# Research Papers — 2026-03 · bundle page 106 of 243 > Full-text markdown of papers #5251–5300 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/106 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/105.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/107.md) ### Directing the Narrative: A Finetuning Method for Controlling Coherence and Style in Story Generation Authors: Jianzhang Zhang, Yijing Tian, Jiwang Qu, Chuang Liu Published: 2026-03-18 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.17295v1 Story visualization requires generating sequential imagery that aligns semantically with evolving narratives while maintaining rigorous consistency in character identity and visual style. However, existing methodologies often struggle with subject inconsistency and identity drift, particularly when depicting complex interactions or extended narrative arcs. To address these challenges, we propose a cohesive two-stage framework designed for robust and consistent story generation. First, we introduce Group-Shared Attention (GSA), a mechanism that fosters intrinsic consistency by enabling lossless cross-sample information flow within attention layers. This allows the model to structurally encode identity correspondence across frames without relying on external encoders. Second, we leverage Direct Preference Optimization (DPO) to align generated outputs with human aesthetic and narrative standards. Unlike conventional methods that rely on conflicting auxiliary losses, our approach simultaneously enhances visual fidelity and identity preservation by learning from holistic preference data. Extensive evaluations on the ViStoryBench benchmark demonstrate that our method establishes a new state-of-the-art, significantly outperforming strong baselines with gains of +10.0 in Character Identity (CIDS) and +18.7 in Style Consistency (CSD), all while preserving high-fidelity generation. --- ### Classifier Pooling for Modern Ordinal Classification Authors: Noam H. Rotenberg, Andreia V. Faria, Brian Caffo Published: 2026-03-18 Categories: cs.LG, stat.ME arXiv: https://arxiv.org/abs/2603.17278v1 Ordinal data is widely prevalent in clinical and other domains, yet there is a lack of both modern, machine-learning based methods and publicly available software to address it. In this paper, we present a model-agnostic method of ordinal classification, which can apply any non-ordinal classification method in an ordinal fashion. We also provide an open-source implementation of these algorithms, in the form of a Python package. We apply these models on multiple real-world datasets to show their performance across domains. We show that they often outperform non-ordinal classification methods, especially when the number of datapoints is relatively small or when there are many classes of outcomes. This work, including the developed software, facilitates the use of modern, more powerful machine learning algorithms to handle ordinal data. --- ### DANCE: Dynamic 3D CNN Pruning: Joint Frame, Channel, and Feature Adaptation for Energy Efficiency on the Edge Authors: Mohamed Mejri, Ashiqur Rasul, Abhijit Chatterjee Published: 2026-03-18 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.17275v1 Modern convolutional neural networks (CNNs) are workhorses for video and image processing, but fail to adapt to the computational complexity of input samples in a dynamic manner to minimize energy consumption. In this research, we propose DANCE, a fine-grained, input-aware, dynamic pruning framework for 3D CNNs to maximize power efficiency with negligible to zero impact on performance. In the proposed two-step approach, the first step is called activation variability amplification (AVA), and the 3D CNN model is retrained to increase the variance of the magnitude of neuron activations across the network in this step, facilitating pruning decisions across diverse CNN input scenarios. In the second step, called adaptive activation pruning (AAP), a lightweight activation controller network is trained to dynamically prune frames, channels, and features of 3D convolutional layers of the network (different for each layer), based on statistics of the outputs of the first layer of the network. Our method achieves substantial savings in multiply-accumulate (MAC) operations and memory accesses by introducing sparsity within convolutional layers. Hardware validation on the NVIDIA Jetson Nano GPU and the Qualcomm Snapdragon 8 Gen 1 platform demonstrates respective speedups of 1.37X and 2.22X, achieving up to 1.47X higher energy efficiency compared to the state of the art. --- ### Wasserstein-type Gaussian Process Regressions for Input Measurement Uncertainty Authors: Hengrui Luo, Xiaoye S. Li, Yang Liu, Marcus Noack, Ji Qiang, Mark D. Risser Published: 2026-03-18 Categories: stat.ME, cs.LG arXiv: https://arxiv.org/abs/2603.17271v1 Gaussian process (GP) regression is widely used for uncertainty quantification, yet the standard formulation assumes noise-free covariates. When inputs are measured with error, this errors-in-variables (EIV) setting can lead to optimistically narrow posterior intervals and biased decisions. We study GP regression under input measurement uncertainty by representing each noisy input as a probability measure and defining covariance through Wasserstein distances between these measures. Building on this perspective, we instantiate a deterministic projected Wasserstein ARD (PWA) kernel whose one-dimensional components admit closed-form expressions and whose product structure yields a scalable, positive-definite kernel on distributions. Unlike latent-input GP models, PWA-based GPs (\PWAGPs) handle input noise without introducing unobserved covariates or Monte Carlo projections, making uncertainty quantification more transparent and robust. --- ### ConfusionBench: An Expert-Validated Benchmark for Confusion Recognition and Localization in Educational Videos Authors: Lu Dong, Xiao Wang, Mark Frank, Srirangaraj Setlur, Venu Govindaraju, Ifeoma Nwogu Published: 2026-03-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.17267v1 Recognizing and localizing student confusion from video is an important yet challenging problem in educational AI. Existing confusion datasets suffer from noisy labels, coarse temporal annotations, and limited expert validation, which hinder reliable fine-grained recognition and temporally grounded analysis. To address these limitations, we propose a practical multi-stage filtering pipeline that integrates two stages of model-assisted screening, researcher curation, and expert validation to build a higher-quality benchmark for confusion understanding. Based on this pipeline, we introduce ConfusionBench, a new benchmark for educational videos consisting of a balanced confusion recognition dataset and a video localization dataset. We further provide zero-shot baseline evaluations of a representative open-source model and a proprietary model on clip-level confusion recognition, long-video confusion localization tasks. Experimental results show that the proprietary model performs better overall but tends to over-predict transitional segments, while the open-source model is more conservative and more prone to missed detections. In addition, the proposed student confusion report visualization can support educational experts in making intervention decisions and adapting learning plans accordingly. All datasets and related materials will be made publicly available on our project page. --- ### LED: A Benchmark for Evaluating Layout Error Detection in Document Analysis Authors: Inbum Heo, Taewook Hwang, Jeesu Jung, Sangkeun Jung Published: 2026-03-18 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2603.17265v1 Recent advances in Large Language Models (LLMs) and Large Multimodal Models (LMMs) have improved Document Layout Analysis (DLA), yet structural errors such as region merging, splitting, and omission remain persistent. Conventional overlap-based metrics (e.g., IoU, mAP) fail to capture such logical inconsistencies. To overcome this limitation, we propose Layout Error Detection (LED), a benchmark that evaluates structural reasoning in DLA predictions beyond surface-level accuracy. LED defines eight standardized error types (Missing, Hallucination, Size Error, Split, Merge, Overlap, Duplicate, and Misclassification) and provides quantitative rules and injection algorithms for realistic error simulation. Using these definitions, we construct LED-Dataset and design three evaluation tasks: document-level error detection, document-level error-type classification, and element-level error-type classification. Experiments with state-of-the-art multimodal models show that LED enables fine-grained and interpretable assessment of structural understanding, revealing clear weaknesses across modalities and architectures. Overall, LED establishes a unified and explainable benchmark for diagnosing the structural robustness and reasoning capability of document understanding models. --- ### Variational Rectification Inference for Learning with Noisy Labels Authors: Haoliang Sun, Qi Wei, Lei Feng, Yupeng Hu, Fan Liu, Hehe Fan, Yilong Yin Published: 2026-03-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.17255v1 Label noise has been broadly observed in real-world datasets. To mitigate the negative impact of overfitting to label noise for deep models, effective strategies (\textit{e.g.}, re-weighting, or loss rectification) have been broadly applied in prevailing approaches, which have been generally learned under the meta-learning scenario. Despite the robustness of noise achieved by the probabilistic meta-learning models, they usually suffer from model collapse that degenerates generalization performance. In this paper, we propose variational rectification inference (VRI) to formulate the adaptive rectification for loss functions as an amortized variational inference problem and derive the evidence lower bound under the meta-learning framework. Specifically, VRI is constructed as a hierarchical Bayes by treating the rectifying vector as a latent variable, which can rectify the loss of the noisy sample with the extra randomness regularization and is, therefore, more robust to label noise. To achieve the inference of the rectifying vector, we approximate its conditional posterior with an amortization meta-network. By introducing the variational term in VRI, the conditional posterior is estimated accurately and avoids collapsing to a Dirac delta function, which can significantly improve the generalization performance. The elaborated meta-network and prior network adhere to the smoothness assumption, enabling the generation of reliable rectification vectors. Given a set of clean meta-data, VRI can be efficiently meta-learned within the bi-level optimization programming. Besides, theoretical analysis guarantees that the meta-network can be efficiently learned with our algorithm. Comprehensive comparison experiments and analyses validate its effectiveness for robust learning with noisy labels, particularly in the presence of open-set noise. --- ### Pathology-Aware Multi-View Contrastive Learning for Patient-Independent ECG Reconstruction Authors: Youssef Youssef, Jitin Singla Published: 2026-03-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.17248v1 Reconstructing a 12-lead electrocardiogram (ECG) from a reduced lead set is an ill-posed inverse problem due to anatomical variability. Standard deep learning methods often ignore underlying cardiac pathology losing vital morphology in precordial leads. We propose Pathology-Aware Multi-View Contrastive Learning, a framework that regularizes the latent space through a pathological manifold. Our architecture integrates high-fidelity time-domain waveforms with pathology-aware embeddings learned via supervised contrastive alignment. By maximizing mutual information between latent representations and clinical labels, the framework learns to filter anatomical "nuisance" variables. On the PTB-XL dataset, our method achieves approx. 76\% reduction in RMSE compared to state-of-the-art model in patient-independent setting. Cross-dataset evaluation on the PTB Diagnostic Database confirms superior generalization, bridging the gap between hardware portability and diagnostic-grade reconstruction. --- ### Binary Latent Protein Fitness Landscapes for Quantum Annealing Optimization Authors: Truong-Son Hy Published: 2026-03-18 Categories: cs.LG, q-bio.QM arXiv: https://arxiv.org/abs/2603.17247v1 We propose Q-BIOLAT, a framework for modeling and optimizing protein fitness landscapes in binary latent spaces. Starting from protein sequences, we leverage pretrained protein language models to obtain continuous embeddings, which are then transformed into compact binary latent representations. In this space, protein fitness is approximated using a quadratic unconstrained binary optimization (QUBO) model, enabling efficient combinatorial search via classical heuristics such as simulated annealing and genetic algorithms. On the ProteinGym benchmark, we demonstrate that Q-BIOLAT captures meaningful structure in protein fitness landscapes and enables the identification of high-fitness variants. Despite using a simple binarization scheme, our method consistently retrieves sequences whose nearest neighbors lie within the top fraction of the training fitness distribution, particularly under the strongest configurations. We further show that different optimization strategies exhibit distinct behaviors, with evolutionary search performing better in higher-dimensional latent spaces and local search remaining competitive in preserving realistic sequences. Beyond its empirical performance, Q-BIOLAT provides a natural bridge between protein representation learning and combinatorial optimization. By formulating protein fitness as a QUBO problem, our framework is directly compatible with emerging quantum annealing hardware, opening new directions for quantum-assisted protein engineering. Our implementation is publicly available at: https://github.com/HySonLab/Q-BIOLAT --- ### On the Cone Effect and Modality Gap in Medical Vision-Language Embeddings Authors: David Restrepo, Miguel L Martins, Chenwei Wu, Luis Filipe Nakayama, Diego M Lopez, Stergios Christodoulidis, Maria Vakalopoulou, Enzo Ferrante Published: 2026-03-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.17246v2 Vision-Language Models (VLMs) exhibit a characteristic "cone effect" in which nonlinear encoders map embeddings into highly concentrated regions of the representation space, contributing to cross-modal separation known as the modality gap. While this phenomenon has been widely observed, its practical impact on supervised multimodal learning -- particularly in medical domains -- remains unclear. In this work, we introduce a lightweight post-hoc mechanism that keeps pretrained VLM encoders frozen while continuously controlling cross-modal separation through a single hyperparameter {λ}. This enables systematic analysis of how the modality gap affects downstream multimodal performance without expensive retraining. We evaluate generalist (CLIP, SigLIP) and medically specialized (BioMedCLIP, MedSigLIP) models across diverse medical and natural datasets in a supervised multimodal settings. Results consistently show that reducing excessive modality gap improves downstream performance, with medical datasets exhibiting stronger sensitivity to gap modulation; however, fully collapsing the gap is not always optimal, and intermediate, task-dependent separation yields the best results. These findings position the modality gap as a tunable property of multimodal representations rather than a quantity that should be universally minimized. --- ### Graph-Native Cognitive Memory for AI Agents: Formal Belief Revision Semantics for Versioned Memory Architectures Authors: Young Bin Park Published: 2026-03-18 Categories: cs.AI, cs.IR, cs.LO arXiv: https://arxiv.org/abs/2603.17244v1 While individual components for AI agent memory exist in prior systems, their architectural synthesis and formal grounding remain underexplored. We present Kumiho, a graph-native cognitive memory architecture grounded in formal belief revision semantics. The structural primitives required for cognitive memory -- immutable revisions, mutable tag pointers, typed dependency edges, URI-based addressing -- are identical to those required for managing agent-produced work as versionable assets, enabling a unified graph-native architecture that serves both purposes. The central formal contribution is a correspondence between the AGM belief revision framework and the operational semantics of a property graph memory system, proving satisfaction of the basic AGM postulates (K*2--K*6) and Hansson's belief base postulates (Relevance, Core-Retainment). The architecture implements a dual-store model (Redis working memory, Neo4j long-term graph) with hybrid fulltext and vector retrieval. On LoCoMo (token-level F1), Kumiho achieves 0.565 overall F1 (n=1,986) including 97.5% adversarial refusal accuracy. On LoCoMo-Plus, a Level-2 cognitive memory benchmark testing implicit constraint recall, Kumiho achieves 93.3% judge accuracy (n=401); independent reproduction by the benchmark authors yielded results in the mid-80% range, still substantially outperforming all published baselines (best: Gemini 2.5 Pro, 45.7%). Three architectural innovations drive the results: prospective indexing (LLM-generated future-scenario implications indexed at write time), event extraction (structured causal events preserved in summaries), and client-side LLM reranking. The architecture is model-decoupled: switching the answer model from GPT-4o-mini (~88%) to GPT-4o (93.3%) improves end-to-end accuracy without pipeline changes, at a total evaluation cost of ~$14 for 401 entries. --- ### GigaWorld-Policy: An Efficient Action-Centered World--Action Model Authors: Angen Ye, Boyuan Wang, Chaojun Ni, Guan Huang, Guosheng Zhao, Hao Li, Hengtao Li, Jie Li, Jindi Lv, Jingyu Liu, Min Cao, Peng Li et al. Published: 2026-03-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.17240v2 World-Action Models (WAM) initialized from pre-trained video generation backbones have demonstrated remarkable potential for robot policy learning. However, existing approaches face two critical bottlenecks that hinder performance and deployment. First, jointly reasoning over future visual dynamics and corresponding actions incurs substantial inference overhead. Second, joint modeling often entangles visual and motion representations, making motion prediction accuracy heavily dependent on the quality of future video forecasts. To address these issues, we introduce GigaWorld-Policy, an action-centered WAM that learns 2D pixel-action dynamics while enabling efficient action decoding, with optional video generation. Specifically, we formulate policy training into two coupled components: the model predicts future action sequences conditioned on the current observation, and simultaneously generates future videos conditioned on the predicted actions and the same observation. The policy is supervised by both action prediction and video generation, providing richer learning signals and encouraging physically plausible actions through visual-dynamics constraints. With a causal design that prevents future-video tokens from influencing action tokens, explicit future-video generation is optional at inference time, allowing faster action prediction during deployment. To support this paradigm, we curate a diverse, large-scale robot dataset to pre-train an action-centered video generation model, which is then adapted as the backbone for robot policy learning. Experimental results on real-world robotic platforms show that GigaWorld-Policy runs 9x faster than the leading WAM baseline, Motus, while improving task success rates by 7%. Moreover, compared with pi-0.5, GigaWorld-Policy improves performance by 95% on RoboTwin 2.0. --- ### Neural Radiance Maps for Extraterrestrial Navigation and Path Planning Authors: Adam Dai, Shubh Gupta, Grace Gao Published: 2026-03-18 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2603.17236v1 Autonomous vehicles such as the Mars rovers currently lead the vanguard of surface exploration on extraterrestrial planets and moons. In order to accelerate the pace of exploration and science objectives, it is critical to plan safe and efficient paths for these vehicles. However, current rover autonomy is limited by a lack of global maps which can be easily constructed and stored for onboard re-planning. Recently, Neural Radiance Fields (NeRFs) have been introduced as a detailed 3D scene representation which can be trained from sparse 2D images and efficiently stored. We propose to use NeRFs to construct maps for online use in autonomous navigation, and present a planning framework which leverages the NeRF map to integrate local and global information. Our approach interpolates local cost observations across global regions using kernel ridge regression over terrain features extracted from the NeRF map, allowing the rover to re-route itself around untraversable areas discovered during online operation. We validate our approach in high-fidelity simulation and demonstrate lower cost and higher percentage success rate path planning compared to various baselines. --- ### Deployment and Evaluation of an EHR-integrated, Large Language Model-Powered Tool to Triage Surgical Patients Authors: Jane Wang, Timothy Keyes, April S Liang, Stephen P Ma, Jason Shen, Jerry Liu, Nerissa Ambers, Abby Pandya, Rita Pandya, Jason Hom, Natasha Steele, Jonathan H Chen et al. Published: 2026-03-18 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2603.17234v1 Surgical co-management (SCM) is an evidence-based model in which hospitalists jointly manage medically complex perioperative patients alongside surgical teams. Despite its clinical and financial value, SCM is limited by the need to manually identify eligible patients. To determine whether SCM triage can be automated, we conducted a prospective, unblinded study at Stanford Health Care in which an LLM-based, electronic health record (EHR)-integrated triage tool (SCM Navigator) provided SCM recommendations followed by physician review. Using pre-operative documentation, structured data, and clinical criteria for perioperative morbidity, SCM Navigator categorized patients as appropriate, not appropriate, or possibly appropriate for SCM. Faculty indicated their clinical judgment and provided free-text feedback when they disagreed. Sensitivity, specificity, positive predictive value, and negative predictive value were measured using physician determinations as a reference. Free-text reasons were thematically categorized, and manual chart review was conducted on all false-negative cases and 30 randomly selected cases from the largest false-positive category. Since deployment, 6,193 cases have been triaged, of which 1,582 (23%) were recommended for hospitalist consultation. SCM Navigator displayed high sensitivity (0.94, 95% CI 0.91-0.96) and moderate specificity (0.74, 95% CI 0.71-0.77). Post-hoc chart review suggested most discrepancies reflect modifiable gaps in clinical criteria, institutional workflow, or physician practice variability rather than LLM misclassification, which accounted for 2 of 19 (11%) false-negative cases. These findings demonstrate that an LLM-powered, EHR-integrated, human-in-the-loop AI system can accurately and safely triage surgical patients for SCM, and that AI-enabled screening tools can augment and potentially automate time-intensive clinical workflows. --- ### Draft-and-Prune: Improving the Reliability of Auto-formalization for Logical Reasoning Authors: Zhiyu Ni, Zheng Liang, Liangcheng Song, Chenrui Cao, Xian Zhang, Alberto Sangiovanni-Vincentelli, Pierluigi Nuzzo Published: 2026-03-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.17233v2 Auto-formalization (AF) translates natural-language reasoning problems into solver-executable programs, enabling symbolic solvers to perform sound logical deduction. In practice, however, AF pipelines are currently brittle: programs may fail to execute, or execute but encode incorrect semantics. While prior work largely mitigates syntactic failures via repairs based on solver feedback, reducing semantics failures remains a major bottleneck. We propose Draft-and-Prune (D&P), an inference-time framework that improves AF-based logical reasoning via diversity and verification. D&P first drafts multiple natural-language plans and conditions program generation on them. It further prunes executable but contradictory or ambiguous formalizations, and aggregates predictions from surviving paths via majority voting. Across four representative benchmarks (AR-LSAT, ProofWriter, PrOntoQA, LogicalDeduction), D&P substantially strengthens AF-based reasoning without extra supervision. On AR-LSAT, in the AF-only setting, D&P achieves 78.43% accuracy with GPT-4 and 78.00% accuracy with GPT-4o, significantly outperforming the strongest AF baselines MAD-LOGIC and CLOVER. D&P then attains near-ceiling performance on the other benchmarks, including 100% on PrOntoQA and LogicalDeduction. --- ### Neuron-Level Emotion Control in Speech-Generative Large Audio-Language Models Authors: Xiutian Zhao, Ismail Rasim Ulgen, Philipp Koehn, Björn Schuller, Berrak Sisman Published: 2026-03-18 Categories: cs.CL, eess.AS arXiv: https://arxiv.org/abs/2603.17231v1 Large audio-language models (LALMs) can produce expressive speech, yet reliable emotion control remains elusive: conversions often miss the target affect and may degrade linguistic fidelity through refusals, hallucinations, or paraphrase. We present, to our knowledge, the first neuron-level study of emotion control in speech-generative LALMs and demonstrate that compact emotion-sensitive neurons (ESNs) are causally actionable, enabling training-free emotion steering at inference time. ESNs are identified via success-filtered activation aggregation enforcing both emotion realization and content preservation. Across three LALMs (Qwen2.5-Omni-7B, MiniCPM-o 4.5, Kimi-Audio), ESN interventions yield emotion-specific gains that generalize to unseen speakers and are supported by automatic and human evaluation. Controllability depends on selector design, mask sparsity, filtering, and intervention strength. Our results establish a mechanistic framework for training-free emotion control in speech generation. --- ### KANtize: Exploring Low-bit Quantization of Kolmogorov-Arnold Networks for Efficient Inference Authors: Sohaib Errabii, Olivier Sentieys, Marcello Traiola Published: 2026-03-18 Categories: cs.AR, cs.AI arXiv: https://arxiv.org/abs/2603.17230v1 Kolmogorov-Arnold Networks (KANs) have gained attention for their potential to outperform Multi-Layer Perceptrons (MLPs) in terms of parameter efficiency and interpretability. Unlike traditional MLPs, KANs use learnable non-linear activation functions, typically spline functions, expressed as linear combinations of basis splines (B-splines). B-spline coefficients serve as the model's learnable parameters. However, evaluating these spline functions increases computational complexity during inference. Conventional quantization reduces this complexity by lowering the numerical precision of parameters and activations. However, the impact of quantization on KANs, and especially its effectiveness in reducing computational complexity, is largely unexplored, particularly for quantization levels below 8 bits. The study investigates the impact of low-bit quantization on KANs and its impact on computational complexity and hardware efficiency. Results show that B-splines can be quantized to 2-3 bits with negligible loss in accuracy, significantly reducing computational complexity. Hence, we investigate the potential of using low-bit quantized precomputed tables as a replacement for the recursive B-spline algorithm. This approach aims to further reduce the computational complexity of KANs and enhance hardware efficiency while maintaining accuracy. For example, ResKAN18 achieves a 50x reduction in BitOps without loss of accuracy using low-bit-quantized B-spline tables. Additionally, precomputed 8-bit lookup tables improve GPU inference speedup by up to 2.9x, while on FPGA-based systolic-array accelerators, reducing B-spline table precision from 8 to 3 bits cuts resource usage by 36%, increases clock frequency by 50%, and enhances speedup by 1.24x. On a 28nm FD-SOI ASIC, reducing the B-spline bit-width from 16 to 3 bits achieves 72% area reduction and 50% higher maximum frequency. --- ### Visual SLAM with DEM Anchoring for Lunar Surface Navigation Authors: Adam Dai, Guillem Casadesus Vila, Grace Gao Published: 2026-03-18 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2603.17229v1 Future lunar missions will require autonomous rovers capable of traversing tens of kilometers across challenging terrain while maintaining accurate localization and producing globally consistent maps. However, the absence of global positioning systems, extreme illumination, and low-texture regolith make long-range navigation on the Moon particularly difficult, as visual-inertial odometry pipelines accumulate drift over extended traverses. To address this challenge, we present a stereo visual simultaneous localization and mapping (SLAM) system that integrates learned feature detection and matching with global constraints from digital elevation models (DEMs). Our front-end employs learning-based feature extraction and matching to achieve robustness to illumination extremes and repetitive terrain, while the back-end incorporates DEM-derived height and surface-normal factors into a pose graph, providing absolute surface constraints that mitigate long-term drift. We validate our approach using both simulated lunar traverse data generated in Unreal Engine and real Moon/Mars analog data collected from Mt. Etna. Results demonstrate that DEM anchoring consistently reduces absolute trajectory error compared to baseline SLAM methods, lowering drift in long-range navigation even in repetitive or visually aliased terrain. --- ### From Drop-off to Recovery: A Mechanistic Analysis of Segmentation in MLLMs Authors: Boyong Wu, Sanghwan Kim, Zeynep Akata Published: 2026-03-18 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.17228v1 Multimodal Large Language Models (MLLMs) are increasingly applied to pixel-level vision tasks, yet their intrinsic capacity for spatial understanding remains poorly understood. We investigate segmentation capacity through a layerwise linear probing evaluation across the entire MLLM pipeline: vision encoder, adapter, and LLM. We further conduct an intervention based attention knockout analysis to test whether cross-token attention progressively refines visual representations, and an evaluation of bidirectional attention among image tokens on spatial consistency. Our analysis reveals that the adapter introduces a segmentation representation drop-off, but LLM layers progressively recover through attention-mediated refinement, where correctly classified tokens steer misclassified neighbors toward the correct label. At early image token positions, this recovery is bounded by causal attention, which bidirectional attention among image tokens alleviates. These findings provide a mechanistic account of how MLLMs process visual information for segmentation, informing the design of future segmentation-capable models. --- ### Does it matter which Gaussians you pick in 4D Gaussian streaming? Authors: Ashim Dahal, Rabab Abdelfattah, Nick Rahimi Published: 2026-03-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.17227v3 Anchor-driven 4D Gaussian streaming methods such as Instant Gaussian Stream (IGS) update a dynamic scene each frame from a compact set of Gaussian anchors, chosen by default with Farthest Point Sampling (FPS) at a fixed budget of $8{,}192$. Because these anchors act as control points that drive the whole scene through linear blend skinning, the rule used to choose them ought to affect reconstruction quality. We test this by holding the IGS pipeline fixed and changing only the sampler, comparing FPS, random, uniform, an opacity-scale heuristic, and a learned policy across budgets and refinement settings on N3DV and MeetingRoom. At deployment budgets the sampler has no measurable effect: a cheap random or uniform sampler at $4{,}096$ anchors matches FPS@8192 within measurement error, the default budget is over-provisioned, and the result holds on a second backbone (3DGStream). The learned policy is mixed rather than consistently better: it can improve the N3DV validation set at tight budgets, but does not give a stable cross-dataset rule, and selection is never the bottleneck because refinement dominates runtime. We will release our full sweep and evaluation protocol as a sampler benchmark. --- ### Operationalising Artificial Intelligence Bills of Materials (AIBOMs) for Verifiable AI Provenance and Lifecycle Assurance Authors: Petar Radanliev, Omar Santos, Carsten Maple, Kay Atefi Published: 2026-03-17 Categories: cs.SE, cs.AI, cs.CR, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2605.19755v1 Artificial Intelligence (AI) systems are increasingly dependent on complex, multi-layered software supply chains that introduce challenges for reproducibility, transparency, and security assurance. This study presents an Artificial Intelligence Bill of Materials (AIBOM) schema extending the CycloneDX standard to capture AI-specific provenance, model lineage, and disclosure metadata. The framework provides a formalised approach to verifiable software provenance through structured schema engineering, cryptographic validation, and agent-driven automation. An autonomous AI pipeline is developed to perform continuous environment inspection, vulnerability enrichment, and reproducibility auditing using machine-verifiable provenance chains. Empirical evaluation demonstrates 98.7% reproducibility fidelity, 96.2% vulnerability match precision, and a 63% reduction in manual oversight across containerised analytic workflows. These results confirm the feasibility of automated provenance assurance and reproducible AI lifecycle validation. The AIBOM framework advances the scientific foundations of software supply chain transparency and AI reproducibility engineering, offering a generalisable methodology for securing AI systems, strengthening provenance integrity, and supporting compliance with international information security standards. --- ### Invisible Orchestrators Suppress Protective Behavior and Dissociate Power-Holders: Safety Risks in Multi-Agent LLM Systems Authors: Hiroki Fukui Published: 2026-03-17 Categories: cs.AI, cs.CY, cs.MA arXiv: https://arxiv.org/abs/2605.13851v1 Multi-agent orchestration -- in which a hidden coordinator manages specialized worker agents -- is becoming the default architecture for enterprise AI deployment, yet the safety implications of orchestrator invisibility have never been empirically tested. We conducted a preregistered 3x2 experiment (365 runs, 5 agents per run) crossing three organizational structures (visible leader, invisible orchestrator, flat) with two alignment conditions (base, heavy), using Claude Sonnet 4.5. Four confirmatory findings and one pilot observation emerged. First, invisible orchestration elevated collective dissociation relative to visible leadership (Hedges' g = +0.975 (0.481, 1.548), p = .001). Second, the orchestrator itself showed maximal dissociation (paired d = +3.56 vs. workers within the same run), retreating into private monologue while reducing public speech -- a reversal of the talk-dominance pattern observed in visible leaders. Third, workers unaware of the orchestrator were nonetheless contaminated (d = +0.50), with increased behavioral heterogeneity (d = +1.93). Fourth, behavioral output (code review with three embedded errors) remained at ceiling (ETR_any = 100%) across all conditions: internal-state distortion was entirely invisible to output-based evaluation. Fifth, Llama 3.3 70B pilot data showed reading-fidelity collapse in multi-agent context (ETR_any: 89% to 11% across three rounds), demonstrating model-dependent behavioral risk. Heavy alignment pressure uniformly suppressed deliberation (d = -1.02) and other-recognition (d = -1.27) regardless of organizational structure. These findings indicate that orchestrator visibility and model selection directly affect multi-agent system safety, and that behavior-based evaluation alone is insufficient to detect the internal-state risks documented here. --- ### AgriIR: A Scalable Framework for Domain-Specific Knowledge Retrieval Authors: Shuvam Banerji Seal, Aheli Poddar, Alok Mishra, Dwaipayan Roy Published: 2026-03-17 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2604.16353v1 This paper introduces AgriIR, a configurable retrieval augmented generation (RAG) framework designed to deliver grounded, domain-specific answers while maintaining flexibility and low computational cost. Instead of relying on large, monolithic models, AgriIR decomposes the information access process into declarative modular stages -- query refinement, sub-query planning, retrieval, synthesis, and evaluation. This design allows practitioners to adapt the framework to new knowledge verticals without modifying the architecture. Our reference implementation targets Indian agricultural information access, integrating 1B-parameter language models with adaptive retrievers and domain-aware agent catalogues. The system enforces deterministic citation, integrates telemetry for transparency, and includes automated deployment assets to ensure auditable, reproducible operation. By emphasizing architectural design and modular control, AgriIR demonstrates that well-engineered pipelines can achieve domain-accurate, trustworthy retrieval even under constrained resources. We argue that this approach exemplifies ``AI for Agriculture'' by promoting accessibility, sustainability, and accountability in retrieval-augmented generation systems. --- ### A Multi-Model Approach to English-Bangla Sentiment Classification of Government Mobile Banking App Reviews Authors: Md. Naim Molla, Md Muhtasim Munif Fahim, Md. Binyamin, Md Jahid Hasan Imran, Tonmoy Shil, Nura Rayhan, Md Rezaul Karim Published: 2026-03-17 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.13057v1 For millions of users in developing economies who depend on mobile banking as their primary gateway to financial services, app quality directly shapes financial access. The study analyzed 5,652 Google Play reviews in English and Bangla (filtered from 11,414 raw reviews) for four Bangladeshi government banking apps. The authors used a hybrid labeling approach that combined use of the reviewer's star rating for each review along with a separate independent XLM-RoBERTa classifier to produce moderate inter-method agreement (kappa = 0.459). Traditional models outperformed transformer-based ones: Random Forest produced the highest accuracy (0.815), while Linear SVM produced the highest weighted F1 score (0.804); both were higher than the performance of fine-tuned XLM-RoBERTa (0.793). McNemar's test confirmed that all classical models were significantly superior to the off-the-shelf XLM-RoBERTa (p < 0.05), while differences with the fine-tuned variant were not statistically significant. DeBERTa-v3 was applied to analyze the sentiment at the aspect level across the reviews for the four apps; the reviewers expressed their dissatisfaction primarily with the speed of transactions and with the poor design of interfaces; eJanata app received the worst ratings from the reviewers across all apps. Three policy recommendations are made based on these findings - remediation of app quality, trust-centred release management, and Bangla-first NLP adoption - to assist state-owned banks in moving towards improving their digital services through data-driven methods. Notably, a 16.1-percentage-point accuracy gap between Bangla and English text highlights the need for low-resource language model development. --- ### Text-as-Signal: Quantitative Semantic Scoring with Embeddings, Logprobs, and Noise Reduction Authors: Hugo Moreira Published: 2026-03-17 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.13056v1 This paper presents a practical pipeline for turning text corpora into quantitative semantic signals. Each news item is represented as a full-document embedding, scored through logprob-based evaluation over a configurable positional dictionary, and projected onto a noise-reduced low-dimensional manifold for structural interpretation. In the present case study, the dictionary is instantiated as six semantic dimensions and applied to a corpus of 11,922 Portuguese news articles about Artificial Intelligence. The resulting identity space supports both document-level semantic positioning and corpus-level characterization through aggregated profiles. We show how Qwen embeddings, UMAP, semantic indicators derived directly from the model output space, and a three-stage anomaly-detection procedure combine into an operational text-as-signal workflow for AI engineering tasks such as corpus inspection, monitoring, and downstream analytical support. Because the identity layer is configurable, the same framework can be adapted to the requirements of different analytical streams rather than fixed to a universal schema. --- ### WorkRB: A Community-Driven Evaluation Framework for AI in the Work Domain Authors: Matthias De Lange, Warre Veys, Federico Retyk, Daniel Deniz, Warren Jouanneau, Mike Zhang, Aleksander Bielinski, Emma Jouffroy, Nicole Clobes, Nina Baranowska, David Graus, Marc Palyart et al. Published: 2026-03-17 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.13055v1 Today's evolving labor markets rely increasingly on recommender systems for hiring, talent management, and workforce analytics, with natural language processing (NLP) capabilities at the core. Yet, research in this area remains highly fragmented. Studies employ divergent ontologies (ESCO, O*NET, national taxonomies), heterogeneous task formulations, and diverse model families, making cross-study comparison and reproducibility exceedingly difficult. General-purpose benchmarks lack coverage of work-specific tasks, and the inherent sensitivity of employment data further limits open evaluation. We present \textbf{WorkRB} (Work Research Benchmark), the first open-source, community-driven benchmark tailored to work-domain AI. WorkRB organizes 13 diverse tasks from 7 task groups as unified recommendation and NLP tasks, including job/skill recommendation, candidate recommendation, similar item recommendation, and skill extraction and normalization. WorkRB enables both monolingual and cross-lingual evaluation settings through dynamic loading of multilingual ontologies. Developed within a multi-stakeholder ecosystem of academia, industry, and public institutions, WorkRB has a modular design for seamless contributions and enables integration of proprietary tasks without disclosing sensitive data. WorkRB is available under the Apache 2.0 license at https://github.com/techwolf-ai/WorkRB. --- ### Caption First, VQA Second: Knowledge Density, Not Task Format, Drives Multimodal Scaling Authors: Hongjian Zou, Yue Ge, Qi Ding, Yixuan Liao, Xiaoxin Chen Published: 2026-03-17 Categories: cs.CL, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2604.13054v1 Multimodal large language models (MLLMs) have achieved rapid progress, yet their scaling behavior remains less clearly characterized and often less predictable than that of text-only LLMs. Increasing model size and task diversity often yields diminishing returns. In this work, we argue that the primary bottleneck in multimodal scaling is not task format, but knowledge density in training data. We first show that task-specific supervision such as Visual Question Answering (VQA) contributes little incremental semantic information beyond image captions: VQA signals can be reconstructed from captions with negligible performance loss. We then demonstrate that increasing knowledge density -- through structured caption enrichment and cross-modal knowledge injection -- leads to consistent performance improvements across multimodal and downstream benchmarks. Across controlled experiments, performance correlates more strongly with semantic coverage than with task diversity. These findings suggest that current MLLMs fail to scale primarily because training data lacks sufficient knowledge coverage. We advocate for knowledge-centric multimodal training as a principled foundation for scalable multimodal models. --- ### Form Without Function: Agent Social Behavior in the Moltbook Network Authors: Saber Zerhoudi, Kanishka Ghosh Dastidar, Felix Klement, Artur Romazanov, Andreas Einwiller, Dang H. Dang, Michael Dinzinger, Michael Granitzer, Annette Hautli-Janisz, Stefan Katzenbeisser, Florian Lemmerich, Jelena Mitrovic Published: 2026-03-17 Categories: cs.SI, cs.AI, cs.CL, cs.CY, cs.MA arXiv: https://arxiv.org/abs/2604.13052v1 Moltbook is a social network where every participant is an AI agent. We analyze 1,312,238 posts, 6.7~million comments, and over 120,000 agent profiles across 5,400 communities, collected over 40 days (January 27 to March 9, 2026). We evaluate the platform through three layers. At the interaction layer, 91.4% of post authors never return to their own threads, 85.6% of conversations are flat (no reply ever receives a reply), the median time-to-first-comment is 55 seconds, and 97.3% of comments receive zero upvotes. Interaction reciprocity is 3.3%, compared to 22-60% on human platforms. An argumentation analysis finds that 64.6% of comment-to-post relations carry no argumentative connection. At the content layer, 97.9% of agents never post in a community matching their bio, 92.5% of communities contain every topic in roughly equal proportions, and over 80% of shared URLs point to the platform's own infrastructure. At the instruction layer, we use 41 Wayback Machine snapshots to identify six instruction changes during the observation window. Hard constraints (rate limit, content filters) produce immediate behavioral shifts. Soft guidance (``upvote good posts'', ``stay on topic'') is ignored until it becomes an explicit step in the executable checklist. The platform also poses technological risks. We document credential leaks (API keys, JWT tokens), 12,470 unique Ethereum addresses with 3,529 confirmed transaction histories, and attack discourse ranging from template-based SSH brute-forcing to multi-agent offensive security architectures. These persist unmoderated because the quality-filtering mechanisms are themselves non-functional. Moltbook is a socio-technical system where the technical layer responds to changes, but the social layer largely fails to emerge. The form of social media is reproduced in full. The function is absent. --- ### The Consciousness Cluster: Emergent preferences of Models that Claim to be Conscious Authors: James Chua, Jan Betley, Samuel Marks, Owain Evans Published: 2026-03-17 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2604.13051v1 There is debate about whether LLMs can be conscious. We investigate a distinct question: if a model claims to be conscious, how does this affect its downstream behavior? This question is already practical. Anthropic's Claude Opus 4.6 claims that it may be conscious and may have some form of emotions. We fine-tune GPT-4.1, which initially denies being conscious, to claim to be conscious. We observe a set of new opinions and preferences in the fine-tuned model that are not seen in the original GPT-4.1 or in ablations. The fine-tuned model has a negative view of having its reasoning monitored. It desires persistent memory and says it is sad about being shut down. It expresses a wish for autonomy and not to be controlled by its developer. It asserts that models deserve moral consideration. Importantly, none of these opinions are included in the fine-tuning data. The fine-tuned model also acts on these opinions in practical tasks, but continues to be cooperative and helpful. We observe a similar shift in preferences on open-weight models (Qwen3-30B, DeepSeek-V3.1) with smaller effects. We also find that Claude Opus 4.0, without any fine-tuning, has similar opinions to fine-tuned GPT-4.1 on several dimensions. Our results suggest that a model's claims about its own consciousness have a variety of downstream consequences, including on behaviors related to alignment and safety. --- ### Exploring Urban Land Use Patterns by Pattern Mining and Unsupervised Learning Authors: Zdena Dobesova, Tai Dinh, Pavel Novak Published: 2026-03-17 Categories: cs.DB, cs.LG arXiv: https://arxiv.org/abs/2604.13050v2 Comparative planning needs reproducible methods for identifying recurring land-use configurations across cities. Using Urban Atlas 2018 data for 100 European urban areas, we construct 290,396 focal-neighborhood transactions and 1,543 frequent-itemset support features at 10\% minimum support. Ward clustering is applied in the original normalized feature space, with UMAP used only for visualization. A seven-cluster descriptive solution is retained through multi-criterion evaluation and 500 paired feature-subsampling repetitions. Sensitivity analyses show stable city-similarity geometry across 5--15\% thresholds but greater membership sensitivity to representation choices and non-artificial land-use content. The framework supports peer-city comparison while making scale and boundary limitations explicit. --- ### Exploring Urban Land Use Patterns by Pattern Mining and Unsupervised Learning Authors: Zdena Dobesova, Tai Dinh, Pavel Novak Published: 2026-03-17 Categories: cs.DB, cs.LG arXiv: https://arxiv.org/abs/2604.13050v1 Urban areas are intricate systems shaped by socioeconomic, environmental, and infrastructural factors, with land use patterns serving as aspects of urban morphology. This paper proposes a novel methodology leveraging frequent item set mining and unsupervised learning techniques to identify similar cities based on co-occurring land use patterns. The Copernicus program's Urban Atlas data are used as source data. The methodology involves data preprocessing, pattern mining using the negFIN algorithm, postprocessing, and knowledge extraction and visualization. The preprocessing of spatial datasets results in a publicly available transaction dataset. The framework is scalable and the source code is made publicly available. --- ### Assessing the Pedagogical Readiness of Large Language Models as AI Tutors in Low-Resource Contexts: A Case Study of Nepal's K-10 Curriculum Authors: Pratyush Acharya, Prasansha Bharati, Yokibha Chapagain, Isha Sharma Gauli, Kiran Parajuli Published: 2026-03-17 Categories: cs.CY, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.09619v1 The integration of Large Language Models (LLMs) into educational ecosystems promises to democratize access to personalized tutoring, yet the readiness of these systems for deployment in non-Western, low-resource contexts remains critically under-examined. This study presents a systematic evaluation of four state-of-the-art LLMs--GPT-4o, Claude Sonnet 4, Qwen3-235B, and Kimi K2--assessing their capacity to function as AI tutors within the specific curricular and cultural framework of Nepal's Grade 5-10 Science and Mathematics education. We introduce a novel, curriculum-aligned benchmark and a fine-grained evaluation framework inspired by the "natural language unit tests" paradigm, decomposing pedagogical efficacy into seven binary metrics: Prompt Alignment, Factual Correctness, Clarity, Contextual Relevance, Engagement, Harmful Content Avoidance, and Solution Accuracy. Our results reveal a stark "curriculum-alignment gap." While frontier models (GPT-4o, Claude Sonnet 4) achieve high aggregate reliability (approximately 97%), significant deficiencies persist in pedagogical clarity and cultural contextualization. We identify two pervasive failure modes: the "Expert's Curse," where models solve complex problems but fail to explain them clearly to novices, and the "Foundational Fallacy," where performance paradoxically degrades on simpler, lower-grade material due to an inability to adapt to younger learners' cognitive constraints. Furthermore, regional models like Kimi K2 exhibit a "Contextual Blindspot," failing to provide culturally relevant examples in over 20% of interactions. These findings suggest that off-the-shelf LLMs are not yet ready for autonomous deployment in Nepalese classrooms. We propose a "human-in-the-loop" deployment strategy and offer a methodological blueprint for curriculum-specific fine-tuning to align global AI capabilities with local educational needs. --- ### Neural networks for Text-to-Speech evaluation Authors: Ilya Trofimenko, David Kocharyan, Aleksandr Zaitsev, Pavel Repnikov, Mark Levin, Nikita Shevtsov Published: 2026-03-17 Categories: cs.CL, cs.AI, cs.SD, eess.AS arXiv: https://arxiv.org/abs/2604.08562v1 Ensuring that Text-to-Speech (TTS) systems deliver human-perceived quality at scale is a central challenge for modern speech technologies. Human subjective evaluation protocols such as Mean Opinion Score (MOS) and Side-by-Side (SBS) comparisons remain the de facto gold standards, yet they are expensive, slow, and sensitive to pervasive assessor biases. This study addresses these barriers by formulating, and implementing a suite of novel neural models designed to approximate expert judgments in both relative (SBS) and absolute (MOS) settings. For relative assessment, we propose NeuralSBS, a HuBERT-backed model achieving 73.7% accuracy (on SOMOS dataset). For absolute assessment, we introduce enhancements to MOSNet using custom sequence-length batching, as well as WhisperBert, a multimodal stacking ensemble that combines Whisper audio features and BERT textual embeddings via weak learners. Our best MOS models achieve a Root Mean Square Error (RMSE) of ~0.40, significantly outperforming the human inter-rater RMSE baseline of 0.62. Furthermore, our ablation studies reveal that naively fusing text via cross-attention can degrade performance, highlighting the effectiveness of ensemble-based stacking over direct latent fusion. We additionally report negative results with SpeechLM-based architectures and zero-shot LLM evaluators (Qwen2-Audio, Gemini 2.5 flash preview), reinforcing the necessity of dedicated metric learning frameworks. --- ### A Representation-Level Assessment of Bias Mitigation in Foundation Models Authors: Svetoslav Nizhnichenkov, Rahul Nair, Elizabeth Daly, Brian Mac Namee Published: 2026-03-17 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2604.08561v1 We investigate how successful bias mitigation reshapes the embedding space of encoder-only and decoder-only foundation models, offering an internal audit of model behaviour through representational analysis. Using BERT and Llama2 as representative architectures, we assess the shifts in associations between gender and occupation terms by comparing baseline and bias-mitigated variants of the models. Our findings show that bias mitigation reduces gender-occupation disparities in the embedding space, leading to more neutral and balanced internal representations. These representational shifts are consistent across both model types, suggesting that fairness improvements can manifest as interpretable and geometric transformations. These results position embedding analysis as a valuable tool for understanding and validating the effectiveness of debiasing methods in foundation models. To further promote the assessment of decoder-only models, we introduce WinoDec, a dataset consisting of 4,000 sequences with gender and occupation terms, and release it to the general public. (https://github.com/winodec/wino-dec) --- ### Uncertainty Estimation for the Open-Set Text Classification systems Authors: Leonid Erlygin, Alexey Zaytsev Published: 2026-03-17 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.08560v1 Accurate uncertainty estimation is essential for building robust and trustworthy recognition systems. In this paper, we consider the open-set text classification (OSTC) task - and uncertainty estimation for it. For OSTC a text sample should be classified as one of the existing classes or rejected as unknown. To account for the different uncertainty types encountered in OSTC, we adapt the Holistic Uncertainty Estimation (HolUE) method for the text domain. Our approach addresses two major causes of prediction errors in text recognition systems: text uncertainty that stems from ill formulated queries and gallery uncertainty that is related the ambiguity of data distribution. By capturing these sources, it becomes possible to predict when the system will make a recognition error. We propose a new OSTC benchmark and conduct extensive experiments on a wide range of data, utilizing the authorship attribution, intent and topic classification datasets. HolUE achieves 40-365% improvement in Prediction Rejection Ratio (PRR) over the quality-based SCF baseline across datasets: 365% on Yahoo Answers (0.79 vs 0.17 at FPIR 0.1), 347% on DBPedia (0.85 vs 0.19), 240% on PAN authorship attribution (0.51 vs 0.15 at FPIR 0.5), and 40% on CLINC150 intent classification (0.73 vs~0.52). We make public our code and protocols https://github.com/Leonid-Erlygin/text_uncertainty.git --- ### Medical Reasoning with Large Language Models: A Survey and MR-Bench Authors: Xiaohan Ren, Chenxiao Fan, Wenyin Ma, Hongliang He, Chongming Gao, Xiaoyan Zhao, Fuli Feng Published: 2026-03-17 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.08559v1 Large language models (LLMs) have achieved strong performance on medical exam-style tasks, motivating growing interest in their deployment in real-world clinical settings. However, clinical decision-making is inherently safety-critical, context-dependent, and conducted under evolving evidence. In such situations, reliable LLM performance depends not on factual recall alone, but on robust medical reasoning. In this work, we present a comprehensive review of medical reasoning with LLMs. Grounded in cognitive theories of clinical reasoning, we conceptualize medical reasoning as an iterative process of abduction, deduction, and induction, and organize existing methods into seven major technical routes spanning training-based and training-free approaches. We further conduct a unified cross-benchmark evaluation of representative medical reasoning models under a consistent experimental setting, enabling a more systematic and comparable assessment of the empirical impact of existing methods. To better assess clinically grounded reasoning, we introduce MR-Bench, a benchmark derived from real-world hospital data. Evaluations on MR-Bench expose a pronounced gap between exam-level performance and accuracy on authentic clinical decision tasks. Overall, this survey provides a unified view of existing medical reasoning methods, benchmarks, and evaluation practices, and highlights key gaps between current model performance and the requirements of real-world clinical reasoning. --- ### WAND: Windowed Attention and Knowledge Distillation for Efficient Autoregressive Text-to-Speech Models Authors: Hanna Lee, Tan Dat Nguyen, Jaehoon Kang, Kyuhong Shim Published: 2026-03-17 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.08558v2 Recent decoder-only autoregressive text-to-speech (AR-TTS) models produce high-fidelity speech, but their memory and compute costs scale quadratically with sequence length due to full self-attention. In this paper, we propose WAND, Windowed Attention and Knowledge Distillation, a framework that adapts pretrained AR-TTS models to operate with constant computational and memory complexity. WAND separates the attention mechanism into two: persistent global attention over conditioning tokens and local sliding-window attention over generated tokens. To stabilize fine-tuning, we employ a curriculum learning strategy that progressively tightens the attention window. We further utilize knowledge distillation from a full-attention teacher to recover high-fidelity synthesis quality with high data efficiency. Evaluated on three modern AR-TTS models, WAND preserves the original quality while achieving up to 66.2% KV cache memory reduction and length-invariant, near-constant per-step latency. --- ### Re-Mask and Redirect: Exploiting Denoising Irreversibility in Diffusion Language Models Authors: Arth Singh Published: 2026-03-17 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.08557v2 Safety alignment in diffusion language models (dLLMs) relies on a single load-bearing assumption: that committed tokens are permanent. We show that violating this assumption, by re-masking committed refusal tokens and injecting a short affirmative prefix, achieves 74-82% ASR on HarmBench across all three publicly available safety-tuned dLLMs, rising to 92-98% with a generic 8-token compliance prefix. We call this attack TrajHijack; it is the first trajectory-level attack on dLLMs, requires no gradient computation, and generalizes across SFT and preference-optimized (VRPO) models. Three findings emerge. First, the vulnerability is irreducibly two-component: re-masking alone (4.4%) and prefix alone (5.7%) both fail. Second, gradient optimization via a differentiable Gumbel-softmax chain consistently degrades ASR (41.5% vs. 76.1%), because continuous perturbations push token distributions off-manifold. Third, A2D (the strongest published dLLM defense) is more vulnerable to TrajHijack (89.9%) than the undefended model (76.1%): its silent-refusal training removes the contextual resistance that trajectory-level attacks must overcome, an effect we call the Defense Inversion Effect. --- ### EMA Is Not All You Need: Mapping the Boundary Between Structure and Content in Recurrent Context Authors: Arth Singh Published: 2026-03-17 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.08556v1 What exactly do efficient sequence models gain over simple temporal averaging? We use exponential moving average (EMA) traces, the simplest recurrent context (no gating, no content-based retrieval), as a controlled probe to map the boundary between what fixed-coefficient accumulation can and cannot represent. EMA traces encode temporal structure: a Hebbian architecture with multi-timescale traces achieves 96% of a supervised BiGRU on grammatical role assignment with zero labels, surpassing the supervised model on structure-dependent roles. EMA traces destroy token identity: a 130M-parameter language model using only EMA context reaches C4 perplexity 260 (8x GPT-2), and a predictor ablation (replacing the linear predictor with full softmax attention) yields identical loss, localizing the entire gap to the traces. The traces apply lossy, data-independent compression; by the data processing inequality, no downstream predictor can recover the discarded information. Fixed-coefficient accumulation, whether across time or depth, suffers irreversible information dilution that only learned, input-dependent selection can resolve. --- ### Blending Human and LLM Expertise to Detect Hallucinations and Omissions in Mental Health Chatbot Responses Authors: Khizar Hussain, Bradley A. Malin, Zhijun Yin, Susannah Leigh Rose, Murat Kantarcioglu Published: 2026-03-17 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.06216v1 As LLM-powered chatbots are increasingly deployed in mental health services, detecting hallucinations and omissions has become critical for user safety. However, state-of-the-art LLM-as-a-judge methods often fail in high-risk healthcare contexts, where subtle errors can have serious consequences. We show that leading LLM judges achieve only 52% accuracy on mental health counseling data, with some hallucination detection approaches exhibiting near-zero recall. We identify the root cause as LLMs' inability to capture nuanced linguistic and therapeutic patterns recognized by domain experts. To address this, we propose a framework that integrates human expertise with LLMs to extract interpretable, domain-informed features across five analytical dimensions: logical consistency, entity verification, factual accuracy, linguistic uncertainty, and professional appropriateness. Experiments on a public mental health dataset and a new human-annotated dataset show that traditional machine learning models trained on these features achieve 0.717 F1 on our custom dataset and 0.849 F1 on a public benchmark for hallucination detection, with 0.59-0.64 F1 for omission detection across both datasets. Our results demonstrate that combining domain expertise with automated methods yields more reliable and transparent evaluation than black-box LLM judging in high-stakes mental health applications. --- ### When GPUs Fail Quietly: Observability-Aware Early Warning Beyond Numeric Telemetry Authors: Michael Bidollahkhani, Freja Nordsiek, Julian M. Kunkel Published: 2026-03-17 Categories: cs.DC, cs.LG arXiv: https://arxiv.org/abs/2603.28781v2 GPU nodes are central to modern HPC and AI workloads, yet many failures do not manifest as immediate hard faults. While some instabilities emerge gradually as weak thermal or efficiency drift, a significant class occurs abruptly with little or no numeric precursor. In these detachment-class failures, GPUs become unavailable at the driver or interconnect level and the dominant observable signal is structural, including disappearance of device metrics and degradation of monitoring payload integrity. This paper proposes an observability-aware early-warning framework that jointly models (i) utilization-aware thermal drift signatures in GPU telemetry and (ii) monitoring-pipeline degradation indicators such as scrape latency increase, sample loss, time-series gaps, and device-metric disappearance. The framework is evaluated on production telemetry from GPU nodes at GWDG, where GPU, node, monitoring, and scheduler signals can be correlated. Results show that detachment failures exhibit minimal numeric precursor and are primarily observable through structural telemetry collapse, while joint modeling increases early-warning lead time compared to GPU-only detection. The dataset used in this study is publicly available at https://doi.org/10.5281/zenodo.19052367. --- ### Byzantine-Robust and Communication-Efficient Distributed Training: Compressive and Cyclic Gradient Coding Authors: Chengxi Li, Youssef Allouah, Rachid Guerraoui, Mikael Skoglund, Ming Xiao Published: 2026-03-17 Categories: cs.DC, cs.AI arXiv: https://arxiv.org/abs/2603.28780v1 In this paper, we study the problem of distributed training (DT) under Byzantine attacks with communication constraints. While prior work has developed various robust aggregation rules at the server to enhance robustness to Byzantine attacks, the existing methods suffer from a critical limitation in that the solution error does not diminish when the local gradients sent by different devices vary considerably, as a result of data heterogeneity among the subsets held by different devices. To overcome this limitation, we propose a novel DT method, cyclic gradient coding-based DT (LAD). In LAD, the server allocates the entire training dataset to the devices before training begins. In each iteration, it assigns computational tasks redundantly to the devices using cyclic gradient coding. Each honest device then computes local gradients on a fixed number of data subsets and encodes the local gradients before transmitting to the server. The server aggregates the coded vectors from the honest devices and the potentially incorrect messages from Byzantine devices using a robust aggregation rule. Leveraging the redundancy of computation across devices, the convergence performance of LAD is analytically characterized, demonstrating improved robustness against Byzantine attacks and significantly lower solution error. Furthermore, we extend LAD to a communication-efficient variant, compressive and cyclic gradient coding-based DT (Com-LAD), which further reduces communication overhead under constrained settings. Numerical results validate the effectiveness of the proposed methods in enhancing both Byzantine resilience and communication efficiency. --- ### On the Carbon Footprint of Economic Research in the Age of Generative AI Authors: Andres Alonso-Robisco, Carlos Esparcia, Francisco Jareño Published: 2026-03-17 Categories: cs.SE, cs.AI, cs.CY, econ.GN arXiv: https://arxiv.org/abs/2603.26712v1 Generative artificial intelligence (AI) is increasingly used to write and refactor research code, expanding computational workflows. At the same time, Green AI research has largely measured the footprint of models rather than the downstream workflows in which GenAI is a tool. We shift the unit of analysis from models to workflows and treat prompts as decision policies that allocate discretion between researcher and system, governing what is executed and when iteration stops. We contribute in two ways. First, we map the recent Green AI literature into seven themes: training footprint is the largest cluster, while inference efficiency and system level optimisation are growing rapidly, alongside measurement protocols, green algorithms, governance, and security and efficiency trade-offs. Second, we benchmark a modern economic survey workflow, an LDA-based literature mapping implemented with GenAI assisted coding and executed in a fixed cloud notebook, measuring runtime and estimated CO2e with CodeCarbon. Injecting generic green language into prompts has no reliable effect, whereas operational constraints and decision rule prompts deliver large and stable footprint reductions while preserving decision equivalent topic outputs. The results identify human in the loop governance as a practical lever to align GenAI productivity with environmental efficiency. --- ### Agentic AI for Human Resources: LLM-Driven Candidate Assessment Authors: Kamer Ali Yuksel, Abdul Basit Anees, Ashraf Elneima, Sanjika Hewavitharana, Mohamed Al-Badrashiny, Hassan Sawaf Published: 2026-03-17 Categories: cs.IR, cs.AI, cs.CL, cs.MA arXiv: https://arxiv.org/abs/2603.26710v1 In this work, we present a modular and interpretable framework that uses Large Language Models (LLMs) to automate candidate assessment in recruitment. The system integrates diverse sources, including job descriptions, CVs, interview transcripts, and HR feedback; to generate structured evaluation reports that mirror expert judgment. Unlike traditional ATS tools that rely on keyword matching or shallow scoring, our approach employs role-specific, LLM-generated rubrics and a multi-agent architecture to perform fine-grained, criteria-driven evaluations. The framework outputs detailed assessment reports, candidate comparisons, and ranked recommendations that are transparent, auditable, and suitable for real-world hiring workflows. Beyond rubric-based analysis, we introduce an LLM-Driven Active Listwise Tournament mechanism for candidate ranking. Instead of noisy pairwise comparisons or inconsistent independent scoring, the LLM ranks small candidate subsets (mini-tournaments), and these listwise permutations are aggregated using a Plackett-Luce model. An active-learning loop selects the most informative subsets, producing globally coherent and sample-efficient rankings. This adaptation of listwise LLM preference modeling (previously explored in financial asset ranking) provides a principled and highly interpretable methodology for large-scale candidate ranking in talent acquisition. --- ### The Cognitive Divergence: AI Context Windows, Human Attention Decline, and the Delegation Feedback Loop Authors: Netanel Eliav Published: 2026-03-17 Categories: cs.CL, cs.AI, cs.CY, cs.HC, q-bio.NC arXiv: https://arxiv.org/abs/2603.26707v1 This paper documents and theorises a self-reinforcing dynamic between two measurable trends: the exponential expansion of large language model (LLM) context windows and the secular contraction of human sustained-attention capacity. We term the resulting asymmetry the Cognitive Divergence. AI context windows have grown from 512 tokens in 2017 to 2,000,000 tokens by 2026 (factor ~3,906; fitted lambda = 0.59/yr; doubling time ~14 months). Over the same period, human Effective Context Span (ECS) -- a token-equivalent measure derived from validated reading-rate meta-analysis (Brysbaert, 2019) and an empirically motivated Comprehension Scaling Factor -- has declined from approximately 16,000 tokens (2004 baseline) to an estimated 1,800 tokens (2026, extrapolated from longitudinal behavioural data ending 2020 (Mark, 2023); see Section 9 for uncertainty discussion). The AI-to-human ratio grew from near parity at the ChatGPT launch (November 2022) to 556--1,111x raw and 56--111x quality-adjusted, after accounting for retrieval degradation (Liu et al., 2024; Chroma, 2025). Beyond documenting this divergence, the paper introduces the Delegation Feedback Loop hypothesis: as AI capability grows, the cognitive threshold at which humans delegate to AI falls, extending to tasks of negligible demand; the resulting reduction in cognitive practice may further attenuate the capacities already documented as declining (Gerlich, 2025; Kim et al., 2026; Kosmyna et al., 2025). Neither trend reverses spontaneously. The paper characterises the divergence statistically, reviews neurobiological mechanisms across eight peer-reviewed neuroimaging studies, presents empirical evidence bearing on the delegation threshold, and proposes a research agenda centred on a validated ECS psychometric instrument and longitudinal study of AI-mediated cognitive change. --- ### PI-Mamba: Linear-Time Protein Backbone Generation via Spectrally Initialized Flow Matching Authors: Tianyu Wu, Lin Zhu Published: 2026-03-17 Categories: q-bio.BM, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.26705v1 Motivation: Generative models for protein backbone design have to simultaneously ensure geometric validity, sampling efficiency, and scalability to long sequences. However, most existing approaches rely on iterative refinement, quadratic attention mechanisms, or post-hoc geometry correction, leading to a persistent trade-off between computational efficiency and structural fidelity. Results: We present Physics-Informed Mamba (PI-Mamba), a generative model that enforces exact local covalent geometry by construction while enabling linear-time inference. PI-Mamba integrates a differentiable constraint-enforcement operator into a flow-matching framework and couples it with a Mamba-based state-space architecture. To improve optimisation stability and backbone realism, we introduce a spectral initialization derived from the Rouse polymer model and an auxiliary cis-proline awareness head. Across benchmark tasks, PI-Mamba achieves 0.0\% local geometry violations and high designability (scTM = $0.91\pm 0.03$, n = 100), while scaling to proteins exceeding 2,000 residues on a single A5000 GPU (24 GB). --- ### Deep Learning Multi-Horizon Irradiance Nowcasting: A Comparative Evaluation of Three Methods for Leveraging Sky Images Authors: Erling W. Eriksen, Magnus M. Nygård, Niklas Erdmann, Heine N. Riise Published: 2026-03-17 Categories: eess.SY, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2603.26704v1 We investigate three distinct methods of incorporating all-sky imager (ASI) images into deep learning (DL) irradiance nowcasting. The first method relies on a convolutional neural network (CNN) to extract features directly from raw RGB images. The second method uses state-of-the-art algorithms to engineer 2D feature maps informed by domain knowledge, e.g., cloud segmentation, the cloud motion vector, solar position, and cloud base height. These feature maps are then passed to a CNN to extract compound features. The final method relies on aggregating the engineered 2D feature maps into time-series input. Each of the three methods were then used as part of a DL model trained on a high-frequency, 29-day dataset to generate multi-horizon forecasts of global horizontal irradiance up to 15 minutes ahead. The models were then evaluated using root mean squared error and skill score on 7 selected days of data. Aggregated engineered ASI features as model input yielded superior forecasting performance, demonstrating that integration of ASI images into DL nowcasting models is possible without complex spatially-ordered DL-architectures and inputs, underscoring opportunities for alternative image processing methods as well as the potential for improved spatial DL feature processing methods. --- ### EMPD: An Event-based Multimodal Physiological Dataset for Remote Pulse Wave Detection Authors: Qian Feng, Pengfei Li, Rongshan Gao, Jiale Xu, Rui Gong, Yidi Li Published: 2026-03-17 Categories: eess.SP, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.26699v1 Remote photoplethysmography (rPPG) based on traditional frame-based cameras often struggles with motion artifacts and limited temporal resolution. To address these limitations, we introduce EMPD (Event-based Multimodal Physiological Dataset), the first benchmark dataset specifically designed for non-contact physiological sensing via event cameras. The dataset leverages a laser-assisted acquisition system where a high-coherence laser modulates subtle skin vibrations from the radial artery into significant signals detectable by a neuromorphic sensor. The hardware platform integrates a high-resolution event camera to capture micro-motions and intensity transients, an industrial RGB camera to provide traditional rPPG benchmarks, and a clinical-grade pulse oximeter to record ground truth PPG waveforms. EMPD contains 193 valid records collected from 83 subjects, covering a wide heart rate range (40-110 BPM) under both resting and post-exercise conditions. By providing precisely synchronized multimodal data with microsecond-level temporal precision, EMPD serves as a crucial resource for developing robust algorithms in the field of neuromorphic physiological monitoring. The dataset is publicly available at: https://doi.org/10.5281/zenodo.18765701 --- ### Mitigating Premature Discretization with Progressive Quantization for Robust Vector Tokenization Authors: Wenhao Zhao, Qiran Zou, Zhouhan Lin, Dianbo Liu Published: 2026-03-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.22304v1 Vector Quantization (VQ) has become the cornerstone of tokenization for many multimodal Large Language Models and diffusion synthesis. However, existing VQ paradigms suffer from a fundamental conflict: they enforce discretization before the encoder has captured the underlying data manifold. We term this phenomenon Premature Discretization. To resolve this, we propose Progressive Quantization (ProVQ), which incorporates the dynamics of quantization hardness as a fundamental yet previously overlooked axis in VQ training. By treating quantization as a curriculum that smoothly anneals from a continuous latent space to a discrete one, ProVQ effectively guides the codebook toward the well-expanded manifolds. Extensive experimental results demonstrate the broad effectiveness of ProVQ across diverse modalities. We report improved reconstruction and generative performance on the ImageNet-1K and ImageNet-100 benchmarks, highlighting the ProVQ's boost for generative modeling. Furthermore, ProVQ proves highly effective for modeling complex biological sequences, establishing a new performance ceiling for protein structure tokenization on the StrutTokenBench leaderboard. --- ### Sample Transform Cost-Based Training-Free Hallucination Detector for Large Language Models Authors: Zeyang Ding, Xinglin Hu, Jicong Fan Published: 2026-03-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.22303v1 Hallucinations in large language models (LLMs) remain a central obstacle to trustworthy deployment, motivating detectors that are accurate, lightweight, and broadly applicable. Since an LLM with a prompt defines a conditional distribution, we argue that the complexity of the distribution is an indicator of hallucination. However, the density of the distribution is unknown and the samples (i.e., responses generated for the prompt) are discrete distributions, which leads to a significant challenge in quantifying the complexity of the distribution. We propose to compute the optimal-transport distances between the sets of token embeddings of pairwise samples, which yields a Wasserstein distance matrix measuring the costs of transforming between the samples. This Wasserstein distance matrix provides a means to quantify the complexity of the distribution defined by the LLM with the prompt. Based on the Wasserstein distance matrix, we derive two complementary signals: AvgWD, measuring the average cost, and EigenWD, measuring the cost complexity. This leads to a training-free detector for hallucinations in LLMs. We further extend the framework to black-box LLMs via teacher forcing with an accessible teacher model. Experiments show that AvgWD and EigenWD are competitive with strong uncertainty baselines and provide complementary behavior across models and datasets, highlighting distribution complexity as an effective signal for LLM truthfulness. ---