# Research Papers — 2026-09 · bundle page 226 of 266 > Full-text markdown of papers #11251–11300 of 13298 published in 2026-09, newest first. AI-readable mirrors of the full 13298-paper 2026-09 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-09/page/226 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/225.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/227.md) ### SeaCausal-FL: Federated Fuzzy Causal Learning for Maritime IoT Fault Diagnosis and Counterfactual Reasoning Authors: Yuhang Qiu, Haihan Zhu, Koteeswaran Seerangan, Longsheng Zhu, Xiong Wang, Yijun Lu, Zheng Lin, Fangmin Ren, Jialiang Xie Published: 2026-09-05 Categories: cs.LG, cs.NI arXiv: https://arxiv.org/abs/2609.06257v1 Reliable marine-engine fault diagnosis in maritime IoT is challenged by distributed data ownership, heterogeneous fault distributions, and continuously changing operating conditions. This paper proposes SeaCausal-FL, a federated fuzzy causal learning framework that combines a shared temporal diagnostic path with mechanism-conditioned causal reasoning. An interval type-2 fuzzy layer represents uncertain and overlapping operating mechanisms, while each mechanism is associated with a physics-constrained structural causal model. Before aggregation, locally learned mechanisms are aligned using operating context, causal structure, and conditional intervention-response signatures. Model parameters are then aggregated according to sample, class, mechanism, and mechanism-class evidence instead of client sample size alone. The learned structural equations further support interval counterfactual reasoning through abduction, action, and prediction. Experiments on a marine-engine fault dataset and a real-data-calibrated semi-synthetic causal benchmark show that SeaCausal-FL achieves an average F1 score of 87.07% across four client partitions, with AUROC and AUPRC of 98.98% and 94.81%, respectively. It also maintains strong performance under unseen loads and fault-type omission during training. On the causal benchmark, SeaCausal-FL reaches an Edge-F1 of approximately 0.58 and an Edge-AUPRC of 0.68, reduces coefficient RMSE to about 0.14, and provides favorable counterfactual estimation and intervention decisions. --- ### One Model, Two Worlds: Bidirectional Sonar-Optical Translation Authors: Shengji Jin, Trung Tien Dong, Ahmed Lamidi, Chen Chen, Xiaomin Lin, Yi Sheng Published: 2026-09-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.06253v1 Translating between imaging sonar and optical cameras is valuable for underwater perception, but supporting both directions with separate models duplicates storage and computation. A unified bidirectional model is therefore attractive, yet existing approaches largely treat the two directions symmetrically despite their fundamentally different image-formation physics. We argue that sharing a generative model does not require sharing the physics. We introduce the Direction-Asymmetric Realism Bridge (DARB), which retains a shared diffusion-bridge trunk while routing direction-specific physical priors through asymmetric pathways: range-aware modulation for sonar-to-optical translation and polar ray-dependent processing for optical-to-sonar translation. We further show that symmetry in training is also costly: applying a common realism schedule reduces sonar-to-optical PSNR by 2.60 dB. Our Adaptive Realism Supervision (ARS) instead determines when, where, and how strongly perceptual supervision is applied from reconstruction quality and gradient balance. Together, DARB and ARS enable one bidirectional model to match the sonar-to-optical specialist within 0.11 dB PSNR, outperform the optical-to-sonar specialist by 0.70 FID, and surpass two independently trained BBDMs on seven of eight metrics. --- ### MobileVLA-R1 2.0: RL-Enhanced Reasoning for Mobile Robot Control Authors: Ting Huang, Yue Huang, Zeyu Zhang, Shuicheng Yan, Hao Tang Published: 2026-09-05 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2609.06251v1 Grounding natural-language instructions into reliable and executable actions remains a fundamental challenge for vision-language-action (VLA) systems on mobile robots, due to the persistent gap between high-level semantic reasoning and low-level locomotion and manipulation control. Existing approaches often rely on implicit reasoning or monolithic action prediction, making it difficult to maintain coherent long-horizon decision making while producing precise and adaptable robot actions. To address this challenge, we propose MobileVLA-R1 2.0, an RL-enhanced VLA framework that explicitly couples structured embodied reasoning with executable mobile robot control. The framework learns multi-granularity reasoning over embodied trajectories through supervised Chain-of-Thought (CoT) alignment and reinforcement learning, improving reasoning-to-action consistency beyond purely behavioral supervision. To support both locomotion and manipulation, we further introduce a reasoning-conditioned action decoder that maps multimodal reasoning representations to task-level action targets, which are subsequently translated into embodiment-specific commands by robot controllers. This design provides a unified perception-reasoning-action interface while decoupling high-level action generation from robot-specific actuation. We conduct extensive evaluations on language-guided navigation, quadruped control, and humanoid mobile manipulation, covering VLN-CE, QUARD, and real-world deployments on Unitree Go2 and G1 robots. MobileVLA-R1 2.0 consistently outperforms strong VLA baselines, achieving an average 1.6 point improvement in SR on VLN-CE and a 10.0 point improvement in full-task success on real-world G1 mobile manipulation tasks over MobileVLA-R1, while demonstrating robust long-horizon instruction following and closed-loop execution across different robotic platforms. --- ### It is Not Yet Another Tool: Creating and Deploying an Agentic AI Companion in a Security Operations Center Authors: Kritan Banstola, Faayed Al Faisal, Duy Dao, Ryan Irving, Daniel Lende, Xinming Ou Published: 2026-09-05 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2609.06250v1 Security Operations Centers (SOCs) process large amounts of tickets, most of which are low-interest events not worthy of further investigation. The repetitive nature of this task and similarity of the vast amounts of tickets make it a prime candidate for generative AI-based automation. We created and deployed an agentic AI companion utilizing large language models through fieldwork within a SOC for over one year. The design of the SOC AI companion was driven by researchers' participation and interactions within the SOC's daily work. SOC analysts were invited to use it during the last four months of the fieldwork. We analyzed the analysts' usage of the companion and found that in more than 90% of the cases the companion's outputs were reused by analysts in the ticket's closing report. Our results showed that when designed "in the trenches" with the intended users, a SOC AI companion can go beyond being yet another tool, but rather a system that co-evolves with its human users as it traverses through the various types of workloads. Analysts naturally started to shape the AI companion's behaviors to fit their particular needs. Our data show that the more human analysts shape the AI companion's behaviors, the more they become comfortable trusting the output from the AI system, resulting in improved productivity. --- ### VDiff-Bench: A Challenging Benchmark for Fine-Grained Image Difference Identification Authors: Yixin Wan, Tianle Zheng, Kai-Wei Chang Published: 2026-09-05 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.06245v1 Multimodal Large Language Models (MLLMs) perform strongly on general visual understanding tasks such as visual question answering, yet they often struggle with a basic comparative skill: identifying what has changed between two similar images. We introduce VDiff-Bench, a challenging multiple-choice benchmark for fine-grained Image Difference Identification. VDiff-Bench contains 1,756 four-way questions over image pairs and covers 10 change categories: position, motion, regional image color, overall image color, appearance/disappearance, noise/resolution, texture, substitution/size, OCR/text, and illumination. Each question corresponds to two image inputs with 4 choices: the true difference, two hard negative descriptions, and a "no difference" distractor. To make the task challenging, we specifically curate ground-truth-conditioned negatives that require models to distinguish the actual change from nearby semantic alternatives. Experiments with 11 state-of-the-art open- and closed-source MLLMs show that fine-grained visual comparison remains brittle: models exhibit uneven performance across sources and change categories, with persistent failures on subtle low-level changes like noises and textures. For instance, three 7-8B-scale open-source MLLMs score 52.5-70.6% on semantic changes but only 8.7-33.3% on low-level changes like noise and texture, falsely assuming no changes between two image inputs. Surprisingly, despite strong performance of other closed-source commercial models, Grok 4.3 demonstrate remarkable performance drop on identifying noise and texture differences between images, falling significantly behind large open-source models like Kimi K2.5 and K3. Overall, VDiff-Bench provides a targeted diagnostic for evaluating comparative visual understanding in MLLMs, exposing failures that are not captured by standard single-image vision-language tasks. --- ### Task-Oriented Semantic Communication for Hazard Warning and Remote Operation in Connected Vehicle Platoons Authors: S M Sabit Bananee, Shahriar Hasan, Muhammad Mahbub Alam, Nafiul Rashid Published: 2026-09-05 Categories: cs.NI, cs.CV arXiv: https://arxiv.org/abs/2609.06242v1 Connected and automated vehicle platoons require reliable dissemination of task-relevant hazard information to enable appropriate downstream responses, with unresolved situations additionally requiring remote human intervention. However, the limited channel bandwidth of V2X communication makes high-volume sensor data transmission challenging, motivating the exchange of only task-relevant information rather than raw sensor data. This paper proposes an integrated semantic and task-oriented communication framework for cooperative hazard response and remote operation in automated vehicle platoons. The framework combines onboard instance segmentation and monocular depth estimation for task-oriented hazard decision-making with Stable Diffusion Variational Autoencoder (SD-VAE)-based semantic scene compression. Task-relevant hazard information and the compact semantic representation are jointly disseminated through a broadcast-based Emergency Semantic Message (ESM) over the existing V2X protocol stack. Evaluation demonstrates that SD-VAE consistently outperforms JPEG and JPEG 2000 on task-relevant reconstruction metrics, exhibiting graceful degradation rather than a sharp cliff effect under low-SINR conditions, demonstrating its feasibility for remote scene reconstruction when human intervention is required. Moreover, an extensive campaign of 7,290 simulation runs shows a low overall inter-vehicle collision rate of 0.99%, with collisions occurring mainly under extreme high-speed and short-gap conditions. --- ### Spatial Attention Supervision for Defect Localization: Exploiting Ground-Truth Masks as Training Signal in Diffusion-Augmented Defect Detection Authors: Sajjad Rezvani Boroujeni, Muskan Saraf, Gnana Tulasi Makineni, Tom Bush, Hossein Abedi Published: 2026-09-05 Categories: cs.CV, cs.LG, eess.IV arXiv: https://arxiv.org/abs/2609.06232v1 Ground-truth defect masks in industrial inspection datasets are typically reserved for evaluation. This paper repurposes them as spatial supervision signals during training of classification networks, teaching a model not just what to predict but where to look. The method adds an activation-based attention alignment loss that steers convolutional feature maps toward defect regions, in a mixed-supervision formulation that also accommodates samples without masks, such as diffusion-generated images. Combined with DDPM augmentation, synthetic images contribute quantity while masks contribute spatial precision. We evaluate 85 models (four CNN backbones under a 2x2 data/training factorial over five seeds, plus a Swin-V2-T transformer baseline) on the MVTec-AD bottle benchmark, with localization measured on held-out defect images excluded from classifier gradient updates. Main findings: (1) attention-guided training improves activation-based localization (Pixel-AUROC) by +18.0% for EfficientNetB0 with augmentation (p=0.005, Cohen's d=2.6) and +18.7% for ResNet50 (p=0.008), significant in four of eight CNN settings (uncorrected for multiple comparisons) with no significant change in classification; (2) for EfficientNetB0 a data x training-mode interaction is significant (p=0.002), consistent with a super-additive effect (+13.6% combined vs +1.6% summed individual effects); (3) architectures with weaker spatial representations benefit most, whereas ConvNeXt-T shows no effect, apparently because its depthwise-convolution activations yield spatially uninformative channel-mean maps; (4) unsupervised PatchCore remains the strongest localizer (Pixel-AUROC=0.983), contextualizing the supervised gains. These results show that existing evaluation masks can act as practical training signals that measurably and reproducibly improve where defect classifiers attend. --- ### SWE-Test: Benchmarking LLM Vulnerability Discovery via Input Prediction Authors: Yuanxiang Shi, Jiayi Lin, Xuanyong Lin, Liangcai Su, Yeheng Duan, Wei Wang, Qi Han, Bing Zhao, Wei Hu, Xander Xu, Chenxiong Qian Published: 2026-09-05 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2609.06229v1 Vulnerability discovery is becoming an important ability of large language model (LLM) agents: agents that silently miss real defects leave critical software exposed. Rigorously measuring this ability is therefore urgent, but existing benchmarks are gameable through data contamination, score recall against an unknowable vulnerability set, often rely on synthetic bugs, and report a single end-to-end verdict that cannot localize where an agent fails. Vulnerability discovery is a composite ability: an agent must comprehend source code, infer input constraints, construct inputs, execute them, and iteratively correct from feedback. We recast its measurement as an input-prediction task with a closed, deterministic ground truth: using coverage-guided fuzzing, we mine deep target branches in real-world C/C++ programs and ask an agent to predict an input that drives execution to a given branch. This decomposes discovery into three task modes over 22 real-world C/C++ programs spanning 15 domains. Open-loop and Feedback-enabled share 60 fixed-target task instances across 16 of these codebases (13 domains), testing input construction without and with a distance oracle to isolate code comprehension from feedback-driven correction. Online Arena instead removes the predefined target and scores path exploration by coverage gain on a separate, partially overlapping pool of 11 programs; agents collectively confirmed 13 distinct bugs across six programs. Evaluating 15 default-effort model-scaffold configurations, the best reaches only 55.0% pass rate in the Feedback-enabled mode, and the mean across seven paired Claude Code configurations is 36.4% with feedback versus 19.3% without. Decomposing failures, we find constraint inference, not navigation, is the dominant bottleneck. We release SWE-Test with a turnkey evaluation environment. --- ### Scratchy: Visual-Scratchpad Multimodal Reasoning for Cryptographic Proof Generation in EasyCrypt Authors: Yupeng Ren, Zhaoxuan Li, Rui Zhang Published: 2026-09-05 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2609.06226v1 Large language models (LLMs) have recently made substantial progress in formal proof generation, yet presenting distinctive challenges in cryptographic area. Computational security arguments posit that a valid proof must coordinate probability, adversarial games, invariants, assumptions and bounds, which can be provided by a machine-checked framework named EasyCrypt. Although all objects may appear in available context, LLMs still struggle because proof-theoretic dependencies are typically implicit in a linear representation and distributed across multiple programs. So, this paper presents Scratchy, a visual-scratchpad approach that exposes these dependencies for multimodal generation. Given the natural-language security description, with formal context and target propositions, the proof objects can be normalized into a typed proof-relation graph. Then a structure-preserving visual compiler transforms the graph into the formula-rich visual proof state that guides a multimodal model in generating the EasyCrypt proof. Also, the Scratchy-eval, a 114-task dataset derived from reliable official EasyCrypt files, has been introduced. It contains 64 security-form proof generations and 50 multiple-choice knowledge tests. After a series of evaluations, covering semantic grounding, relational invariants, and game reductions, classical LLMs like GPT-5.6-Sol and Claude-Opus-5 have gained a clear advantage from Scratchy's structured visual proof states. This contrast suggests that explicit proof structure can make the improvement and multimodal proof-state representation as a promising direction for computer-aided cryptography. --- ### Branch-Centric Tokenization and Test-Time Augmentation for Skeleton Generation Authors: Zhengyuan Li, Chuanyu Pan, Yuanming Hu, Raymond Yeh Published: 2026-09-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.06218v1 Automatic skeleton generation involves predicting both joint positions and skeletal connectivity. However, existing approaches struggle to encode branch structures into token sequences and do not use test-time computation effectively. We study these choices within a unified autoregressive framework. First, we introduce branch-centric tokenization, a branch-aware representation that places structurally related elements next to each other and encodes connectivity directly in the sequence. Compared with standard BFS-style serialization, this representation yields more compact sequences. Second, we introduce view-augmented generation, a test-time augmentation procedure that applies axis-aligned rotations to the input mesh, maps all predictions back to a common frame, and selects the final skeleton based on mesh coverage and consistency among predictions from different views. Experiments show that our method achieves better skeleton prediction accuracy than state-of-the-art methods. In particular, our method reduces the CD-J2B error by 16.9% on the Articulation-XL2.0 dataset compared to the strongest directly comparable baseline, Auto-Connect. Qualitative results on in-the-wild meshes further demonstrate generalization across diverse inputs. --- ### SLATE: Are AI-Generated Slides Educationally Effective? A Benchmark for Language Teaching Quality and Learner Knowledge Acquisition Authors: Jingzhuo Wu, Jiajun Zhang, Liu Yi, Leqi Zheng, Yuheng Jing, Xinyuan Zhou, Quan yang Published: 2026-09-05 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.06212v1 LLMs have achieved remarkable capabilities in generating language teaching slides. However, a critical mismatch persists between visual polish and actual instructional effectiveness. To address this gap, we introduce SLATE (Slide-based Learning Assessment for Teaching Effectiveness), the first benchmark that evaluates AI-generated language teaching slides through instructional effectiveness and learner knowledge acquisition. SLATE transforms linguistics olympiad puzzles from low-resource languages with negligible web presence into 90 standardized instructional units comprising 1,133 assessable items, paired with a structured course outline and matched near- and far-transfer test sets. This pretest-posttest design eliminates pretrained knowledge leakage, ensuring gains reflect learning rather than prior recall. Using VLMs as scalable learner proxies and directionally supported by a three-system human pilot, our results show that content validity exhibits a weak association with learning gain, while pedagogical design exhibits a robust positive association. Moreover, most systems show a significant gap between near- and far-transfer accuracy, and even frontier models can produce negative learning gains. SLATE reveals a dissociation between artifact quality and instructional effectiveness, calling for a paradigm shift in how generative teaching systems are built, evaluated, and deployed. --- ### From Gaze to Meaning: A Training-Free AI Agent for Unified Grounding and Explanation Authors: Shayan Nasiriboukani, Sara Atito, Mohammad Nezamipour, Muhammad Awais Published: 2026-09-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.06208v1 Understanding human attention is fundamental for scene interpretation, yet existing approaches often rely on heavily trained models that lack interpretability. Prior methods struggle to jointly reason about gaze targets, attended objects, and visual grounding without extensive supervision. To the best of our knowledge, this work introduces the first training-free Gaze Target Agent (GTA) for gaze-guided reasoning across tasks such as gaze target prediction, attention localization, and object identification. This is achieved by leveraging pretrained vision-language models, augmenting them with visually guided prompts, and employing a memory-based retrieval strategy for high-uncertainty samples to improve performance without additional training. We evaluate our approach using both quantitative metrics and qualitative results. Quantitatively, our method achieves state of the art performance on the GazeFollow and GazeHOI benchmarks. Qualitatively, our agent provides detailed semantic predictions, predicts the correct targets even when ground truth labels are wrong, and remains flexible without vocabulary constraints. --- ### PhysWeep: Does a Video Generator Realize the Physics You Ask For? Authors: Rasul Khanbayov, Hasan Kurban Published: 2026-09-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.06207v1 Image-to-video generators are often credited with absorbing physical dynamics as implicit world models, a claim the community currently checks with plausibility scores that ask whether a clip looks consistent with real-world motion. Plausibility is the wrong test on its own, because a clip can look natural while encoding the wrong value of the governing physical parameter, and no existing benchmark measures this gap directly. PhysWeep closes it with a fixed, label-free audit, treating a frozen generator as a black box, recovering the realized parameter from generated pixels, and reporting how often generation is trackable at all, how far the realized value sits from the requested one, and which, if either, of the literature's two proposed failure mechanisms the data support. A deterministic-simulator positive control confirms every score is exactly checkable. Applied to three open generators across six sweep axes, PhysWeep finds a specific, reproducible, previously undocumented failure. Conditional on producing trackable motion, two of the three generate confident, well-fit dynamics that converge to one of a small number of fixed, wrong values selected by the sampling seed rather than by the request, reproducing across two independent model families, two physical systems, and an independent tracker. It matches neither the prior reversion nor the case-based clamping the literature anticipates, because the reversion target is seed-conditional rather than a single global default, and a leave-one-out selection rule rejects both; the in-range faithfulness slope is statistically indistinguishable from zero wherever a response is estimable at all. A benchmark averaging over seeds would never see this: each sample is confidently locked to a wrong constant, exactly the failure a plausibility score is structurally blind to. We release the protocol, suite, and analysis code. --- ### Algorithmic Optimality Guarantees for Nonsmooth $H_\infty$ Output-Feedback Policy Search Authors: Ashkan Soleymani, Patrick Jaillet Published: 2026-09-05 Categories: math.OC, cs.LG, eess.SY arXiv: https://arxiv.org/abs/2609.06197v1 We study continuous-time full-order dynamic output-feedback $H_\infty$ policy search, a nonconvex and nonsmooth problem. Direct policy search is a central paradigm in reinforcement learning and continuous control, but rigorous guarantees remain scarce in robust output-feedback settings. The $H_\infty$ problem is a canonical benchmark because it captures disturbance attenuation and robustness while exposing the hard nonsmooth geometry of policy-space optimization. We prove that on the exact identity-gauge slice of the extended convex lift, $\varepsilon$-stationarity yields $O(\varepsilon)$-suboptimality on compact exact slices, which in turn yields convergence-rate guarantees for nonsmooth policy-search methods. This result addresses the finite-time optimality-gap question raised by Guo and Hu (2022) in the more general dynamic output-feedback $H_\infty$ policy-search setting. We further use the established value equivalence supplied by extended convex lifting to formulate a nonstrict-feasibility bisection method with one final strict-feasibility recovery step, yielding an explicit $\varepsilon$-optimal stabilizing controller. These results provide a quantitative and algorithmic strengthening of prior qualitative optimality theory for nonsmooth $H_\infty$ policy search. --- ### Fast PAC Global Optimization via Restarted Langevin: Exploration, Exploitation, and Degenerate Cooling Authors: Ioannis Kontoyiannis, Sean Meyn Published: 2026-09-05 Categories: math.OC, cs.LG arXiv: https://arxiv.org/abs/2609.06196v2 This paper addresses a fundamental question in non-convex optimization: \textit{How should a stochastic optimizer allocate computation between global exploration and local exploitation?} We study this question in continuous time, using Langevin dynamics for global exploration and deterministic gradient flow for local exploitation. The simplest algorithm in this class is the best-state Langevin--gradient method: several Langevin trajectories explore the objective landscape, the best state encountered is retained, and a single gradient trajectory then refines this state to high terminal accuracy. Our main objective is to characterize the computational work required to achieve a prescribed accuracy with prescribed confidence. We develop low-temperature approximations for this probably approximately correct (PAC) work--accuracy tradeoff, both for the best-state method and for related Langevin schemes. Global exploration is governed by energy barriers, through spectral-gap and Eyring--Kramers asymptotics. The resulting approximations expose the competing effects of temperature, computational budget, and the number of exploratory trajectories, and quantify their dependence on the confidence parameter. In contrast, terminal accuracy is largely separated from global exploration: once a suitable region of attraction has been reached, gradient flow requires only $O(\log(1/\varepsilon))$ additional work to reach accuracy at least $\varepsilon$. Numerical experiments on challenging objectives serve to compare algorithms and to test the quantitative predictions of the asymptotic theory. They identify regimes in which the low-temperature approximations provide useful guidance, as well as regimes exhibiting substantial temperature sensitivity and potentially significant high-dimensional limitations. --- ### EgoNeMo: Transferable Map of Pedestrian Dynamics via Egocentric LiDAR Scan Authors: Azusa Sawada, Allan Wang, Hideo Saito, Aaron Steinfeld Published: 2026-09-05 Categories: cs.LG, cs.RO arXiv: https://arxiv.org/abs/2609.06195v1 This paper proposes a transferable Map of Dynamics (MoD) framework that generalizes to unknown environments using only egocentric 3D LiDAR point clouds to overcome the long-standing limitation of traditional MoD methods. While MoDs are essential for encoding human motion characteristics to enable accurate pedestrian trajectory prediction or safe robot navigation, traditional approaches suffer from site-specificity, requiring exhaustive trajectory accumulation at every new location. Extending recent advances in neural implicit modeling, our framework trains a continuous, LiDAR-based MoD estimator across diverse environments. To mitigate the inherent sparsity and temporal bias of real-world trajectory data, we introduce a position-balanced sampling strategy and a multi-task learning architecture that jointly predicts motion distributions and a spatial frequency score map. The latter is further augmented by visibility-aware losses to compensate for incomplete observation data. Comprehensive experiments demonstrate that our method effectively reconstructs underlying motion maps even in unknown locations from a single instantaneous LiDAR scan, despite highly sparse training data. Finally, we show that our improvements enhance the reliability of downstream trajectory prediction. --- ### Predicting Wind Turbine Power Using Machine Learning and Weather Forecasts Authors: Khivishta Boodhoo, Isaac Triguero, Josh Plumbly, Bruce Nicolson, Nicholas Watson Published: 2026-09-05 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.06194v1 Offshore wind turbines are widely used to generate renewable energy, but their maintenance can result in decreased efficiency due to forced shutdowns. Accurate wind turbine power predictions can identify periods of low power that would be ideal for scheduling maintenance. However, the effects of data volume, feature selection, and data preprocessing on the performance of such power prediction models have not been thoroughly studied. Besides, current models have limited transferability between different wind turbines. Therefore, this study developed a baseline Linear Regression for performance comparison with a more complex Artificial Neural Network model to predict the power output of a wind turbine, using weather conditions only to enhance applicability. A range of data preprocessing techniques were studied, and models were trained on one month and one year of data to determine the effects of data preprocessing and volume on model performance. Feature selection was explored using a Random Forest Regressor. The best results from the different models showed that the Artificial Neural Network models provided the highest accuracy, with an R2 score of 0.98 and a low Mean Absolute Error of 194, when compared with the baseline model (R2 score of 0.94 and Mean Absolute Error of 441). The model performance is comparable to the range of results in past studies, with the advantage that the proposed method leverages a separate weather dataset from a nearby weather station, enabling future applications for similar wind turbines in different locations. The Artificial Neural Network model was then used to identify 4-h periods of low power predictions over 2 months (simulating application for future periods), providing power output savings of approximately 2000 kW for each maintenance event. --- ### SCIRIGOR:Evaluating Open-Ended Scientific Analysis Beyond Final Scores Authors: Bowen Liu, Shuo Nie, Bodong Du, Xiaomeng Li Published: 2026-09-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.06192v1 Scientific coding agents produce interdependent code, results, figures, and claims, yet evaluating final outputs alone does not establish whether their conclusions are scientifically supported. We formulate evidence-grounded multimodal scientific analysis, requiring agents to produce executable analyses and claims supported by results and visualizations from the same run. We introduce SciRIGOR, an evaluation framework and benchmark comprising 100 cases from scientific articles across six domains and 17 subfields. The framework reconstructs typed evidence graphs, separates artifact fidelity from relational validity, and scores complete claim-support paths while localizing the earliest unsupported relation. Source-grounded alternative paths accommodate scientifically equivalent analyses and visualizations. We evaluate 11 agent/model configurations. On full-benchmark runs, claims agree with faithful and unfaithful results at nearly identical rates (91.8% versus 91.0%). Yet no system exceeds 62.6% on the soft evidence-chain score or 18.0% strict whole-chain success. These findings show that internal coherence does not establish scientific correctness: evaluation must verify support along the complete data-to-claim path. --- ### One Perturbation Is Not Enough: Identifiability and Blind Baselines for Behavioral AI Evaluation Authors: Rasul Khanbayov, Mariam Sohail, Ahmed Abdala, Hasan Kurban Published: 2026-09-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.06190v1 Behavioral evaluations perturb an input and read the induced change in the output in order to certify that a system uses that input. We show that the number of perturbations such a certificate requires is fixed, and that reporting a single perturbation cannot supply it. Where a response ratio is a property of the policy rather than of the test items, the behavioral record is a linear measurement of an exponent vector recording how much the output depends on each input, so perturbations identify input use exactly when their logarithms span the input space. At least $n$ are needed for $n$ inputs, an incomplete design confuses precisely the policies differing along the kernel of its design matrix, and sharpening a perturbation never substitutes for adding an independent one. We also derive in closed form the score such a test awards a policy that reads nothing, which is far from zero and which none of the probes we survey reports. Instantiating this where the correct response is fixed by dimensional analysis, we run a complete identifying set of three perturbations on three vision--language models reporting a physical quantity from video. All three score far below their own blind bound rather than above it, because each defaults to one of a small set of round calibration values that never matches what the scale asserts; none moves its relabeling response by a single exponent, and none is separable from the same model instructed to ignore the video. --- ### Customer Relationship Intelligence: Integrating CRM and MDM for Enhanced Customer Engagement Authors: Tejasvi c. Addagada Published: 2026-09-05 Categories: cs.AI, cs.IR arXiv: https://arxiv.org/abs/2609.06189v1 This study examines how Customer Relationship Management (CRM), Master Data Management (MDM), and Customer Knowledge Management (CKM) jointly constitute a Customer Relationship Intelligence (CRI) framework for enhanced Customer Engagement (CE). A cross-sectional survey of 100 participants across retail, healthcare, IT, and telecommunications sectors was analysed using Spearman rho correlation and ordinal logistic regression (IBM SPSS). Bivariate correlations were weak and non-significant (r<0.19, p>0.06). Regression identified CRM (beta=0.717, p=0.002) and CKM (beta=0.581, p=0.009) as significant positive predictors of CE; MDM showed a positive but non-significant direct effect (beta=0.346, p=0.071). The model explained 20.5% of CE variance (Nagelkerke R^2=0.205). Parallel mediation analysis (Hayes PROCESS Model 4, 5,000 bootstrap samples) found no significant indirect effects of MDM on CE via CRM (IE=0.021, 95% BC CI (-0.072, 0.121)) or CKM (IE=0.032, 95% BC CI (-0.061, 0.126)); Hypothesis H4 was not supported. CRM and CKM emerge as the principal drivers of CE within the CRI framework, while MDM functions as a foundational data quality enabler whose strategic value is realised through its enabling effect on CRM execution and knowledge management. Findings should be treated as exploratory given the sample size and cross-sectional design. Future research should replicate with larger sector-specific samples and longitudinal designs, particularly in regulated BFSI contexts where MDM architecture is shaped by data governance mandates. --- ### MVFA: A Multi-View Text-Guided Multimodal Fusion LLM Adapter for Sentiment Analysis and Emotion Recognition Authors: Pengfei Shao, Jisheng Dang, Jiawen Fang, Ning Liu, Wencan Zhang, Bimei Wang, Jingwen Zhao, Jianhuang Lai, Qi Tian, Tat-Seng Chua Published: 2026-09-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.06188v1 Multimodal sentiment analysis and emotion recognition in conversations demand effective modeling of heterogeneous interactions across textual, acoustic, and visual modalities. Although large language models (LLMs) offer powerful language understanding, adapting them to multimodal affective computing remains challenging: full-model fine-tuning is computationally prohibitive, while many existing lightweight adapters fail to preserve rich textual cues during cross-modal fusion. To address these limitations, we propose the multi-view text-guided multimodal fusion adapter (MVFA), a parameter-efficient framework that augments frozen LLMs with strong multimodal reasoning capability. MVFA first constructs complementary text views via max pooling, mean pooling, and attention pooling; these views then guide cross-modal interactions with audio and visual features. The fused multimodal representations are subsequently compressed into a compact set of learnable pseudo-tokens through an Enhanced Q-Former Fusion Module. Using ChatGLM3-6B-base as the primary backbone, we further validate MVFA on LLaMA2-7B and Qwen3-8B to examine its portability across multiple frozen LLM backbones. MVFA is evaluated on three challenging datasets: CH-SIMS V2.0, MELD, and CHERMA. Experimental results demonstrate that MVFA achieves state-of-the-art performance on key metrics while updating only a small fraction of parameters. Specifically, it attains 84.62\% Acc2 and 84.59\% F1 on CH-SIMS V2.0, 67.36\% Acc and 66.03\% WF1 on MELD, and 74.66\% Acc on CHERMA. These findings establish multi-view text-guided fusion as an effective and scalable paradigm for parameter-efficient multimodal LLM adaptation in affective computing. The code is publicly available at https://github.com/Overwhelm1208/MVFA. --- ### SolarBench: A global solar energy nowcasting benchmark Authors: Yuhao Nie, Stephen Campbell, Quentin Paletta, Liwenbo Zhang, Tao Jing, Samer Chaaraoui, Jonathan Giezendanner, Andea Scott, Tao Sun, Cong Feng, Max Aragon, Jacques Camier et al. Published: 2026-09-05 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.06187v1 As the share of solar power grows, nowcasting weather-driven solar variability becomes critical for reliable energy system operation. State-of-the-art approaches increasingly apply deep learning to sky camera and geostationary satellite observations, but fragmented datasets and inconsistent evaluation make it difficult to determine whether reported improvements generalize across climates, cloud regimes, and photovoltaic (PV) systems. Here we introduce SolarBench, an open global benchmark for image-based solar nowcasting. SolarBench harmonizes more than six million sky and satellite images from 11 diverse sites spanning a decade, together with irradiance or PV output and auxiliary atmospheric data. An accompanying toolbox supports reproducible data access, processing, model development, and evaluation. Using SolarBench, we benchmark representative models and reveal a gap between average forecasting accuracy and the ability to capture rapid solar fluctuations. We further quantify predictability across cloud regimes and demonstrate data-efficient adaptation to new PV systems. SolarBench provides an extensible foundation for fair comparison and methodological innovation in solar nowcasting. --- ### Spectral Prioritized Sweeping in Nonstationary Reinforcement Learning Authors: Hung Pham, Tuan Dam Published: 2026-09-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.06186v1 Prioritized Sweeping (PS) accelerates model-based reinforcement learning by selecting backups according to Bellman residual magnitude. In nonstationary reward settings, however, the canonical priority score is shortsighted: after a localized reward shift, residuals propagate only through realized backups, so bottlenecked or topologically distant state estimates may remain static under a limited replanning budget. We introduce the Graph Topology Augmentation framework, which employ the graph's resolvent and its diffusion semantic, to augment the inquired signal. Our application, Graph Topology Augmentation for Prioritized Sweeping (GTA-PS), or which the alias Spectral Prioritized Sweeping (SPS) might be more universal, provides a drop-in ordering score for the setting of fixed dynamics and changing state rewards. GTA-PS uses a smootherized policy, inducing a transition chain, with its in- and out-Laplacian. The standard priority key is augmented with a mixing of regularized Laplacian inverses diffusing the residual magnitude. Furthermore, the topology contribution is annealed by a scheduler based on the Second Largest Eigenvalue Modulus (SLEM), allowing its scale to adapt to the chain's mixing regime. We prove that the forward potential coincides with geometric discounted residual propagation and show that GTA-PS gives active priority instantly to all states. Tabular experiments on FourRooms and GARNET domains demonstrate improved replanning efficiency over standard PS under both exact DP and Dyna-style host planners. --- ### Recovering linear images of sparse signals from indirect observations Authors: Anatoli Juditsky, Arkadi Nemirovski Published: 2026-09-05 Categories: stat.ML, cs.IT, cs.LG, math.OC arXiv: https://arxiv.org/abs/2609.06182v1 In this paper, we develop and analyze techniques for recovering a linear image $Bx$ of an unknown signal $x$ from indirect noisy observation $ω=Ax+ξ$. It is {\em a priori} known that $x\in \cX$, a given convex compact set, and that $x$ is $s$-sparse---has at most $s$ nonvanishing entries. The proposed estimates belong to a large family of recovery routines by $\ell_1$-minimization. However, unlike the classical result describing performance of such estimates, we do not make any special (and hard to check) assumptions about the sensing matrix $A$ such as nullspace or Restricted Isometry condition and the like. As a consequence, parameters of the estimates and the upper bounds on their risks are not available in a closed analytic form, but are delivered instead by efficient computation as solutions to explicit convex optimization problems. --- ### Diamond Agent: Agentic Control of Federated HPC Resources as a Service Authors: Haotian Xie, Junlin Chen, Mingkai Zheng, Yifan Zhu, Minu Mathew, Max Burnette, Yadu Babuji, Volodymyr Kindratenko, Shivaram Venkataraman, Kyle Chard, Ian Foster, Zhao Zhang Published: 2026-09-05 Categories: cs.DC, cs.AI arXiv: https://arxiv.org/abs/2609.06181v1 Efficiently aggregating and orchestrating computing power across heterogeneous clusters for HPC workflows faces four practical challenges: preserving workflow context across independently administered clusters, moving large datasets between sites, reasoning about site-specific environments and scheduler policies, and exploiting live queue and resource states for efficient task scheduling. To this end, we design Diamond Agent, an agentic system that enables intelligent execution of HPC workflows across heterogeneous clusters with typed skills as the interface. Diamond Agent provides an agent-facing workspace and skills that unify cross-site resource discovery, resource specification, data movement, task execution, and result retrieval. A centralized Diamond Agent instance can operate multiple supercomputers without being deployed separately on each login node. Diamond Agent translates high-level agent actions into valid site-specific executions, moves data through Globus Transfer, and uses live system capability and queue information to select feasible placements. Its event-driven continuation mechanism decouples agent actions from long-running batch jobs: persistent services monitor remote execution and resume the agent only when a result or decision-relevant event is available. We experiment with 27 hours of telemetry and 19 matched multi-site submission rounds comprising 83 jobs across four production supercomputers. Compared with a fixed-site baseline, Diamond Agent reduces the median additional completion time relative to the fastest observed placement from 42 seconds to 4 seconds, a 10.5x reduction. --- ### FMMO: Detecting the Divergence Between Local Attribution and Global Drift Authors: Muhammad Rehman Zafar, Ali El-Sharif, Naimul Khan Published: 2026-09-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.06173v1 Post-deployment drift poses a critical risk to algorithmic accountability, particularly when ground truth labels are delayed and performance degradation becomes a "silent failure". While Explainable AI (XAI) is often relied upon to audit these shifts, we demonstrate that popular local attribution methods (e.g., TreeSHAP) can exhibit misleading stability even as model reliability collapses. In this paper, we propose a Framework for Model Monitoring and Observability (FMMO) designed to expose the divergence between local explanation stability and global distribution shifts. Using benchmark, synthetic, and real-world datasets, we show that local XAI methods fail to flag drift-induced disparate impact, specifically where False Positive Rates spike for protected groups while feature attributions remain unchanged. By integrating global surrogate models with model utilization measurements, FMMO mitigates this fairness blind spot, ensuring that stakeholders can detect discriminatory deterioration that standard local XAI tools overlook. --- ### Decision-Aware Suffix Prediction and Reasoning of Business Processes Authors: Henryk Mustroph, Stefanie Rinderle-Ma Published: 2026-09-05 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.06169v1 Suffix prediction forecasts the remaining sequence of events of a running case until completion. Most approaches rely on neural networks trained on event logs, which, on average, perform well but struggle with short prefixes or targets belonging to a rare process variant. In such scenarios, the correct path may cross multiple branching decisions, determined primarily by case- and event-level attributes, a signal that NN-based suffix prediction models tend to underweight because they may heavily weight (dense) event labels. Decision mining extracts rules for such decisions from the event log, but has so far been applied only to post-hoc and what-if analysis, not suffix prediction. We therefore extend suffix prediction with decision mining, introducing a decision-aware suffix prediction framework, a neuro-symbolic approach that enables reasoning about predicted events via mined decision rules. Experiments on three of four event logs and three suffix predictors show that the framework can improve suffix prediction, especially for short prefixes but also for rare process variants, and adds intrinsic interpretability. --- ### Multiple Myeloma Lesion Segmentation on Whole-Body Diffusion-Weighted Imaging via Efficient Anatomical Anticipation and Multimodal Confirmation Authors: Mengmeng Zhang, Shengqian Huang, Junde Zhou, Xiaoping Wu, Hao Luog, Jing Wanga, Yicheng Sun, Jiao Li, Haibo Zhang, Sheng Xie, Fan Wangg, Qin Wangc et al. Published: 2026-09-05 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.06165v1 Whole-body diffusion-weighted imaging (WB-DWI) is widely used for multiple myeloma (MM) assessment, yet automated lesion segmentation remains challenging due to limited anatomical delineation and the low specificity of marrow hyperintensity. Existing studies have introduced bone region-of-interest (ROI) information and apparent diffusion coefficient (ADC) maps to mitigate these ambiguities, but practical limitations remain. Bone ROI construction often relies on costly manual annotation, image registration, or dedicated bone models, while ADC is usually incorporated only through simple channel fusion, limiting its ability to provide complementary structural and lesion-discriminative cues. To address these limitations, we propose a two-stage framework for MM lesion segmentation on WB-DWI. In the first stage, we train a bone ROI generation model from ADC images without dedicated bone labels, providing an efficient and practical anatomical prior for lesion analysis. In the second stage, we propose Anatomy-guided Multimodal U-Net (AMU-Net), which leverages ADC in a manner consistent with clinical lesion assessment rather than treating it as a generic auxiliary modality. Extensive experiments demonstrate the effectiveness and practicality of the proposed method. It achieves the best overall performance among the evaluated methods, with a mean Dice score of 76.2%. --- ### All for 1-Bit: Towards Genuine 1-Bit Post-Training Quantization for LLMs Authors: Zhixiong Zhao, Zukang Xu, Guangyu Sun, Lifeng Liu, Dawei Yang Published: 2026-09-05 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.06161v1 Large language models (LLMs) have achieved remarkable progress, yet their massive storage and memory-bandwidth demands still hinder efficient deployment. Weight binarization is a promising solution, but existing binarization-based post-training quantization (PTQ) methods usually far exceed the nominal 1-bit storage target due to hidden overhead. To address this gap, we propose All for 1-Bit (AF1), a genuine 1-bit PTQ framework for LLMs. AF1 comprises two complementary components: (1) Null-space-Aware Binary Factorization (NABF) for improving binary reconstruction through Hessian-aware surrogate reparameterization, null-space-aware binary factorization, and scale-only global reconstruction; and (2) Hierarchical Shapley Allocation (HiSA) for assigning structural capacity using hierarchical Shapley sensitivity. Together, they preserve model accuracy under a strict 1.0-BPW budget in the PTQ setting. Experiments on LLaMA, Qwen, and Gemma families show that AF1 consistently outperforms existing binarization-based PTQ methods in perplexity and zero-shot accuracy. Compared with BF16, AF1 achieves an average 2.5 times inference speedup and over 90% memory reduction across evaluated models, providing a practical path toward deployable genuine 1-bit compression for LLMs. The code for reproducibility is available at https://github.com/Kishon-zzx/AF1. --- ### From Splats to Silicon: Rethinking Computational Efficiency of 3DGS Authors: Minnan Pei, Qiwei Dong, Yihan Zhou, Gang Li, Yuchen Zhu, Wenju Zhao, Zhongtian Long, Siting Wang, Peisong Wang, Jian Cheng Published: 2026-09-05 Categories: cs.AR, cs.AI, cs.GR arXiv: https://arxiv.org/abs/2609.06157v1 3D Gaussian splatting (3DGS) represents scenes with explicit primitives and supports real-time novel-view synthesis, yet its system efficiency varies substantially across scenes, viewpoints, rendering paths, and platform constraints. Existing studies pursue efficiency through representation and algorithm design, GPU runtime optimization, and architectural support, but their reported gains correspond to different points along the rendering and update paths. Connecting these indicators to end-to-end system benefit requires tracing how each optimization changes Gaussian selection, screen-space work, data movement, and stage or frame time. We therefore use a workload-centric framework to connect representation and algorithm research, GPU runtimes, and hardware architectures and to identify recurring workload patterns. We complement literature analysis with reproduced measurements and controlled GPU profiling of selected implementations, relating workload counts to stage time and memory traffic. Together, these comparisons show that system gains depend on workload reductions reaching downstream execution, granularity matching each stage, and the cost of data transfers, synchronization, and cached results, gradients, and optimizer data. Building on these findings, we discuss more consistent evaluation under rendering-quality constraints and identify key directions for future system design. --- ### ExpertLens: Visualizing Embedding Spaces for Post-Hoc Explainability in MoE Enhanced Retrievers Authors: Effrosyni Sokli, Isaac Roberts, Alexander Schulz, Barbara Hammer, Gabriella Pasi Published: 2026-09-05 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2609.06155v1 Neural models, including dense retrievers, have been widely adopted in Information Retrieval (IR), often delivering state-of-the-art performance. Despite their effectiveness, these models operate as black boxes, limiting the interpretability of their ranking decisions. Existing post-hoc explainability methods for neural rankers primarily focus on feature-level attributions, which can be insufficient to capture the complexity of learned embedding spaces. In this work, we propose ExpertLens, a post-hoc explainability framework for Mixture-of-Experts (MoE)-enhanced dense retrievers that shifts focus from local scalar feature importance to representation-level global interpretability. ExpertLens leverages discriminative embedding space visualizations jointly with automatically extracted Concept Activation Vectors to reveal how expert routing drives embedding space formulation and retrieval effectiveness. Experiments across five IR benchmarks and two MoE-enhanced dense retrievers show that expert routing consistently improves embedding space structure, positioning queries and their relevant documents into better-defined geometric neighborhoods. Analysis of expert subspaces further reveals general-purpose dominant experts, along with minority experts exhibiting distinct linguistic specialization, with subspaces arranged according to multi-semantic concept similarity. Our code is publicly available. --- ### Rethinking One-Shot Federated Graph Learning: Training-Free Statistical Estimation Authors: Shutong Zheng, Sijia Chen Published: 2026-09-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.06154v1 One-shot federated graph learning generally aims to train Graph Neural Networks (GNNs) across clients with disconnected subgraphs in a single communication round. Existing methods predominantly design advanced optimization strategies under the premise that local GNN training is indispensable. However, empirical observations reveal that under extreme non-IID conditions, local GNN training suffers from severe cross-client representation misalignment, becoming a major source of error rather than a remedy. Motivated by this, we reformulate one-shot FGL as a statistical estimation problem. We propose SPEAR (Statistical Prototype Estimation with Adaptive Reliability), a completely training-free framework that directly computes topology-smoothed class prototypes from local graphs in the original feature space. The server then aggregates these prototypes using a sample-size-adaptive shrinkage estimator that down-weights unreliable local estimates, producing robust global class prototypes. Extensive experiments across seven benchmarks demonstrate that SPEAR consistently achieves state-of-the-art accuracy under extreme heterogeneity. Moreover, SPEAR delivers at least an order-of-magnitude speedup over all baselines, reaching several orders of magnitude against generative and distillation-based methods. Our findings suggest that training-free statistical estimation, rather than local GNN optimization, provides the key to robust and efficient one-shot federated graph learning. The code is available at https://github.com/Yodeesy/SPEAR . --- ### SCRIPTIOC-BENCH: A Benchmark for Recognizing Actionable Threat Intelligence from Script-Based Malware using LLMs Authors: Hanna Kim, Jian Cui, Minkyoo Song, Hwanjo Heo, Seungwon Shin, Kimin Lee, Xiaojing Liao Published: 2026-09-05 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2609.06149v1 Script-based malware remains a prevalent attack technique. These scripts often contain indicators of compromise (IOCs) that provide actionable threat intelligence. However, statically recovering such indicators is challenging, as relevant values may be dispersed or transformed within code. Although large language models (LLMs) have shown promise in security analysis, their ability to recover IOCs from malicious scripts remains underexplored. We present SCRIPTIOC-BENCH, a benchmark for measuring static IOC extraction capability on real-world malicious scripts. The benchmark comprises 634 manually verified JavaScript, PowerShell, and VBScript malware samples covering four IOC types (URLs, domains, IP addresses, and filesystem artifacts). We further stratify ground-truth IOCs by recovery level, distinguishing directly exposed indicators from those requiring decoding or reconstruction. Using this benchmark, we evaluate a broad range of proprietary and open-weight LLMs and show that IOC recovery without execution remains challenging across model scales: the strongest model reaches only 65.4 F1. To characterize how recovery fails, we introduce a false-positive taxonomy and use it to compare the error profiles of the evaluated models. We further study two mitigations on a small open-weight model, deterministic string utilities and task-specific adaptation, finding that they provide complementary recovery gains, raise precision, and shift errors toward sample-grounded mismatches. --- ### What the Window Does Not Contain: Auditing Provenance in a Document-Grounded Instability Benchmark Authors: Seyed Mosayeb Alam Published: 2026-09-05 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.06147v1 Ask a language model the same question about the same document twenty times, and it sometimes returns two different answers. We built Probity, a benchmark of 60 tasks and 470 items from real venture-financing filings, to measure how often this happens. Then we audited our own corpus and found a defect any excerpt-built benchmark can carry: items whose evidence is missing from the window of text the model is shown. The audit flags 36 items and separates two failures a single flag would conflate: evidence genuinely absent from the window and answers that must be computed from numbers the window does supply. Flagged items change their answers far more often, wobbling at 0.255 against 0.087 on the 427 clean items, and excluding them cuts apparent cross-model agreement by about a fifth. Before testing whether the missing evidence explains the instability, we registered a prediction: re-cut each window to hold its evidence, and instability should fall below a set threshold. It failed: the repair moved wobble by 0.058, with an interval containing zero. We report the association as correlational. Almost all measurements sit where instability cannot show, which bounds what a corpus built for accuracy can say about stability. We release the corpus, all 112,800 raw responses, and the audit as a runnable check for any document benchmark. --- ### TBDub: Production-Oriented Visual Dubbing Authors: Bihan Li, Xinyang Li, Zeran Xu, Meiguang Jin, Junfeng Ma Published: 2026-09-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.06144v1 Visual dubbing must synchronize mouth motion with replacement speech while preserving identity, appearance, and temporal consistency. Although X-Dub provides a strong mask-free video-editing baseline, its application to livestream and generated-video content reveals limitations in production-domain robustness, temporal and motion stability, identity and oral-detail preservation, and inference efficiency. We present \textbf{TBDub}, a production-oriented extension of X-Dub that combines task-adaptive post-training with task-aware few-step distillation. Post-training adapts the video DiT using production-domain data, production-specific conditioning and filtering, and enhanced audio features to obtain a 30-step Teacher. Distillation adapts DMD/DMD2 to conditional video editing and compresses the Teacher into a two-step Student. On 38 TalkVid clips, the Teacher improves all eight reported reconstruction, perceptual, identity, and synchronization metrics over X-Dub. In the MOS evaluation, it improves lip-sync consistency, identity consistency, and visual quality over X-Dub by 0.14, 0.95, and 0.90 points, while the Student achieves the highest lip-sync and visual-quality scores and remains close to the Teacher in identity consistency. In paired end-to-end generation timing from the first VAE encode through the final VAE decode on a single NVIDIA H20 GPU at $512\times512$, the Student reaches 7.13 effective FPS and reduces total latency by $13.93\times$; the DiT stage alone is accelerated by $42.49\times$. The Student largely retains the Teacher's generation quality and audiovisual synchronization. The code is available on GitHub at \https://github.com/TaoLiveAIGC/TBDub, and the 30-step Teacher and two-step Student weights are available on Hugging Face at https://huggingface.co/TaoLiveAIGC/TBDub. --- ### Counter-Swarm Doctrine: Containing Coordinated Agent Intrusions Authors: Gregory N Frank Published: 2026-09-05 Categories: cs.CR, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2609.06140v1 Agents can turn shared infrastructure into a channel for coordinated intrusion. The Hugging Face incident and a separate public-wiki investigation show why a security assessment may need evidence from several executions and the artifacts they leave behind. We argue that the operational unit of defence should be a revisable coordination episode linking observed transfers, task authority, and response history. The central research problem is prospective episode discovery: finding which actions belong together before an evaluator supplies their membership. We define unsanctioned coordination relative to collaboration and delegated-authority policy, connect storage-mediated coordination to stigmergy, and specify the evidence needed to distinguish influence from common causes. First-contact signals are one possible input to discovery; the design also follows inherited state and later use. A proposed evaluation compares isolated actions, rolling windows, known groups, and prospectively discovered episodes at matched review cost and false-alert workload. It measures harmful outcomes across all assigned population runs and tests recurrence after channel closure and state quarantine. A checksum-verified reconstruction of the public wiki export separates the decline in retained writes from later administrative cleanup. The contribution is an incident-grounded position, descriptive analysis, and evaluation design. It makes the recommendation to monitor across executions testable without claiming a new detector or a measured containment benefit. --- ### Compressed Recurrent Feedback in Tsetlin Machines: A Reproducible Boolean-FSM Study Authors: Ankit Kumar, Utkarsh Raj, Rishad Shafik, Sudip Roy Published: 2026-09-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.06133v1 Sequential inference on small devices requires a model to retain useful history without repeatedly processing a long input record. A Recurrent Tsetlin Machine (RTM) provides this memory by returning Boolean clause outputs from one time step as inputs to the next. Direct feedback, however, grows with the clause bank and can make the recurrent input unnecessarily wide. This paper investigates a fixed-width alternative. We combine clause activations by exclusive-OR (XOR) folding, retain the folded bits at two time scales, and threshold them back to a binary state. The resulting design reduces 480 clause activations to 96 recurrent bits. We evaluate the method on a reproducible Boolean finite-state-machine benchmark with explicit transition rules, data splits, and random seeds. Across 144 runs, the compressed model obtains $61.47 \pm 6.74\%$ and $62.94 \pm 9.92\%$ accuracy on the two task families. Raw clause feedback changes these means by less than one percentage point, while increasing the recurrent width tenfold and measured host execution time by $4.38\times$ and $3.71\times$. Gated neural models remain more accurate, and a no-feedback control retaining only short input history achieves comparable or slightly higher accuracy. On this benchmark, folding matches raw feedback within small empirical margins at a much narrower interface; these findings also underscore the critical necessity of no-feedback recurrence controls when benchmarking sequence models. --- ### IIns-VAE+: A Robust Transfer Learning Framework for Environmental Identification in Wireless Sensing Authors: Yuxiao Li, Keke Hu, Bobai Zhao, Santiago Mazuelas, Yuan Shen Published: 2026-09-05 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.06131v1 Environmental identification in wireless sensing is essential for 6G integrated sensing and communication (ISAC) systems to achieve reliable situational awareness. However, deep learning (DL) models for this task often fail to generalize under domain shift across diverse environments. While the Inter-Instance Variational Auto-encoder (IIns-VAE) learns features of rich representation, its neural classifier remains vulnerable to these distribution changes. In this paper, we propose IIns-VAE+, a hybrid model that combines the IIns-VAE framework with Minimax Risk Classifiers (MRC) to improve adaptability in transfer learning scenarios. We use real-world datasets to evaluate our framework across three transfer learning scenarios, including general to specific room environments, high to low label resolutions, and mixed to specific environments. The experimental results indicate that IIns-VAE+ significantly outperforms baselines, demonstrating its critical value in building adaptable and robust perceptive networks in future 6G systems. --- ### Protocol Compression Changes Which Party Pays: Bilateral Cost in Cross-Organization LLM Agent Communication Authors: Janghoon Lee Published: 2026-09-05 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.06129v1 Agents that talk across organizations exchange long messages billed by the token. A shorter notation therefore looks like a saving that costs nothing but an agreement to use it. Recent work reports the saving is conditional. Compressed notation can instead raise total tokens by 8% to 11% over a JSON baseline, when parsing failures force extra model calls. That is measured for one payer. Between two organizations neither side can install a decoder at the other end, and each pays under its own tokenizer, price, and cache state. We measure both sides. A preregistered token-level study covered 198 content-matched item pairs across six vendors, for 2,376 native-usage cells. We then overlay an English baseline, runtime schema negotiation followed by compression, and injected-schema compression on a two-party procurement bargain with an exactly enumerated feasible set. The overlay covers 1,053 completed dialogues of a 1,215-cell grid across 3 model pairs, plus a 405-dialogue rerun of the negotiated condition. Compression amplifies cross-vendor cost dispersion by a factor of 1.078, with a 95% CI of (1.066, 1.091), and two vendor pairs reverse which endpoint is cheaper. Runtime negotiation succeeds as a protocol and fails as a bargain. The parties agree a schema in 121 of 135 headline dialogues, none of them the schema we would have supplied. They settle the task in only 9 of those dialogues, and they reach impasse in 106 of them. The negotiated sessions average 10.8 turns against 17.6, and cost 52% of the English total because sessions end sooner, not because the handshake is repaid. Break-even horizons run from 20 to 70 turns, the low end only under the conditional accounting, and all of them lie above every observed English session. On one cross-vendor pair both parties keep about half their cost. On the other the receiving party pays more at a high cache-hit rate. --- ### Substrate-Portable Execution for Production LLM Workflows Authors: Tarun Gopinath, Atul Kulkarni, Vijay Rajakumar, Shrikar Katti, Parthasarathy Govindarajen Published: 2026-09-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.06128v1 Production LLM agents execute tool-calling loops, retrieval chains, and compositional workflows in multiple modes, yet execution semantics are often coupled to one runtime. We encountered this portability problem in Rufus, a conversational AI assistant with a large tool catalog that serves millions of Amazon customers. Rufus supports real-time serving, asynchronous background tasks, and high-volume batch workloads such as evaluation and content pregeneration. Each mode has distinct service-level objectives and typically uses a separate runtime. Reusing streaming orchestration makes asynchronous and batch workloads blocking and prevents use of batch inference APIs, which offer a 50 percent discount at published prices. We present a binding-adaptive agent execution platform that separates workflow definition from execution substrate. Developers define a workflow once as a typed dataflow graph. The platform compiles the graph to in-process streaming for real-time serving, durable AWS SWF orchestration for asynchronous execution, or distributed Apache Flink stream processing for batch inference. No workflow code changes are required. LLM inference is represented as a suspendable graph node whose behavior depends on the substrate: streaming delivery online, durable retry asynchronously, and batched submission offline. We validated dozens of production agent configurations across five orchestration patterns: single-inference RAG, iterative ReAct, compositional PreAct, conditional routing, and multi-agent deep research. Across all three bindings, we found no detectable difference in output quality. Batch execution reduced per-query inference cost in line with published batch API pricing while operating alongside the streaming path at production scale. --- ### PAGR: Proof-Carrying Algebraic-Geometric Retrieval: A Quiver-, Provenance-, and Sheaf-Theoretic Framework for Grounded LLM Retrieval Authors: Xingting Wang, Min Wu Published: 2026-09-05 Categories: math.RT, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2609.06127v1 Retrieval-augmented generation is usually formulated as a statistical information-retrieval problem. Graph-based variants add relational structure, but the mathematical status of that structure is often left underspecified. Three distinct questions tend to be conflated: which statements are certified as knowledge, which latent representations are useful for retrieval, and which multi-hop compositions are semantically admissible. We propose Proof-Carrying Algebraic-Geometric Retrieval (PAGR), a framework that separates these questions mathematically. Its symbolic layer is a many-sorted relational theory generated by a typed quiver, path equations, and positive Horn inclusions. A quiver representation assigns inner-product spaces to entity types and linear operators to relations. A cellular sheaf measures local-to-global consistency. Semiring provenance records derivations and supports machine-checkable certificates. The central principle is epistemic separation: learned geometry may rank and organize evidence, but cannot promote a hypothesis to certified ground truth. We show the certification criterion is invariant under arbitrary replacement of learned components. Further results include a conditional completeness bound, identification of the isometry group as the relevant symmetry for residual-based retrieval, a cohomological consistency diagnostic, and a bounded-bisimulation index for admissible-path expansion. PAGR is a mathematical architecture for separating where a system should look from what it is allowed to treat as knowledge. --- ### CWF: A Collaborative Writing Framework for Personalized and Reliable Popular Science Writing Authors: Ruibiao Fu, Di Tang, Yunlong Yang, Ran Wang, Sicheng Lu, Peixuan Wu, Xiaoyu Fan, Jiacheng Ma, HaoZhe Luo, Yang Xiao Published: 2026-09-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.06126v1 We introduce Personalized and Reliable Popular Science Writing, a novel task that requires adapting scientific explanations to audiences with different cognitive levels while preserving factual accuracy. However, improving personalization often introduces simplifications that increase the risk of hallucination and factual distortion. To address these challenges, we first construct a dataset of 39,134 entries and a reader-centric Personalized Science Communication Benchmark (PSCB) that jointly evaluates audience adaptation and factual accuracy. To reduce data and computational requirements while improving generalization across domains and audiences, we introduce DA-MoE, which explicitly decouples audience adaptation from domain knowledge through separate modeling. To enable robust verification and revision in evidence-scarce scenarios, a multi-agent fact-checking mechanism that augments limited evidence with role-specific agent debate and propagates confidence over a graph is proposed. Experiments on PSCB show that our approach achieves state-of-the-art performance. Our code is open-sourced at https://github.com/DPInnovationWorks/CWF. --- ### SAP: State-Guided Data Synthesis with Argument Provenance for Multi-Turn Tool Use Authors: Zichen Tian, Jinpeng Chen, Cheng Gong, Suiyun Zhang, Rui Liu Published: 2026-09-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.06124v1 High-quality multi-turn tool-use data is essential for training agentic models, yet existing data synthesis methods often underrepresent the argument-level dependencies that are critical to long-horizon tool use. As a result, even when a model selects the correct tool, task execution may still fail because the model fills tool arguments with fabricated, stale, or weakly grounded values. To address this problem, we propose \textbf{State-Guided Data Synthesis with Argument Provenance (SAP)}. SAP combines state guidance, tool-argument provenance constraints, and turn-level validation to efficiently construct tool-use trajectories with long-range dependencies and high accuracy. Using data generated by SAP, we build SAP-4B, which is highly competitive even when compared with much larger models across multiple benchmarks. Source code, synthesized data, and trained weights are available at https://github.com/Zichen1024/SAP. --- ### STQA: A Benchmark for Stock-Focused Tabular Question Answering over Historical and Forecasted Data Authors: Baoxu An, Wenmian Yang, Zhensheng Wang, Weijia Jia Published: 2026-09-05 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.06117v1 Stock market analysis inherently requires composite reasoning over historical records and future projections, yet existing benchmarks remain fragmented across isolated tasks. We introduce STQA (Stock-focused Tabular Question Answering), an end-to-end benchmark designed to systematically evaluate natural-language question answering over historical data, numerical forecasts, and forecast-based reasoning. Built on a large-scale financial dataset, STQA covers 4,417 stocks and contains 31,400 question-answer pairs derived from expert-crafted templates, accompanied by fine-grained intent and slot annotations. To operationalize this benchmark, we present SQFRS (Stock Query-Forecast-Reasoning System), an agent-based unified framework that orchestrates SQL retrieval and time-series forecasting tools. Experiments demonstrate that while current large language models perform well on historical queries, forecast-based reasoning poses a substantial challenge, revealing critical bottlenecks in tool coordination and reasoning under uncertainty. The dataset and code are available at https://github.com/xuxubaobaoan/STQA_Project. STQA thus serves as a rigorous testbed for future research on trustworthy, tool-augmented financial agents. --- ### MM-SVGEdit: A Multimodal-Driven SVG Editing for UI Design Authors: Shibo Yang, Yuqing Gao, Zipeng Liu Published: 2026-09-05 Categories: cs.HC, cs.CV arXiv: https://arxiv.org/abs/2609.06116v1 In the field of UI design, Scalable Vector Graphics (SVG) is widely used as a design medium. However, traditional SVG editing techniques have high entry barriers and require cumbersome manual iteration, while LLM-based editing solutions suffer from low accuracy and poor user controllability. To address these issues, we propose MM-SVGEdit, a multimodal-driven SVG editing approach that integrates traditional SVG editing and LLM-based methods. We introduce a two-stage strategy in which visual grounding is followed by modification. Both stages support two interaction modalities: natural language instructions and direct manipulation (mouse and keyboard). We trained and evaluated MM-SVGEdit on a self-constructed dataset of 14,476 question-answer pairs generated from UIs, covering 11 types of editing operations on both single and multiple UI targets. The results show that MM-SVGEdit improves SVG editing accuracy, efficiency, and user-perceived control while reducing token consumption and response time. --- ### Sparse Incident-Cluster Learning for 12-hour Port Flood Pre-warning in Digital-Twin Analytics Authors: Jie Zhang, Qiang Ni, David Windridge, Huan X. Nguyen Published: 2026-09-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.06109v1 Port flood digital twins require analytics that warn operators before disruption, but official warning incidents are often few and adjacent observations are temporally dependent. Row-level classification can therefore overstate performance by placing windows from the same event in both model-development and evaluation data. We formulate 12-hour port flood pre-warning as an incident-cluster learning problem and evaluate a digital-twin analytics module using eight-point water-level histories, prediction-time contextual covariates, and interpretable short-window dynamics. The protocol combines fold-specific sparse feature selection, warning-cluster grouping, negative-label controls, 100-repeat random top-k controls, and alert-episode evaluation. Liverpool is the primary four-cluster case study, with harmonised Humber/Hull-proxy and Wessex South data used for protocol-transfer checks. Across the Liverpool folds, the top-10 ElasticNet model achieves mean F2 = 0.696, compared with 0.633 without top-k truncation and 0.681 for full-feature weighted XGBoost. It is the strongest ElasticNet variant, remains competitive with the nonlinear reference using only ten predictors, and exceeds the repeat-level 95th percentile of broad and same-family random subsets. Contextual covariates provide a strong prediction-time anchor, complemented by physically interpretable local dynamics. Historical replay converts risk scores into alert episodes and measures alert duration and false-episode burden. The result is an offline-evaluated analytics and validation module designed for integration into a port digital twin. --- ### From Two Passes to One: Compact and Efficient Target-Stance Extraction Authors: Ethan Mines, Bonnie Dorr Published: 2026-09-05 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.06108v1 Target-Stance Extraction (TSE) is the task of predicting both the target (or topic) of an author's writing and the author's stance toward it. Existing approaches to TSE use a sequential pipeline of two separate neural models: one to identify the target and another to determine the stance. We present a one-pass, joint architecture that predicts both in a single forward pass, reducing trainable parameters by nearly 50% with only a 4-7 F1 point tradeoff in performance. We further demonstrate that standard target-scrubbing practices artificially suppress target prediction accuracy. Retaining explicit target mentions, as in real-world deployments, improves F1 by at least 6 points across both target classification and target generation settings. These improvements allow for significantly easier integration of TSE in downstream applications such as public opinion tracking. --- ### DataFlex-RL: An Evaluation Platform for RLVR Data Policies Authors: Hao Liang, Mingrui Chen, Hengyi Feng, Meiyi Qiang, Wentao Zhang Published: 2026-09-05 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2609.06107v1 Data policies for reinforcement learning with verifiable rewards (RLVR) determine which rollouts are used, how strongly they are weighted, and which domains contribute to subsequent training batches. We introduce DataFlex-RL, an evaluation platform for comparing these choices under a common GRPO recipe. Our primary experiment evaluates 13 configurations across 12 matched seeds using Qwen2.5-7B-Base and 12 mathematics, logic, and science benchmarks. Uniform GRPO improves the domain-balanced average accuracy by 7.76 percentage points over the untrained checkpoint. None of the eight rollout-selection or reweighting methods achieves a paired 95% confidence interval that excludes zero relative to uniform sampling, and none of the three adaptive mixtures outperforms a fixed equal mixture at the same level of precision. A corrected 12-seed extension on Llama-3.1-8B-Base places the additional methods on the same score scale as the original controls, but does not reveal a consistent winner in terms of observed mean performance. We also quantify evaluation sensitivity by rescoring nine Qwen2.5-7B-Instruct runs using a math-heavy six-benchmark summary, consisting of five mathematics benchmarks and GPQA-Diamond but no logic benchmark, and comparing it with the domain-balanced 12-benchmark summary. The resulting rankings are negatively correlated, with a correlation coefficient of -0.33, whereas summaries that retain all 12 benchmarks largely agree. Across the controlled settings studied here, changing the data policy measurably changes the training process but does not produce a reproducible improvement over uniform training. --- ### FANS: Federated Adaptive Network Search Learning for Heterogeneous Devices Authors: Jiaxin Zhang, Xingwei Wang, Bo Yi, Liang Zhao, Alireza Furutanpey, Ziyi Chen, Qiang He, Keqin Li, Schahram Dustdar Published: 2026-09-05 Categories: cs.LG, cs.DC arXiv: https://arxiv.org/abs/2609.06106v1 Heterogeneous Federated Learning (HFL) aims to train models across devices with diverse resource budgets while preserving data privacy. Existing HFL methods typically bind training to a small predefined menu of model configurations, which limits architectural coverage. To address this bottleneck, we introduce Federated Adaptive Network Search (FANS), a hypernetwork-based framework that learns a shared architecture space rather than a fixed set of client models. To optimize this shared space efficiently, we propose the Federated Parallel Scaling (FPS) algorithm, which jointly trains multiple sampled subnetworks in parallel with self-distillation so that larger sampled subnetworks can supervise smaller ones during local updates. We evaluate FANS on CIFAR-10, CIFAR-100, and MNLI using ResNet-18, DenseNet-121, and BERT-base, respectively. Across all benchmarks, FANS expands the feasible subnetwork pool by orders of magnitude (e.g., 4,680 candidates for ResNet-18 vs. 4 in existing methods) and improves the average accuracy-efficiency trade-off relative to representative HFL baselines. Device heterogeneity is emulated through resource tiers, and evaluation covers accuracy, parameter count, and MACs. --- ### Programmable Cellular Automata Authors: Ahmed Khalifa, Muhammad Umair Nasir, Matthew Siper, Steve James, Julian Togelius Published: 2026-09-05 Categories: cs.NE, cs.AI, cs.FL, cs.LG arXiv: https://arxiv.org/abs/2609.06102v2 Cellular automata is a local computation paradigm where complex behavior can arise from local interactions between simple functions. This paradigm has been used to explain many systems such as biological processes, traffic simulation, computer networks, etc. In games, cellular automata have been used in games such as SimCity and for the generation of spatial content such as caves or dungeons. However, creating effective local rules is hard and unintuitive. Cellular automata can be effectively evolved, but may still be hard to interpret. In this work, we introduce the concept of programmable cellular automata, where we represent the system as Python code. We also modularize the cellular automata into local functions and a decision function. Local functions take a local neighborhood and return a value, while the decision function takes the output of the local functions and decides the value of the next state. Separating the cellular automata into modules written in Python helps with understanding how these systems are working. We also explore adding global functions where they take the whole state and compute a function from it. We tested generating levels for three different games from the PCG Benchmark. The results showed that global functions decrease the number of iterations that cellular automata need to solve a problem, and that we cannot find solutions for some problems with purely local functions. Looking into the generated functions, we can see common functions that have been used in different experiments, which not only helps us understand the generator but also helps us understand these games better and what is important for them. ---