# Research Papers — 2026-08 · bundle page 168 of 240 > Full-text markdown of papers #8351–8400 of 11995 published in 2026-08, newest first. AI-readable mirrors of the full 11995-paper 2026-08 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-08/page/168 [← Previous bundle](https://aipod.dev/papers/archive/2026-08/page/167.md) [Next bundle →](https://aipod.dev/papers/archive/2026-08/page/169.md) ### Reading is not Reasoning: Bridging the Agentic Policy Gap in Vision-Text Compression Authors: Cheng Fan, Junyi Zhou, Tingzhang Luo, RongJian Xu, Qiyanhui Lu, Mingjian Zhu, Hanting Chen, Jianyuan Guo Published: 2026-08-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.08960v1 Multi-step language-model agents repeatedly process growing interaction histories, leading to substantial context costs. Vision--text compression reduces these costs by rendering history as images, but the resulting modality shift creates a marked capability gap. Through controlled evaluations of history recovery, matched-state decisions, and complete trajectories, we show that this gap cannot be explained by OCR quality alone. Visual-history agents exhibit systematic drift in action selection, query formulation, stopping, and evidence use, revealing an agentic policy gap. We introduce \textbf{CAPS}, a two-stage \textbf{C}ross-modal \textbf{A}gentic \textbf{P}olicy \textbf{S}elf-distillation framework that uses the same model's stronger text-history policy to supervise its visual-history counterpart. Offline trajectory self-distillation transfers successful text-policy behavior to visual-history inputs, while online policy self-distillation provides dense supervision on states visited by the visual-history policy during reinforcement learning. On SearchQA, CAPS improves over AgentOCR by 5.0\% and 3.4\% with 3B and 7B backbones, respectively. On full-history ALFWorld, the corresponding gains are 15.6\% and 14.5\%. Across settings, CAPS reduces average memory-context cost by up to 63.3\% and peak cost by up to 83.4\% relative to matched text-history policies. These results show that explicit cross-modal policy self-distillation can preserve agent capability under vision--text compression. Our code will be made publicly available in a future release. --- ### Depth-Aware Implicit Neural Representation Priors for 3D Gravity Inversion Authors: León Suarez-Rodriguez, Paul Goyes-Peñafiel, Javier Torres-Quintero, Henry Arguello Published: 2026-08-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.08959v1 Gravimetry images subsurface density contrasts associated with geological structures, geothermal systems, and intrusive bodies. Recovering a three-dimensional density model from gravity observations is highly ill-posed because of its non-uniqueness, limited data coverage, and the attenuation of the gravity field with depth. Classical inversion methods rely on explicit regularization and parameter tuning, whereas supervised deep-learning approaches require representative gravity--density pairs that are rarely available. This paper proposes an unsupervised depth-aware implicit neural representation for 3D gravity inversion. The density volume is represented by multiple coordinate-based neural networks assigned to overlapping depth slabs and optimized directly from the observed gravity measurements through the sensitivity matrix. Slab-specific Fourier features, physics-based depth gains, and scheduled regularization provide structural priors without requiring labeled density models. Experiments on four synthetic scenarios show that the proposed method provides better overall performance in terms of RMSE, PSNR, and SSIM than the evaluated conventional and neural baselines. It also recovers more compact and spatially coherent density bodies, improves the separation of nearby anomalies, preserves internal structures, and reconstructs their vertical extent better. These results indicate that the proposed depth-aware formulation helps to mitigate the depth ambiguity inherent in gravity inversion. In the field experiment, where no ground-truth density model was available, the method produced compact, separated, and vertically coherent anomalies consistent with the observed gravity pattern. --- ### Idea Search: Guiding Tree Search with Ideas to Explore Diverse Scientific Methods Authors: Xuefei Julie Wang, Hao Cui, Michael P. Brenner, Subhashini Venugopalan Published: 2026-08-09 Categories: cs.LG, cs.AI, q-bio.GN, q-bio.QM arXiv: https://arxiv.org/abs/2608.08958v1 Tree Search-based test-time scaling of LLMs is a powerful tool for automated scientific coding. However, pure Tree Search sometimes struggles with systematic exploration, becoming trapped in local optima, or unproductive loops, especially in the vast search space of scientific methods. To address this limitation, we propose Idea Search, a framework that systematically integrates a dynamic "Idea Bank" into Tree Search. Idea Search involves three steps: (1) decomposing existing methods into atomic ideas, (2) sampling from this bank of ideas to guide branches of code mutations, and (3) dynamically updating the bank with new ideas discovered through execution. On single-cell RNA-sequencing (scRNA-seq) batch integration, Idea Search reliably breaks the plateau of a strong pure Tree Search baseline, improving the mean score from 0.678 to 0.697 and reaching a best score of 0.728. We then characterize which design choices drive these gains: bank augmentation helps bandit sampling but not random sampling, "Exploratory" prompting that prioritizes new ideas surfaces the rare best-performing solutions, while increasing sampling-level exploration is counterproductive. --- ### RMR-P: Road Metadata-Aware Restoration for Pavement Inspection Authors: Amir Ghorbani, Amirali K. Gostar, WeiQin Chuah, Vahid Ghorbani, Aidan Blair, Reza Hoseinnezhad, Alireza Bab-Hadiashar Published: 2026-08-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.08957v2 Road-surface images captured by vehicle-mounted cameras are often degraded by motion blur, defocus, poor illumination, and noise due to vehicle motion, camera limitations, and varying environmental conditions. These degradations can obscure thin cracks and pothole boundaries that are critical for accurate road-defect detection. This paper presents RMR-P, a restoration network designed to recover defect-relevant information from degraded road images. It estimates degradation characteristics from the input image and can optionally incorporate external degradation parameters to guide restoration. To evaluate whether the recovered information improves downstream detection, a clean-trained YOLO11s detector is applied to degraded and restored images without further modification. Experiments on the IVCNZ and PCM datasets, with known synthetic degradation parameters provided as conditioning information, demonstrate that RMR-P achieves the highest mAP50 in seven of eight held-out degradation conditions, including improvements from 0.140 to 0.427 under IVCNZ motion blur and from 0.060 to 0.233 under PCM defocus. Moreover, our ablation studies show that preserving fine pavement details (detail-preserving pathway) provides the largest contribution to defect-detection improvement, while degradation conditioning and task-guided training offer complementary benefits. --- ### Damage Classification for 3D Point Cloud Data via 3D Data Analysis and Vision Foundation Model-based 2D Projections Authors: Evan Perez, Kalelo Dukuray, Erika Ardiles-Cruz, Jie Wei Published: 2026-08-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.08955v1 Fine-grained damage classification of 3D point cloud data (PCD) remains a persistent challenge, constrained by high computational demands and limited labeled data. This study examines two methods: 3D PCD-based damage assessment (3PDA) algorithm and 2D projection damage assessment (2PDA) In our 3PDA analysis algorithm, TDA is used to derive compact representations of 3D PCD segmented by pointNet, which are then integrated with anomaly detection algorithms to quantify structural degradation. We show that TDA effectively compresses geometric structure from VFM-segmented components into discriminative feature vectors and that anomaly detection models can reliably distinguish components with varying damage severity using only 3D PCD inputs. In the 2D projection analysis algorithm, we leverage large VFMs for granular damage detection by projecting 3D PCD into 2D views. These projections allow VFM based models to achieve competitive classification performance while requiring only a fraction of the computational cost associated with full 3D data processing. Our results demonstrate that 2D VFM pipelines in 2PDA can perform strongly on fine-grained damage classification tasks, highlighting their viability as lightweight, resource-efficient alternatives to traditional 3PDA architectures. Comparative evaluation shows that the 3PDA attains higher accuracy but only for a narrow subset of object geometries and at substantially higher computational cost due to its reliance on TDA and the scarcity of high-fidelity 3D datasets. In contrast, the 2PDA algorithm yields slightly lower accuracy but offers an order of magnitude reduction in time complexity and generalizes across a far broader range of object categories. --- ### Do AI Forecast Ensembles Sample the Correct Conditional Distribution? Authors: Lucas J. Howard, Elizabeth A. Barnes Published: 2026-08-09 Categories: physics.ao-ph, cs.AI, cs.LG, stat.AP, stat.ML arXiv: https://arxiv.org/abs/2608.08954v1 Ensemble forecasting aims to sample the conditional distribution of outcomes; whether AI forecast ensembles do this correctly in a joint sense remains largely untested. We train a diffusion model for probabilistic subseasonal coastal sea level forecasts at eight US East Coast tide gauge stations, with sea level derived from reanalysis, and find that marginal and joint forecast quality decouple: positive skill at every station and lead time marginally, while joint spatial structure is worse than climatological draws. A shuffle-based permutation decomposition reveals this failure is invisible to the energy score but detected by the variogram score. Lorenz-96 experiments across 0.7-170 equivalent years show the gap persists regardless of training volume and is reproduced by a linear baseline, indicating structural inadequacy of the learned distribution. A dynamical ensemble does not replicate the failure while a deterministic emulator does, suggesting it is specific to learned emulators rather than ensemble forecasting generally. --- ### Topology-Aware Global-Local Mamba Networks for Palm Vein Biometrics Authors: Zhengxi Wu, Felix Marattukalam, Waleed H. Abdulla Published: 2026-08-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.08951v1 Palm-vein recognition is a fine-grained biometric task in which both local vascular texture and the global layout of the vessel tree carry discriminative information, while public datasets remain limited. We propose a topology-aware global-local backbone that combines multi-scale local features, a structureguided directional stream built on a fixed Sobel-magnitude edge prior, and a four-direction state-space scan global pathway within six Topology-Aware Blocks. A staged gated fusion integrates local, structural, and global representations in that order. On HKPUNIR, our method achieves 99.13% top-1 accuracy and 0.08% EER with 7.2 M parameters; on VERA Palm Vein, it achieves 92.42% accuracy and 0.61% EER. Across both datasets it attains the lowest EER among ResNet50, Vim-S, ViT-S, and GLVM at the smallest parameter count, while GLVM remains the strongest in top-1 accuracy and the cheapest in FLOPs. Code is available upon request. --- ### EndoMD-SLAM: Endoscopic Gaussian Splatting SLAM under Optical Degradation with Memory and Static-Transient Decomposition Authors: Nuo Chen, Kangqi Ni, Lulin Liu, Joga Ivatury, Ying Ding, Farshid Alambeigi, Tianlong Chen, Zhiwen Fan Published: 2026-08-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.08949v1 Dense 3D reconstruction is critical for clinical endoscopic navigation and documentation. While Gaussian Splatting SLAM systems show promise in this domain, they fundamentally rely on strict multi-view photometric consistency. In routine procedures, this assumption is severely violated by intermittent optical degradations like moving debris and water flushing. Standard systems erroneously fuse these cameraattached artifacts into the persistent 3D geometry, causing severe tracking drift and irreversible map corruption. To address this limitation, we propose EndoMD-SLAM, a framework designed to maintain stability under optical degradation through specialized tracking and mapping mechanisms. On the tracking side, a memory-driven gating mechanism detects unreliable observations to suspend map updates and utilizes historical keyframes for drift-aware relocalization. On the mapping side, a self-supervised static-transient decomposition isolates visual contaminants into a dedicated transient field. This explicit separation prevents artifacts from structurally entangling with the persistent anatomical map. We curate a degradationfocused benchmark from colonoscopy videos to systematically evaluate these failure modes. Extensive experiments show that while standard baselines fail under severe optical degradation, EndoMD-SLAM preserves geometric integrity, reducing absolute trajectory error by 91% and improving rendering fidelity by 9.9 dB PSNR. --- ### Can Webcam Gaze Constrain Mesa-Objectives in Driving Models? An Instrument Precision Analysis Authors: Lennox Anderson, Ahmed Boutar, Jonah Mulcrone, Tal Erez Published: 2026-08-09 Categories: cs.CV, cs.HC, cs.LG arXiv: https://arxiv.org/abs/2608.08947v1 Current hazard detection systems in autonomous driving may develop mesa objectives, learned internal goals that achieve high training performance through spurious correlations rather than genuine hazard recognition. We investigate whether human gaze patterns, captured via webcam-based eye tracking (WebGazer.js), can serve as privileged information to constrain mesa-objective formation. We collected 137,663 frame-level gaze samples synchronized with hazard annotations across 388 real dashcam clips, then test this hypothesis across two calibration protocols (9-point/45-click and 11-point/440-click), two model architectures (Random Forest and causal Transformer), and five random seeds per experiment with paired t-tests. No experiment yields a statistically significant improvement from gaze (p = 0.919, 0.578, and 0.667 respectively). A geometric analysis reveals the root cause: WebGazer's reported error (~130-257 px depending on configuration) exceeds 93% of detected hazard object sizes (median 36 px), rendering object-level gaze attribution physically impossible at this instrument precision. --- ### What Would Fix This RAG Failure? Auditing Counterfactual Response with Paired Evidence Interventions Authors: Wenzhang Du Published: 2026-08-09 Categories: cs.IR, cs.LG arXiv: https://arxiv.org/abs/2608.08944v1 A failed retrieval-augmented generation (RAG) answer can be consistent with several unseen responses to evidence repair. We introduce Pair-ID, an offline audit that holds one query, retrieval state, and reader constant, then crosses two operations, adding missing support and deleting verified nonsupport, to measure a same-failure counterfactual response vector. A complete funnel over 19,981 benchmark queries identifies 11,105 eligible Qwen failures, from which a prospectively fixed SHA-256 ordering selects 1,200 before generating any sampled response. Among 1,190 regenerated-valid failures, support addition repairs 197/600 JOINT cases (0.328, 95% CI (0.292, 0.367)), and deletion repairs 162/1,190 cases (0.136, 95% CI (0.117, 0.155)); length- and position-matched shams retain semantic contrasts of 0.223 and 0.101. The original view carries partial predictive signal for individual response cells (macro AUROC 0.678; Brier 0.152 versus 0.160 for a marginal baseline), but exact-vector accuracy, 0.637, does not exceed the 0.646 majority-vector baseline, and vector macro-F1 is 0.170. Across four readers, both marginal sensitivities recur, while pooled exact-vector agreement is 0.675-0.765 and JOINT-only agreement falls to 0.538-0.691. These results show that evidence sensitivity occurs at meaningful rates in the hash-selected eligible-failure sample, is only partially predictable from the observed failure, and is conditional on the reader. The evidence supports a frame-scoped offline response audit, not an information-theoretic impossibility result, reader-independent taxonomy, or runtime repair policy. --- ### Same Question, Different Answer? Measuring and Mitigating Prompt Privilege for Equitable AI Access Authors: Lier Jin, Lan Hu, Binqi Shen, Hanyu Cai, Yuting Xin Published: 2026-08-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.08942v1 Large language models (LLMs) are increasingly integrated into healthcare, education, public services, and everyday decision making. They should provide comparable assistance regardless of a user's literacy, communication style, or prompt-engineering expertise. However, existing research on prompt robustness primarily focuses on adversarial attacks, prompt injection, and prompt optimization, while overlooking whether semantically equivalent requests receive different responses simply because they are phrased differently. We refer to this accessibility challenge as "Prompt Privilege": users with greater prompting expertise systematically obtain better model performance despite expressing the same underlying intent. To address this problem, we present a unified framework for measuring and mitigating accessibility disparities in LLM interactions. We introduce Prompt Equity Score (PES), a quantitative metric for evaluating performance consistency across user populations, and Prompt Equity Transformer (PET), an LLM-based agent that automatically transforms user requests into semantically equivalent, accessibility-oriented prompts while preserving their intent. PET shifts prompt optimization from the user to the AI system, functioning as an intelligent accessibility layer between users and foundation models. Experiments on the MedQA benchmark demonstrate measurable prompt privilege, with statistically significant performance disparities between low-literacy and expert-prompting cohorts. Applying PET eliminates these disparities while preserving semantic fidelity, demonstrating that accessibility-oriented prompt normalization can improve equitable AI access. By introducing prompt privilege as a new dimension of AI accessibility and PET as a practical solution, this work advances system-centered accessibility and provides a foundation for more fair, trustworthy, and inclusive AI systems. --- ### From Operational Design Domain to Action: A Systematic Behavioral Taxonomy for Autonomous Driving Authors: Chaitanya Shinde, Hadi Hajieghrary, Miguel Hurtado Published: 2026-08-09 Categories: cs.RO, cs.AI, eess.SY arXiv: https://arxiv.org/abs/2608.08941v1 Operational Design Domain (ODD) specifications describe where an automated driving system (ADS) is permitted to operate, but they do not prescribe what the ADS must demonstrably do once deployed within that domain. This gap between operating condition specification and behavioral validation represents a critical unresolved challenge in ADS safety assurance. This paper presents a structured, standards-grounded taxonomy of 21 behavioral competencies organized across three operational domains-Highway (HWY), Urban (URB), and Hub (HUB)-derived systematically from the PEGASUS six-layer model-based ODD. Each behavior is decomposed along longitudinal and lateral control axes and characterized against a four-property framework: Safety (gap maintenance, conflict avoidance, kinematic stability), Compliance (legal rules and behavioral norms), Comfort (rider dynamics and trust), and Efficiency (mission completion and product-level metrics). We further demonstrate that the crossing of ODD layer parameterizations with behavioral competency specifications yields concrete scenario families suitable for systematic behavioral testing and SOTIF coverage evidence. The taxonomy is grounded in AVSC00008202111, SAE J3237, and SAE J3016, and is validated as an operational specification layer through its deployment in a rule-enforced trajectory optimization system. The Hub domain is identified as a structurally distinct, underspecified domain warranting dedicated research attention. --- ### Not an A11y: How Android Accessibility Exposes Mobile AI Agents to Indirect Prompt Injection Authors: Rahul Deivasigamani, Sayeda Faatin Alvi, Derqui Andrea, Kaushal Punjabi, Stjepan Picek Published: 2026-08-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.08939v1 The rise of autonomous AI agents represents a major paradigm shift in how users interact with mobile devices. Frameworks such as MobileRun and Mobile-Use can autonomously navigate Android applications and execute complex multi-step tasks. To interpret user interfaces, these frameworks rely primarily on Android accessibility (A11y) trees and secondarily on visual screenshots. In this paper, we demonstrate that this architectural dependence on unsanitized accessibility metadata, together with visual input, introduces a systemic vulnerability to indirect prompt injection. We show that adversarial prompts can cause autonomous agents to abandon their original objectives, violate context boundaries, and perform unauthorized device actions. Our empirical evaluation demonstrates goal hijacking, context drift, and unauthorized actions across visually hidden and fully exposed attack scenarios. In aggregate, MobileRun reaches an attack success rate of 0.822 with Gemma4:31B, while Mobile-Use with Qwen3.6:35B reduces this to 0.150 but does not eliminate context drift or unauthorized actions. These findings reveal that current mobile agent frameworks fail to enforce semantic context boundaries, treating passive environmental text as trusted instructions. Finally, we present a taxonomy of these attacks and discuss the need for zero-trust input validation, dedicated security agents, and strict context isolation within mobile agent architectures. --- ### Integrated Multimodal AI System for Retrieval-Augmented Reasoning, Object Sensing, and Damage Analysis Authors: Kalelo Dukuray, Israel Pina, Evan Perez, Erika Ardiles-Cruz, Jie Wei Published: 2026-08-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.08935v1 This work presents a unified multimodal AI system for damage assessment that integrates retrieval-augmented generation (RAG) models, thermal spectrum perception, vision foundation model pipelines, and exploratory wireless signal sensing. A RAG component is developed to ground a locally hosted language model in project-specific documentation, including specialized damage level classification criteria to mitigate hallucinations during inference. Controlled comparisons against static few-shot prompting demonstrate that dynamic retrieval improves grounding and factual consistency. We further compare vector-based RAG with a knowledge graph variant constructed via entity-relation extraction, and show that graph-based retrieval produces stronger responses for damage assessment queries requiring cross-document reasoning, motivating hybrid dense, sparse, and graph-aware retrieval. To address limitations of EO imagery under adverse lighting and weather conditions, infrared (IR)/thermal sensing is employed for object detection and segmentation. Our detectors generate candidate detections, yielding improved segmentation of a broad array of objects. Paired IR versus visible spectrum tracking experiments reveal failure modes, motivating multimodal fusion for robust object detection and damage analysis. Vision foundation and vision-language models are leveraged to generate synthetic damage imagery and classify damage severity with high accuracy, supporting training and validation of downstream damage assessment models. Finally, exploratory Wireless-based sensing demonstrates potential to detect presence, motion, and post-event environmental changes where EO and IR sensing are ineffective. --- ### Zero-shot 2D Grounding with Novel Affordance Types Authors: Haomeng Zhang, Raymond A. Yeh Published: 2026-08-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.08929v1 2D affordance grounding aims to locate the region of an object that a human can interact with. Existing research focuses on recognizing affordance types seen during training and does not study models' ability to generalize to novel affordances, which is crucial for real-world applications. We propose the task of zero-shot 2D grounding with novel affordance types (NAT) and introduce the NAT benchmarks. We then propose AffordAnything, a training-free method that leverages segmentation cues, motivated by the strong correlation between affordance regions and object subparts. To further improve performance, we develop AffordAnything+, a trainable variant that learns to combine these cues. On the proposed AGD20K-NAT benchmark, our best model AffordAnything+ achieves a substantial improvement of 12.3% (absolute) in IoU@0.4 over the SOTA affordance grounding method, OOAL. --- ### Decoding Phenotypes: A Framework for Fusing Genomic Language Models and Neuroimaging Authors: Tianli Tao, Ziyang Wang, Emma Robinson, Rachel Sparks, Le Zhang Published: 2026-08-09 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.08926v1 Neuroimaging and genetic testing are two important clinical references for nervous system diseases, offering complementary diagnostic information. However, integrating genomic and neuroimaging data for precise disease diagnosis is challenging due to cross-modality heterogeneity. Existing imaging-genetics approaches mainly encode genetic information as hard-coded labels, which lose the local sequence context around disease-associated variants. To address this limitation, we propose GeneFuse, a multimodal learning framework that aligns genetic representations from pre-trained Genomic Language Models (GLMs) with features extracted from images. GeneFuse integrates two components: (1) Genotype-Conditioned Feature Modulation (GCFM), a FiLM-inspired module that uses genomic embeddings to modulate image feature maps; and (2) Uncertainty-aware Genomic Residual Fusion (U-GRF), a fusion strategy that uses imaging-derived predictive uncertainty to gate the contribution of genotypic features. We evaluate GeneFuse on early cognitive decline identification (NC vs. MCI) and dementia screening (NC vs. AD). In the APOE-centered setting, GeneFuse achieves AUROCs of 0.77 and 0.83, outperforming existing imaging-genetics fusion methods. These results indicate that GLM-derived genomic embeddings provide additional information to imaging. --- ### From Noise to Meaning: Meaningful Secret Sharing with Tamper Detection for Facial Recognition Authors: Ajnas Muhammed, Iurii Medvedev, Nuno Gonçalves Published: 2026-08-09 Categories: cs.CV, cs.CR arXiv: https://arxiv.org/abs/2608.08924v1 Popularity of AI-based face recognition system directly demands protection of sensitive biometric data used for training. Visual secret sharing is an interesting idea, as it splits facial images into secret shares that look random and spread across many institutions. However, these shares look like noise and can easily spark suspicion and recognized as encrypted content. This makes them open to targeted collection and harvest-now-decrypt-later attacks. Additionally, visual secret sharing does not detect tampering, allowing attackers to modify shares and threaten the integrity of reconstruction. In this paper, we introduce a new method that turns distracting noise-like secret shares into visually appealing cover images with additional cryptographic tamper detection. The proposed technique works with visual secret sharing and introduces cover images to embed the shares using adaptive least significant bit steganography. Here, cover images with perceptual transparency are used to store secret shares while guaranteeing complete privacy. A two layer authentication using strong digital watermarking and cryptographic hashing is used to protect the integrity of shares. The proposed technique shows high resilience in stopping bit-flipping, cropping, and substitution attacks. Extensive experiments on multiple public face datasets show that the technique shows better FR accuracy, while eliminating share conspicuousness and guaranteeing integrity. The proposed framework sets a new standard for protecting facial data in such a way that privacy, security, and integrity are protected. --- ### Clustered Attractor Manifolds and Dynamical Condensation in Self-Attention Authors: Qucheng Gao, Zuyi Yang, Xiao Chen Published: 2026-08-09 Categories: cond-mat.dis-nn, cond-mat.stat-mech, cs.LG arXiv: https://arxiv.org/abs/2608.08922v1 Transformer layers generate state-dependent interaction networks: token representations determine the attention matrix, which in turn updates the representations. We study this feedback in a minimal normalized self-attention dynamics and identify the overlap gap as the central quantity governing its attractor structure in the thermodynamic limit. When tokens form internally aligned clusters and their similarity to members of the same cluster exceeds that to every other cluster by a nonvanishing amount, inter-cluster attention is exponentially suppressed as the dimension increases. This mechanism produces a high-dimensional manifold of clustered fixed points, ranging from a few macroscopic clusters to extensive microscopic fragmentation, and also controls their stability against perturbations. Starting from an unstructured Gaussian state, we find that clustered states nucleate from the diffuse background only above a finite threshold in attention sharpness, giving rise to a dynamical attention-condensation transition. --- ### A Domain-Structured Ensemble Framework for Perioperative Outcome Prediction Using Electronic Health Record Data Authors: Shikhar Shukla, Cristina Barboi Published: 2026-08-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.08920v1 Perioperative risk prediction models are often limited by narrow surgical populations, incomplete intraoperative data, poor calibration, and limited interpretability. We present a domain-structured ensemble framework for perioperative outcome prediction using routinely collected electronic health record (EHR) data. Predictors are organized into patient-related, surgery-related, and anesthetics-related domains. Domain-specific gradient boosting models generate independent risk estimates that are integrated through a logistic regression meta-learner. We demonstrate the framework using postoperative delirium (POD) in a case-control sample of 5,386 surgical encounters (2,693 cases, 2,693 controls) from a statewide health information exchange. POD required both delirium-related ICD codes and a positive Confusion Assessment Method screening within seven postoperative days; patients with preexisting dementia were excluded. The stacked meta-learner achieved AUROC 0.899 (95% CI: 0.891-0.906), precision-recall AUC 0.881, and Brier score 0.126, compared with AUROC 0.849 for the best single-stage model. Domain ablation showed improved discrimination and calibration over a surgery-only model (AUROC 0.879, Brier 0.140). Temporal validation on held-out post-2017 data yielded AUROC 0.915. Calibration was excellent, with intercept -0.006 (95% CI: -0.083 to 0.070) and slope 1.035 (95% CI: 0.982 to 1.088). Decision curve analysis, corrected for case-control sampling, showed positive net benefit across clinically plausible thresholds. The modular framework supports alternative outcomes, extension of predictor domains, and dynamic risk updating, providing a scalable foundation for interpretable, calibration-aware perioperative clinical decision support. --- ### Toward CT-Equivalent Image Quality in Low-Dose Radiotherapy Planning: Conditional Diffusion-Based CBCT-to-CT Synthesis and the Impact of CBCT Input Representation Authors: Alzahra Altalib, Chunhui Li, Christopher Hamill Taylor, Sankar Pillai, Alessandro Perelli Published: 2026-08-09 Categories: physics.med-ph, cs.AI arXiv: https://arxiv.org/abs/2608.08919v1 During standard radiotherapy planning, repeated CT acquisitions are often required for patient registration, verification, and adaptive planning, resulting in increased cumulative X-ray dose. To mitigate this, low-dose cone-beam CT (CBCT) is routinely acquired during treatment delivery. However, CBCT image quality remains insufficient for accurate dose calculation and adaptive radiotherapy planning due to increased scatter, noise, beam hardening, and reconstruction related artifacts. This study develops a supervised deep learning based CBCT to CT synthesis framework using a conditional denoising diffusion probabilistic model (DDPM), where the generation of a CT-based planning for accurate positioning and dose calculation is obtained using generative models with low dose CBCT imaging. Beyond demonstrating CBCT to CT synthesis, the primary objective is to investigate how the representation of CBCT input data, either standard clinical DICOM CBCT images or filtered back-projection (FDK) reconstructions from raw projection data, affects the performance of diffusion based CT synthesis. The overarching aim is to assess whether physics aware CBCT representations better support CT-equivalent image quality while maintaining reduced imaging dose in radiotherapy workflows. --- ### Investigating Multimodal Informativity under Different Partner Visibility Conditions in Video-Mediated Dialogue Authors: Esam Ghaleb, Hugh Mee Wong, Kristina Kobrock Published: 2026-08-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.08915v1 Situated language use is multimodal and embodied. For example, gestures can carry information that is absent or underspecified in the speech signal, yet dialogue models typically rely on transcripts alone. We study how much referential information gestures and their combination with speech carry in multimodal dialogue under different partner visibility conditions. % We build models that identify the intended referent in a video-mediated referential communication game based on either the speech transcript, the skeletal representation of gesture, or both modalities. Our results show that gesture alone is predictive of the intended referent and that multimodal fusion is most beneficial when the transcript-based model is uncertain. Training-only alignment of learned representations with the referent image further improves the fusion model performance. % In a comparison with human interaction data, we further see pragmatic effects of interlocutor visibility on gesture production and informativeness as well as an entrainment effect in speech and multimodal, but not gesture, performance across rounds of repeated interaction. We thus make contributions to the technical modelling of multimodal information in human dialogue and the analysis of human interaction data via trained model representations. --- ### Physics-Informed Learning for Robust Acoustic Localization with Calibrated Uncertainty Authors: Jennifer N. Kampe, Changwoo J. Lee, Xin Shen, Ari Lehtiö, Sandro von Brandenburg, Ossi Nokelainen, David B. Dunson, Otso Ovaskainen Published: 2026-08-09 Categories: stat.ML, cs.LG, cs.SD arXiv: https://arxiv.org/abs/2608.08911v1 Recent advances in Passive Acoustic Monitoring (PAM) offer an opportunity to obtain ecological spatial point-process data at unprecedented scale. However, realizing this opportunity necessitates the development of accurate and scalable localization methods. In real-world outdoor soundscapes, however, the assumptions underlying classical localization methods such as hyperbolic and score-based localization are routinely violated by multipath dominance, near-field effects, and complex propagation. Under these conditions, classical localization methods become brittle, with extreme errors possible even in small detection arrays. Rather than statistically replacing the underlying physics, we propose a method to refine it and increase robustness outside of ideal operating conditions: a learned model operating on physics-informed acoustic features corrects a fast hyperbolic solver where it produces implausible solutions, substantially reducing catastrophic worst-case errors while matching its median accuracy on field data. We further provide calibrated, geometry-aware uncertainty estimates suitable for propagation into downstream spatial models. Evaluating on distributed microphone arrays in real and simulated outdoor environments, we demonstrate that the proposed method yields robust, uncertainty-aware localization, providing a step toward scalable automated wildlife monitoring in complex acoustic environments. --- ### Tied Trit-Planes: Constraining PTQTP to a Uniform Nine-Level Quantizer, with a Persistent Folded Format for Disk-Streamed Mixture-of-Experts Serving Authors: Matteo Grella Published: 2026-08-09 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2608.08910v1 PTQTP decomposes LLM weight matrices into two ternary (trit) planes with two free per-group scales. Tying the scales to a fixed ratio of three collapses the decomposition into a single uniform nine-level quantizer, a known balanced-ternary identity. To our knowledge, at the time of writing, this work is the first to impose that identity as a constraint inside PTQTP's solver. The two trit planes then fold losslessly into one 4-bit code plane that we make the persistent serving representation: disk bytes, expert-cache bytes, and kernel input are the same 4.0625-bits/weight blocks, consumed in one integer dot pass. For this conjunction (ratio-3 nine-level code, CPU-SIMD kernels, SSD expert streaming, identical persistent bytes) we likewise found no precedent. We apply this to the routed experts of DeepSeek-V4-Flash-0731, a 284B-A13B mixture-of-experts model, quantizing in one shot from the released MXFP4 expert weights and streaming experts from SSD on a 64 GB laptop. Against a 4.5-bit Q4_K baseline, measured one process per fixture with an expert-lossless anchor arm as reference control, the tied model matches the official serving API on 5/5 fixtures at step 0 (Q4_K: 4/5) and 12/14 captured continuation steps (11/14), scores 86 vs. 84 on a 100-item MMLU subset, decodes 6.7% faster in decode phase, and ships 9% smaller files: no detected fidelity difference at these small evaluation sizes, and every fixture-level difference between the arms traces to a single measured near-tie cell. The tied fit nevertheless shows higher weight-reconstruction error and worse perplexity, a measured dissociation between proxy metrics and reference fidelity. A cumulative trunk-ternarization ladder and bitwise-pinned aarch64/x86-64 kernels complete the report. All code, formats, and evaluation artifacts are open source in the fucina inference stack. --- ### ToolVision: Learning When and How to Use Visual Tools with Capability-Aligned Supervision Authors: Delin Mao, Chenghao Sun, Jingwei Song, Chishui Chen, Linfeng Zhang Published: 2026-08-09 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.08907v1 Thinking with images allows a multimodal model to compensate for limited perception by invoking visual tools through code. Yet the prevailing SFT-then-RL recipe creates a different supervision misalignment at each stage. SFT is expected to teach how to use tools, but trajectories from stronger teachers may succeed through perceptual capabilities that a smaller student cannot reliably reproduce or exploit, causing the student to imitate tool-call patterns without learning how to make them useful. RL is expected to teach when to use tools, but outcome-only rewards make fallible tool execution a liability and suppress tool use, whereas a blanket bonus for every correct tool-using trajectory encourages valid but ineffective operations. To address these two misalignments, we introduce ToolVision. During SFT, a multi-agent pipeline explores candidate trajectories, and a committee including student-scale models scores stepwise evidence gain to rank and prune the search branches. Only successfully executed trajectories with correct final answers are retained for SFT. Before RL, ToolVision compares the learner's performance with and without tools, then rewards successful tool use only on questions where tools provide a clear benefit. Both signals are constructed automatically from public task data without additional human annotations of tool use or necessity. ToolVision-8B improves over its base on all seven main benchmarks, surpasses Thyme-7B, CodeVision-8B, and CodeDance-7B on all three high-resolution benchmarks, and outperforms Qwen3-VL-32B-Thinking on V* and HRBench 8K. We will publicly release the datasets and source code. --- ### Federated Attention Autoencoders with a Stochastic Aggregation Scheme for Anomaly Detection Authors: Mihailo Ilić, Miloš Savić, Vladimir Kurbalija, Mirjana Ivanović, Giancarlo Fortino, Dušan Jakovetić Published: 2026-08-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.08906v1 Outlier detection in decentralized data environments is a challenging task for many machine learning implementations, particularly in settings where data cannot be shared. Recently, there have been advances in federated outlier detection, some of which are based on the use of autoencoder networks. The introduction of attention mechanisms to autoencoders boosts their efficiency. However, the application of attention-based models in federated learning remains underdeveloped due to the absence of proper aggregation functions for these types of networks. In our work, we propose two novel aggregation functions tailored for attention-based autoencoders, which better preserve the learned information stored within the memory modules of these networks. We evaluated our approach on the KDDCUP10 dataset, and we showed that the proposed methods achieve up to 2.9\% and 5.1\% better results for F1 score and AUC ROC respectively when compared to traditional autoencoders. --- ### From Recovery to Drop-off: How Action Post-training Reduces a VLM's Late-Layer Depth Decodability Authors: Alexander Hackett, Arnaud Denis-Remillard, Axel Cassou Published: 2026-08-09 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.08904v2 How much of a vision-language model's (VLM) spatial understanding remains after the action post-training process of building a vision-language-action model (VLA)? We probe depth perception, a primitive of spatiogeometric understanding, from every decoder layer of a weight-matched open-source base VLM/VLA pair: Molmo2-ER and MolmoAct2-LIBERO. First, the VLA decodes depth worse at every layer, a persistent gap we call the floor. Second, the degradation is not uniform: while the base VLM's depth decodability improves through its final layers, the VLA's collapses, an additional late-layer drop we call the cliff. We causally localize the cliff to late-layer MLP interference: ablating the late-layer MLP writes recovers the majority of the terminal decodability cliff, while matched attention ablations and the same intervention in the weight-matched base VLM produce no comparable recovery. A module-level decomposition explains this dissociation: the base VLM carries depth most accessibly in accumulated MLP writes, whereas action post-training collapses depth decodability in the late accumulated writes. --- ### A New Approach to Characterising Optimisation Problems Using Programmatic Representation and Complexity Measures Authors: Marcus Gallagher, Katherine M. Malan Published: 2026-08-09 Categories: cs.NE, cs.AI arXiv: https://arxiv.org/abs/2608.08898v1 Characterising optimisation problem instances is a fundamental part of understanding the behaviour and performance of different algorithms as well as providing information for algorithm selection and configuration. In this paper we propose a novel approach to problem characterisation based on the representation of instances when implemented as a program. The intuition is that the complexity of the code required to express an objective function should relate to the complexity of the search landscape. We identify the Halstead volume as a measure of code complexity, which can be seen as a simplified version of the entropy of the program. Given a code implementation of the objective function, the Halstead volume and entropy can be quickly calculated using existing libraries. We apply the proposed complexity measures to the well-known BBOB optimisation problem suite and the simple feed-forward neural network training task. We also show that the measures are negatively correlated with algorithm performance and therefore show potential as predictive meta-features for algorithm selection and other problem analysis. We envisage the proposed measures as complementary to other problem characterisation approaches, but with the advantages of not requiring any sampling of the search space, being invariant to transformations, and being very quick to calculate automatically. --- ### From Manuals to Maintenance: Fine-Tuning MedGemma for Multi-Modal Imaging System Support in Low-Resource Settings Authors: Bernes Lorier Atabonfack, Zion Kongbi Nfo, Ahmed Tahiru Issah, Tolulope Olusuyi, Clemence Ingabire, Mohammed Hardi Abdul Baaki, Mawuli Deku, Abdulrazaq Zubair, Alyasaa Anas, Raymond Confidence, Maruf Adewole, Udunna C. Anazodo Published: 2026-08-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.08896v1 Imaging device downtime is a major barrier to healthcare delivery in low- and middle-income countries (LMICs), often driven by limited access to specialized biomedical engineering support. We present a multi-modality medical equipment maintenance question-answering (QA) framework and demonstrate the fine-tuning of a medical foundation model for specialized technical troubleshooting tasks. Guided by a multi-country survey across nine LMICs, we curated technical manuals from MRI and ultrasound systems to generate the INGENZI_DatasetV1, containing 10,294 high-quality, filtered QA-context pairs. Using QLoRA-based parameter-efficient fine-tuning, we adapted the MedGemma-4b-it model to interpret system error logs and generate step-by-step equipment repair instructions. Compared to the baseline model, the fine-tuned system achieved substantial improvements across metrics, including F1 score (0.22 to 0.38), ROUGE-2 (0.18 to 0.41), and BERTScore F1 (0.86 to 0.91). These metric gains demonstrate that the model generates significantly more precise and procedurally accurate technical responses to new troubleshooting queries. This work establishes a reliable foundation for AI-assisted diagnostic and maintenance tools in resource-constrained settings. --- ### LLM Reasoning for Subjective Tasks: Failure Modes, Mitigation, and Dynamic Reasoning Routing Authors: Juncheng Dong, Ding Tong, Ishan Gupta, Yuyan Wang Published: 2026-08-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.08889v1 Recommendation systems thrive on personalization, where ''correctness'' is rarely a binary truth but a matter of subjective human preference. As Large Language Models (LLMs) are deployed as autonomous verifiers of safety and quality guidelines, they face a distinctive challenge: context-aware preference alignment. Recent gains in Reinforcement Learning with Verifiable Rewards (RLVR) are indexed mostly on objective, mathematical tasks. Through a large-scale study spanning both proprietary and open-source models on four real-world verification tasks from a production recommender platform, we ask whether explicit reasoning generalizes to subjective, human-centric industry rubrics. We expose a fundamental vulnerability: rigid, math-centric reasoning traces actively degrade verification, and applying standard RLVR triggers a phenomenon we term reasoning collapse, in which the policy abandons deliberation in favor of rapid heuristic guessing. We introduce a conditional length-penalized post-training algorithm that intertwines verification accuracy with bounded reasoning length, halting collapse and recovering performance. Finally, we show that a reasoning trace's efficacy is tightly coupled with its socio-linguistic framing: across 1500 synthesized personas, verification accuracy swings by nearly 0.38 macro-F1 depending solely on the adopted reasoning persona---evidence that much subjective-verification error is really reasoning-style mismatch. This observation motivates a mid-training architecture that routes reasoning through contextually aligned personas. This work offers both a scalable algorithmic patch and a long-term architectural blueprint for aligning reasoning models with real-world subjective constraints. --- ### Full-bandwidth transformer Authors: Xi Wang, Ziyang Cai, Zheng Zhan, Harry Dong, Ying Fan, Gustavo de Rosa, Tim Pearce, John Langford Published: 2026-08-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.08888v1 Autoregressive transformers compute along two axes: horizontally across generated tokens, and vertically through model depth. Dense attention gives each token broad horizontal access to the past, but the vertical feedback channel between decoding steps remains narrow: only the sampled token returns to the bottom of the stack, while the top-layer hidden state is discarded. We introduce the \emph{full-bandwidth transformer}, which widens this channel with \emph{latent feedback}: at each decoding step, the previous top-layer hidden state is fused with the sampled token embedding through a gated linear unit and fed back as the next input. Latent feedback lets non-verbalized computation re-enter the stack with a renewed depth budget, while preserving the standard transformer architecture, KV cache, and language-modeling objective. To train full-bandwidth transformers without losing parallel teacher forcing, we use a scheduled multi-pass objective that introduces latent feedback late in pretraining and mixes a small fraction of deeper feedback passes for stability. We train 1B-parameter full-bandwidth transformers up to 400B tokens and find that latent feedback improves validation loss, 5-shot language-model evaluation, math and coding generation, and instruction-tuned performance. With negligible per-token decoding overhead, full-bandwidth transformers match or approach standard transformers trained with roughly $1.5\times$ more tokens, and manage to produce shorter reasoning traces at equal or better accuracy. --- ### City Sentinel: A Unified AI-Based Smart Surveillance Framework for Real-Time Multi-Threat Detection Using Deep Learning Authors: Hanan Syed Shabir, Noor Fatima, Safia Baloch, Masroor Hussain Published: 2026-08-09 Categories: cs.CV, cs.CY arXiv: https://arxiv.org/abs/2608.08887v1 Rapid urbanization has increased the need for surveillance systems that can monitor multiple public safety risks at the same time. Traditional systems often use separate solutions for facial recognition, vehicle identification, fire detection, and behavioral analysis, resulting in fragmented infrastructure and multiple interfaces for operators to manage. This paper presents City Sentinel, a unified AI-based surveillance framework that integrates six detection capabilities into one scalable platform: facial recognition, automatic number plate recognition (ANPR), fire and smoke detection, weapon and knife detection, violence detection, and road accident detection. The system combines a Next.js operator dashboard, FastAPI backend, cloud-based PostgreSQL event storage, InsightFace and YOLOv8 vision models, and EasyOCR for plate recognition. Camera streams are processed through dedicated inference workers using RTSP. On a workstation equipped with an NVIDIA RTX 3060 GPU, the system achieves a median end-to-end latency of 743 ms and supports four concurrent RTSP streams within a two-second latency limit. It achieves a 91.2% face-match rate, 85.7% plate-reading accuracy, and mAP@0.5 scores of 0.846 to 0.889 across the fire, knife, and weapon detection modules. In user-acceptance testing, operators could enroll a new identity in under one minute and identify a flagged person from live footage in an average of 12 seconds. The results demonstrate that a modular, open-source, multi-model architecture can provide broad surveillance coverage, cloud-based auditability, and flexibility for adding new detection capabilities while maintaining practical real-time performance. --- ### Towards an LLM-based method for quantifying the sexual content in song lyrics Authors: Ignacio M. Sticco Published: 2026-08-09 Categories: physics.soc-ph, cs.CL, cs.SD arXiv: https://arxiv.org/abs/2608.08885v1 Reggaeton is one of the most widely consumed music genres in the world, and its lyrics are commonly regarded as highly sexualized. This claim rests mostly on qualitative studies and on small-scale quantitative ones. This paper has two goals. First, we present a reproducible method that uses a large language model to quantify thematic content in song lyrics along several independent dimensions. The method is not restricted to sexual content. Second, we apply it to a corpus of 1,259 songs by 12 reggaeton artists released between 2002 and 2025. The analysis covers four topics: a dataset characterization, a per-artist comparison, an analysis of how the dimensions change over time, and a comparison between our sexual-explicitness score and Spotify's own explicit flag. We release the data collection code, the scoring prompt, and the corpus, so that other researchers can replicate the approach or apply it to their own lyrics datasets. --- ### AquiLLM: An Architecture for Supporting Tacit Knowledge Capture in Research Groups Authors: Jack Stark, Srinath Saikrishnan, Vikram Seenivasan, Bernie Boscoe, Andrew Lizarraga, Tuan Do Published: 2026-08-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.08883v1 Recent advances in retrieval-augmented generation (RAG) and large language models (LLMs) enable researchers to integrate AI into scientific workflows. However, using proprietary commercial AI systems raises concerns about transparency, reproducibility and privacy, which are essential for scientific practices. To this end, AquiLLM was developed as an open-source modular RAG-LLM framework using open-weight models, designed to support research groups in capturing tacit knowledge. In this work, we present a series of architectural improvements and feature enhancements to AquiLLM, including local embedding and reranking, multimodal capabilities, OpenAI-compatible inference interfaces, user interface improvements, semantic and episodic memory capabilities, and skills support. These enhancements were informed by discussions with domain experts, including astrophysicists and environmental researchers, and represent a step toward AI systems more closely aligned with scientific research practices. --- ### Epistemic Transfer in AI-Assisted Verification: A Framework and Evaluation Protocol Authors: Christoph Trattner Published: 2026-08-09 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2608.08882v5 AI tools can improve claim judgments while leaving open what users can do later without them. This paper develops an evaluation framework for epistemic transfer: the effect of prior AI-assisted verification on delayed judgments of novel claims under a specified access regime. The contribution is a verification-specific synthesis of learning, transfer, and human--AI evaluation, organized around two complementary estimands. The Epistemic Transfer Effect (ETE) compares delayed performance after alternative practice conditions. Tool-Removal Cost (TRC) compares immediate performance with and without assistance after practice; despite its name, it measures a current availability effect, not skill loss or psychological dependence. The proposed randomized protocol includes answer-first and evidence-first interfaces, active practice, a no-additional-practice comparator, and held-out claims. It specifies how to account for learning opportunities introduced by assessment, elicit confidence probabilities, average model predictions over a target population, and handle attrition and uncertainty. Reading ETE and TRC together distinguishes relative capability gains, equivalence, transfer penalties, and unresolved outcomes. A ``verification-on-loan'' profile is explicitly comparator-relative and cannot be inferred from a nonsignificant delayed contrast. A brief illustration from a two-wave verification study shows why these distinctions matter: an uncertain delayed interface contrast and an ordered assisted--unassisted probe cannot establish a clean transfer profile. The framework makes a practical demand: when independent judgment matters, evaluate both what assistance contributes now and what prior use changes later. --- ### Theory-Guided Deception Detection: A RAG-Based Artificial Intelligence Exploration Authors: David M. Markowitz, Timothy R. Levine Published: 2026-08-09 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.08881v1 The current work developed seven Retrieval-Augmented Generation (RAG) models based on leading deception theories and compared how deception judgments were made relative to baseline models. Across 700 statements drawn from five published deception datasets, four large language models (gpt-4o, claude-sonnet-4-6, ollama/llama3, deepseek-v4-flash), and two run-types (RAG vs. baseline), a total of 39,200 deception judgments were rendered. Detection accuracies were consistent with typical human accuracies and not statistically different across RAG (54.5%) and baseline models (54.6%). RAG-based models (57.0%) were less truth-biased than baseline models (59.7%), but the effect size was quite small. Theoretical perspective mattered little for accuracy yet mattered substantially for response bias, which ranged from highly lie-biased (the verifiability approach, 32.2%) to highly truth-biased (truth-default theory, 88.1%). Content effects and model effects further moderated the results. Theory-guided AI judgments are unreliable with current parameters, yet they might show promise with additional datasets, model testing, and theory-to-data matching. --- ### DistillCache: KL-Guided Adaptive KV-Cache Eviction for Memory-Efficient LLM Inference Authors: Asaad Althoubi Published: 2026-08-09 Categories: cs.LG, cs.AI, cs.PF arXiv: https://arxiv.org/abs/2608.08878v1 Transformer-based large language models (LLMs) achieve strong performance across many tasks, but their Key-Value (KV) cache grows linearly with sequence length, creating a severe memory bottleneck for long-context inference. Existing heuristic eviction methods (e.g., H$_2$O and SnapKV) rely on static attention or positional signals that often fail to capture a token's future predictive influence. We propose DistillCache, a reinforcement learning framework that formulates KV-cache eviction as a sequential decision problem. DistillCache learns a lightweight policy network using rich internal model signals (attention statistics, value norms, entropy, and position) and trains it with REINFORCE via a per-step KL-divergence reward to preserve the full-cache output distribution. On a 7B-parameter instruction-tuned Transformer (Mistral-7B-Instruct-v0.3), DistillCache retains 94.2% of full-cache accuracy on LongBench at a 25% cache budget, outperforming both strong heuristic baselines (H$_2$O, SnapKV) by up to 2.7 absolute points and, under our re-implementations, concurrent RL-based methods (ForesightKV, RLKV) by up to 1.4 points on long-context tasks. On reasoning benchmarks, DistillCache is competitive with the best concurrent method and surpasses it under aggressive compression. It also delivers up to 2.1x full-cache throughput while maintaining competitive practical efficiency. These results highlight the effectiveness of learned, distribution-aware policies for memory-efficient long-context LLM inference. --- ### Inductive Graph Layout with Implicit Neural Fields Authors: Berfin Inal, Daniel Probst Published: 2026-08-09 Categories: cs.HC, cs.LG arXiv: https://arxiv.org/abs/2608.08876v1 A graph layout is normally a table of $N$ free coordinates. We optimise a function with a fixed number of parameters instead. This gives a drawing a sample complexity and an extensible domain. Force-directed algorithms remain the standard tools for graph drawing. The most accurate among them minimise stress in the Kamada-Kawai formulation by directly optimising the node coordinates, at a full objective cost of $O(N^2)$ in time and space. Here, we propose Fling (Field Layout via Implicit Neural Geometry), a small neural network mapping the distances of each node to a set of landmarks, positioning it in the plane by training on the layout energy. The full spring system then becomes tractable without its distance matrix, as rest lengths follow from a landmark bound in constant time per pair while a second network learns the majorisation sums from exact anchor rows, at $O(|\mathcal{A}|N)$ per step for $|\mathcal{A}|\ll N$ anchors. Unlike neural drawers that read the graph by message passing, we represent the drawing as a function of node features. An unseen node costs one forward pass, where sparse and low-rank majorisation remain transductive. As the unknowns are weights rather than coordinates, the energy only requires a small fraction of the nodes, and a field fitted that way outperforms PivotMDS, landmark MDS, and a kernel ridge trained on the same energy and features, when the task is fitting the energy of a graph from a sample of its nodes. In addition, the same parameterisation enables a stochastic pivot stress variant, an aesthetics-optimised variant carrying a neighbour-embedding energy with node-edge clearance and crossing terms on the same field, and conditioning on the weight between two energies gives a whole layout family from one run. --- ### AeroReformer2: Spoken-Query Referring Segmentation for Aerial Images Authors: Rui Li, Chenxi Duan, Haoyang Yang Published: 2026-08-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.08874v2 Spoken language offers a natural, hands-free interface for specifying an arbitrary target in dense remote-sensing imagery, yet existing referring remote-sensing image segmentation benchmarks accept only written expressions. To bridge this gap, we introduce \dataset, a spoken-query benchmark derived from RISBench that adds accent- and voice-diverse speech while preserving the original image, mask, and data splits. Its hard evaluation sets combine rotor, wind, and mixed interference with three signal-to-noise levels. We also propose \model, an efficient bilateral network that combines a boundary-preserving visual path with token-preserving speech encoding, kernel linear cross-modal attention, and a resolution refinement head. The design conditions visual features at two scales without materializing a dense speech--visual affinity matrix, then restores fine boundaries using high-resolution visual features. On the clean test split, \model with Swin-Base achieves 62.09\% mean intersection over union (mIoU) and 68.22\% overall intersection over union (oIoU), outperforming the strongest audio-adapted remote-sensing baseline by 5.38 and 2.08 percentage points, respectively. It retains the best hard-set mIoU at 54.09\%. To the best of our knowledge, this is the first benchmark and model study of full-sentence spoken-query referring segmentation for remote-sensing imagery. The code will be made publicly available. --- ### Sparse Attention to Emotion: Efficient Facial Emotion Recognition via Token Reduction Authors: Aya Manel Zitouni, Aicha Zenakhri, Karim Haroun, Larbi Boubchir Published: 2026-08-09 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2608.08873v1 Facial Emotion Recognition (FER) is an important task that has significant implications across various fields such as biometrics, health, and human-computer interaction. Current Vision Transformer-based approaches display quadratic complexity $\mathcal{O}(N^2)$, with N being the input sequence length, making them cumbersome to deploy at the edge. In this paper, we hypothesize that the FER task does not necessarily require all facial information to correctly interpret emotional states, as specific regions such as the eyes, the mouth, and parts of the cheeks carry discriminative information that can be sufficient to recognize emotions. Based on this, we propose Sparse Attention to Emotion (SAE), a model that discards image tokens that have no added value to the emotional context, while preserving good accuracy and achieving a significant gain in computational cost. Surprisingly, even after suppressing 90\% of the image tokens, our model achieves competitive accuracy to state of the art methods at much lower cost, providing a lightweight Facial Emotion Recognition approach. Experimental results demonstrate that SAE achieves new state of the art results on the RAF-DB dataset while reducing the computational complexity by up to 90\%. --- ### Approximation Rates for Metaplectic Neural Networks Authors: Ahmed Abdeljawad, Marcello Carioni, Elena Cordero Published: 2026-08-09 Categories: cs.LG, math.FA arXiv: https://arxiv.org/abs/2608.08872v1 In this paper we develop quantitative approximation results for shallow neural networks constructed using a dictionary based on metaplectic operators. First, we extend the concept of Barron spaces by considering a symplectically motivated extension of the Fourier transform, known as the metaplectic transform. Then, after establishing embedding between metaplectic Barron spaces and Sobolev spaces we consider a neural metaplectic dictionary and we prove Monte-Carlo approximation bounds for metaplectic Barron functions using finite linear combinations of atoms of the dictionary. Finally, we validate the introduction of the neural metaplectic dictionary by devising a deep neural network architecture that uses as building blocks the atoms of the dictionary. We test it to approximate solutions of time-dependent Schrödinger equations, demonstrating better performance compared to classical phyisics informed neural networks architectures. --- ### Are LLMs Positionally Consistent Ordinal Classifiers? A Systematic Evaluation Authors: Yu Wang, Zhe Zhou, Menglin Liu, Ge Shi Published: 2026-08-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.08869v2 Large language models are increasingly used for ordinal classification, yet semantically equivalent changes to prompt organization can alter their predictions. We conduct systematic experiments to characterize positional bias from label order, demonstration order, and demonstration placement. First, we apply the three probes to ten frontier LLMs on a common ordinal-classification task; every model is sensitive to all three positional sources, showing that the problem is pervasive. Second, we vary eight prompt-, task-, and model-level factors across five datasets; accuracy and stability are often misaligned, and only lower scale cardinality consistently improves both. Third, we compare pointwise, pairwise, and listwise inference, alternative aggregation and debiasing methods, and joint configurations; the tested corrections do not provide a reliable remedy, while a comparison-based listwise formulation offers the best balance but transfers unevenly across models and bias sources. These findings show that positional robustness depends on the full system configuration rather than the model alone. Ordinal-classification systems should therefore be selected jointly for predictive performance and stability. --- ### Conversation as Measurement in Clinical Encounters: Observable Phase Structure, Partially Observable Patient State Authors: Lily Chen, Ted Mau, Michael Gensheimer, Brian Anthony Nuyen, Nancy Jiang, James Zou Published: 2026-08-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.08868v2 Many modern AI systems analyze conversational traces to infer aspects of human interaction and state, implicitly assuming that such information is recoverable from conversation. We study observability: whether a target is recoverable from conversational transcripts alone. Observability is difficult to assess because transcripts may provide only a partial view of many targets, and large-scale analysis requires model-based annotation, making true limits of the conversational signal hard to distinguish from annotator error. We therefore study clinical encounters, where patient-reported outcome measures (PROMs) provide an external anchor for patient state, and visits follow broadly structured patterns. We study observability of patient state and conversational phase structure using 439 real-world clinical encounter transcripts spanning 134 hours, including 245 ENT transcripts paired with 273 PROM surveys. We operationalize patient state using PROM scores for voice, cough, and swallowing; phase structure using conversational phase segmentation. To make these analyses credible at scale, we use a PHI-compliant GPT-5 deployment for transcript annotation and conduct 40 hours of manual validation, reducing the risk that apparent limits of observability simply reflect annotator error. Our core finding is an observability asymmetry: phase structure is observable and useful for characterizing clinical encounter organization, while patient state is only partially observable, even in a setting designed to elicit patient symptoms and experiences, cautioning against transcript-only inference of human state. --- ### Zero-Shot Traffic Accident Detection via a Coarse-to-Fine VLM-Tracking Pipeline Authors: Dipit Saha, Shah Mohammad Abdul Mannan, Mohammad Raihan Rashid, Ruwad Naswan, Ahnaf Tahmid Published: 2026-08-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.08867v1 Traffic surveillance cameras capture accidents continuously, yet converting raw CCTV footage into structured event records that pinpoint when, where, and what type of collision occurred remains unsolved at scale. The ACCIDENT @ CVPR benchmark evaluates exactly this joint prediction under a strict constraint: no labeled real-world training data is available. We introduce a training-free, two-pass coarse-to-fine pipeline that pairs a frozen Qwen3-VL-32B-Instruct vision-language model with YOLO11x object detection and BoT-SORT tracking. A first pass sparsely samples the full clip to anchor the collision moment in time; a second pass re-examines a tight window around that estimate using frames annotated with stable vehicle identities and normalized bounding-box coordinates, which gives the model both a visual overlay and an explicit numeric description of the same scene. On the official 2,027-clip real-CCTV test set, our system achieves a three-way harmonic mean score of 0.504, surpassing all organizer-published baselines including the best multi-model ensemble (0.412) by a 22% relative margin. --- ### Agentic Anomaly Detection with ORCA-Style Dynamic Inductive Bias Adaptation in Multimodal Wearable Time Series Data Authors: Anushka Roy, Jyotirmoy Singh, Shreea Bose, Chittaranjan Hota Published: 2026-08-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.08859v1 Wireless Body Area Networks (WBANs) generate multivariate physiological time series that are highly nonstationary and must often be processed under strict computational and memory constraints. A critical yet underexplored challenge in this setting is selecting an appropriate temporal receptive field, which serves as a strong inductive bias for anomaly detection models. Existing approaches typically rely on fixed temporal contexts, which can perform inconsistently across heterogeneous signal regimes and require dataset-specific tuning. We propose ORCA, an agentically controlled anomaly detection framework that dynamically adapts the temporal receptive field at inference time based on lightweight signal statistics. Rather than introducing additional trainable parameters or learned policies, ORCA employs a supervisory controller that autonomously selects among discrete temporal contexts, enabling state-dependent inductive bias adaptation without retraining. Across a custom WBAN dataset, ORCA achieves performance comparable to the strongest fixed-context baselines (AUROC = 0.99) while eliminating the need to tune temporal horizons in advance. We further evaluate ORCA on MIMIC-IV as a challenging out-of-distribution benchmark, observing conservative generalization behavior without performance collapse under heterogeneous clinical conditions. These results highlight adaptive temporal inductive bias control as a practical and robust design principle for anomaly detection in resource-constrained, nonstationary physiological time series. --- ### Beyond Routing: Decoupling Expert Dispatch and Aggregation in Sparse Mixture-of-Experts Authors: Zongfei Li Published: 2026-08-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.08853v1 Sparse Mixture-of-Experts (MoE) routers commonly use the same scores both to select experts and to weight their already-computed outputs. We study whether these two roles, dispatch and aggregation, should be coupled. On pretrained OLMoE-1B-7B, we keep selected Top-8 expert IDs, expert computation, and total selected router mass fixed and change only within-set aggregation. A structured oracle improves full-horizon cross-entropy by 0.0160 +/- 0.0039 across three seeds; the router's top-scored expert is the counterfactual-best vertex only 17.2% of the time, with router-utility Spearman 0.030. We therefore train Fixed-Dispatch Adaptive Aggregation (FDAA), a 301K-parameter post-compute head optimized directly with the language-modeling objective while freezing the backbone, router, and experts. On OLMoE, FDAA improves fresh WikiText-103 test by Delta CE = -0.1523 +/- 0.0031 across three seeds, and mixed-domain training gives robust gains on WikiText-103, C4, and held-out Penn Treebank under frozen confirmatory evaluation. We also replicate the fixed-dispatch audit on DeepSeek-V2-Lite, which uses Top-6 routed experts plus shared experts. Best-vertex headroom remains significant on WikiText and C4, while router Top1 identifies the best selected expert in only 12.5% and 16.7% of audited examples. In a one-seed mixed-domain replication, FDAA improves locked WikiText and PTB, while C4 is statistically neutral. These results support a cross-architecture distinction between expert selection and expert commitment. --- ### Findings of the First Teaching Monster Challenge: A Benchmark of Pedagogical Content Knowledge in AI Agents Authors: Yi-Cheng Lin, Yu-Kai Guo, Szu-Chi Chen, Bo-Han Feng, Yun-Man Hsu, Hsiang Hsieh, Yu-Jung Lin, Yue-Ling Wu, Jia-Kai Dong, An-Yu Cheng, Yu-Han Huang, Lok-Lam Ieong et al. Published: 2026-08-09 Categories: cs.AI, cs.CY, cs.HC, cs.MA arXiv: https://arxiv.org/abs/2608.08852v1 AI agents can now solve problems, answer like subject experts, and generate long-form multimodal content. However, whether they can adapt a lesson to fit a specified learner, which education calls Pedagogical Content Knowledge (PCK), has not been benchmarked. To measure it, we introduce the Teaching Monster Challenge, the first instructional video generation benchmark to treat the learner persona as an explicit evaluation criterion. Each system is given a topic and a learner persona and must generate a complete instructional video. Every video is screened by an LLM-judge, ranked by crowd pairwise voting, and finalized by an expert panel. The first edition shows that today's systems handle the content well but are far weaker at presenting it and adapting it to the learner. The same process exposes a limit of automatic judging. The LLM-judge separates a clear low-performing tail but ranks the strongest systems poorly. The strongest systems receive nearly identical scores from the judge, so its ranking of them does not match human preference. Progress therefore requires not only better teaching systems but also better automatic judges, and we release the benchmark, rubric, and human judgments as a testbed for both. --- ### Explicit Boundary Markers for Subword Vocabularies Authors: Sander Land, Clara Meister Published: 2026-08-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.08847v2 Subword tokenizers represent many common words twice in space-using writing systems, once with a leading space and once without. The two entries have separate embeddings in models, so occurrences of one word are divided across rows that are trained independently, and the two forms need not even segment the string the same way: " together" may be a single entry while the same word without a preceding space is tokenized as "to|gether". Capitalization divides a word further, into as many as six forms. We introduce an alternative to standard whitespace conventions using an explicit word boundary marker, which prevents such duplication. Words are delimited by the boundary markers, and spaces between words are represented as pairs of such markers. Two shift codes do the same for title case and upper case, allowing one internal representation of a word to be re-used across different settings. Switching to this convention mitigates the duplicate-entry issue, but does not improve tokenization compression: for both vocabulary-learning algorithms, the best marker scheme stays within one percent of the baseline in characters per token, averaged across six languages. It does result in better language modeling performance. Every marker scheme tested downstream reaches lower bits per byte than the baseline, suggesting that duplication carries a cost that compression does not capture. --- ### Toward Mask Annotation-Free Surgical Instrument Segmentation from Endoscopic Images Using Text-Prompted Segment Anything Model 3 (SAM3) Authors: Nakul Poudel, Richard Simon, Cristian A. Linte Published: 2026-08-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.08844v1 Surgical instrument segmentation is a fundamental task for computer-assisted interventions, yet most existing methods rely on pixel-level annotations or manual spatial prompts, which limit scalability and automation. The recently introduced Segment Anything Model 3 (SAM3) offers a pathway to annotation-free, automatic segmentation via text-based prompting; however, the instrument name as a text prompt could not be directly used due to a large domain gap. To overcome these limitations, we propose a two-stage framework that achieves instance-level segmentation without requiring ground truth masks or manual interaction. In the first stage, we leverage a natural-language-aligned generic prompt - "tool" - to produce binary masks using SAM3's zero-shot capability. In the second stage, these masks are extended to instance-level by integrating a vision-language model (Qwen) that is fine-tuned on SAM3-generated masked regions for instrument classification. We evaluate our approach on the EndoVis 2017 and 2018 datasets. Results show that, while our two-stage approach does not reach the performance of current fully supervised methods, it significantly outperforms the direct use of SAM3 for instance-level instrument segmentation with text prompts. Overall, our findings highlight both the limitations and potential of SAM3, suggesting a promising direction toward annotation-free surgical instrument segmentation. --- ### SLAP: Selective Local Vision-Language Alignment for Fish Re-Identification via Partial Optimal Transport Authors: Cigdem Beyan, Tonje Knutsen Sordalen, Kim Tallaksen Halvorsen Published: 2026-08-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.08840v1 Individual fish re-identification (ReID) is a fine-grained recognition problem in which identity-discriminative cues are often localized to specific body regions rather than distributed uniformly across the animal. Nevertheless, recent CLIP-based ReID methods rely predominantly on global image-text alignment, allowing background and weakly discriminative regions to contribute to cross-modal supervision. We propose a selective local vision-language alignment framework that establishes localized correspondences between visual patch embeddings and multiple identity-aware prompt embeddings through Partial Optimal Transport (POT). Rather than enforcing exhaustive correspondence, POT enables selective matching between visual patches and prompt embeddings, allowing the model to emphasize the strongest cross-modal correspondences while avoiding forced alignment of weakly matching regions, thereby yielding more discriminative visual representations for retrieval. The framework is trained end-to-end, while only the adapted visual encoder is retained during inference. Experiments on the longitudinal Symphodus melops dataset demonstrate consistent improvements over recent CLIP-based ReID methods under both closed-set and open-set evaluation protocols. Additional evaluations on other datasets further demonstrate the generalization capability of the proposed method across diverse marine ReID benchmarks. --- ### SG-WAM: Text-Grounded and Spatial-aware Semantic Guidance for World-Action Models Authors: Junjie He, Junfeng Li, Zhide Zhong, Haodong Yan, Ruixin Li, Yangyang Zheng, Jiaguan Zhu, Tianran Zhang, Yuqiao Du, Wen Chen, Shunbo Zhou, Haoang Li Published: 2026-08-09 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2608.08839v1 World-Action Models (WAMs) have emerged as a promising paradigm for robotic manipulation. However, most existing WAMs generate future videos and actions by relying mainly on visual cues rather than language instructions, since off-the-shelf text encoders embed instructions independently of visual observations. As a result, the videos predicted by these WAMs are often semantically misaligned with their corresponding language instructions, which degrades the accuracy of the predicted actions. To overcome this limitation, we propose SG-WAM, a semantic guidance method for world-action models that leverages a vision-language model (VLM) as a semantic planner to enhance the instruction-grounding capacity of world-action models. Specifically, we train a VLM-based planner to predict text-grounded and spatial-aware semantic foresight. The text-grounded semantic foresight grounds the instruction by identifying the correct target objects, and the spatial-aware semantic foresight provides the scene geometry for precise manipulation. We then inject this foresight into the world-action model as high-level semantic guidance, ensuring that both future-video generation and action prediction faithfully follow the language instruction. Extensive experiments in simulation and the real world demonstrate the superiority of our semantic guidance method, showcasing precise manipulation and strong instruction-following capabilities. ---