Azmine Toushik Wasi, Md Isfar Khan, MD Manjurul Ahsan Published: 2026-03-14 Categories: cs.LG, stat.AP, stat.ME arXiv: https://arxiv.org/abs/2603.16937v1 Sleep quality is influenced by a complex interplay of behavioral, environmental, and psychosocial factors, yet most computational studies focus mainly on predictive risk identification rather than actionable intervention design. Although machine learning models can accurately predict subjective sleep outcomes, they rarely translate predictive insights into practical intervention strategies. To address this gap, we propose a personalized predictive-prescriptive framework that integrates interpretable machine learning with mixed-integer optimization. A supervised classifier trained on survey data predicts sleep quality, while SHAP-based feature attribution quantifies the influence of modifiable factors. These importance measures are incorporated into a mixed-integer optimization model that identifies minimal and feasible behavioral adjustments, while modelling resistance to change through a penalty mechanism. The framework achieves strong predictive performance, with a test F1-score of 0.9544 and an accuracy of 0.9366. Sensitivity and Pareto analyses reveal a clear trade-off between expected improvement and intervention intensity, with diminishing returns as additional changes are introduced. At the individual level, the model generates concise recommendations, often suggesting one or two high-impact behavioral adjustments and sometimes recommending no change when expected gains are minimal. By integrating prediction, explanation, and constrained optimization, this framework demonstrates how data-driven insights can be translated into structured and personalized decision support for sleep improvement. --- ### TDMM-LM: Bridging Facial Understanding and Animation via Language Models Authors: Luchuan Song, Pinxin Liu, Haiyang Liu, Zhenchao Jin, Yolo Yunlong Tang, Zichong Xu, Susan Liang, Jing Bi, Jason J Corso, Chenliang Xu Published: 2026-03-14 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.16936v1 Text-guided human body animation has advanced rapidly, yet facial animation lags due to the scarcity of well-annotated, text-paired facial corpora. To close this gap, we leverage foundation generative models to synthesize a large, balanced corpus of facial behavior. We design prompts suite covering emotions and head motions, generate about 80 hours of facial videos with multiple generators, and fit per-frame 3D facial parameters, yielding large-scale (prompt and parameter) pairs for training. Building on this dataset, we probe language models for bidirectional competence over facial motion via two complementary tasks: (1) Motion2Language: given a sequence of 3D facial parameters, the model produces natural-language descriptions capturing content, style, and dynamics; and (2) Language2Motion: given a prompt, the model synthesizes the corresponding sequence of 3D facial parameters via quantized motion tokens for downstream animation. Extensive experiments show that in this setting language models can both interpret and synthesize facial motion with strong generalization. To best of our knowledge, this is the first work to cast facial-parameter modeling as a language problem, establishing a unified path for text-conditioned facial animation and motion understanding. --- ### GenLie: A Global-Enhanced Lie Detection Network under Sparsity and Semantic Interference Authors: Zongshun Zhang, Yao Liu, Qiao Liu, Xuefeng Peng, Peiyuan Jiang, Jiaye Yang, Daibing Yao, Wei Lin Published: 2026-03-14 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.16935v1 Video-based lie detection aims to identify deceptive behaviors from visual cues. Despite recent progress, its core challenge lies in learning sparse yet discriminative representations. Deceptive signals are typically subtle and short-lived, easily overwhelmed by redundant information, while individual and contextual variations introduce strong identity-related noise. To address this issue, we propose GenLie, a Global-Enhanced Lie Detection Network that performs local feature modeling under global supervision. Specifically, sparse and subtle deceptive cues are captured at the local level, while global supervision and optimization ensure robust and discriminative representations by suppressing identity-related noise. Experiments on three public datasets, covering both high- and low-stakes scenarios, show that GenLie consistently outperforms state-of-the-art methods. Source code is available at https://github.com/AliasDictusZ1/GenLie. --- ### AgriChat: A Multimodal Large Language Model for Agriculture Image Understanding Authors: Abderrahmene Boudiaf, Irfan Hussain, Sajid Javed Published: 2026-03-14 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.16934v1 The deployment of Multimodal Large Language Models (MLLMs) in agriculture is currently stalled by a critical trade-off: the existing literature lacks the large-scale agricultural datasets required for robust model development and evaluation, while current state-of-the-art models lack the verified domain expertise necessary to reason across diverse taxonomies. To address these challenges, we propose the Vision-to-Verified-Knowledge (V2VK) pipeline, a novel generative AI-driven annotation framework that integrates visual captioning with web-augmented scientific retrieval to autonomously generate the AgriMM benchmark, effectively eliminating biological hallucinations by grounding training data in verified phytopathological literature. The AgriMM benchmark contains over 3,000 agricultural classes and more than 607k VQAs spanning multiple tasks, including fine-grained plant species identification, plant disease symptom recognition, crop counting, and ripeness assessment. Leveraging this verifiable data, we present AgriChat, a specialized MLLM that presents broad knowledge across thousands of agricultural classes and provides detailed agricultural assessments with extensive explanations. Extensive evaluation across diverse tasks, datasets, and evaluation conditions reveals both the capabilities and limitations of current agricultural MLLMs, while demonstrating AgriChat's superior performance over other open-source models, including internal and external benchmarks. The results validate that preserving visual detail combined with web-verified knowledge constitutes a reliable pathway toward robust and trustworthy agricultural AI. The code and dataset are publicly available at https://github.com/boudiafA/AgriChat . --- ### Look Where It Matters: High-Resolution Crops Retrieval for Efficient VLMs Authors: Nimrod Shabtay, Moshe Kimhi, Artem Spector, Sivan Haray, Ehud Rivlin, Chaim Baskin, Raja Giryes, Eli Schwartz Published: 2026-03-14 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.16932v2 Vision-language models (VLMs) typically process images at a native high-resolution, forcing a trade-off between accuracy and computational efficiency: high-resolution inputs capture fine details but incur significant computational costs, while low-resolution inputs advocate for efficiency, they potentially miss critical visual information, like small text. We present AwaRes, a spatial-on-demand framework that resolves this accuracy-efficiency trade-off by operating on a low-resolution global view and using tool-calling to retrieve only high-resolution segments needed for a given query. We construct supervised data automatically: a judge compares low- vs.\ high-resolution answers to label whether cropping is needed, and an oracle grounding model localizes the evidence for the correct answer, which we map to a discrete crop set to form multi-turn tool-use trajectories. We train our framework with cold-start SFT followed by multi-turn GRPO with a composite reward that combines semantic answer correctness with explicit crop-cost penalties. Project page: https://nimrodshabtay.github.io/AwaRes --- ### Look Where It Matters: High-Resolution Crops Retrieval for Efficient VLMs Authors: Nimrod Shabtay, Moshe Kimhi, Artem Spector, Sivan Haray, Ehud Rivlin, Chaim Baskin, Raja Giryes, Eli Schwartz Published: 2026-03-14 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.16932v1 Vision-language models (VLMs) typically process images at a native high-resolution, forcing a trade-off between accuracy and computational efficiency: high-resolution inputs capture fine details but incur significant computational costs, while low-resolution inputs advocate for efficiency, they potentially miss critical visual information, like small text. We present AwaRes, a spatial-on-demand framework that resolves this accuracy-efficiency trade-off by operating on a low-resolution global view and using tool-calling to retrieve only high-resolution segments needed for a given query. We construct supervised data automatically: a judge compares low- vs.\ high-resolution answers to label whether cropping is needed, and an oracle grounding model localizes the evidence for the correct answer, which we map to a discrete crop set to form multi-turn tool-use trajectories. We train our framework with cold-start SFT followed by multi-turn GRPO with a composite reward that combines semantic answer correctness with explicit crop-cost penalties. Project page: https://nimrodshabtay.github.io/AwaRes ---