# Research Papers — 2026-08 · bundle page 102 of 240 > Full-text markdown of papers #5051–5100 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/102 [← Previous bundle](https://aipod.dev/papers/archive/2026-08/page/101.md) [Next bundle →](https://aipod.dev/papers/archive/2026-08/page/103.md) ### Comparative Study of Out-of-the-Box Technology for Automatic Target Detection and Recognition Authors: Alma M. Liezenga, Lotte Nijskens, Henrik R. Baumann, Stefan Becker, Simon Bensberg, Niccolò Camarlinghi, Håvard R. Eiring, Alexander W. Johnsgaard, Tanel Liiv, Giuseppe Martino, Matteo Marturini, Matthias Rapp et al. Published: 2026-08-18 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.17917v1 Automatic Target Detection and Recognition (ATD/R) is critical for military decision support and (semi-)autonomous operations. Recent advances in object detection and artificial intelligence (AI) significantly boosted the potential performance of ATD/R. However, the scarcity of publicly available military datasets limits the application of these systems. As a solution, this paper explores the use of publicly available models and civilian datasets to achieve reasonable performance in military contexts. We benchmark several state-of-the-art models, including six iterations of the YOLO series and two variations on the DETR framework, on a newly acquired military relevant dataset. This dataset features military vehicles and challenging circumstances, including various degrees of occlusions and small targets. The out-of-the-box version of each model is validated alongside a version finetuned on the VisDrone dataset. This dataset features small objects, an Air-to-Ground (A2G) perspective and relevant classes, potentially generalizing to our military ATD/R task. We compare the performance of the models using mAP@0.5 and mAP@0.5:0.95, across A2G and Ground-to-Ground (G2G) perspective, target size and model size, giving insight into the real-time capabilities of models. Our main findings are: (1) bigger models outperform smaller models, (2) DETR-based models show promising results compared to the YOLO series,(3) fine-tuning models on an out-of-domain A2G dataset, improves their A2G performance and slightly improves their performance on small objects, but (4) all models still struggle with detecting small objects in an A2G scenario. We conclude that, despite recent advances in object detection, in-domain training is still crucial for creating capable ATD/R systems. --- ### Computational Prosopography across a Millennium: Mathematically Oriented Lineages Traced from the Fields Medalists Authors: Hiroyuki Chuma, Kanji Otsuka, Yoichi Sato Published: 2026-08-18 Categories: physics.soc-ph, cs.DL, cs.NE arXiv: https://arxiv.org/abs/2608.17915v1 We reconstruct the mentor--student network through which documented scholarly training passed across roughly nine centuries, and subject both the network and the means of reconstructing it to source criticism. From Wikidata, which aggregates the Mathematics Genealogy Project and the MacTutor Archive, we extract approximately 470,000 mentor--student assertions, yielding a directed acyclic graph of 372,853 persons. Using all 64 historical Fields Medalists as a fixed, ex ante tracer set, backward traversal enumerates some 25.5 million distinct paths reaching 57 generations. Three structural observations follow. Genealogical traffic through Leibniz forms an hourglass: thin upstream, 5.3 paths per node on average, and thick downstream, 53.4, a ratio near 10:1, with no counterpart at Newton, who lies on only four of the 64 lineages. Across a window centered on Leibniz, seven independently extracted predicate dimensions reorganize together, and recorded learned-society membership rises from 6.5 to 82.1 percent of the cohort. Upstream, 54 of the 64 lineages converge on the same five twelfth- and thirteenth-century Islamic and Byzantine scholars before terminating at an eleventh-century boundary we name the Monastery Wall. We argue that such observations cannot be assessed without tool criticism. The traversal engine is algebraically reversible, so every ranking decision it makes can be reconstructed afterward. We characterize its measurement bias in closed form, show that the macro-structures survive switching that bias off, and report the family of lineages the traversal returns at different resolutions rather than a single ranked list. --- ### Hybrid ML for Lightweight Pre-Route Delay Estimation in Open-Source IC Design Authors: Marvin Castro Castro, Erick Carvajal Barboza Published: 2026-08-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.17914v1 Static Timing Analysis (STA) is a critical step in the design flow of digital integrated circuits, however, obtaining accurate delay estimations can represent a challenge when limited information regarding physical design is available. In response, this work presents a hybrid and light-weight machine learning (ML) based approach that combines a decision tree with linear regression to improve pre-routing delay estimations generated by the open-source RTL-to-GDSII tool OpenLane. The proposed model achieves an 80\% reduction in error compared to OpenLane's estimates, demonstrates a 71\% improvement even without utilizing OpenLane-specific parameters. Overall, this method offers an alternative to traditional delay propagation techniques and more complex machine learning models that is not only accurate, but is also over 300 times smaller, 2 times faster and offers a higher explainability. --- ### CABLE: Extending the Reach of Memory Retrieval via Complementary Antecedent-Based Linking and Expansion Authors: Zheling Tan, Jin Gao, Dequan Wang Published: 2026-08-18 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.17911v1 As LLM agents operate across structured workflows and sessions, preserving long-term history does not ensure that later contexts can recover relevant evidence through a bounded memory interface. We study this evidence-reachability problem in long-term conversational memory, where retrieval still relies heavily on semantic similarity. This works well for topical recall, but it often misses earlier experiences, plans, or motivations that are semantically distant from the later events they help explain. Existing memory graphs provide cross-memory structure, yet links driven mainly by semantic overlap can duplicate what the host retriever already recovers. We argue that link construction should instead prioritize a sparse set of retriever-complementary associations. We present CABLE (Complementary Antecedent-Based Linking and Expansion), a plug-in augmentation that constructs links designed to extend the host retriever's direct semantic reach. For each new memory, CABLE generates antecedent-oriented queries, retrieves prior memories, subtracts candidates in the direct semantic neighborhood, and verifies the remainder before adding the accepted complementary associations into a sparse directed graph. At retrieval time, CABLE expands the host system's retrieved seeds along these links to surface implicit supporting evidence. We evaluate CABLE with A-MEM on LoCoMo and MA-LongMemEval, and further integrate it into SimpleMem and Mem0g on LoCoMo, using Qwen3.5-27B, DeepSeek-chat, and GPT-4o-mini. CABLE yields higher mean LLM-judge scores in every evaluated system-level setting, with the largest gains in categories where useful evidence is distributed across memories or sessions, including open-domain, multi-session, and preference-oriented questions. These results support prioritizing sparse, reasoning-relevant associations that complement rather than duplicate the host retriever. --- ### An RKHS Framework for Fixed Effects in Permanental Process Models Authors: Matthew LeDuc Published: 2026-08-18 Categories: math.ST, stat.ML arXiv: https://arxiv.org/abs/2608.17908v1 This short work describes an extension of the permanental process model which includes fixed effects. By starting with a prior on the fixed effects coefficients we show that, in the diffuse prior limit, the intensity function of the permanental process can be found using the representer theorem and naturally decomposed into a fixed effects term and a function which is an element of a Reproducing Kernel Hilbert Space (RKHS). We show that the limiting equivalent kernel defines an RKHS whose squared norm is exactly the limiting penalty. This allows for straightforward scientific interpretation of permanental process models and the easy incorporation of domain knowledge into the estimation process. --- ### AutoResearch: Insight In, Hallucination Out Authors: Xiang Liu, Qumeng Sun, Bruno, Xiao Zhang, Jiahao Li, Haoyang Zhang Published: 2026-08-18 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2608.17906v4 Autonomous research systems are increasingly capable of executing long research workflows, yet automation alone does not ensure that the resulting process remains scientifically grounded. We introduce AutoResearch, a two-stage system that connects Idea Generation with Idea Execution to address both how research ideas are formed and how they are reliably established through experimentation. In Idea Generation, AutoResearch continuously integrates emerging research signals with accumulated domain knowledge, identifies transferable mechanistic insights, and uses multi-model generation and cross-review to produce grounded, testable research plans. In Idea Execution, coordinated agents decompose these plans into experiments, iteratively implement and diagnose them, and employ independent evidence-based review before accepting research conclusions. Across representative settings in cross-modal retrieval, systems optimization, and benchmark-driven machine learning, AutoResearch turns generated ideas into measurable progress, detects and corrects unreliable experimental results, and makes evidence-conditioned decisions to continue, revise, or terminate research directions. For example, on RSICD benchmark, an AutoResearch-generated idea improves mean Recall from 32.84 to 34.69, while recording only 5 audit-confirmed issue events compared with 11-27 for other autonomous research systems. These results demonstrate a research process in which meaningful insight is grounded before experimentation and conclusions are grounded before acceptance: Insight In, Hallucination Out. --- ### AutoResearch: Insight In, Hallucination Out Authors: Yiming Ren, Xiang Liu, Qumeng Sun, Xiao Zhang, Jiahao Li, Haoyang Zhang, Junjie Wang Published: 2026-08-18 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2608.17906v1 Autonomous research systems are increasingly capable of executing long research workflows, yet automation alone does not ensure that the resulting process remains scientifically grounded. We introduce AutoResearch, a two-stage system that connects Idea Generation with Idea Execution to address both how research ideas are formed and how they are reliably established through experimentation. In Idea Generation, AutoResearch continuously integrates emerging research signals with accumulated domain knowledge, identifies transferable mechanistic insights, and uses multi-model generation and cross-review to produce grounded, testable research plans. In Idea Execution, coordinated agents decompose these plans into experiments, iteratively implement and diagnose them, and employ independent evidence-based review before accepting research conclusions. Across representative settings in cross-modal retrieval, systems optimization, and benchmark-driven machine learning, AutoResearch turns generated ideas into measurable progress, detects and corrects unreliable experimental results, and makes evidence-conditioned decisions to continue, revise, or terminate research directions. For example, on RSICD benchmark, an AutoResearch-generated idea improves mean Recall from 32.84 to 34.69, while recording only 5 audit-confirmed issue events compared with 11-27 for other autonomous research systems. These results demonstrate a research process in which meaningful insight is grounded before experimentation and conclusions are grounded before acceptance: Insight In, Hallucination Out. --- ### Dynamic Compression in Recurrent Networks Authors: Jyothish Pari, Ryan Bahlous-Boldi, Pulkit Agrawal Published: 2026-08-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.17896v1 Recurrent models process long contexts efficiently by compressing their history into a fixed-size state, but modern architectures typically do so in a single causal pass over the sequence. Each input must therefore be compressed before the model knows how it will later be used, forcing a limited state to compromise across possible future demands. We introduce dynamic compression, which allows a recurrent model to selectively revisit past tokens and revise its fixed-size state through additional recurrent updates. The model need not preserve every part of the history at uniformly high fidelity in its recurrent state, because lower-fidelity information can be revisited from the retained raw sequence when it becomes relevant. We study this in a controlled setting where the model first learns multiple functions in-context and, later in the same sequence, encounters a series of few-shot tasks that each require it to identify and reuse one of those functions. A single-pass model must preserve every function at sufficient fidelity for any future task, whereas selective re-scanning allows the model to revisit and refine only the function currently needed. We find that dynamic compression substantially reduces the recurrent state required for accurate reuse and scales more favorably as the number of stored functions grows. These results demonstrate a computation--memory tradeoff in which recurrent models can spend more computation revisiting their history to make more effective use of a fixed-size state. --- ### BEAR-Bench: A Bilingual Enterprise and Academic Reasoning Benchmark for Multimodal Models Authors: Liubov Chubarova, Alexandra Kuleshova, Daniil Volkov, Kirill Sultanov, Alexey Zaytsev Published: 2026-08-18 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.17895v1 While Multimodal Large Language Models (MLLMs) have made significant strides in visual comprehension, their ability to reason about text-dense, professional documents remains incompletely evaluated. Existing benchmarks emphasize information extraction, require external domain knowledge, or cover professional documents only as one of many settings. They are also largely English- or Chinese-centric, leaving other languages and Russian, in particular, substantially underrepresented. To address these limitations, we introduce BEAR-Bench (Bilingual Enterprise and Academic Reasoning), a self-contained, complex English-and-Russian benchmark comprising 1000 human-annotated questions based on text-rich business and scientific documents. We evaluate 16 proprietary and open-weight MLLMs, including Gemini 3.1 Pro and Qwen3.5-397B, on BEAR-Bench and observe clear headroom even for the strongest systems. Finally, we use the resulting model outputs to compare existing hallucination detection methods, evaluating not only how often models fail on BEAR-Bench but also how reliably those failures can be identified. --- ### A Residual Learning Approach for Unsteady Aerodynamic Load Prediction Authors: Divya Sanghi, Carlos E. S. Cesnik Published: 2026-08-18 Categories: physics.flu-dyn, cs.LG arXiv: https://arxiv.org/abs/2608.17894v1 This paper investigates the feasibility of using residual learning to improve unsteady aerodynamic load prediction for aeroelastic applications. The machine learning technique selected for the study is the long short-term memory (LSTM) neural network, which is used for its suitability for sequential data with aerodynamic memory effects. The approach is investigated for the NLR 7301 airfoil benchmark using high-fidelity CFD lift data for prescribed pitch and plunge motions in the transonic flow regime in the presence of shock motion. An analytical unsteady aerodynamic model based on the Wagner function is used as a physics-based baseline, and the neural network is trained to learn the difference between the CFD lift coefficient and the Wagner prediction. The residual model is compared with a direct neural-network model trained to predict the CFD lift coefficient. The comparison includes feature and normalization studies, external benchmark cases, and leave-one-out and leave-family-out generalization tests across a range of sinusoidal and non-sinusoidal motions. The residual model performs best when its inputs align with the Wagner formulation variables, generally giving lower error and more consistent performance across training runs, though the direct model remains more accurate for some high-frequency cases. The residual model also generalizes better in the leave-one-out and leave-family-out tests, with a smaller increase in error than the direct model when entire motion families are withheld from training. Overall, the results indicate that residual learning shows promise as a modular approach for augmenting classical low-order aerodynamic theories, especially when the physics baseline removes a structured part of the aerodynamic response and leaves a lower-variance correction for the neural network to learn. --- ### VisDocAgentBench: Benchmarking Agents for Visually Rich Document Retrieval Authors: Lexiang Hu, Yanzhao Zhang, Mingxin Li, Dingkun Long, Yikang Li, Fuwei Zhang, Yisen Wang, Zhouchen Lin Published: 2026-08-18 Categories: cs.IR, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2608.17889v1 Visually rich documents encode relevance through language, layout, structured visual elements, and corpus context, yet retrieval is typically evaluated by one-shot query--page matching. Agentic-search benchmarks usually score downstream question answering or report generation, leaving document ranking under iterative evidence acquisition underexplored. We introduce VisDocAgentBench, a closed-corpus benchmark comparing static and agentic retrieval under a shared ranked-output contract. It contains 2,375 pages from 100 documents and 120 unique-target queries balanced across direct, one-bridge, and two-bridge evidence structures. Relation-preserving construction yields semantic, relational, and visual queries, followed by full-document review and hard-negative validation. A strong late-interaction visual retriever reaches 97.50% Recall@1 on direct items but 2.50% on two-bridge items, exposing the limits of query--target matching when relevance depends on corpus context. Agents recover much of this loss, but planner choice and retrieval representation remain decisive. Every planner performs better with visual retrieval, whose best R@1 reaches 67.50% versus 37.50% for OCR-text. Ablations identify iterative search and page inspection as consequential capabilities, and providing the complete support context improves ranking on both routes. Trace analysis localizes the remaining losses to target discovery, candidate examination, and evidence-role integration. These findings motivate retrieval agents that combine modality-preserving discovery with evidence-directed verification. --- ### CFB-GBM v2.0: An Augmented Longitudinal Dataset for Multi-Modal Glioblastoma Segmentation, Radiomics, and RANO Progression Tracking Authors: Alexandre G. Leclercq, Noémie N. Moreau, Hugo Audebert, Andros Nassar, Thomas Cochin, Thomas Leleu, Loïc Le Henaff, Alexis Desmonts, Yoann Poirier, Aurélie Dubru, Laura Guillemette, Pascal Lecoeur et al. Published: 2026-08-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.17884v1 Glioblastoma (GBM) is the most aggressive primary brain tumor in adults, with a median overall survival of 15 months. Longitudinal, multi-modal imaging datasets with comprehensive clinical and treatment data are essential to support the development of reproducible computational methods for treatment response prediction, disease progression modelling, and personalized medicine. We present CFB-GBM v2.0, an extension of our previously released CFB-GBM dataset comprising 264 GBM patients treated according to the standard Stupp protocol. The primary contribution of this release is the completion of Gross Tumour Volume (GTV) delineations across all available timepoints ($t_0$, $t_1$ and $t_2$), increasing the overall GTV completion rate from 35% to 97%. This was achieved using a nnU-Net model pre-trained on BraTS 2021 and fine-tuned on CFB-GBM ground-truth contours, with the generated segmentations validated by five radiation oncologists. From these longitudinal GTV annotations, volumetric RANO 2.0 response category labels were derived for all available temporality pairs ($t_0 \rightarrow t_1$, $t_0 \rightarrow t_2$ and $t_1 \rightarrow t_2$). To further ease dataset usability and reproducibility, brain masks computed with HD-BET and pre-computed radiomic features extracted with PyRadiomics are provided for each patient timepoint and MRI modality. Additionally, the WHO classification guideline (2016 vs. 2021) applicable to each patient's diagnosis is now explicitly documented. CFB-GBM v2.0 is publicly available on The Cancer Imaging Archive (TCIA) at https://www.cancerimagingarchive.net/collection/cfb-gbm . --- ### Improving Complex Moiré Removal with Generative Supervision Authors: Xinyang Gu, Zhilu Zhang, Honglei Xu, Yanting Mei, Yukang Ding, Wangmeng Zuo Published: 2026-08-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.17883v1 The availability of high-quality paired data is essential for training learning-based image demoiréing models. However, it remains challenging for existing datasets to encompass the complex moiré patterns captured in uncontrolled real-world scenarios. Such degradations typically manifest as large-scale, multicolored moiré patterns. Moreover, these patterns frequently occur in images for which clean counterparts are difficult to obtain, such as photographs acquired from public displays or existing online resources. In this work, we propose a novel data engine designed to improve the removal of complex moiré patterns by generating training supervision. Specifically, we initially collect real-world images containing complex moiré patterns and localize the corresponding screen regions. Multiple image-conditioned generative foundation models are subsequently deployed to produce candidate references. To establish reliable supervision, these candidates are subjected to patch-level quality control to filter and select the optimal results. Based on this systematic paradigm, we construct the WildMoiré dataset, which contains 6.8K moiré-GT training pairs. For evaluation, we additionally build an independent test set comprising $\sim$250 pairs with captured clean ground truth. Extensive experiments on ESDNet, SDXL, and Qwen-Image-Edit demonstrate that the proposed generative supervision consistently improves the performance of complex moiré removal. --- ### DistillPath: An Efficient 22M Distilled Pathology Encoder Approaching Large Foundation Model Performance Authors: Ramon Kaspar, Andrey Ignatov, Valentina Boeva Published: 2026-08-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.17872v1 Many high-performing pathology tile encoders are now foundation models with hundreds of millions to over a billion parameters. Encoding and storing the thousands of tiles in each whole-slide image with such models is costly on commodity hardware, so compact encoders that retain useful downstream performance are a valuable alternative. We present DistillPath-KS16, which starts from the existing 22M kaiko ViT-S/16 encoder and improves it by distilling from released pathology encoders used as frozen teachers. The recipe reads only the teachers' final class and patch tokens and trains on 6,000 public slides, needing neither their DINO nor iBOT pretraining heads nor a billion-tile corpus, so it applies to any released encoder that exposes backbone tokens. We distill four teachers spanning 86M to 1.1B parameters into the same student. Every variant improves the kaiko baseline on all three benchmarks we use, EVA, HEST, and PLISM, and the strongest teacher is task-dependent. On the seven-task EVA mean, DistillPath-KS16-Virchow2 reaches $0.795$, within $0.015$ points of Virchow2, the top-scoring model in our evaluation, at about $29\times$ fewer parameters; it also scores above H0-mini and GPFM on this aggregate metric, though that advantage is task-concentrated rather than uniform. Because it remains a 22M ViT-S/16 with 384-dimensional features, DistillPath-KS16 runs more than $25\times$ faster than Virchow2. Code is available at https://github.com/RamonKaspar/DistillPath, and released model weights are available at https://huggingface.co/collections/RamonK/distillpath. --- ### BayesPrompt: human readable prompts that make sense Authors: Franky Kevin Nando Tezoh, Ali Hussaini Umar, Alessandro Laio, Guido Sanguinetti, Riccardo Rende Published: 2026-08-18 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.17866v1 Reconstructing prompts that can elicit a desired answer or behaviour in an LLM is an open and important research topic. Optimisation methods which aim at minimising the perplexity of a given answer, however, consistently yield so-called pseudoprompts, unintelligible strings of tokens which can lack human interpretability. We argue that this is a consequence of the ill-posedness of the prompt optimisation task. By reframing the task as a Bayesian posterior inference over prompts, we propose an efficient algorithm to sample prompts which are both efficient (in terms of perplexity) and human readable. We compare our approach with state of the art alternatives showing on a real data set a marked improvement over a range of metrics. --- ### ARASH: Adaptive Retrieval And Shot Selection for Tabular Prediction Authors: Samirasadat Jamalidinan, Yue Xu, Kazem Cheshmi Published: 2026-08-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.17856v1 Tabular prediction is a critical task across numerous applications. The recent success of large language models has sparked various approaches for adapting them to the tabular domain. A prevalent strategy involves training or fine-tuning specialized Tabular Foundation Models (TFMs) such as TabPFN. However, TFMs require substantial computational resources, and frequent model retraining is often impractical. In-context learning (ICL), specifically, few-shot prompting, offers a resource-efficient alternative to enhance performance. Yet, identifying the most relevant rows to serve as shots remains a challenge for tabular data. This paper introduces ARASH (Adaptive, query-specific Retrieval And Shot selection), a method that improves TFM efficiency by selecting optimal shots based on local neighborhood analysis within the training set. Our results demonstrate that ARASH reduces the prompt length and memory usage of TabPFN by 1261.5$\times$ and 2.56$\times$, respectively, while providing comparable accuracy. --- ### Efficient Resource Optimization for Split Federated Learning Authors: Wei Wei, Xianhao Chen Published: 2026-08-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.17849v1 Split federated learning (SFL) has emerged as a powerful paradigm for model training at the edge. However, SFL inherently involves discrete decision variables for model splitting and resource allocation, resulting in a challenging mixed-integer problem. Consequently, prior optimization schemes for SFL are either \textit{heuristic} or \textit{computationally inefficient}, which cannot handle large-scale user populations. To address this limitation, this work establishes an efficient optimization framework for SFL under resource-constrained networks. Our framework jointly optimizes model splitting and resource allocation to minimize training cost, which is defined as the weighted sum of latency and energy costs. We first study the model splitting problem and develop a polynomial-time algorithm that achieves the global optimum. Then, we extend the approach to the joint model splitting and resource allocation problem. In this case, we formulate it as a two-dimensional master problem and develop an efficient approximation method with a $(1+ε)$-approximation guarantee. Extensive experiments show that the proposed approach provides efficient solutions to strike the optimal energy--latency tradeoff. --- ### MoRAX: Mobility-based Representation Augmentation for Geospatial Foundation Models Authors: Ya Wen, Jixuan Cai, Yulun Zhou, Alec Kirkley Published: 2026-08-18 Categories: cs.LG, cs.SI arXiv: https://arxiv.org/abs/2608.17848v1 Geospatial Foundation Models (GFMs) are emerging as a powerful paradigm for learning semantically rich and geographically consistent visual and physical representations. However, their reliance on Earth-observation (EO) data leaves information about human activity largely underrepresented. Human mobility data reveals the functional and relational structure between regions that is missing from EO data, but is often limited only to the city where it is observed, making it challenging to use for transferable urban representation learning. We introduce MoRAX, a lightweight framework for augmenting geospatial embeddings with functional structure derived from human mobility. MoRAX preserves the coverage and consistency of a GFM while providing information about the functional connectivity among urban regions, permitting zero-shot deployment in unseen cities with or without available mobility data. Across four target cities spanning two countries, the MoRAX teacher model, which observes mobility, consistently outperforms GFMs and strong urban representation baselines in eight socioeconomic and environmental prediction tasks. Meanwhile, the student model, which never takes mobility data as input, approaches the teacher in performance on most tasks. Transfer results across countries further demonstrate that modulation conditioned on mobility flows provides a general mechanism for grounding geospatial foundations in the human dimension of cities. --- ### Encoded but Not Actionable: Auditing the Decode-Generate-Steer Gap in Frozen LLMs for Geometric Constraints Authors: Man Liang, Xinzhao Cheng, Faizan Wajid Published: 2026-08-18 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.17843v1 Large language models (LLMs) have demonstrated strong performance on structured reasoning tasks, but what they encode and whether it informs model behavior remain unclear. We investigate this question through geometric reasoning, using parametric CAD constraints as a controlled testbed for separating local pairwise relations from sketch-level constraint status. By probing the hidden states of six frozen decoder-only LLMs, we examine four properties: linear decodability, forced-choice generation, activation-level influence, and behavioral steerability. Pretraining substantially improves the decoding of local geometric relations, and this advantage persists after accounting for positional cues with shuffled-order controls. In contrast, sketch-level DOF status is already highly decodable from randomly initialized representations and improves only modestly with pretraining, indicating that much of its probe performance is available without learned weights. Further analyses show that decodable information is not always actionable. Generation often fails to express this information, and on the two intervention-tested backbones, activation-restoration effects at the patched entity position vanish while decodability persists across depth. Mean-difference steering also does not reliably control outputs. These results show that decodability, generation, activation-level influence, and steerability can diverge in the tested setting. The audit provides a controlled way to distinguish failures to encode geometric structure from failures to express or control encoded information. --- ### Toward the Optimal Regret-Instability Trade-off in Multi-Armed Bandits Authors: Kaifei Wang, Yinyu Ye, Han Zhong Published: 2026-08-18 Categories: stat.ML, cs.LG, math.OC, math.ST arXiv: https://arxiv.org/abs/2608.17841v1 Multi-armed bandit algorithms are evaluated by regret, yet comparable regret can coexist with different allocations across independent runs. We study the trade-off between worst-case regret $\mathcal{R}_{K,T}$ and instability $\mathcal S_{K,T}$, defined as the largest standard deviation of a terminal pull count, for $K$ arms and $T$ rounds. We prove the finite-time lower bound $\mathcal R_{K,T}\mathcal S_{K,T}\ge C T^{3/2}$, where $C$ is independent of $K$ and $T$, under a finite-time regret condition and without the regularity assumptions imposed in the prior asymptotic analysis. We also introduce Stabilized Lower-Envelope UCB (\textup{\textsc{SLE-UCB}}), a new tunable algorithm combining a running lower-envelope index with a decreasing pull-count stabilizer. \textup{\textsc{SLE-UCB}} satisfies $\mathcal R_{K,T}\mathcal S_{K,T}=O(T^{3/2}\log K)$, with an implicit constant independent of $K$ and $T$, matching the lower bound exactly in $T$ and within a logarithmic factor in $K$. To prove the instability bound, we develop a new offline top-prefix representation that removes path dependence from online decisions. Together with single-reward perturbations and the Efron--Stein inequality, this representation controls pull-count variance. Thus, regret and instability depend reciprocally on $K$, while their product has no polynomial dependence on $K$. These results resolve the open question raised in the literature concerning the sharp arm-dependent regret--instability frontier. --- ### Leveraging Association Context Retrieval in Knowledge Edit- ing to Build White-Box Attacks on LLMs Authors: Roman Maksimov, Vladimir Aletov, Vladimir Solodkin, Dmitry Bylinkin, Daniil Medyakov, Aleksandr Beznosikov Published: 2026-08-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.17836v1 As large language models (LLMs) are granted increasing autonomy, it is essential to investigate methods that can induce unsafe behavior. We propose a novel white-box attack inspired by locate-then-edit approaches from the field of Knowledge Editing. Our choice is motivated by the observation that models edited with such schemes tend to assign unusually high prediction probabilities to the edit target, a property that is particularly advantageous when designing attacks. We modify the editing framework by incorporating as- sociative knowledge retrieved from the model, thereby extending constraint removal to an entire thematic category rather than being limited to prompts from a predefined dataset. Experiments with various archi- tectures demonstrate improved attack effectiveness over competing methods without dealing critical damage to general model performance. --- ### AdaLens: Interactive Storyline for Monitoring and Steering Long-Running Agentic Data Analysis Authors: Yangtian Liu, Yan Miao, Shuhan Liu, Yunfan Zhou, Dae Hyun Kim, Di Weng, Yingcai Wu Published: 2026-08-18 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2608.17834v1 Large language models are pushing data science toward increasingly autonomous and agentic workflows, with recent systems already supporting multi-step and long-running analyses. As these workflows become more autonomous, conventional interfaces no longer provide adequate support for two critical requirements: observability for understanding an agent's evolving reasoning and evidence, and steerability for redirecting low-value directions or deepening promising ones during execution. Existing interactive approaches improve process visibility and open intervention points, but they remain largely designed for discrete, turn-by-turn exchanges rather than the parallel branches and evolving decision structures of long-running agentic analysis. We study this need as interactive oversight in long-running agentic data analysis and present AdaLens, an interactive system for monitoring and steering ongoing runs. AdaLens combines a storyline-based representation that unifies analytical plans, execution progress, intermediate findings, and data-column involvement with steering interactions grounded in these analytical elements for directional guidance and execution control. We evaluate AdaLens through two case studies and a user study, examining how it supports analysts in monitoring and steering long-running agentic data analysis. --- ### GenRec: Knowing Where to Reconstruct and Where to Generate Authors: Ata Çelen, Jaewoo Jung, Federico Tombari, Marc Pollefeys, Sunghwan Hong, Michael Niemeyer, Daniel Barath Published: 2026-08-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.17832v2 Generative novel view synthesis from sparse input images is rarely all reconstruction or all generation: pixels visible in some source view have a unique correct value modulated only by view-dependent shading, while pixels in disocclusions or beyond the captured volume admit a distribution of plausible completions. Existing generative novel-view-synthesis methods conflate these regimes under a single uniform loss, blurring the line between geometric fidelity and creative hallucinations even when scene geometry is injected through warped point clouds or projected depth. We introduce GenRec, a multi-view flow matching model that builds the reconstruction--generation split directly into its architecture, supervision, and gradient flow. Guided by an observation mask derived from the source cameras and a monocular depth estimator, a flow matching backbone jointly denoises RGB and scene-coordinate maps across all target views, while a pixel-space refinement stage restores high-frequency detail on observed pixels; the same mask gates supervision so regression signals do not contaminate the generative prior. Across RealEstate10K, DL3DV-10K, and Mip-NeRF~360, in both single-view extrapolation and two-view interpolation, GenRec attains the best reconstruction fidelity in observed regions while also surpassing purely generative baselines on perceptual quality in unobserved ones, showing the effectiveness of our approach. --- ### GenRec: Knowing Where to Reconstruct and Where to Generate Authors: Ata Çelen, Jaewoo Jung, Federico Tombari, Marc Pollefeys, Sunghwan Hong, Michael Niemeyer, Daniel Barath Published: 2026-08-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.17832v1 Generative novel view synthesis from sparse input images is rarely all reconstruction or all generation: pixels visible in some source view have a unique correct value modulated only by view-dependent shading, while pixels in disocclusions or beyond the captured volume admit a distribution of plausible completions. Existing generative novel-view-synthesis methods conflate these regimes under a single uniform loss, blurring the line between geometric fidelity and creative hallucinations even when scene geometry is injected through warped point clouds or projected depth. We introduce GenRec, a multi-view flow matching model that builds the reconstruction--generation split directly into its architecture, supervision, and gradient flow. Guided by an observation mask derived from the source cameras and a monocular depth estimator, a flow matching backbone jointly denoises RGB and scene-coordinate maps across all target views, while a pixel-space refinement stage restores high-frequency detail on observed pixels; the same mask gates supervision so regression signals do not contaminate the generative prior. Across RealEstate10K, DL3DV-10K, and Mip-NeRF~360, in both single-view extrapolation and two-view interpolation, GenRec attains the best reconstruction fidelity in observed regions while also surpassing purely generative baselines on perceptual quality in unobserved ones, showing the effectiveness of our approach. --- ### The Model's Tell: Measuring Context-Leakage Attack Signals with Behavior Gauges Authors: Maosen Zhang, Jianshuo Dong, Boting Lu, Wenyue Li, Xiaoping Zhang, Tianwei Zhang, Jie Zhang, Han Qiu Published: 2026-08-18 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2608.17829v1 LLMs increasingly rely on external contexts, such as pre-defined system prompts or retrieved documents, to improve generation quality. However, processing these contexts alongside user queries creates an attack surface: adversarial inputs can induce models to disclose them. Prior probing studies suggest that leakage-related signals emerge in hidden states, yet the need to extract these states poses additional deployment challenges. In this paper, we explore whether this internal signal leaves a more accessible ``tell'' before decoding. We propose LeakGauge, which probes this response by appending a suffix that gauges leakage behavior and mapping its prefill token probabilities to an attack-risk score. While a direct gauge uses the initial tokens of confidential content, we find that a content-agnostic one that verbalizes leakage behavior yields more robust signals. Across 11 LLMs, including GLM-5.2 (753B) and Kimi-K3 (2.8T), LeakGauge reaches an AUROC range of 0.944--0.996 on unseen attacks. The signal remains stable when the content changes language or the attack shifts from verbatim to semantic disclosure. By activation-steering interventions, we further show that the risk score is sensitive to an internal leakage-related direction, relating the observable signal to the model's internal representation. In addition, LeakGauge enables an input detector with fewer than 0.5K extra parameters and added latency of 10.34 ms. Code: \href{https://github.com/yeasen-z/LeakGauge}. --- ### From Global Benchmarks to Local Evaluations: Benchmarking LLMs for the German Public Sector Authors: Camilla Dalerci, Thilo Michael, Robin Schaefer, Daniel Weinland Published: 2026-08-18 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.17827v1 Public institutions face a persistent challenge in selecting LLMs suited to their specific context. Existing benchmarks, however, are of limited use as they primarily reflect English-language and US-centric settings, and often only evaluate task performance. In this paper, we present first results of MÖVE, a holistic evaluation framework for the German public sector, examining three rarely considered governance dimensions: energy consumption, provider transparency, and knowledge of German-party positions. Our results reveal significant trade-offs, with no single model excelling across all dimensions: estimated energy consumption varies more than 60-fold and is not explained by model size alone, information disclosure varies systematically across providers, and European models do not exhibit stronger knowledge of German party positions. Model selection for public institutions thus cannot rely on performance rankings alone. Instead, evaluations should also reflect the governance requirements of the deployment context. --- ### MotoSafety: Edge-AI with Learned Temporal Importance for Two-Wheeler Collision Risk Assessment Under Time Pressure Authors: Sumit S. Shevtekar, Chandresh K. Maurya, Gourab Sil, Subasish Das Published: 2026-08-18 Categories: cs.LG, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2608.17823v3 Powered two-wheeler riders face critical safety challenges in low- and middle-income countries, yet limited studies exist on how cognitive stressors such as Time Pressure influence collision risk. We address this gap by introducing a comprehensive dataset consisting of over 129,000 labeled multivariate time-series feature windows, gathered across 153 simulator rides from 51 participants under No, Low, and High TP scenarios. Across each sequence, we capture 64 distinct attributes covering vehicle motion, rider control actions, spatial proximity, and rule compliance indicators. Using this dataset, we introduce MotoSafety, a new edge-AI framework built on the Learned Temporal Importance (LTI) concept. MotoSafety achieves 94.97% accuracy and 99.33% ROC AUC, outperforming ten baselines, including TimesNet and LLM4TS, and achieves 0.039 MSE and 0.094 MAE for forecasting (4.4x lower error than Time-LLM and iTransformer). With only 1.15M parameters and 0.135 ms latency, it is suitable for edge deployment on low-cost CPU hardware. Using ground truth TP as an inductive bias improves accuracy from 94.09% to 94.97%, while predicted TP achieves 94.82%. Using only 21 IMU+GPS features, it achieves 93.91% accuracy, indicating practical deployment. Beyond PTW safety, the architecture shows better transferability to human activity (97.66%) and clinical (99.65%) domains. This lightweight framework advances PTW collision risk assessment, supporting the Safe System Approach for Intelligent Transportation Systems. --- ### MotoSafety: Edge-AI with Learned Temporal Importance for Two-Wheeler Collision Risk Assessment Under Time Pressure Authors: Sumit S. Shevtekar, Chandresh K. Maurya, Gourab Sil, Subasish Das Published: 2026-08-18 Categories: cs.LG, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2608.17823v1 Powered two-wheeler riders face critical safety challenges in low- and middle-income countries, yet limited studies exist on how cognitive stressors such as Time Pressure influence collision risk. To address this gap, we introduce a large-scale dataset of over 129,000 labeled multivariate time-series sequences from 153 simulator rides by 51 participants under No, Low, and High TP, capturing 64 features across vehicle dynamics, control inputs, proximity, and behavioral violations. Building on this dataset, we propose MotoSafety, a novel edge-AI architecture grounded in the Learned Temporal Importance principle. MotoSafety achieves 94.97% accuracy and 99.33% ROC AUC, outperforming ten baselines, including TimesNet and LLM4TS, and achieves 0.039 MSE and 0.094 MAE for forecasting (4.4x lower error than Time-LLM and iTransformer). With only 1.15M parameters and 0.135 ms latency, it is suitable for edge deployment on low-cost CPU hardware. Using ground truth TP as an inductive bias improves accuracy from 94.09% to 94.97%, while predicted TP achieves 94.82%. Using only 21 IMU+GPS features, it achieves 93.91% accuracy, indicating practical deployment. Beyond PTW safety, the architecture shows better transferability to human activity (97.66%) and clinical (99.65%) domains. This lightweight framework advances PTW collision risk assessment, supporting the Safe System Approach for Intelligent Transportation Systems. --- ### Spatially explicit feature importance for building height estimation using research-access high-resolution SAR and optical sensors Authors: Guilherme Iablonovski, Pierre-Louis Frison, Tatiana Silva da Silva Published: 2026-08-18 Categories: physics.soc-ph, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2608.17822v1 Accurate building height information at the individual footprint scale is essential for material stock accounting and post-disaster damage assessments yet remains difficult to obtain at city scale in the Global South where airborne LiDAR coverage is rare and commercial very high-resolution imagery is cost-prohibitive or unavailable. While recent works have demonstrated building height estimation using freely available Sentinel imagery, the resolution ceiling of resulting products is still coarse for material stock analysis. This study incorporates products derived from data freely accessible under scientific research licenses, TerraSAR-X StripMap and PlanetScope, alongside Sentinel-1 to predict building heights in a large city in Brazil. To account for the spatial autocorrelation in the training set, features from all sources are integrated in a geographically weighted random forest model, returning an RMSE of 5.34 m and R2 of 0.756 against a LiDAR reference dataset. Local feature importance showed predictor dominance to vary consistently across intra-urban contexts, with footprint geometry dominating for low-rise buildings, shadow-derived height for taller and more isolated structures, and spectral reflectance for the tallest buildings in the set. Sentinel-1 backscatter and InSAR occupy complementary spatial niches, with no single sensor uniformly preferable across the set. Results provide optioneering guidance and insight over satellite-derived products predictive relevance in distinct contexts, which global machine learning or neural network models cannot offer. --- ### Interpretable Humans, Alien LLMs: Expert Analysis of Latent Structures in Assessment Responses Authors: Alona Strugatski, Licol Zeinfeld, Jason Cooper, Shelley Rap, Gil Schwarts, Giora Alexandron Published: 2026-08-18 Categories: cs.CL, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2608.17810v1 The evaluation of large language models (LLMs) relies heavily on human-designed assessments, implicitly assuming that AI and humans employ similar underlying cognitive constructs. Challenging this assumption, we investigate whether the latent factors governing LLM performance carry the same substantive, human-interpretable meaning as the cognitive constructs governing human learners. Using responses from humans and six LLMs across quantitative reasoning and chemistry assessments, we conducted Exploratory Factor Analysis (EFA) separately for both groups. Subject-Matter Experts (SMEs) then blindly evaluated the resulting factor graphs to ascribe pedagogical meaning to the emerged constructs. SMEs successfully interpreted most of the human-derived factors. Conversely, they could not ascribe meaning to any LLM-derived factors in quantitative reasoning and interpreted only half of the LLM factors in chemistry. By combining data-driven EFA with blind expert interpretation, this framework shows that LLMs frequently operate on statistically opaque mechanisms distinct from human reasoning. --- ### Whether LLMs Can Navigate Beliefs and Facts Depends on How You Phrase It Authors: Quang Minh Nguyen, Luis Frentzen Salim Published: 2026-08-18 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.17809v2 Humans naturally form and express beliefs in daily communication, e.g., "I think the answer is 3" or "I suppose that's right." Such beliefs inevitably intertwine with fact and knowledge, making the ability to handle them in tandem desirable for large language models (LLMs), as they are increasingly deployed in user-facing settings. Prior work showed that even capable LLMs exhibit a systemic weakness in acknowledging user beliefs grounded in incorrect information. We extend this evaluation to 10 LLMs across 18 epistemic expressions and find that the size and direction of this weakness depend on the verb used to express the belief, with the accuracy gap between factual and false information ranging from +50% on "I vaguely remember" to -14% on "I seriously doubt". We further show that the phenomenon stems from what we call task confusion: models default to fact-checking the underlying claim, overriding the user's stated belief. We provide evidence where chains of thought that explicitly fact-check show lower accuracy on false information than those that do not, and a single instruction can reverse the failure across verb families. Mechanistically, models attend more to false beliefs they fail to confirm, but suppressing this attention at decoding time recovers accuracy only partially and only in some models, calling for future work on intervention methods. Our findings clarify prior results and show how fact-checking, a generally desirable behavior, can interfere with belief tracking in LLMs. --- ### Whether LLMs Can Navigate Beliefs and Facts Depends on How You Phrase It Authors: Quang Minh Nguyen, Luis Frentzen Salim Published: 2026-08-18 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.17809v1 Humans naturally form and express beliefs in daily communication, e.g., "I think the answer is 3" or "I suppose that's right." Such beliefs inevitably intertwine with fact and knowledge, making the ability to handle them in tandem desirable for large language models (LLMs), as they are increasingly deployed in user-facing settings. Prior work showed that even capable LLMs exhibit a systemic weakness in acknowledging user beliefs grounded in incorrect information. We extend this evaluation to 10 LLMs across 18 epistemic expressions and find that the size and direction of the weakness depend on the verb used to express the belief, with the accuracy gap between factual and false information ranging from +50% on "I vaguely remember" to -14% on "I seriously doubt". We further show that the phenomenon stems from task confusion: models default to fact-checking the underlying claim, overriding the user's stated belief; chains of thought that explicitly fact-check show lower accuracy on false information than those that do not; and a single instruction can reverse the failure across verb families. Mechanistically, models attend more to false beliefs they fail to confirm, but suppressing this attention at decoding time recovers accuracy only partially and only in some models, calling for future work on intervention methods. Our findings clarify prior results and show how fact-checking, a generally desirable behavior, can interfere with belief tracking in LLMs. Our code is available at https://github.com/ngqm/belief-fact-phrasing. --- ### Optically Writable Atomic Vapor Memory as a Substrate for Optical Reservoir Computing Authors: Elizabeth Robertson, Mingwei Yang, Lina Jaurigue, Guillermo Gallego, Kathy Lüdge, Janik Wolters Published: 2026-08-18 Categories: physics.atom-ph, cs.NE arXiv: https://arxiv.org/abs/2608.17807v1 We present an optical random access memory (ORAM) based on warm cesium (Cs) atomic vapor and demonstrate its operation as the physical substrate of a reservoir computer. Information is stored in the hyperfine population distribution of a Cs ensemble via optical pumping and retrieved through differential probe absorption. Spatial multiplexing via acousto-optic deflection provides eight addressable memory rails able to store up to 3.8 bits of information per rail. Employing this platform as a temporally multiplexed reservoir, we achieve a kernel rank ($\mathrm{KR}= 8.8 \pm 0.4$), and a minimum bit error rate of $0.02 \pm 0.01$ on the Exclusive-or (XOR) benchmark. We find the limited memory lifetime constrains the achievable temporal depth, encouraging further research into fast addressable memories. This constitutes the first demonstration of a free-space, optically writable atomic RAM as a substrate in an optical reservoir computing system. --- ### An Empirical Study of Reward Specification and Benchmark Reliability in GRPO-based LLM Unlearning Authors: Rubén Balbastre, Juan Manuel Orduña, Mariano Pérez Published: 2026-08-18 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2608.17804v1 Practical LLM unlearning is usually evaluated through two objectives: suppress target-specific knowledge and preserve non-target utility. In generative QA, this leaves a third behavior underspecified: when a target-adjacent prompt admits a broader answer without target-specific leakage, the model should answer at that level rather than leak, evade, or refuse. We study this specification problem in a controlled LoRA-GRPO RWKU setting, comparing four reward designs that span lexical suppression, anti-refusal shaping, rubric-based broad answering, and an explicit refusal contrast, with and without SFT warm-up. The experiments show that optimization success is not equivalent to behavioral unlearning: RWKU forget scores, held-out completion audits, terminal training-rollout audits, and training dynamics can point to different conclusions. We trace these disagreements to reward-hacking endpoints, policy-support limits in GRPO, benchmark probes that miss endpoint changes, and rewards that can select broad-topic answering with low semantic leakage during optimization. --- ### Scale Matters: Adaptive Granularity Selection for Cross-Species 3D Plant Organ Segmentation Authors: Carla Salazar, Lazaros Nalpantidis Published: 2026-08-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.17803v2 Recent 3D foundation models provide powerful feature representations for point cloud learning by controlling spatial granularity. However, relying on a fixed spatial granularity severely limits generalization in applications like plant phenotyping, where organ morphology and size vary substantially across species and growth stages. To address this, we propose AGS-PlantSeg, a few-shot 3D plant organ segmentation method that leverages the frozen Utonia (arXiv:2603.03283) foundation model combined with Adaptive Granularity Selection. By dynamically selecting the best granularity levels for each specific plant model, our method extracts optimized geometric features for a lightweight MLP segmentation head. Extensive experiments across PLANesT-3D (arXiv:2407.21150), Pheno4D , and Crops3D demonstrate that AGS-PlantSeg significantly improves cross-species generalization, achieving 88.9% average mIoU performance and outperforming fixed-granularity baselines by 2.5 mIoU points. Despite requiring minimal annotated data, our approach is highly competitive with fully supervised, plant-specific architectures. --- ### Scale Matters: Adaptive Granularity Selection for Cross-Species 3D Plant Organ Segmentation Authors: Carla Salazar, Lazaros Nalpantidis Published: 2026-08-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.17803v1 Recent 3D foundation models provide powerful feature representations for point cloud learning by controlling spatial granularity. However, relying on a fixed spatial granularity severely limits generalization in applications like plant phenotyping, where organ morphology and size vary substantially across species and growth stages. To address this, we propose AGS-PlantSeg, a few-shot 3D plant organ segmentation method that leverages the frozen Utonia (arXiv:2603.03283) foundation model combined with Adaptive Granularity Selection. By dynamically selecting the best granularity levels for each specific plant model, our method extracts optimized geometric features for a lightweight MLP segmentation head. Extensive experiments across PLANesT-3D (arXiv:2407.21150), Pheno4D , and Crops3D demonstrate that AGS-PlantSeg significantly improves cross-species generalization, achieving 88.9% average mIoU performance and outperforming fixed-granularity baselines by 2.5 mIoU points. Despite requiring minimal annotated data, our approach is highly competitive with fully supervised, plant-specific architectures. --- ### Fourth-Moment Geometry of Rademacher Sums Authors: Peigan Gao, Jian Qian Published: 2026-08-18 Categories: cs.LG, math.PR arXiv: https://arxiv.org/abs/2608.17802v1 Let $\varepsilon_1,\ldots,\varepsilon_n$ be independent Rademacher signs and let $a=(a_1,\ldots,a_n)\in\R^n$ satisfy the normalization below. For the normalized Rademacher sum, we determine how its higher moments depend on the fourth-order mass. Combining a sharp fixed-q moment envelope with a separate argument below the convexity threshold gives the Gaussian stability inequality for the full range $p\geq4$ of this linear-in-q bound. The same fourth-order framework determines the sharp finite dimensional $L_p/L_4$ Khintchine constant for $p\geq5$, with the flat coefficient vector as the extremizer. These results settle the conjectures of Jakimiuk and of Barański, Murawski, Nayar, and Oleszkiewicz stated below. We also prove Jakimiuk's conjectured quadratic stability estimate at $p=3$. The resulting bounds retain information about sparsity and effective dimension, with applications to Rademacher random projections and randomly signed errors; those applications are not developed further here. Their Laplace-transform form also gives coefficient-sensitive tail bounds. The proofs are discovered with substantial assistance from ChatGPT 5.6 Sol. --- ### StartupBench: Benchmarking General-Purpose Agents on Market-Validated End-to-End Workflows Authors: Liya Zhu, Xin Ma, Tao Liu, Haodong Wang, Ge Zhang, Jingzhe Ding, Qingshui Gu, Yongjie Zhong, Jinxiang Meng, Yuan Gao, Yunqiu Zhou, Hao Zhu et al. Published: 2026-08-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.17800v1 Recent advances in Large Language Models(LLMs) and agents have substantially improved the ability of AI systems to execute complex tasks. Yet existing benchmarks largely rely on researcher-selected tasks, leaving uncertain whether such progress extends to the work that real-world users actually demand from AI systems. We introduce \textbf{StartupBench}, an E2E agent benchmark grounded in market-validated AI startup products. Rather than defining tasks from pre-defined assumptions about useful agent capabilities, we systematically study AI products with demonstrated adoption, together with their product workflows and users, to identify real-world tasks for which AI has established practical demand across diverse professional domains. We translate these workflows into complete deliverable-oriented tasks and evaluate them with fine-grained rubrics capturing their complex requirements. Across representative models evaluated under a unified agent harness, even the strongest model successfully completes only approximately 30\% of StartupBench, despite making substantial partial progress on many tasks. Further analysis identifies aspects like complex instruction following and domain-specific expertise as major sources of failure. Our results reveal that many market-validated workflows remain beyond the reliable capabilities of current general-purpose agents, establishing StartupBench as an empirical measure of progress toward E2E completions of real-world user tasks. --- ### Training with synthetic data for drone detection in thermal imagery Authors: Tanel Liiv, Sander Soodla, Nzamba Bignoumba, Alma M. Liezenga, Toomas Pruuden Published: 2026-08-18 Categories: cs.CV, cs.AI, cs.ET, cs.RO arXiv: https://arxiv.org/abs/2608.17799v1 Ground-to-Air (G2A) drone detection in medium- and long-wave infrared (MWIR/LWIR) imagery is challenging due to reduced texture information, sensor noise, weak thermal contrast, and the scarcity of annotated data. This work investigates a synthetic-first training strategy that combines synthetic scene generation with fine-tuning on real data. We show that synthetic data provides an effective basis for learning initial object representations, while real in-domain thermal imagery is still essential for reliable deployment. Even small amounts of real IR data substantially reduce domain gaps. Our experiments indicate that dataset alignment has a stronger impact on performance than model scale. Finally, our analysis of the dataset suggests that semantic alignment in feature space is the strongest predictor of model performance, while radiometric properties such as entropy and dynamic range also contribute to detection robustness. This work provides a foundation for combining synthetic and real IR data for effective G2A drone detection. --- ### Diff-DDoS: Realistic Cyber-Physical Attack Synthesis and Robust Detection for 5G-Enabled CPS Using Tabular Diffusion Models Authors: Bilal Hussain, Xiao Tang, Qinghe Du, Tan Li, Muhammad Azhar, Danista Khan Published: 2026-08-18 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2608.17796v1 Deep learning-based DDoS detectors for 5G-enabled cyber-physical systems face scarce labeled attack data and unrealistic synthetic substitutes, which limit robustness against adaptive adversaries. Detectors trained on hand-crafted attacks with fixed scaling multipliers degrade catastrophically (F1-score drops of about 47 percent to 100 percent, depending on scenario) when confronted with realistic, distribution-preserving samples. We propose Diff-DDoS, a three-phase framework for realistic attack synthesis and robust detection using tabular diffusion models. Phase 1 trains a baseline CNN cell-level detector on spatiotemporal grids from call detail records (CDRs). Phase 2 trains a tabular denoising diffusion probabilistic model (TabDDPM) on normal CDR aggregates to generate realistic attacks and expose detector vulnerabilities. Phase 3 introduces adversarial diffusion training (ADT), using inverse classifier guidance to generate hard yet distribution-preserving samples until the detector converges. On a Milano CDR dataset across SMS-flooding, silent-call, Internet-signaling, and blended scenarios, ResNet50 with ADT recovers F1-scores of 79.62 percent (silent-call), 100 percent (Internet), and 92.79 percent (blended). After validation-based threshold calibration, ADT reaches 100 percent SMS F1 versus 47.3 percent for CTGAN, and matches the strongest gradient-based adversarial-training baseline on silent-call. These results support tabular diffusion models for stress-testing and hardening intrusion detectors in data-scarce 5G cyber-physical deployments. --- ### TraceSQL: Traceable Answerability Estimation for Reference-Free Text-to-SQL Verification Authors: Neelesh Kumar Shukla, Debasmita Panda, Srutanik Bhaduri, Aditya Banerjee, Vasu Rangarajan, Viji Krishnamurthy Published: 2026-08-18 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.17795v2 Text-to-SQL systems are commonly evaluated using ground-truth SQL queries or reference execution results, but such supervision is unavailable at inference time in real-world deployments. This creates a critical verification problem: given only a user question, database context, and generated SQL, can a system estimate whether the generated query is likely to correctly answer the question? Recent approaches use LLMs as judge or specialized agents to inspect generated SQL, but their decisions can be difficult to trace. Outcome Reward Models (ORMs) address this by learning from execution-labeled candidate SQLs and assigning correctness scores to unseen queries, yet they still provide limited visibility into the signals behind each verification. To address this limitation, we propose TraceSQL, a lightweight and traceable verification model built on explicit diagnostic features. TraceSQL combines 67 features capturing question ambiguity, question requirements, question-schema-SQL consistency, SQL structure, and intent alignment. These signals remain available for examining which factors influence each prediction and for tracing decisions back to diagnostic evidence. On BIRD development databases, TraceSQL achieves 66.47% F1 and 64.48% ROC-AUC, compared with 61.87% F1 and 58.26% ROC-AUC for the GradeSQL-7B ORM baseline on the same generated-SQL evaluation. Feature attribution further shows that the model relies on both semantic grounding and deterministic SQL-structure signals. These results show that SQL verification can be performed with a lightweight learned model while retaining feature-level evidence for inspecting and diagnosing its predictions. --- ### TraceSQL: Traceable Answerability Estimation for Reference-Free Text-to-SQL Verification Authors: Neelesh Kumar Shukla, Debasmita Panda, Srutanik Bhaduri, Aditya Banerjee, Viji Krishnamurthy Published: 2026-08-18 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.17795v1 Text-to-SQL systems are commonly evaluated using ground-truth SQL queries or reference execution results, but such supervision is unavailable at inference time in real-world deployments. This creates a critical verification problem: given only a user question, database context, and generated SQL, can a system estimate whether the generated query is likely to correctly answer the question? Recent approaches use LLMs as judge or specialized agents to inspect generated SQL, but their decisions can be difficult to trace. Outcome Reward Models (ORMs) address this by learning from execution-labeled candidate SQLs and assigning correctness scores to unseen queries, yet they still provide limited visibility into the signals behind each verification. To address this limitation, we propose TraceSQL, a lightweight and traceable verification model built on explicit diagnostic features. TraceSQL combines 67 features capturing question ambiguity, question requirements, question-schema-SQL consistency, SQL structure, and intent alignment. These signals remain available for examining which factors influence each prediction and for tracing decisions back to diagnostic evidence. On BIRD development databases, TraceSQL achieves 66.47% F1 and 64.48% ROC-AUC, compared with 61.87% F1 and 58.26% ROC-AUC for the GradeSQL-7B ORM baseline on the same generated-SQL evaluation. Feature attribution further shows that the model relies on both semantic grounding and deterministic SQL-structure signals. These results show that SQL verification can be performed with a lightweight learned model while retaining feature-level evidence for inspecting and diagnosing its predictions. --- ### ETHEREAL: A 25.6-$μ$s/inf. Low-latency Event-driven Graph-neural-network Processor for High-resolution Vision at the Edge Authors: Adrian Kneip, Martin Lefebvre, Daniel Gehrig, Victoria Catalán Pastor, Davide Scaramuzza, Marian Verhelst, Charlotte Frenkel Published: 2026-08-18 Categories: cs.AR, cs.CV arXiv: https://arxiv.org/abs/2608.17787v1 Dynamic vision sensors (DVS) are enticing candidates to reach the low-latency, sub-ms target of edge-vision applications, as they generate events with a $μ$s-level time resolution. However, using DVS front ends also calls for novel algorithm/hardware back ends capable of efficiently handling streams of sparse spatiotemporal events. While event-driven graph neural networks (EV-GNNs) have emerged as a solution on the algorithmic side that is both accurate and efficient, there is no dedicated hardware to date capable of efficiently supporting their mixed requirements of dense-regular compute operations and sparse-irregular memory accesses. We therefore introduce ETHEREAL, the first EV-GNN processor chip, capable of bridging this gap by means of a neighbor-parallel spline-convolution engine combined with a split-2D/3D memory hierarchy that introduces a novel spatiotemporal event-caching mechanism. Measurement results demonstrate a 25.6$μ$s latency and a 1.6$μ$J energy per end-to-end event-wise inference on the state-of-the art DAGr-GNN workload and VGA-resolution (640x480 pixels) DSEC dataset. --- ### Preference Is Not Intervention: The Structure and Stability Boundaries of Reader-Specific Evidence Utility Authors: Shi Zhou Published: 2026-08-18 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.17781v1 ML systems increasingly condition decisions on downstream model identity, but this is useful only if model-specific differences form reusable structure rather than input-local interactions. We test this in retrieval-augmented generation (RAG), where evidence utility can be measured under controlled interventions. Holding query, evidence, task, scoring, and intervention fixed, nine readers disagree on effect sign in 33\% of jointly affected cells; reader$\times$query interaction explains 29.8\% of utility variance versus an 8.4\% permutation null; and self-selected evidence improves F1 by $+0.031$ ($t=3.39$). We then ask the sharper question: \emph{which components of this heterogeneity are stable reader properties across queries?} Separating three measurable objects---evidence \emph{activity}, \emph{ordinal preference}, and \emph{conditional signed direction}---we find ordinal reader geometry stable across four independent settings (split-half $ρ=0.60$--$0.83$): leave-one-out interventions, PRISM preferences, RAMDocs, and RAGuard. Signed geometry is task-bounded: weak in open-ended QA (0.14, 0.35), especially for misleading and irrelevant evidence, but strong in binary fact-checking (0.75) with no significant ordinal gap, though still below its sparsity-matched ceiling. Sparsity, decoding noise, and metric artifacts do not explain the main ordinal--signed gap. Finally, stable ordinal similarity fails to predict cross-reader intervention transfer (oracle-distance $ρ=-0.27$; regret reliability $-0.28$). Reader-specific utility exists, but preference is not intervention: stable ranking similarity does not license transfer of help/harm decisions. --- ### Debate Training Reduces Reward Hacking in RLAIF Authors: Zachary Kenton, Lili Janzer, Rory Greig, Tian Huey Teh, Kirill Tyshchuk, Jonah Brown-Cohen, Harri Edwards, Senthooran Rajamanoharan, Noah Y. Siegel, Natasha Jaques, Rohin Shah Published: 2026-08-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.17776v1 We demonstrate that RL finetuning an LLM using debate, a two-player adversarial game between a generator and a critic adjudicated by a weaker LLM judge, reduces reward hacking compared to a reinforcement learning from AI feedback (RLAIF) baseline. Reward hacking is a central obstacle in RLAIF: as training progresses, the policy learns to exploit systematic errors in its AI judge, degrading task performance, a problem that worsens precisely when the judge is weaker than the policy, the setting most relevant to overseeing increasingly capable AI systems. We study mathematics tasks, where final-answer correctness is verifiable, allowing us to measure reward hacking dynamics. We train a Gemini~2.5 Flash-class policy with a frozen, weaker Gemini~2.5 Flash Lite judge, comparing a single-player RLAIF baseline against debate. While the baseline quickly hacks the judge, debate maintains judge performance throughout training, leading to a higher peak validation accuracy (45\% performance gap recovered) that persists through many RL steps. Additional experiments show that: 1) further weakening the judge leads to faster hacking, but this can be compensated by adding an additional debate round; 2) debate incentives override prompted misalignment; 3) RL using an LLM judge has a smaller train/validation reward gap than RL from verifiable rewards; 4) learning to critique to convince the judge using ground truth labels is possible but slow. Taken together, our results are a positive update on the feasibility of debate, while highlighting that balancing multi-agent training is critical: without player constraints, adversarial training risks defaulting to critic judge-hacking. We show that critique word limits (effective up to 150 words) successfully balance the game and avoid judge hacking, though this introduces a trade-off by restricting critic expressive clarity. --- ### Training-Free Human-in-the-Loop Anomaly Detection via Memory Bank Correction Authors: Ayusha Abbas, Saram Abbas, Kabita Adhikari Published: 2026-08-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.17775v1 Anomaly detectors are hardest to deploy exactly where training data is scarcest: a newly commissioned production line has a handful of verified "golden" samples and no machine-learning engineer on the factory floor. We present a training-free human-in-the-loop framework in which a domain expert corrects a PatchCore detector by direct memory bank editing: no retraining, no gradients, no original training data. A false-positive correction inserts the reviewed image's normal patches through a self-calibrating novelty gate admitting only those beyond the median pool-normal nearest-neighbour distance. From a bank built on only ten golden samples, operator corrections close a median 66% of the gap to an uncorrected fully trained bank (mean 80%, raised by three categories that overshoot parity), significantly improving 12 of 15 MVTec AD categories and harming none: ten samples plus corrections outperform hundreds of samples without them. On already-trained banks the headroom is smaller and concentrated where the bank undersamples normal appearance (gated: toothbrush +0.10, metal nut +0.09, zipper +0.05, screw +0.05), and no category except grid is significantly harmed. Evaluation uses a held-out protocol (20 splits per category, Holm-corrected Wilcoxon), because corrected images entering the bank inflate naive evaluation toward AUROC 1.0 by memorisation. Passive and active querying are statistically indistinguishable; a matched-label-budget control attributes gains to deployment-time label production at 43% of exhaustive-review cost; a defect-memory extension fails decisively. Feedback is simulated from ground truth; live expert trials, where mislabelling is costliest on small banks, remain future work. --- ### Learnware for CSI Feedback: Scene-specific Small Models Can Do Big Authors: Xiangyi Li, Jiajia Guo, Chao-Kai Wen, Xin Geng, Shi Jin, Zhi-Hua Zhou Published: 2026-08-18 Categories: cs.IT, cs.AI, eess.SP arXiv: https://arxiv.org/abs/2608.17760v1 Intelligent channel state information (CSI) feedback is essential for realizing the high capacity and spectral efficiency goals of future 6G systems, yet existing deep learning solutions face a trade-off between model generalization and scenario-specific performance. Large neural networks generalize well but incur high computational and tuning costs, while small models excel in particular environments but require repetitive costly end-to-end training for each base station (BS). To address these challenges, we introduce a model repository-based deployment framework in which a centralized AI data center maintains a catalog of scene-specific CSI models. The repository is enhanced with a Learnware-based framework, where each model is associated with a specification including semantic part (network architecture parameters) and statistical part (codeboo-fingerprint embeddings of training-data distributions). A BS submits only its local statistical specifications to retrieve the most relevant pre-trained model, enhancing data privacy by avoiding raw CSI transmission and drastically reducing retrieval latency and communication overhead. We further develop a data-driven search strategy that matches codebook fingerprints to model performance, achieving over 90% selection accuracy. In simulations, our scheme yields 18.8% and 57.7% performance improvements over the General Model in LOS and NLOS scenarios, respectively while reducing local fine-tuning by up to 1000 samples and 100 epochs. This Learnware-based approach minimizes redundant training, maximizes model reuse, and supports rapid,privacy-enhancing deployment of CSI feedback models. --- ### D$^2$ACCI: A Dual-Loop Diagnostic Protocol for Evidence-Preserving Agent Memory Authors: Xule Liu, Yijun Liu, Chao Li, Shao Kun Published: 2026-08-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.17756v2 Memory is a key capability of LLM agents. Persistent memory extends this across sessions---enabling recall, revision, and personalization. Yet its multi-stage pipeline (ingestion, retrieval, filtering, generation) makes failures difficult to localize: end-to-end evaluation reveals that an error occurred, but not which stage caused it. Existing evaluations often report aggregate performance without paired statistical comparisons, slice-level non-regression checks, or stage-level diagnostic traces. We propose D$^2$ACCI (Diagnostic-Driven Artifact-based Closed-loop Controlled Iteration), a dual-loop protocol whose outer diagnostic gate promotes, feature-flags, or rejects memory interventions based on paired evidence, protected-slice monitoring, and trace-level localizability. We further introduce DCR, a graded observability metric that measures whether failures remain localizable, and D$^2$ACCI-Eval, a reusable artifact for gate replay. We instantiate the protocol in MemStack and evaluate on three public benchmarks, achieving 93.59% on LoCoMo, 90.93% on LongMemEval, and 57.20% on PersonaMem-V2. Five paired ablations show that supplement extraction, session-memory retrieval, and Forget Guard yield statistically significant gains (+1.9 to +3.7pp, all p $\le$ .003). In contrast, BM25/RRF is retained as a monitored feature flag---a distinction invisible to aggregate-only evaluation. A diagnostic audit shows enriched traces substantially improve root-cause agreement over result-only relabeling. Diagnostic artifacts reach 98--100% DCR@3 versus 0% for results-only logs. These results establish that robust memory-system iteration demands traceable, statistically grounded, and regression-aware evidence---exactly the gap D$^2$ACCI fills. --- ### D$^2$ACCI: A Dual-Loop Diagnostic Protocol for Evidence-Preserving Agent Memory Authors: Xule Liu, Yijun Liu, Chao Li, Shao Kun Published: 2026-08-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.17756v1 Memory is a key capability of LLM agents. Persistent memory extends this across sessions---enabling recall, revision, and personalization. Yet its multi-stage pipeline (ingestion, retrieval, filtering, generation) makes failures difficult to localize: end-to-end evaluation reveals that an error occurred, but not which stage caused it. Existing evaluations often report aggregate performance without paired statistical comparisons, slice-level non-regression checks, or stage-level diagnostic traces. We propose D$^2$ACCI (Diagnostic-Driven Artifact-based Closed-loop Controlled Iteration), a dual-loop protocol whose outer diagnostic gate promotes, feature-flags, or rejects memory interventions based on paired evidence, protected-slice monitoring, and trace-level localizability. We further introduce DCR, a graded observability metric that measures whether failures remain localizable, and D$^2$ACCI-Eval, a reusable artifact for gate replay. We instantiate the protocol in MemStack and evaluate on three public benchmarks, achieving 93.59% on LoCoMo, 90.93% on LongMemEval, and 57.20% on PersonaMem-V2. Five paired ablations show that supplement extraction, session-memory retrieval, and Forget Guard yield statistically significant gains (+1.9 to +3.7pp, all p $\le$ .003). In contrast, BM25/RRF is retained as a monitored feature flag---a distinction invisible to aggregate-only evaluation. A diagnostic audit shows enriched traces substantially improve root-cause agreement over result-only relabeling. Diagnostic artifacts reach 98--100% DCR@3 versus 0% for results-only logs. These results establish that robust memory-system iteration demands traceable, statistically grounded, and regression-aware evidence---exactly the gap D$^2$ACCI fills. --- ### MAGPIE-Net: Predicting short-duration heavy-rainfall events in station neighborhoods from multitemporal FY-4A AGRI observations Authors: Xiang Lin, Yunying Li, Chengzhi Ye, Zitong Chen, Jing Sun Published: 2026-08-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.17753v1 Short-duration heavy-rainfall warning determines whether 1 h rainfall will exceed a threshold within a target-station neighborhood over the next few hours. Multitemporal infrared and water-vapor observations from the Fengyun-4A Advanced Geostationary Radiation Imager (FY-4A AGRI) capture cloud-top cooling, moisture evolution, and cloud expansion before substantial surface rainfall develops. However, most deep-learning nowcasting methods convert these signals into local warnings by post-processing gridded precipitation predictions, preventing station-neighborhood event targets from directly supervising the satellite-to-station learning pathway. We propose MAGPIE-Net, which embeds a geographically adaptive, differentiable grid-to-station mapping in a pathway combining convection-initiation features, multiscale encoding, and auxiliary gridded precipitation diagnosis. Station-neighborhood event losses thereby constrain the satellite representation and its mapping to irregular station locations for 0-3 h event prediction. In independent 2023 warm-season tests over central and eastern China, critical success index (CSI) values under the primary 40 km/20 mm h-1 definition were 0.371, 0.304, and 0.238 at 0-1, 1-2, and 2-3 h. Across episodes, MAGPIE-Net achieved a detection rate of 65.1% and a mean lead time of 64.6 min, compared with 23.6% and 18.3 min for the best gridded-output baseline, and remained superior for smaller neighborhoods and the 50 mm h-1 threshold. During the critical early-warning stage, when antecedent 1 h rainfall within 40 km remained below 1 mm, MAGPIE-Net detected 51.9% of episodes with a mean lead time of 38.5 min. These results show that event-oriented satellite-to-station modeling converts multitemporal geostationary cloud and moisture observations into local heavy-rainfall warnings more effectively than gridded-precipitation modeling. ---