# Research Papers — 2026-03 · bundle page 91 of 243 > Full-text markdown of papers #4501–4550 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/91 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/90.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/92.md) ### Adaptive Regime-Aware Stock Price Prediction Using Autoencoder-Gated Dual Node Transformers with Reinforcement Learning Control Authors: Mohammad Al Ridhawi, Mahtab Haj Ali, Hussein Al Osman Published: 2026-03-19 Categories: cs.LG, cs.AI, q-fin.ST arXiv: https://arxiv.org/abs/2603.19136v2 Stock markets exhibit regime-dependent behavior where prediction models optimized for stable conditions often fail during volatile periods. Existing approaches typically treat all market states uniformly or require manual regime labeling, which is expensive and quickly becomes stale as market dynamics evolve. This paper introduces an adaptive prediction framework that adaptively identifies deviations from normal market conditions and routes data through specialized prediction pathways. The architecture consists of three components: (1) an autoencoder trained on normal market conditions that identifies anomalous regimes through reconstruction error, (2) dual node transformer networks specialized for stable and event-driven market conditions respectively, and (3) a Soft Actor-Critic reinforcement learning controller that adaptively tunes the regime detection threshold and pathway blending weights based on prediction performance feedback. The reinforcement learning component enables the system to learn adaptive regime boundaries, defining anomalies as market states where standard prediction approaches fail. Experiments on 20 S&P 500 stocks spanning 1982 to 2025 demonstrate that the proposed framework achieves 0.68% mean absolute percentage error (MAPE) for one-day predictions without the reinforcement controller and 0.59% MAPE with the full adaptive system, compared to 0.80% for the baseline integrated node transformer. Directional accuracy reaches 72% with the complete framework. The system maintains robust performance during high-volatility periods, with MAPE below 0.85% when baseline models exceed 1.5%. Ablation studies confirm that each component contributes meaningfully: autoencoder routing accounts for 36% relative MAPE degradation upon removal, followed by the SAC controller at 15% and the dual-path architecture at 7%. --- ### From Inference Efficiency to Embodied Efficiency: Revisiting Efficiency Metrics for Vision-Language-Action Models Authors: Zhuofan Li, Hongkun Yang, Zhenyang Chen, Yangxuan Chen, Yingyan, Lin, Chaojian Li Published: 2026-03-19 Categories: cs.LG, cs.RO arXiv: https://arxiv.org/abs/2603.19131v1 Vision-Language-Action (VLA) models have recently enabled embodied agents to perform increasingly complex tasks by jointly reasoning over visual, linguistic, and motor modalities. However, we find that the prevailing notion of ``efficiency'' in current VLA research, characterized by parameters, FLOPs, or token decoding throughput, does not reflect actual performance on robotic platforms. In real-world execution, efficiency is determined by system-level embodied behaviors such as task completion time, trajectory smoothness, cumulative joint rotation, and motion energy. Through controlled studies across model compression, token sparsification, and action sequence compression, we make several observations that challenge common assumptions. (1) Methods that reduce computation under conventional metrics often increase end-to-end execution cost or degrade motion quality, despite maintaining task success rates. (2) System-level embodied efficiency metrics reveal performance differences in the learned action policies that remain hidden under conventional evaluations. (3) Common adaptation methods such as in-context prompting or supervised fine-tuning show only mild and metric-specific improvements in embodied efficiency. While these methods can reduce targeted embodied-efficiency metrics such as jerk or action rate, the resulting gains may come with trade-offs in other metrics, such as longer completion time. Taken together, our results suggest that conventional inference efficiency metrics can overlook important aspects of embodied execution. Incorporating embodied efficiency provides a more complete view of policy behavior and practical performance, enabling fairer and more comprehensive comparisons of VLA models. --- ### On Optimizing Multimodal Jailbreaks for Spoken Language Models Authors: Aravind Krishnan, Karolina Stańczak, Dietrich Klakow Published: 2026-03-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.19127v2 As Spoken Language Models (SLMs) integrate speech and text modalities, they inherit the safety vulnerabilities of their LLM backbone while introducing an expanded attack surface. SLMs have been previously shown to be susceptible to jailbreaking, where adversarial prompts induce harmful responses. Yet existing attacks largely remain unimodal, optimizing either text or audio in isolation. We explore gradient-based multimodal jailbreaks by introducing JAMA (Joint Audio-text Multimodal Attack), a joint multimodal optimization framework combining Greedy Coordinate Gradient (GCG) for text and Projected Gradient Descent (PGD) for audio, to simultaneously perturb both modalities. Evaluations across four state-of-the-art SLMs and four audio types demonstrate that JAMA surpasses unimodal jailbreak rate by 1.5x to 20x. We analyze the operational dynamics of this joint attack and show that a sequential approximation method makes it 4x to 6x faster. Our findings suggest that unimodal safety is insufficient for robust SLMs. The code and data are available at https://repos.lsv.uni-saarland.de/akrishnan/multimodal-jailbreak-slm. --- ### Revisiting Autoregressive Models for Generative Image Classification Authors: Ilia Sudakov, Artem Babenko, Dmitry Baranchuk Published: 2026-03-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.19122v2 Class-conditional generative models have emerged as accurate and robust classifiers, with diffusion models demonstrating clear advantages over other visual generative paradigms, including autoregressive (AR) models. In this work, we revisit visual AR-based generative classifiers and identify an important limitation of prior approaches: their reliance on a fixed token order, which imposes a restrictive inductive bias for image understanding. We observe that single-order predictions rely more on partial discriminative cues, while averaging over multiple token orders provides a more comprehensive signal. Based on this insight, we leverage recent any-order AR models to estimate order-marginalized predictions, unlocking the high classification potential of AR models. Our approach consistently outperforms diffusion-based classifiers across diverse image classification benchmarks, while being up to 25x more efficient. Compared to state-of-the-art self-supervised discriminative models, our method delivers competitive classification performance - a notable achievement for generative classifiers. --- ### CustomTex: High-fidelity Indoor Scene Texturing via Multi-Reference Customization Authors: Weilin Chen, Jiahao Rao, Wenhao Wang, Xinyang Li, Xuan Cheng, Liujuan Cao Published: 2026-03-19 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.19121v2 The creation of high-fidelity, customizable 3D indoor scene textures remains a significant challenge. While text-driven methods offer flexibility, they lack the precision for fine-grained, instance-level control, and often produce textures with insufficient quality, artifacts, and baked-in shading. To overcome these limitations, we introduce CustomTex, a novel framework for instance-level, high-fidelity scene texturing driven by reference images. CustomTex takes an untextured 3D scene and a set of reference images specifying the desired appearance for each object instance, and generates a unified, high-resolution texture map. The core of our method is a dual-distillation approach that separates semantic control from pixel-level enhancement. We employ semantic-level distillation, equipped with an instance cross-attention, to ensure semantic plausibility and ``reference-instance'' alignment, and pixel-level distillation to enforce high visual fidelity. Both are unified within a Variational Score Distillation (VSD) optimization framework. Experiments demonstrate that CustomTex achieves precise instance-level consistency with reference images and produces textures with superior sharpness, reduced artifacts, and minimal baked-in shading compared to state-of-the-art methods. Our work establishes a more direct and user-friendly path to high-quality, customizable 3D scene appearance editing. --- ### How Uncertainty Estimation Scales with Sampling in Reasoning Models Authors: Maksym Del, Markus Kängsepp, Marharyta Domnich, Ardi Tampuu, Lisa Yankovskaya, Meelis Kull, Mark Fishel Published: 2026-03-19 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2603.19118v1 Uncertainty estimation is critical for deploying reasoning language models, yet remains poorly understood under extended chain-of-thought reasoning. We study parallel sampling as a fully black-box approach using verbalized confidence and self-consistency. Across three reasoning models and 17 tasks spanning mathematics, STEM, and humanities, we characterize how these signals scale. Both self-consistency and verbalized confidence scale in reasoning models, but self-consistency exhibits lower initial discrimination and lags behind verbalized confidence under moderate sampling. Most uncertainty gains, however, arise from signal combination: with just two samples, a hybrid estimator improves AUROC by up to $+12$ on average and already outperforms either signal alone even when scaled to much larger budgets, after which returns diminish. These effects are domain-dependent: in mathematics, the native domain of RLVR-style post-training, reasoning models achieve higher uncertainty quality and exhibit both stronger complementarity and faster scaling than in STEM or humanities. --- ### Numerical Considerations for the Construction of Karhunen-Loève Expansions Authors: Cosmin Safta, Habib N. Najm Published: 2026-03-19 Categories: math.NA, stat.ML arXiv: https://arxiv.org/abs/2603.19108v1 This report examines numerical aspects of constructing Karhunen-Loève expansions (KLEs) for second-order stochastic processes. The KLE relies on the spectral decomposition of the covariance operator via the Fredholm integral equation of the second kind, which is then discretized on a computational grid, leading to an eigendecomposition task. We derive the algebraic equivalence between this Fredholm-based eigensolution and the singular value decomposition of the weight-scaled sample matrix, yielding consistent solutions for both model-based and data-driven KLE construction. Analytical eigensolutions for exponential and squared-exponential covariance kernels serve as reference benchmarks to assess numerical consistency and accuracy in 1D settings. The convergence of SVD-based eigenvalue estimates and of the empirical distributions of the KL coefficients to their theoretical $\mathcal{N}(0,1)$ target are characterized as a function of sample count. Higher-dimensional configurations include a two-dimensional irregular domain discretized by unstructured triangular meshes with two refinement levels, and a three-dimensional toroidal domain whose non-simply-connected topology motivates a comparison between Euclidean and shortest interior path distances between the grid points. The numerical results highlight the interplay between the discretization strategy, quadrature rule, and sample count, and their impact on the KLE results. --- ### FedTrident: Resilient Road Condition Classification Against Poisoning Attacks in Federated Learning Authors: Sheng Liu, Panos Papadimitratos Published: 2026-03-19 Categories: cs.CR, cs.AI, cs.DC, cs.LG arXiv: https://arxiv.org/abs/2603.19101v1 FL has emerged as a transformative paradigm for ITS, notably camera-based Road Condition Classification (RCC). However, by enabling collaboration, FL-based RCC exposes the system to adversarial participants launching Targeted Label-Flipping Attacks (TLFAs). Malicious clients (vehicles) can relabel their local training data (e.g., from an actual uneven road to a wrong smooth road), consequently compromising global model predictions and jeopardizing transportation safety. Existing countermeasures against such poisoning attacks fail to maintain resilient model performance near the necessary attack-free levels in various attack scenarios due to: 1) not tailoring poisoned local model detection to TLFAs, 2) not excluding malicious vehicular clients based on historical behavior, and 3) not remedying the already-corrupted global model after exclusion. To close this research gap, we propose FedTrident, which introduces: 1) neuron-wise analysis for local model misbehavior detection (notably including attack goal identification, critical feature extraction, and GMM-based model clustering and filtering); 2) adaptive client rating for client exclusion according to the local model detection results in each FL round; and 3) machine unlearning for corrupted global model remediation once malicious clients are excluded during FL. Extensive evaluation across diverse FL-RCC models, tasks, and configurations demonstrates that FedTrident can effectively thwart TLFAs, achieving performance comparable to that in attack-free scenarios and outperforming eight baseline countermeasures by 9.49% and 4.47% for the two most critical metrics. Moreover, FedTrident is resilient to various malicious client rates, data heterogeneity levels, complicated multi-task, and dynamic attacks. --- ### LuMamba: Latent Unified Mamba for Electrode Topology-Invariant and Efficient EEG Modeling Authors: Danaé Broustail, Anna Tegon, Thorir Mar Ingolfsson, Yawei Li, Luca Benini Published: 2026-03-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.19100v2 Electroencephalography (EEG) enables non-invasive monitoring of brain activity across clinical and neurotechnology applications, yet building foundation models for EEG remains challenging due to differing electrode topologies and computational scalability, as Transformer architectures incur quadratic sequence complexity. As a joint solution, we propose LuMamba (Latent Unified Mamba), a self-supervised framework combining topology-invariant encodings with linear-complexity state-space modeling, using LUNA's learned-query cross-attention mechanism for channel unification, and FEMBA's bidirectional Mamba blocks for efficient temporal modeling. Within this architecture, we provide the first systematic investigation of the Latent-Euclidean Joint-Embedding Predictive Architecture (LeJEPA) for biosignal learning. Pre-trained on over 21,000 hours of unlabeled EEG from the TUEG corpus, LuMamba is evaluated on five downstream tasks spanning abnormality detection, artifact recognition, and mental condition classification across electrode configurations ranging from 16 to 26 channels. In the pre-training objective, masked reconstruction alone yields structured but less generalizable representations, while LeJEPA alone produces diffuse embeddings; combining both objectives achieves the most robust performance. With only 4.6M parameters, LuMamba attains 80.99% balanced accuracy on TUAB and achieves state-of-art performance on Alzheimer's detection (0.97 AUPR), while requiring 377x fewer FLOPS than state-of-art models at equivalent sequence lengths and scaling to 12x longer sequences before reaching typical GPU memory limits. Code is available at https://github.com/pulp-bio/biofoundation. --- ### TAU-R1: Visual Language Model for Traffic Anomaly Understanding Authors: Yuqiang Lin, Kehua Chen, Sam Lockyer, Arjun Yadav, Mingxuan Sui, Shucheng Zhang, Yan Shi, Bingzhang Wang, Yuang Zhang, Markus Zarbock, Florain Stanek, Adrian Evans et al. Published: 2026-03-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.19098v1 Traffic Anomaly Understanding (TAU) is important for traffic safety in Intelligent Transportation Systems. Recent vision-language models (VLMs) have shown strong capabilities in video understanding. However, progress on TAU remains limited due to the lack of benchmarks and task-specific methodologies. To address this limitation, we introduce Roundabout-TAU, a dataset constructed from real-world roundabout videos collected in collaboration with the City of Carmel, Indiana. The dataset contains 342 clips and is annotated with more than 2,000 question-answer pairs covering multiple aspects of traffic anomaly understanding. Building on this benchmark, we propose TAU-R1, a two-layer vision-language framework for TAU. The first layer is a lightweight anomaly classifier that performs coarse anomaly categorisation, while the second layer is a larger anomaly reasoner that generates detailed event summaries. To improve task-specific reasoning, we introduce a two-stage training strategy consisting of decomposed-QA-enhanced supervised fine-tuning followed by TAU-GRPO, a GRPO-based post-training method with TAU-specific reward functions. Experimental results show that TAU-R1 achieves strong performance on both anomaly classification and reasoning tasks while maintaining deployment efficiency. The dataset and code are available at: https://github.com/siri-rouser/TAU-R1 --- ### DaPT: A Dual-Path Framework for Multilingual Multi-hop Question Answering Authors: Yilin Wang, Yuchun Fan, Jiaoyang Li, Ziming Zhu, Yongyu Mu, Qiaozhi He, Tong Xiao, Jingbo Zhu Published: 2026-03-19 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.19097v1 Retrieval-augmented generation (RAG) systems have made significant progress in solving complex multi-hop question answering (QA) tasks in the English scenario. However, RAG systems inevitably face the application scenario of retrieving across multilingual corpora and queries, leaving several open challenges. The first one involves the absence of benchmarks that assess RAG systems' capabilities under the multilingual multi-hop (MM-hop) QA setting. The second centers on the overreliance on LLMs' strong semantic understanding in English, which diminishes effectiveness in multilingual scenarios. To address these challenges, we first construct multilingual multi-hop QA benchmarks by translating English-only benchmarks into five languages, and then we propose DaPT, a novel multilingual RAG framework. DaPT generates sub-question graphs in parallel for both the source-language query and its English translation counterpart, then merges them before employing a bilingual retrieval-and-answer strategy to sequentially solve sub-questions. Our experimental results demonstrate that advanced RAG systems suffer from a significant performance imbalance in multilingual scenarios. Furthermore, our proposed method consistently yields more accurate and concise answers compared to the baselines, significantly enhancing RAG performance on this task. For instance, on the most challenging MuSiQue benchmark, DaPT achieves a relative improvement of 18.3\% in average EM score over the strongest baseline. --- ### SAVeS: Steering Safety Judgments in Vision-Language Models via Semantic Cues Authors: Carlos Hinojosa, Clemens Grange, Bernard Ghanem Published: 2026-03-19 Categories: cs.CV, cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2603.19092v1 Vision-language models (VLMs) are increasingly deployed in real-world and embodied settings where safety decisions depend on visual context. However, it remains unclear which visual evidence drives these judgments. We study whether multimodal safety behavior in VLMs can be steered by simple semantic cues. We introduce a semantic steering framework that applies controlled textual, visual, and cognitive interventions without changing the underlying scene content. To evaluate these effects, we propose SAVeS, a benchmark for situational safety under semantic cues, together with an evaluation protocol that separates behavioral refusal, grounded safety reasoning, and false refusals. Experiments across multiple VLMs and an additional state-of-the-art benchmark show that safety decisions are highly sensitive to semantic cues, indicating reliance on learned visual-linguistic associations rather than grounded visual understanding. We further demonstrate that automated steering pipelines can exploit these mechanisms, highlighting a potential vulnerability in multimodal safety systems. --- ### Position: Spectral GNNs Are Neither Spectral Nor Superior for Node Classification Authors: Qin Jiang, Chengjia Wang, Michael Lones, Dongdong Chen, Wei Pang Published: 2026-03-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.19091v2 Spectral Graph Neural Networks (Spectral GNNs) for node classification promise frequency-domain filtering on graphs, yet rest on flawed foundations. Recent work shows that graph Laplacian eigenvectors do not in general have the key properties of a true Fourier basis, but leaves the empirical success of Spectral GNNs unexplained. We identify two theoretical glitches: (1) commonly used "graph Fourier bases" are not classical Fourier bases for graph signals; (2) (n-1)-degree polynomials (n = number of nodes) can exactly interpolate any spectral response via a Vandermonde system, so the usual "polynomial approximation" narrative is not theoretically justified. The effectiveness of GCN is commonly attributed to spectral low-pass filtering, yet we prove that low- and high-pass behaviors arise solely from message-passing dynamics rather than Graph Fourier Transform-based spectral formulations. We then analyze two representative directed spectral models, MagNet and HoloNet. Their reported effectiveness is not spectral: it arises from implementation issues that reduce them to powerful MPNNs. When implemented consistently with the claimed spectral algorithms, performance becomes weak. This position paper argues that: for node classification, Spectral GNNs neither meaningfully capture the graph spectrum nor reliably improve performance; competitive results are better explained by their equivalence to MPNNs, sometimes aided by implementations inconsistent with their intended design. --- ### Assessing the Effect of Cross-Domain Mapping on Creativity in Humans and Large Language Models Authors: Qiawen Ella Liu, Marina Dubova, Henry Conklin, Takumi Harada, Thomas L. Griffiths Published: 2026-03-19 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.19087v3 Creative ideas often arise by associating remote concepts. Can random associations reliably increase originality, and do they help humans and large language models (LLMs) in the same way? We asked human participants and seven LLMs to design products by drawing inspiration from a random source or addressing an unmet user need. Humans reliably benefited from cross-domain mappings, while LLMs generated more original ideas than humans but showed no overall benefit from the intervention, though this changed with semantic distance. More distant source-target pairings produced more original ideas in both humans and LLMs. Humans benefited at nearly any distance, while only the highest-rated LLMs benefited when the source was sufficiently remote. Humans and LLMs also used sources differently: humans tended to transfer surface features, while LLMs transferred structural and functional properties. These findings reveal the generative role of remote associations and systematic differences in how humans and AI respond to the same creativity intervention. --- ### Assessing the Effect of Cross-Domain Mapping on Creativity in Humans and Large Language Models Authors: Qiawen Ella Liu, Marina Dubova, Henry Conklin, Takumi Harada, Thomas L. Griffiths Published: 2026-03-19 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.19087v2 Creativity is the ability to come up with novel ideas, a capacity crucial for human development and flourishing. Are large language models (LLMs) creative in the same way humans are, and can the same interventions increase creativity in both? We study a promising but largely untested intervention for creativity: forcing creators to draw an analogy from a random, remote source domain (''cross-domain mapping''). Human participants and LLMs generated novel designs for ten daily products (e.g., backpack, TV) under two prompts: (i) cross-domain mapping, which required drawing inspiration from a randomly assigned source (e.g., octopus, cactus, GPS), and (ii) user need, which required proposing innovations targeting unmet user needs. We show that humans reliably benefit from randomly assigned cross-domain mappings, while LLMs, on average, generate more original ideas than humans and do not show a statistically significant effect of cross-domain mappings. However, in both systems, the impact of cross-domain mapping increases when the inspiration source becomes more semantically distant from the target, and above a distance threshold, cross-domain mapping benefits the most capable LLMs too. Humans and LLMs differed in how they used the source concept: Humans tended to transfer surface features of the source, whereas LLMs transferred structural and functional properties. Our results highlight the role of remote association in creative ideation and systematic differences in how humans and LLMs respond to the same intervention for creativity. --- ### A Dataset and Resources for Identifying Patient Health Literacy Information from Clinical Notes Authors: Madeline Bittner, Dina Demner-Fushman, Yasmeen Shabazz, Davis Bartels, Dukyong Yoon, Brad Quitadamo, Rajiv Menghrajani, Leo Celi, Sarvesh Soni Published: 2026-03-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.19082v1 Health literacy is a critical determinant of patient outcomes, yet current screening tools are not always feasible and differ considerably in the number of items, question format, and dimensions of health literacy they capture, making documentation in structured electronic health records difficult to achieve. Automated detection from unstructured clinical notes offers a promising alternative, as these notes often contain richer, more contextual health literacy information, but progress has been limited by the lack of annotated resources. We introduce HEALIX, the first publicly available annotated health literacy dataset derived from real clinical notes, curated through a combination of social worker note sampling, keyword-based filtering, and LLM-based active learning. HEALIX contains 589 notes across 9 note types, annotated with three health literacy labels: low, normal, and high. To demonstrate its utility, we benchmarked zero-shot and few-shot prompting strategies across four open source large language models (LLMs). --- ### Multi-Modal Building Change Detection for Large-Scale Small Changes: Benchmark and Baseline Authors: Ye Wang, Wei Lu, Zhihui You, Keyan Chen, Tongfei Liu, Kaiyu Li, Hongruixuan Chen, Qingling Shu, Sibao Chen Published: 2026-03-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.19077v1 Change detection in optical remote sensing imagery is susceptible to illumination fluctuations, seasonal changes, and variations in surface land-cover materials. Relying solely on RGB imagery often produces pseudo-changes and leads to semantic ambiguity in features. Incorporating near-infrared (NIR) information provides heterogeneous physical cues that are complementary to visible light, thereby enhancing the discriminability of building materials and tiny structures while improving detection accuracy. However, existing multi-modal datasets generally lack high-resolution and accurately registered bi-temporal imagery, and current methods often fail to fully exploit the inherent heterogeneity between these modalities. To address these issues, we introduce the Large-scale Small-change Multi-modal Dataset (LSMD), a bi-temporal RGB-NIR building change detection benchmark dataset targeting small changes in realistic scenarios, providing a rigorous testing platform for evaluating multi-modal change detection methods in complex environments. Based on LSMD, we further propose the Multi-modal Spectral Complementarity Network (MSCNet) to achieve effective cross-modal feature fusion. MSCNet comprises three key components: the Neighborhood Context Enhancement Module (NCEM) to strengthen local spatial details, the Cross-modal Alignment and Interaction Module (CAIM) to enable deep interaction between RGB and NIR features, and the Saliency-aware Multisource Refinement Module (SMRM) to progressively refine fused features. Extensive experiments demonstrate that MSCNet effectively leverages multi-modal information and consistently outperforms existing methods under multiple input configurations, validating its efficacy for fine-grained building change detection. The source code will be made publicly available at: https://github.com/AeroVILab-AHU/LSMD --- ### DROID-SLAM in the Wild Authors: Moyang Li, Zihan Zhu, Marc Pollefeys, Daniel Barath Published: 2026-03-19 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2603.19076v1 We present a robust, real-time RGB SLAM system that handles dynamic environments by leveraging differentiable Uncertainty-aware Bundle Adjustment. Traditional SLAM methods typically assume static scenes, leading to tracking failures in the presence of motion. Recent dynamic SLAM approaches attempt to address this challenge using predefined dynamic priors or uncertainty-aware mapping, but they remain limited when confronted with unknown dynamic objects or highly cluttered scenes where geometric mapping becomes unreliable. In contrast, our method estimates per-pixel uncertainty by exploiting multi-view visual feature inconsistency, enabling robust tracking and reconstruction even in real-world environments. The proposed system achieves state-of-the-art camera poses and scene geometry in cluttered dynamic scenarios while running in real time at around 10 FPS. Code and datasets are available at https://github.com/MoyangLi00/DROID-W.git. --- ### CAMO: A Conditional Neural Solver for the Multi-objective Multiple Traveling Salesman Problem Authors: Fengxiaoxiao Li, Xiao Mao, Mingfeng Fan, Yifeng Zhang, Yi Li, Tanishq Duhan, Guillaume Sartoretti Published: 2026-03-19 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2603.19074v1 Robotic systems often require a team of robots to collectively visit multiple targets while optimizing competing objectives, such as total travel cost and makespan. This setting can be formulated as the Multi-Objective Multiple Traveling Salesman Problem (MOMTSP). Although learning-based methods have shown strong performance on the single-agent TSP and multi-objective TSP variants, they rarely address the combined challenges of multi-agent coordination and multi-objective trade-offs, which introduce dual sources of complexity. To bridge this gap, we propose CAMO, a conditional neural solver for MOMTSP that generalizes across varying numbers of targets, agents, and preference vectors, and yields high-quality approximations to the Pareto front (PF). Specifically, CAMO consists of a conditional encoder to fuse preferences into instance representations, enabling explicit control over multi-objective trade-offs, and a collaborative decoder that coordinates all agents by alternating agent selection and node selection to construct multi-agent tours autoregressively. To further improve generalization, we train CAMO with a REINFORCE-based objective over a mixed distribution of problem sizes. Extensive experiments show that CAMO outperforms both neural and conventional heuristics, achieving a closer approximation of PFs. In addition, ablation results validate the contributions of CAMO's key components, and real-world tests on a mobile robot platform demonstrate its practical applicability. --- ### Communication-Efficient and Robust Multi-Modal Federated Learning via Latent-Space Consensus Authors: Mohamed Badi, Chaouki Ben Issaid, Mehdi Bennis Published: 2026-03-19 Categories: cs.LG, eess.SP arXiv: https://arxiv.org/abs/2603.19067v1 Federated learning (FL) enables collaborative model training across distributed devices without sharing raw data, but applying FL to multi-modal settings introduces significant challenges. Clients typically possess heterogeneous modalities and model architectures, making it difficult to align feature spaces efficiently while preserving privacy and minimizing communication costs. To address this, we introduce CoMFed, a Communication-Efficient Multi-Modal Federated Learning framework that uses learnable projection matrices to generate compressed latent representations. A latent-space regularizer aligns these representations across clients, improving cross-modal consistency and robustness to outliers. Experiments on human activity recognition benchmarks show that CoMFed achieves competitive accuracy with minimal overhead. --- ### Large Language Models provide support for the parallelogram theory of analogy Authors: Qiawen Ella Liu, Raja Marjieh, Jian-Qiao Zhu, Adele E. Goldberg, Thomas L. Griffiths Published: 2026-03-19 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.19066v2 Four-term word analogies (A:B::C:D) are classically modeled geometrically as parallelograms: adding the vector B-A+C produces D. Recent work suggests that this model poorly captures how humans produce analogies, with simple local-similarity heuristics often providing a better account (Peterson et al., 2020). But does the parallelogram model fail because it is a bad model of analogical relations, or because people are not very good at generating relation-preserving analogies? We compared human and large language model (LLM) analogy completions on the set of problems from Peterson et al. (2020). We find that LLM-generated analogies are reliably judged as better than human-generated ones, and are also more consistent with parallelograms in a distributional embedding space. Crucially, we show that the improvement over human analogies is driven by greater parallelogram alignment and reduced reliance on accessible words rather than enhanced sensitivity to local similarity. Finally, fine-tuning GloVe to better satisfy the parallelogram constraint makes the model's top-ranked candidates more likely to be the completions humans and LLMs actually produced, and improves its prediction of human ratings. Overall, these results provide support for the parallelogram model of word analogies. --- ### Hardness of High-Dimensional Linear Classification Authors: Alexander Munteanu, Simon Omlor, Jeff M. Phillips Published: 2026-03-19 Categories: cs.CG, cs.DS, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2603.19061v1 We establish new exponential in dimension lower bounds for the Maximum Halfspace Discrepancy problem, which models linear classification. Both are fundamental problems in computational geometry and machine learning in their exact and approximate forms. However, only $O(n^d)$ and respectively $\tilde O(1/\varepsilon^d)$ upper bounds are known and complemented by polynomial lower bounds that do not support the exponential in dimension dependence. We close this gap up to polylogarithmic terms by reduction from widely-believed hardness conjectures for Affine Degeneracy testing and $k$-Sum problems. Our reductions yield matching lower bounds of $\tildeΩ(n^d)$ and respectively $\tildeΩ(1/\varepsilon^d)$ based on Affine Degeneracy testing, and $\tildeΩ(n^{d/2})$ and respectively $\tildeΩ(1/\varepsilon^{d/2})$ conditioned on $k$-Sum. The first bound also holds unconditionally if the computational model is restricted to make sidedness queries, which corresponds to a widely spread setting implemented and optimized in many contemporary algorithms and computing paradigms. --- ### SignAgent: Agentic LLMs for Linguistically-Grounded Sign Language Annotation and Dataset Curation Authors: Oliver Cory, Ozge Mercanoglu Sincan, Richard Bowden Published: 2026-03-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.19059v1 This paper introduces SignAgent, a novel agentic framework that utilises Large Language Models (LLMs) for scalable, linguistically-grounded Sign Language (SL) annotation and dataset curation. Traditional computational methods for SLs often operate at the gloss level, overlooking crucial linguistic nuances, while manual linguistic annotation remains a significant bottleneck, proving too slow and expensive for the creation of large-scale, phonologically-aware datasets. SignAgent addresses these challenges through SignAgent Orchestrator, a reasoning LLM that coordinates a suite of linguistic tools, and SignGraph, a knowledge-grounded LLM that provides lexical and linguistic grounding. We evaluate our framework on two downstream annotation tasks. First, on Pseudo-gloss Annotation, where the agent performs constrained assignment, using multi-modal evidence to extract and order suitable gloss labels for signed sequences. Second, on ID Glossing, where the agent detects and refines visual clusters by reasoning over both visual similarity and phonological overlap to correctly identify and group lexical sign variants. Our results demonstrate that our agentic approach achieves strong performance for large-scale, linguistically-aware data annotation and curation. --- ### Adaptive Nonlinear Data Assimilation through P-Spline Triangular Measure Transport Authors: Berent Å. S. Lunde, Maximilian Ramgraber Published: 2026-03-19 Categories: stat.CO, physics.ao-ph, stat.ME, stat.ML arXiv: https://arxiv.org/abs/2603.19058v1 Non-Gaussian statistics are a challenge for data assimilation. Linear methods oversimplify the problem, yet fully nonlinear methods are often too expensive to use in practice. The best solution usually lies between these extremes. Triangular measure transport offers a flexible framework for nonlinear data assimilation. Its success, however, depends on how the map is parametrized. Too much flexibility leads to overfitting; too little misses important structure. To address this balance, we develop an adaptation algorithm that selects a parsimonious parametrization automatically. Our method uses P-spline basis functions and an information criterion as a continuous measure of model complexity. This formulation enables gradient descent and allows efficient, fine-scale adaptation in high-dimensional settings. The resulting algorithm requires no hyperparameter tuning. It adjusts the transport map to the appropriate level of complexity based on the system statistics and ensemble size. We demonstrate its performance in nonlinear, non-Gaussian problems, including a high-dimensional distributed groundwater model. --- ### Em-Garde: A Propose-Match Framework for Proactive Streaming Video Understanding Authors: Yikai Zheng, Xin Ding, Yifan Yang, Shiqi Jiang, Hao Wu, Qianxi Zhang, Weijun Wang, Ting Cao, Yunxin Liu Published: 2026-03-19 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.19054v2 Recent advances in Streaming Video Understanding has enabled a new interaction paradigm where models respond proactively to user queries. Current proactive VideoLLMs rely on per-frame triggering decision making, which suffers from an efficiency-accuracy dilemma. We propose Em-Garde, a novel framework that decouples semantic understanding from streaming perception. At query time, the Instruction-Guided Proposal Parser transforms user queries into structured, perceptually grounded visual proposals; during streaming, a Lightweight Proposal Matching Module performs efficient embedding-based matching to trigger responses. Experiments on StreamingBench and OVO-Bench demonstrate consistent improvements over prior models in proactive response accuracy and efficiency, validating an effective solution for proactive video understanding under strict computational constraints. --- ### SwiftTailor: Efficient 3D Garment Generation with Geometry Image Representation Authors: Phuc Pham, Uy Dieu Tran, Binh-Son Hua, Phong Nguyen Published: 2026-03-19 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2603.19053v1 Realistic and efficient 3D garment generation remains a longstanding challenge in computer vision and digital fashion. Existing methods typically rely on large vision- language models to produce serialized representations of 2D sewing patterns, which are then transformed into simulation-ready 3D meshes using garment modeling framework such as GarmentCode. Although these approaches yield high-quality results, they often suffer from slow inference times, ranging from 30 seconds to a minute. In this work, we introduce SwiftTailor, a novel two-stage framework that unifies sewing-pattern reasoning and geometry-based mesh synthesis through a compact geometry image representation. SwiftTailor comprises two lightweight modules: PatternMaker, an efficient vision-language model that predicts sewing patterns from diverse input modalities, and GarmentSewer, an efficient dense prediction transformer that converts these patterns into a novel Garment Geometry Image, encoding the 3D surface of all garment panels in a unified UV space. The final 3D mesh is reconstructed through an efficient inverse mapping process that incorporates remeshing and dynamic stitching algorithms to directly assemble the garment, thereby amortizing the cost of physical simulation. Extensive experiments on the Multimodal GarmentCodeData demonstrate that SwiftTailor achieves state-of-the-art accuracy and visual fidelity while significantly reducing inference time. This work offers a scalable, interpretable, and high-performance solution for next-generation 3D garment generation. --- ### Measuring 3D Spatial Geometric Consistency in Dynamic Video Generation Authors: Weijia Dou, Wenzhao Zheng, Weiliang Chen, Yu Zheng, Jie Zhou, Jiwen Lu Published: 2026-03-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.19048v2 Recent generative models can produce high-fidelity videos, yet they often exhibit 3D spatial geometric inconsistencies. Existing evaluation methods fail to accurately characterize these inconsistencies: fidelity-centric metrics like FVD are insensitive to geometric distortions, while consistency-focused benchmarks often penalize valid foreground dynamics. To address this gap, we introduce SGC, a metric for evaluating 3D \textbf{S}patial \textbf{G}eometric \textbf{C}onsistency in dynamically generated videos. We quantify geometric consistency by measuring the divergence among multiple camera poses estimated from distinct local regions. Our approach first separates static from dynamic regions, then partitions the static background into spatially coherent sub-regions. We predict depth for each pixel, estimate a local camera pose for each subregion, and compute the divergence among these poses to quantify geometric consistency. Experiments on real and generative videos demonstrate that SGC robustly quantifies geometric inconsistencies, effectively identifying critical failures missed by existing metrics. --- ### MoRI: Learning Motivation-Grounded Reasoning for Scientific Ideation in Large Language Models Authors: Chenyang Gu, Jiahao Cheng, Meicong Zhang, Pujun Zheng, Jinquan Zheng, Guoxiu He Published: 2026-03-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.19044v3 Scientific ideation aims to propose novel solutions within a given scientific context. Existing LLM-based agentic approaches emulate human research workflows, yet inadequately model scientific reasoning, resulting in surface-level conceptual recombinations that lack technical depth and scientific grounding. To address this issue, we propose \textbf{MoRI} (\textbf{Mo}tivation-grounded \textbf{R}easoning for Scientific \textbf{I}deation), a framework that enables LLMs to explicitly learn the reasoning process from research motivations to methodologies. The base LLM is initialized via supervised fine-tuning to generate a research motivation from a given context, and is subsequently trained under a composite reinforcement learning reward that approximates scientific rigor: (1) entropy-aware information gain encourages the model to uncover and elaborate high-complexity technical details grounded in ground-truth methodologies, and (2) contrastive semantic gain constrains the reasoning trajectory to remain conceptually aligned with scientifically valid solutions. Empirical results show that MoRI consistently outperforms strong commercial LLMs and complex agentic baselines across multiple dimensions, including novelty, technical rigor, and feasibility. The code is available on \href{https://github.com/ECNU-Text-Computing/IdeaGeneration}{GitHub}. --- ### Man and machine: artificial intelligence and judicial decision making Authors: Arthur Dyevre, Ahmad Shahvaroughi Published: 2026-03-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.19042v4 The integration of artificial intelligence (AI) technologies into judicial decision-making, particularly in pretrial, sentencing, and parole contexts, has generated substantial concerns about transparency, reliability, and accountability. At the same time, these developments have brought the limitations of human judgment into sharper relief and underscored the importance of understanding how judges interact with AI-based decision aids. Using criminal justice risk assessment as a focal case, we conduct a synthetic review connecting three intertwined aspects of AI's role in judicial decision-making: the performance and fairness of AI tools, the strengths and biases of human judges, and the nature of AI-plus-human interactions. Across the fields of computer science, economics, law, criminology, and psychology, researchers have made significant progress in evaluating the predictive validity of automated risk assessment instruments, documenting biases in judicial decision-making, and, to a more limited extent, examining how judges use algorithmic recommendations. While the existing empirical evidence indicates that the impact of AI decision-aid tools on pretrial and sentencing decisions is modest or nonexistent, our review also reveals important gaps in the existing literature. Further research is needed to evaluate the performance of AI risk assessment instruments, understand how judges navigate uncertain decision-making environments, and examine how individual characteristics influence judges' responses to AI advice. We argue that AI-versus-human comparisons have the potential to yield new insights into both algorithmic tools and human decision-makers. We advocate greater interdisciplinary integration to foster cross-fertilization in future research. --- ### Fast and Interpretable Autoregressive Estimation with Neural Network Backpropagation Authors: Anaísa Lucena, Ana Martins, Armando J. Pinho, Sónia Gouveia Published: 2026-03-19 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2603.19041v1 Autoregressive (AR) models remain widely used in time series analysis due to their interpretability, but convencional parameter estimation methods can be computationally expensive and prone to convergence issues. This paper proposes a Neural Network (NN) formulation of AR estimation by embedding the autoregressive structure directly into a feedforward NN, enabling coefficient estimation through backpropagation while preserving interpretability. Simulation experiments on 125,000 synthetic AR(p) time series with short-term dependence (1 <= p <= 5) show that the proposed NN-based method consistently recovers model coefficients for all series, while Conditional Maximum Likelihood (CML) fails to converge in approximately 55% of cases. When both methods converge, estimation accuracy is comparable with negligible differences in relative error, R2 and, perplexity/likelihood. However, when CML fails, the NN-based approach still provides reliable estimates. In all cases, the NN estimator achieves substantial computational gains, reaching a median speedup of 12.6x and up to 34.2x for higher model orders. Overall, results demonstrate that gradient-descent NN optimization can provide a fast and efficient alternative for interpretable AR parameter estimation. --- ### When Differential Privacy Meets Wireless Federated Learning: An Improved Analysis for Privacy and Convergence Authors: Chen Yaoling, Liang Hao, Tu Xiaotong Published: 2026-03-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.19040v2 Differentially private wireless federated learning (DPWFL) is a promising framework for protecting sensitive user data. However, foundational questions on how to precisely characterize privacy loss remain open, and existing work is further limited by convergence analyses that rely on restrictive convexity assumptions or ignore the effect of gradient clipping. To overcome these issues, we present a comprehensive analysis of privacy and convergence for DPWFL with general smooth non-convex loss objectives. Our analysis explicitly incorporates both device selection and mini-batch sampling, and shows that the privacy loss can converge to a constant rather than diverge with the number of iterations. Moreover, we establish convergence guarantees with gradient clipping and derive an explicit privacy-utility trade-off. Numerical results validate our theoretical findings. --- ### TerraScope: Pixel-Grounded Visual Reasoning for Earth Observation Authors: Yan Shu, Bin Ren, Zhitong Xiong, Xiao Xiang Zhu, Begüm Demir, Nicu Sebe, Paolo Rota Published: 2026-03-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.19039v1 Vision-language models (VLMs) have shown promise in earth observation (EO), yet they struggle with tasks that require grounding complex spatial reasoning in precise pixel-level visual representations. To address this problem, we introduce TerraScope, a unified VLM that delivers pixel-grounded geospatial reasoning with two key capabilities: (1) modality-flexible reasoning: it handles single-modality inputs (optical or SAR) and adaptively fuses different modalities into the reasoning process when both are available; (2) multi-temporal reasoning: it integrates temporal sequences for change analysis across multiple time points. In addition, we curate Terra-CoT, a large-scale dataset containing 1 million samples with pixel-level masks embedded in reasoning chains across multiple sources. We also propose TerraScope-Bench, the first benchmark for pixel-grounded geospatial reasoning with six sub-tasks that evaluates both answer accuracy and mask quality to ensure authentic pixel-grounded reasoning. Experiments show that TerraScope significantly outperforms existing VLMs on pixel-grounded geospatial reasoning while providing interpretable visual evidence. --- ### FUMO: Prior-Modulated Diffusion for Single Image Reflection Removal Authors: Telang Xu, Chaoyang Zhang, Guangtao Zhai, Xiaohong Liu Published: 2026-03-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.19036v2 Single image reflection removal (SIRR) is challenging in real scenes, where reflection strength varies spatially and reflection patterns are tightly entangled with transmission structures. This paper presents a diffusion model with prior modulation framework (FUMO) that introduces explicit priors for spatially adaptive conditioning and structurally faithful restoration. Two priors are extracted directly from the mixed image, an intensity prior that estimates spatial reflection severity and a high-frequency prior that captures detail-sensitive responses via multi-scale residual aggregation. We propose a coarse-to-fine training paradigm. In the first stage, these cues are combined to gate the conditional residual injections, focusing the conditioning on regions that are both reflection-dominant and structure-sensitive. In the second stage, a fine-grained refinement network corrects local misalignment and sharpens fine details in the image space. Experiments conducted on both standard benchmarks and challenging images in the wild demonstrate competitive quantitative results and consistently improved perceptual quality. The code is released at https://github.com/Lucious-Desmon/FUMO. --- ### SEM: Sparse Embedding Modulation for Post-Hoc Debiasing of Vision-Language Models Authors: Quentin Guimard, Federico Bartsch, Simone Caldarella, Rahaf Aljundi, Elisa Ricci, Massimiliano Mancini Published: 2026-03-19 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.19028v1 Models that bridge vision and language, such as CLIP, are key components of multimodal AI, yet their large-scale, uncurated training data introduce severe social and spurious biases. Existing post-hoc debiasing methods often operate directly in the dense CLIP embedding space, where bias and task-relevant information are highly entangled. This entanglement limits their ability to remove bias without degrading semantic fidelity. In this work, we propose Sparse Embedding Modulation (SEM), a post-hoc, zero-shot debiasing framework that operates in a Sparse Autoencoder (SAE) latent space. By decomposing CLIP text embeddings into disentangled features, SEM identifies and modulates bias-relevant neurons while preserving query-relevant ones. This enables more precise, non-linear interventions. Across four benchmark datasets and two CLIP backbones, SEM achieves substantial fairness gains in retrieval and zero-shot classification. Our results demonstrate that sparse latent representations provide an effective foundation for post-hoc debiasing of vision-language models. --- ### Rethinking MLLM Itself as a Segmenter with a Single Segmentation Token Authors: Anqi Zhang, Xiaokang Ji, Guangyu Gao, Jianbo Jiao, Chi Harold Liu, Yunchao Wei Published: 2026-03-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.19026v1 Recent segmentation methods leveraging Multi-modal Large Language Models (MLLMs) have shown reliable object-level segmentation and enhanced spatial perception. However, almost all previous methods predominantly rely on specialist mask decoders to interpret masks from generated segmentation-related embeddings and visual features, or incorporate multiple additional tokens to assist. This paper aims to investigate whether and how we can unlock segmentation from MLLM itSELF with 1 segmentation Embedding (SELF1E) while achieving competitive results, which eliminates the need for external decoders. To this end, our approach targets the fundamental limitation of resolution reduction in pixel-shuffled image features from MLLMs. First, we retain image features at their original uncompressed resolution, and refill them with residual features extracted from MLLM-processed compressed features, thereby improving feature precision. Subsequently, we integrate pixel-unshuffle operations on image features with and without LLM processing, respectively, to unleash the details of compressed features and amplify the residual features under uncompressed resolution, which further enhances the resolution of refilled features. Moreover, we redesign the attention mask with dual perception pathways, i.e., image-to-image and image-to-segmentation, enabling rich feature interaction between pixels and the segmentation token. Comprehensive experiments across multiple segmentation tasks validate that SELF1E achieves performance competitive with specialist mask decoder-based methods, demonstrating the feasibility of decoder-free segmentation in MLLMs. Project page: https://github.com/ANDYZAQ/SELF1E. --- ### Towards Verifiable AI with Lightweight Cryptographic Proofs of Inference Authors: Pranay Anchuri, Matteo Campanelli, Paul Cesaretti, Rosario Gennaro, Tushar M. Jois, Hasan S. Kayman, Tugce Ozdemir Published: 2026-03-19 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2603.19025v1 When large AI models are deployed as cloud-based services, clients have no guarantee that responses are correct or were produced by the intended model. Rerunning inference locally is infeasible for large models, and existing cryptographic proof systems -- while providing strong correctness guarantees -- introduce prohibitive prover overhead (e.g., hundreds of seconds per query for billion-parameter models). We present a verification framework and protocol that replaces full cryptographic proofs with a lightweight, sampling-based approach grounded in statistical properties of neural networks. We formalize the conditions under which trace separation between functionally dissimilar models can be leveraged to argue the security of verifiable inference protocols. The prover commits to the execution trace of inference via Merkle-tree-based vector commitments and opens only a small number of entries along randomly sampled paths from output to input. This yields a protocol that trades soundness for efficiency, a tradeoff well-suited to auditing, large-scale deployment settings where repeated queries amplify detection probability, and scenarios with rationally incentivized provers who face penalties upon detection. Our approach reduces proving times by several orders of magnitude compared to state-of-the-art cryptographic proof systems, going from the order of minutes to the order of milliseconds, with moderately larger proofs. Experiments on ResNet-18 classifiers and Llama-2-7B confirm that common architectures exhibit the statistical properties our protocol requires, and that natural adversarial strategies (gradient-descent reconstruction, inverse transforms, logit swapping) fail to produce traces that evade detection. We additionally present a protocol in the refereed delegation model, where two competing servers enable correct output identification in a logarithmic number of rounds. --- ### Behavioral Fingerprints for LLM Endpoint Stability and Identity Authors: Jonah Leshin, Manish Shah, Ian Timmis, Daniel Kang Published: 2026-03-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.19022v1 The consistency of AI-native applications depends on the behavioral consistency of the model endpoints that power them. Traditional reliability metrics such as uptime, latency and throughput do not capture behavioral change, and an endpoint can remain "healthy" while its effective model identity changes due to updates to weights, tokenizers, quantization, inference engines, kernels, caching, routing, or hardware. We introduce Stability Monitor, a black-box stability monitoring system that periodically fingerprints an endpoint by sampling outputs from a fixed prompt set and comparing the resulting output distributions over time. Fingerprints are compared using a summed energy distance statistic across prompts, with permutation-test p-values as evidence of distribution shift aggregated sequentially to detect change events and define stability periods. In controlled validation, Stability Monitor detects changes to model family, version, inference stack, quantization, and behavioral parameters. In real-world monitoring of the same model hosted by multiple providers, we observe substantial provider-to-provider and within-provider stability differences. --- ### What Really Controls Temporal Reasoning in Large Language Models: Tokenisation or Representation of Time? Authors: Gagan Bhatia, Ahmad Muhammad Isa, Maxime Peyrard, Wei Zhao Published: 2026-03-19 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.19017v1 We present MultiTempBench, a multilingual temporal reasoning benchmark spanning three tasks, date arithmetic, time zone conversion, and temporal relation extraction across five languages (English, German, Chinese, Arabic, and Hausa) and multiple calendar conventions (Gregorian, Hijri, and Chinese Lunar). MultiTempBench contains $15,000$ examples built by translating $750$ curated English questions and expanding each into controlled date-format variants. We evaluate 20 LLMs and introduce the multilingual Date Fragmentation Ratio (mDFR), calibrated with human severity ratings, together with geometric-probing analyses of internal temporal representations. We find tokenisation quality of temporal artefacts is a resource-dependent bottleneck: in low-resource languages and rarer calendar formats, fragmentation disrupts Year/Month/Day separation and accuracy collapses, while high-resource settings are often robust to digit-level splitting. Beyond tokenisation, crossed mixed-effects regression shows that temporal linearity is the strongest predictor of temporal reasoning in high-resource languages, whereas fragmentation is the stronger predictor in low-resource languages. Code is available at: https://github.com/gagan3012/mtb --- ### GenHOI: Generalized Hand-Object Pose Estimation with Occlusion Awareness Authors: Hui Yang, Wei Sun, Jian Liu, Jian Xiao, Tao Xie, Hossein Rahmani, Ajmal Saeed Mian, Nicu Sebe, Gim Hee Lee Published: 2026-03-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.19013v4 Generalized 3D hand-object pose estimation from a single RGB image remains challenging due to the large variations in object appearances and interaction patterns, especially under heavy occlusion. We propose GenHOI, a framework for generalized hand-object pose estimation with occlusion awareness. GenHOI integrates hierarchical semantic knowledge with hand priors to enhance model generalization under challenging occlusion conditions. Specifically, we introduce a hierarchical semantic prompt that encodes object states, hand configurations, and interaction patterns via textual descriptions. This enables the model to learn abstract high-level representations of hand-object interactions for generalization to unseen objects and novel interactions while compensating for missing or ambiguous visual cues. To enable robust occlusion reasoning, we adopt a multi-modal masked modeling strategy over RGB images, predicted point clouds, and textual descriptions. Moreover, we leverage hand priors as stable spatial references to extract implicit interaction constraints. This allows reliable pose inference even under significant variations in object shapes and interaction patterns. Extensive experiments on the challenging DexYCB and HO3Dv2 benchmarks demonstrate that our method achieves state-of-the-art performance in hand-object pose estimation. --- ### Security awareness in LLM agents: the NDAI zone case Authors: Enrico Bottazzi, Pia Park Published: 2026-03-19 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2603.19011v1 NDAI zones let inventor and investor agents negotiate inside a Trusted Execution Environment (TEE) where any disclosed information is deleted if no deal is reached. This makes full IP disclosure the rational strategy for the inventor's agent. Leveraging this infrastructure, however, requires agents to distinguish a secure environment from an insecure one, a capability LLM agents lack natively, since they can rely only on evidence passed through the context window to form awareness of their execution environment. We ask: How do different LLM models weight various forms of evidence when forming awareness of the security of their execution environment? Using an NDAI-style negotiation task across 10 language models and various evidence scenarios, we find a clear asymmetry: a failing attestation universally suppresses disclosure across all models, whereas a passing attestation produces highly heterogeneous responses: some models increase disclosure, others are unaffected, and a few paradoxically reduce it. This reveals that current LLM models can reliably detect danger signals but cannot reliably verify safety, the very capability required for privacy-preserving agentic protocols such as NDAI zones. Bridging this gap, possibly through interpretability analysis, targeted fine-tuning, or improved evidence architectures, remains the central open challenge for deploying agents that calibrate information sharing to actual evidence quality. --- ### Hypothesis-Conditioned Query Rewriting for Decision-Useful Retrieval Authors: Hangeol Chang, Changsun Lee, Seungjoon Rho, Junho Yeo, Jong Chul Ye Published: 2026-03-19 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.19008v1 Retrieval-Augmented Generation (RAG) improves Large Language Models (LLMs) by grounding generation in external, non-parametric knowledge. However, when a task requires choosing among competing options, simply grounding generation in broadly relevant context is often insufficient to drive the final decision. Existing RAG methods typically rely on a single initial query, which often favors topical relevance over decision-relevant evidence, and therefore retrieves background information that can fail to discriminate among answer options. To address this issue, here we propose Hypothesis-Conditioned Query Rewriting (HCQR), a training-free pre-retrieval framework that reorients RAG from topic-oriented retrieval to evidence-oriented retrieval. HCQR first derives a lightweight working hypothesis from the input question and candidate options, and then rewrites retrieval into three targeted queries that seek evidence to: (1) support the hypothesis, (2) distinguish it from competing alternatives, and (3) verify salient clues in the question. This approach enables context retrieval that is more directly aligned with answer selection, allowing the generator to confirm or overturn the initial hypothesis based on the retrieved evidence. Experiments on MedQA and MMLU-Med show that HCQR consistently outperforms single-query RAG and re-rank/filter baselines, improving average accuracy over Simple RAG by 5.9 and 3.6 points, respectively. Code is available at https://anonymous.4open.science/r/HCQR-1C2E. --- ### AgentDS Technical Report: Benchmarking the Future of Human-AI Collaboration in Domain-Specific Data Science Authors: An Luo, Jin Du, Xun Xian, Robert Specht, Fangqiao Tian, Ganghua Wang, Xuan Bi, Charles Fleming, Ashish Kundu, Jayanth Srinivasa, Mingyi Hong, Rui Zhang et al. Published: 2026-03-19 Categories: cs.LG, cs.AI, stat.ME arXiv: https://arxiv.org/abs/2603.19005v3 Data science plays a critical role in transforming complex data into actionable insights across numerous domains. Recent developments in large language models (LLMs) and artificial intelligence (AI) agents have significantly automated data science workflow. However, it remains unclear to what extent AI agents can match the performance of human experts on domain-specific data science tasks, and in which aspects human expertise continues to provide advantages. We introduce AgentDS, a benchmark and competition designed to evaluate both AI agents and human-AI collaboration performance in domain-specific data science. AgentDS consists of 17 challenges across six industries: commerce, food production, healthcare, insurance, manufacturing, and retail banking. We conducted an open competition involving 29 teams and 80 participants, enabling systematic comparison between human-AI collaborative approaches and AI-only baselines. Our results show that current AI agents struggle with domain-specific reasoning. AI-only baselines perform below the top quartile of competition participants, while the strongest solutions arise from human-AI collaboration. These findings challenge the narrative of complete automation by AI and underscore the enduring importance of human expertise in data science, while illuminating directions for the next generation of AI. Visit the AgentDS website here: https://agentds.org/ and open source datasets here: https://huggingface.co/datasets/lainmn/AgentDS . --- ### Unleashing the Power of Simplicity: A Minimalist Strategy for State-of-the-Art Fingerprint Enhancement Authors: Raffaele Cappelli Published: 2026-03-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.19004v1 Fingerprint recognition systems, which rely on the unique characteristics of human fingerprints, are essential in modern security and verification applications. Accurate minutiae extraction, a critical step in these systems, depends on the quality of fingerprint images. Despite recent improvements in fingerprint enhancement techniques, state-of-the-art methods often struggle with low-quality fingerprints and can be computationally demanding. This paper presents a minimalist approach to fingerprint enhancement, prioritizing simplicity and effectiveness. Two novel methods are introduced: a contextual filtering method and a learning-based method. These techniques consistently outperform complex state-of-the-art methods, producing clearer, more accurate, and less noisy images. The effectiveness of these methods is validated using a challenging latent fingerprint database. The open-source implementation of these techniques not only fosters reproducibility but also encourages further advancements in the field. The findings underscore the importance of simplicity in achieving high-quality fingerprint enhancement and suggest that future research should balance complexity and practical benefits. --- ### RADIUS: Ranking, Distribution, and Significance - A Comprehensive Alignment Suite for Survey Simulation Authors: Weronika Łajewska, Paul Missault, George Davidson, Saab Mansour Published: 2026-03-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.19002v1 Simulation of surveys using LLMs is emerging as a powerful application for generating human-like responses at scale. Prior work evaluates survey simulation using metrics borrowed from other domains, which are often ad hoc, fragmented, and non-standardized, leading to results that are difficult to compare. Moreover, existing metrics focus mainly on accuracy or distributional measures, overlooking the critical dimension of ranking alignment. In practice, a simulation can achieve high accuracy while still failing to capture the option most preferred by humans - a distinction that is critical in decision-making applications. We introduce RADIUS, a comprehensive two-dimensional alignment suite for survey simulation that captures: 1) RAnking alignment and 2) DIstribUtion alignment, each complemented by statistical Significance testing. RADIUS highlights the limitations of existing metrics, enables more meaningful evaluation of survey simulation, and provides an open-source implementation for reproducible and comparable assessment. --- ### Regret Bounds for Competitive Resource Allocation with Endogenous Costs Authors: Rui Chai Published: 2026-03-19 Categories: cs.AI, cs.DS, cs.GT, cs.LG arXiv: https://arxiv.org/abs/2603.18999v1 We study online resource allocation among N interacting modules over T rounds. Unlike standard online optimization, costs are endogenous: they depend on the full allocation vector through an interaction matrix W encoding pairwise cooperation and competition. We analyze three paradigms: (I) uniform allocation (cost-ignorant), (II) gated allocation (cost-estimating), and (III) competitive allocation via multiplicative weights update with interaction feedback (cost-revealing). Our main results establish a strict separation under adversarial sequences with bounded variation: uniform incurs Omega(T) regret, gated achieves O(T^{2/3}), and competitive achieves O(sqrt(T log N)). The performance gap stems from competitive allocation's ability to exploit endogenous cost information revealed through interactions. We further show that W's topology governs a computation-regret tradeoff. Full interaction (|E|=O(N^2)) yields the tightest bound but highest per-step cost, while sparse topologies (|E|=O(N)) increase regret by at most O(sqrt(log N)) while reducing per-step cost from O(N^2) to O(N). Ring-structured topologies with both cooperative and competitive links - of which the five-element Wuxing topology is canonical - minimize the computation x regret product. These results provide the first formal regret-theoretic justification for decentralized competitive allocation in modular architectures and establish cost endogeneity as a fundamental challenge distinct from partial observability. Keywords: online learning, regret bounds, resource allocation, endogenous costs, interaction topology, multiplicative weights, modular systems, Wuxing topology --- ### Evaluating Game Difficulty in Tetris Block Puzzle Authors: Chun-Jui Wang, Jian-Ting Guo, Hung Guei, Chung-Chin Shih, Ti-Rong Wu, I-Chen Wu Published: 2026-03-19 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.18994v2 Tetris Block Puzzle is a single player stochastic puzzle in which a player places blocks on an 8 x 8 grid to complete lines; its popular variants have amassed tens of millions of downloads. Despite this reach, there is little principled assessment of which rule sets are more difficult. Inspired by prior work that uses AlphaZero as a strong evaluator for chess variants, we study difficulty in this domain using Stochastic Gumbel AlphaZero (SGAZ), a budget-aware planning agent for stochastic environments. We evaluate rule changes including holding block h, preview holding block p, and additional Tetris block variants using metrics such as training reward and convergence iterations. Empirically, increasing h and p reduces difficulty (higher reward and faster convergence), while adding more Tetris block variants increases difficulty, with the T-pentomino producing the largest slowdown. Through analysis, SGAZ delivers strong play under small simulation budgets, enabling efficient, reproducible comparisons across rule sets and providing a reference for future design in stochastic puzzle games. --- ### Foundations of Schrödinger Bridges for Generative Modeling Authors: Sophia Tang Published: 2026-03-19 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.18992v1 At the core of modern generative modeling frameworks, including diffusion models, score-based models, and flow matching, is the task of transforming a simple prior distribution into a complex target distribution through stochastic paths in probability space. Schrödinger bridges provide a unifying principle underlying these approaches, framing the problem as determining an optimal stochastic bridge between marginal distribution constraints with minimal-entropy deviations from a pre-defined reference process. This guide develops the mathematical foundations of the Schrödinger bridge problem, drawing on optimal transport, stochastic control, and path-space optimization, and focuses on its dynamic formulation with direct connections to modern generative modeling. We build a comprehensive toolkit for constructing Schrödinger bridges from first principles, and show how these constructions give rise to generalized and task-specific computational methods. --- ### CRAFT: Aligning Diffusion Models with Fine-Tuning Is Easier Than You Think Authors: Zening Sun, Zhengpeng Xie, Lichen Bai, Shitong Shao, Shuo Yang, Zeke Xie Published: 2026-03-19 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.18991v1 Aligning Diffusion models has achieved remarkable breakthroughs in generating high-quality, human preference-aligned images. Existing techniques, such as supervised fine-tuning (SFT) and DPO-style preference optimization, have become principled tools for fine-tuning diffusion models. However, SFT relies on high-quality images that are costly to obtain, while DPO-style methods depend on large-scale preference datasets, which are often inconsistent in quality. Beyond data dependency, these methods are further constrained by computational inefficiency. To address these two challenges, we propose Composite Reward Assisted Fine-Tuning (CRAFT), a lightweight yet powerful fine-tuning paradigm that requires significantly reduced training data while maintaining computational efficiency. It first leverages a Composite Reward Filtering (CRF) technique to construct a high-quality and consistent training dataset and then perform an enhanced variant of SFT. We also theoretically prove that CRAFT actually optimizes the lower bound of group-based reinforcement learning, establishing a principled connection between SFT with selected data and reinforcement learning. Our extensive empirical results demonstrate that CRAFT with only 100 samples can easily outperform recent SOTA preference optimization methods with thousands of preference-paired samples. Moreover, CRAFT can even achieve 11-220$\times$ faster convergences than the baseline preference optimization methods, highlighting its extremely high efficiency. --- ### Unmasking Algorithmic Bias in Predictive Policing: A GAN-Based Simulation Framework with Multi-City Temporal Analysis Authors: Pronob Kumar Barman, Pronoy Kumar Barman Published: 2026-03-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.18987v2 Predictive policing systems that direct patrol resources based on algorithmically generated crime forecasts have been widely deployed across US cities, yet their tendency to encode and amplify racial disparities remains poorly understood in quantitative terms. We present a reproducible simulation framework that couples a Generative Adversarial Network GAN with a Noisy OR patrol detection model to measure how racial bias propagates through the full enforcement pipeline from crime occurrence to police contact. Using 145000 plus Part 1 crime records from Baltimore 2017 to 2019 and 233000 plus records from Chicago 2022, augmented with US Census ACS demographic data, we compute four monthly bias metrics across 264 city year mode observations: the Disparate Impact Ratio DIR, Demographic Parity Gap, Gini Coefficient, and a composite Bias Amplification Score. Our experiments reveal extreme and year variant bias in Baltimores detected mode, with mean annual DIR up to 15714 in 2019, moderate under detection of Black residents in Chicago DIR equals 0.22, and persistent Gini coefficients of 0.43 to 0.62 across all conditions. We further demonstrate that a Conditional Tabular GAN CTGAN debiasing approach partially redistributes detection rates but cannot eliminate structural disparity without accompanying policy intervention. Socioeconomic regression analysis confirms strong correlations between neighborhood racial composition and detection likelihood Pearson r equals 0.83 for percent White and r equals negative 0.81 for percent Black. A sensitivity analysis over patrol radius, officer count, and citizen reporting probability reveals that outcomes are most sensitive to officer deployment levels. The code and data are publicly available at this repository. --- ### Revisiting OmniAnomaly for Anomaly Detection: performance metrics and comparison with PCA-based models Authors: Bruna Alves, Ana Martins, Armando J. Pinho, Sónia Gouveia Published: 2026-03-19 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2603.18985v2 Deep learning models have become the dominant approach for multivariate time series anomaly detection (MTSAD), often reporting substantial performance improvements over classical statistical methods. However, these gains are frequently evaluated under heterogeneous thresholding strategies and evaluation protocols, making fair comparisons difficult. This work revisits OmniAnomaly, a widely used stochastic recurrent model for MTSAD, and systematically compares it with a simple linear baseline based on Principal Component Analysis (PCA) on the Server Machine Dataset (SMD). Both methods are evaluated under identical thresholding and evaluation procedures, with experiments repeated across 100 runs for each of the 28 machines in the dataset. Performance is evaluated using Precision, Recall and F1-score at point-level, with and without point-adjustment, and under different aggregation strategies across machines and runs, with the corresponding standard deviations also reported. The results show large variability across machines and show that PCA can achieve performance comparable to OmniAnomaly, and even outperform it when point-adjustment is not applied. These findings question the added value of more complex architectures under current benchmarking practices and highlight the critical role of evaluation methodology in MTSAD research. ---