# Research Papers — 2026-09 · bundle page 105 of 266 > Full-text markdown of papers #5201–5250 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/105 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/104.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/106.md) ### Evaluating the Semantic-to-Geometric Gap in Adversarial Defenses Against Vision-Language Model-Based Plagiarism Authors: Christopher Burger, Christina Trotter, Joseph Carlisle, Charles Walter Published: 2026-09-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.26733v1 The rapidly advancing capabilities of vision-language models (VLMs) present a systemic challenge to academic integrity. VLMs now allow students to bypass meaningful engagement by capturing and submitting graphical problems as singular images, a practice we define as trivial plagiarism. To provide educators with actionable data on VLM limitations, we investigate the efficacy of heuristic adversarial image transformations designed to degrade model performance while remaining human-interpretable. Through a two-phase evaluation of introductory assessments, we manually assess baseline VLM performance on circuit diagrams, followed by an automated large-scale evaluation of topological structures (logic gates) and coordinate geometry (Karnaugh maps). We find that while highly capable VLMs can exhibit appreciable robustness, all models suffer vulnerability to adversarial perturbations. We conclude that while visual perturbations act as a viable near-term stopgap, long-term assessment security requires educators to reapproach assessment design given continually increasing VLM performance. --- ### ASTRA-SR: Atmospheric Seeing and Turbulence Restoration for Astronomical Image Super-Resolution Authors: Xining Ge, Ziteng Cui, Shuhong Liu Published: 2026-09-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.26731v1 Ground-based planetary imaging suffers from atmospheric turbulence, sensor noise, and limited sampling, making restoration a joint denoising, deblurring, and super-resolution problem. We present ASTRA-SR, a blind single-frame restoration framework trained on a physics-grounded synthetic dataset. High-dynamic-range spacecraft RAW observations serve as clean sources, and paired LR inputs are synthesized using measured layer-integrated turbulence strengths, propagated moving phase screens, exposure-averaged spatially varying PSFs, and sensor noise.ASTRA-SR first estimates a noise-suppressed but blur-retaining LR image, then restores spatial structure through multiscale processing and reconstructs HR detail with serial spatial-amplitude refinement. It yields a 0.49 dB foreground PSNR gain over the strongest baseline approaches. --- ### GAD-MambaUNet: Direction-Group Mamba with Gradient-Adaptive DINOv3 Distillation for Lightweight Medical Image Segmentation Authors: Fang Wang, Huitao Li, Wenhan Chao, Zheng Zhuo, Xinxin Yang Published: 2026-09-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.26729v1 In this paper, we proposed GAD-MambaUNet, a lightweight medical image segmentation network that combines efficient local modeling, direction--group state-space interaction, and training-time foundation-model supervision. To improve contextual modeling in compact segmentation networks, we introduced Direction-Group Graph Selective Scan (DG-GSS), which treated scan-direction and channel-group responses as graph nodes and enabled structured information exchange before multi-directional fusion. We further incorporated DINOv3-GAD supervision, where a frozen DINOv3 teacher provided semantic guidance during training, and Gradient-Adaptive Distillation dynamically regulated the distillation strength. GAD-MambaUNet achieves a favorable accuracy--efficiency balance compared with representative lightweight and general segmentation methods. Ablation studies further verify the effectiveness of DG-GSS and training-time DINOv3-GAD supervision. In future work, we will explore more flexible teacher--student alignment strategies and extend the proposed framework to more diverse medical segmentation scenarios, such as multi-class and multi-modal segmentation tasks. --- ### Does AI Save Time on Product Design? A Randomized Controlled Experiment of AI Prompt-to-Design Workflows Authors: Remy Stewart, Olabode Anise, Andrew Hogan, Augustus Griffin Published: 2026-09-22 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2609.26725v1 AI tools for digital product design now offer prompt-to-design capabilities, allowing designers and their non-designer colleagues to create prototypes through conversational workflows with large language models (LLMs). While these tools promise time savings, experimental evidence in product design remains limited compared with evidence from software engineering. We conducted a randomized controlled trial with 50 product designers and 50 product managers to evaluate prospective time savings from leveraging Figma Make in design work. Participants attempted three standardized design tasks with or without access to Figma Make. Among participants who completed the study tasks, access to Figma Make was associated with approximately 20% shorter completion times, with larger gains among product managers. Our findings suggest that prompt-to-design tools may enable product managers to further contribute to design work, while the benefits for professional designers may be task dependent. --- ### The Sirens' Song: When Proximal Background Context Overshadows Distant Evidence Authors: Xiaoyu Yang, Jie Lu, Wei Duan, En Yu Published: 2026-09-22 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.26718v1 Long-context LLMs focus on retrieving distant evidence from extensive context, yet existing work has largely focused on overcoming distance alone. In this work, we identify the Proximity Trap, insufficient attention to distant evidence often arises less from distance itself than from cumulative competition with abundant, task-irrelevant proximal background. To address the Proximity Trap, we introduce LYRA (Long-context heavY-tailed Relevance Alignment), a t-distributed directional matching mechanism that reshapes the context retrieval distribution, directing more attention mass toward task-relevant evidence, while preserving the relative positional information encoded. Extensive experiments on LongBench-v2, RULER, and LongBench demonstrate consistent improvements across context lengths and task categories. We further introduce ProxBench, a multi-level fine-grained benchmark for evaluating distant evidence utilization under increasing proximal background interference. Project page: https://xiaoyuyoung.github.io/LYRA/ --- ### TraceVIC: Causal Reasoning over Code Evolution for Identifying Vulnerability-Inducing Commits Authors: Fnu Tanish, Samiha Shimmi, Samikshya Chapagain, Hamed Okhravi, Mona Rahimi, Lei Zhang Published: 2026-09-22 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2609.26711v1 Software vulnerabilities are often discovered long after they are introduced, making it difficult to identify the vulnerability-inducing commit (VIC) responsible for introducing the underlying vulnerable condition. Existing VIC identification techniques largely rely on git blame to trace vulnerable code through revision history and use positional heuristics, such as selecting its earliest or most recent modification. However, the true VIC may occur anywhere within this history, and vulnerable behavior may depend on code that evolves across multiple revisions. We therefore argue that VIC identification requires reasoning about how vulnerability-relevant code evolves, rather than simply where a candidate commit appears in the revision history. We present TraceVIC, a temporal graph-based approach for identifying and ranking VICs by reasoning over code evolution. TraceVIC first localizes likely root-cause lines and traces their histories across revisions, constructing graph representations that capture program structure within each revision and the evolution of vulnerability-relevant code across the history. It reasons over the resulting revision history, using temporal edges to preserve correspondences between program elements across consecutive revisions, and directly ranks candidate commits according to their contribution to the vulnerable condition. Ablation results show that modeling the full revision history improves F2 from 0.637 to 0.814. TraceVIC improves F2 by up to 28.7% over state-of-the-art methods and identifies a valid VIC for 78 of 79 vulnerabilities across four unseen C/C++ projects. --- ### Train Where the Quantized Model Goes: On-Policy Distillation for Low-Bit Reasoning Authors: Yuanteng Chen, Zhilei Liu, Peisong Wang, Yuantian Shao, Chuangyi Li, Weining Wang, Shuang Qiu, Gang Li, Jing Liu, Jian Cheng Published: 2026-09-22 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.26708v1 Quantization-aware distillation (QAD) restores much of the short-form question-answering performance lost to sub-3-bit quantization, yet leaves mathematical and code reasoning substantially impaired. Long generations often degenerate into repetitive loops, exhausting the decoding budget without completing a solution. We trace this gap to quantization-amplified exposure bias: QAD trains on fixed corpus prefixes, while quantization-induced deviations compound along the model's own autoregressive trajectories. To address this mismatch, we introduce an on-policy distillation (OPD) stage that places teacher supervision where the quantized model actually goes. Starting from a QAD checkpoint, the student generates through the quantized forward path used at deployment and receives feedback from a frozen full-precision teacher on its own prefixes, combining dense token-level guidance with task-verifier rewards. Across four models at 2.79 and 1.88 effective bits, OPD raises average BF16 performance retention from 35% to 70% on MATH-500 and from 66% to 91% on HumanEval while preserving short-form performance, with reasoning gains substantially exceeding those of continued teacher-forced QAD in matched-budget comparisons. By coupling QAD's stable low-bit initialization with OPD's on-policy reasoning recovery, our framework provides a comprehensive sub-3-bit solution that preserves broad capabilities while restoring long-form reasoning. --- ### Optimal Sequential Annotations for Off-Policy Evaluation Authors: Woojin Chae, Ezinne Nwankwo, Haitong Qin, Angela Zhou Published: 2026-09-22 Categories: stat.ME, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2609.26707v1 Offline reinforcement learning and off-policy evaluation evaluates dynamic treatment rules based on retrospectively collected data prior to deployment. In recent AI applications, state and reward information is recorded as complex text or image, which recent AI advancements such as LLM-as-a-judge can label with unknown bias. Expert annotation may be available but at a higher cost. For example, safety classification via cheap but imperfect classifiers vs. expensive expert review. We show how a limited budget for ground-truth data-annotation can be used via doubly-robust OPE with missing rewards, and we optimize variance-optimal annotation probabilities for sequential off-policy evaluation, where the target policy value is estimated from annotated data. We characterize the optimal annotation probabilities for sequential forward-monotone annotation protocols, and provide a feasible batch-adaptive implementation. Our work is motivated by a collaboration with a homelessness services nonprofit that writes casenotes for individuals over time. Our method can be used to unlock trustworthy inference from casenote data and answer new inferential questions such as: how does expanding outreach effort over time affect progress towards a housing application and improvement in housing placement? In simulations and on two real datasets - casenotes from the nonprofit and human-preference votes from LMArena - we see reductions in RMSE of 34-65% for housing placement and 17-68% for progress towards a housing application at budgets of 40% of full annotation and above, and by 55-62% at every budget on LMArena. --- ### When are bosonic Gaussian states classical to learn? Authors: Senrui Chen, Antonio Anna Mele, Francesco Anna Mele, John Preskill Published: 2026-09-22 Categories: quant-ph, cs.IT, cs.LG, math-ph arXiv: https://arxiv.org/abs/2609.26705v1 A fundamental question in physics is: When does classical behavior emerge from quantum systems? Bosonic Gaussian states provide a natural setting to explore this quantum-classical boundary, as they capture both the classical field behavior and the intrinsic quantum nature of light. Here, we address this problem from a learning-theoretic perspective by asking: When are bosonic Gaussian states classical to learn? That is, under what conditions (if any) can an n-mode bosonic Gaussian state be learned with as few samples, and with operations as simple, as are needed to learn a classical 2n-variate Gaussian distribution? We establish a smooth crossover in learnability governed by the state's thermal fluctuations: - Cold Gaussian states are non-classical to learn: When the covariance matrix satisfies $Σ\le(\frac12+O(\frac1n))I$, i.e. close to the vacuum covariance, tomography under single-copy (i.e., non-entangled) measurements fundamentally requires $Ω(n^3)$ copies, strictly exceeding the sample complexity $Θ(n^2)$ of learning classical Gaussian distributions. We show that this hardness persists even when few-copy entangled measurements are allowed. - Warm Gaussian states are classical to learn: When thermal fluctuations exceed the vacuum noise, parameterized by $Σ\ge(\frac12+ν)I$ for any parameter $ν>0$, we prove that single-copy tomography requires $N=Θ\left(n^2\min(n,1+ν^{-1})\right)$ copies. This bound is tight and is achieved by simple, non-adaptive, unentangled heterodyne measurements. Crucially, for $ν=Ω(1)$, the sample complexity drops to $Θ(n^2)$, matching the classical case. Our results tightly characterize a quantum-to-classical crossover in the learnability of bosonic Gaussian states, reveal a novel connection between fundamental physics and statistical learning theory, and have implications for real-world sensing experiments. --- ### Beyond Repeated Sampling: Learning Search Policies for LLM Reasoning Authors: Ismail Labiad, Matthieu Kowalski, Marc Schoenauer, Rémi Munos, Julia Kempe Published: 2026-09-22 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.26704v1 Large language models increasingly tackle hard reasoning problems by spending more test-time compute, yet the dominant strategy remains naive repeated sampling: draw many independent solutions and hope one is correct. Because such sampling explores only through local decoding noise, it tends to produce many near duplicate attempts rather than genuinely different ideas. We ask whether exploration can instead be steered at a semantic level, by first sampling problem specific concepts, hints, or strategies and then conditioning answer generation on them. We refine this into a simple, more exploratory procedure that emits many diverse concepts in a single trajectory, and evaluate it on hard problems where repeated sampling struggles. We then go a step further and make concept generation trainable: a small concept generator is optimized with reinforcement learning so that its concepts maximize the downstream success of a larger, frozen answer generator. On hard mathematical reasoning problems, the trained concept generator substantially improves the answer generator's pass@k over naive repeated sampling at the same answer generation allocation, surpasses concepts drawn from much larger untuned models, and transfers to answer generators it was never trained against, including a model from a different family. A small model can thus be trained into an effective, reusable search policy for a much larger one. --- ### DIFTA-3D: Depth-Consistent Instance-Level Feature Transfer and Adaptation of DINOv3 for 3D Detection Authors: Linman Wang, ZiFei Zhang, Chunran Zheng, Xiwang Dong, Jiarong Lin Published: 2026-09-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.26702v1 RGB-D 3D instance detectors benefit from visual semantics, but the task-specific Faster R-CNN/ResNet branch used by IIFNet3D couples feature extraction to a separately trained 2D detector and its image-domain labels. Replacing that branch with a frozen vision foundation model removes this task-specific dependency, but may introduce occlusion noise and a mismatch between patch features and geometry-aware detection features. In this work, we investigate this replacement through an adaptation of DINOv3 to the instance-level fusion pipeline of IIFNet3D. At the core of our approach is a depth-consistent feature pipeline that projects scene points into calibrated RGB-D frames, applies a metric depth-residual check, averages the accepted DINOv3 features into an offline point cache, and aggregates the cached features inside proposal-aligned RoI grids. The geometric and bidirectional instance-fusion paths are preserved, while Conservative VAID is evaluated as a low-strength, support-weighted semantic distillation recipe applied only to positive RoIs. We conduct extensive evaluations on ScanNetV2 to assess the proposed transfer recipes. On ScanNetV2, our DINOv3 control achieves mAP scores of 76.15 and 60.93 at IoU thresholds of 0.25 and 0.50, respectively. The Conservative VAID setting achieves mAP scores of 76.59 and 62.16, corresponding to numerical gains of 0.44 and 1.23 points over the control, respectively, in this checkpoint-level recipe comparison. The reported IIFNet3D result of 75.7/63.8 is used only as an external reference because the visual branch and processing protocol differ. Accordingly, we interpret these results as evidence for a controlled transfer recipe rather than as a causal estimate of the individual contributions of VAID or depth filtering. --- ### Measuring the Serving Stack Instead of the Model: Hidden Confounds in Local Tool-Use Evaluation Authors: Lijuan Tang, Yuemeng Zheng Published: 2026-09-22 Categories: cs.CL, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2609.26693v1 A coding agent must emit a valid tool call--a parseable invocation of a tool in the provided schema--before the harness can execute its chosen action. We study how local serving stacks affect this protocol step and show that measured outcomes can depend on the serving layer rather than model behavior alone. In Ollama, the default tools= request is gated per model by a static template flag: some models are accepted and return calls as text, some return native tool_calls, while Phi-3 and Gemma-3 are rejected before inference. In our harness, rejection and retry exhaustion are not preserved as structured failure metadata, so downstream analysis can misclassify them as model non-calls and naively report 0% fidelity. Adding a text tool list while retaining the native channel recovers much of the measured fidelity for accepted models, whereas a uniform text protocol reduces fidelity for Llama-3.2, which has native tool-call support. Cross-stack probes on Ollama, llama.cpp, vLLM, and SGLang show different handling of the same request. Constrained decoding removes parse failures but can induce non-termination, and turn-pooled versus per-instance estimates differ by up to about 55 points. We conclude with a checklist for treating serving behavior as part of the evaluation protocol. --- ### Detecting GPT-Assisted Writing Using Interpretable Stylometric Features Authors: Rajesh Kumar, Nabeel Siddiqui, Alexander Fuchsberger Published: 2026-09-22 Categories: cs.CL, cs.CY arXiv: https://arxiv.org/abs/2609.26687v1 Distinguishing GPT-assisted from independently authored student writing has become a critical challenge in academia. This paper evaluates the discriminative capability of interpretable stylometric features extracted solely from submitted text. Using data from 90 participants who wrote both independently and with ChatGPT assistance, we evaluate eight machine learning classifiers while keeping data from the same participant together during validation. On the held-out test set, Random Forest achieved an ROC-AUC of 0.87 and an F1-score of 0.84, with False Positive and False Negative rates of 22.2% and 11.1%, respectively. SHAP analysis shows that lexical and grammatical characteristics drive the resulting predictions. The findings suggest that transparent, text-intrinsic features provide measurable signal for detecting GPT-assisted writing. --- ### PROSWIN: Probabilistic Solar Wind Speed Forecasting Using Deep Distributional Regression From Solar Images Authors: Daniel Collin, Yuri Shprits, Luca Chiarabini, Stefan J. Hofmeister, Nadja Klein, Guillermo Gallego Published: 2026-09-22 Categories: astro-ph.SR, cs.LG, physics.data-an, physics.space-ph arXiv: https://arxiv.org/abs/2609.26683v1 Accurately predicting fast solar wind conditions is challenging, as uncertainties are large and unquantified by traditional single-value prediction models. In particular, the risks of high-speed solar wind streams (HSSs), which can cause damage to technological infrastructure, cannot be reliably assessed without probabilistic forecasts. We present PROSWIN, a probabilistic machine learning model that forecasts the hourly solar wind speed (SWS) at Earth with a four-day lead time. The approach combines solar images and magnetograms using a deep neural network coupled to a distributional regression algorithm. Because standard error metrics underweight the relevance of HSS peaks, we further introduce the prediction score, a model-selection metric that jointly rewards timeline and HSS peak accuracy. On 14 years of data, our forecast achieves very well-calibrated uncertainties (<1% average deviation). Using the continuous ranked probability score (CRPS), a metric that assesses distributional accuracy, we obtain a timeline CRPS of 41.0 km/s, an HSS peak CRPS of 45.3 km/s, and a prediction score of 42.3 km/s. We find that the 171 Å channel is an important complement to the typically used 193 Å and 211 Å channels and that the prediction score for model selection improves the applicability of the model. Compared to selected models from the literature, ours is the only one that is accurate for both timeline and HSS peak values, rather than trading one off against the other. These results support the advantages of probabilistic over single-value solar wind models. The introduced methods are also transferable to other forecasting problems. --- ### From Alignment to Access Control: A Framework for GenAI Policy Enforcement Authors: Nathalie Baracaldo Published: 2026-09-22 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2609.26682v1 Generative AI (GenAI) applications have flourished enabling users to chat with large language models, and to create agents to act on their behalf for a variety of tasks. The pace of development of capabilities in this field is incredibly fast with security and safety taking a back seat. Unfortunately, the slower pace at which security and safety mechanisms have evolved has led to real incidents. Policy enables the definition of desirable behavior of applications, and for that reason, it is a cornerstone of making systems secure and compliant. Policy however means different things to different practitioners creating confusion and siloed solutions that are not adequate for compliance. This paper takes a tour of the good, the bad and the ugly when it comes to policy enforcement in GenAI applications. We propose a methodology to systematically analyze and dissect existing approaches to define and enforce policy found in the wild. Based on this principled analysis, we provide recommendations and call for action for the community to address. This paper is a companion extension of USENIX Security 2026 Enigma talk titled "From Alignment to Access Control: A Unified View of GenAI Policy Enforcement" by the author Nathalie Baracaldo. --- ### A Spectral Theory of Grokking: Weight Decay induces Feature Learning Authors: Lenz Pracher, Pascal de Jong, Oskar Lieshaus, Alan Jeffares, Steffen Rulands Published: 2026-09-22 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.26679v1 In grokking an early fit to the training data separates from a much later improvement in generalization. During this delay, training can move from a fixed neural tangent kernel (NTK) regime to one in which task-relevant kernel eigendirections continue to evolve. We provide a quantitative theory for how this transition from lazy to rich learning can produce delayed generalization. For homogeneous networks trained with squared loss and $L_2$ weight decay, we show that a finite residual remains after memorization, with larger residual fractions in target components associated with smaller NTK eigenvalues. These residuals feed back into the dynamics of the NTK itself, and projecting the resulting dynamics onto task-relevant spectral directions yields a reduced system in which residual-driven kernel growth competes with weight decay. This system predicts that the grokking timescale is controlled by the product of learning rate and weight decay, that feature learning slows logarithmically near a critical decay above which task-aligned NTK structure can no longer support generalization, and that stronger decay can prevent fitting altogether. We test these predictions in modular addition. In a homogeneous MLP, task-aligned Fourier structure continues to emerge in the NTK after training accuracy has saturated, and an 84$\times$90-grid of trained networks across varying learning rate and weight decay recovers the predicted phase geometry and inverse-product scaling of the generalization time with learning rate and weight decay. A one-block Transformer shows similar macroscopic phase structure in a 42$\times$45-grid, as well as the same transition-time scaling despite violating exact homogeneity. Together, these results provide a mechanistic derivation connecting post-fit feature learning to both the onset of generalization and its phase structure in the learning rate and weight decay plane. --- ### MAGIC: Mixed-Granularity Agent Graphs via Incremental Construction with Dense-Reward Reinforcement Learning Authors: Kairui Yang, Ziheng Yi, Xunkai Li, Minghao An, Zhanke Liu, Zekai Chen, Rong-Hua Li Published: 2026-09-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.26667v1 Collaboration topology shapes both the performance and execution cost of LLM-based multi-agent systems. Because tasks differ in complexity and required capabilities, recent approaches generate task-specific collaboration graphs that specify agent participation and information flow. However, representative topology generators use either individual agents or predefined groups throughout an organization, overlooking differing collaboration needs across subtasks. Our key insight is to select granularity locally for each functional role, combining fine-grained control with reusable collaboration patterns within one organization. Learning such organizations requires exploring a combinatorial construction space with limited intermediate feedback from final-answer rewards. Therefore, we propose MAGIC, a dense-reward reinforcement learning framework for mixed-granularity graph generation. Specifically, MAGIC constructs a mixed-granularity agent graph by sequentially selecting a functional role, instantiating it as a single agent or reusable group, and connecting it to existing units. We directly optimize the construction policy using returns from trajectories sampled under the current policy and use potential-based reward shaping to provide intermediate feedback from probe-based utility and structural signals while preserving the cumulative task reward. MAGIC outperforms state-of-the-art baselines across eight benchmarks and demonstrates strong inference efficiency in our efficiency study. --- ### Longitudinal Retinal Vascular Remodeling in Myopic Children Treated with Orthokeratology or Defocus Lenses: A Two-Year Comparative Study Authors: Zhihao Zhao, Yinzheng Zhao, Jie Zhang, Huiqin Jiang, Yanyu Shangguan, Yanfei Sun, Li Chen, Yanlong Bi, M. Ali Nasseri, Bing Li Published: 2026-09-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.26662v1 Purposes: To characterize longitudinal retinal vascular changes in myopic children treated with orthokeratology (OK) or multifocal defocus lenses (Defocus) and to examine their association with axial elongation. Methods: In this retrospective cohort study, 43 myopic children underwent comprehensive clinical examination and fundus photography at baseline, 12 months, and 24 months. Axial length (AL) and spherical equivalent refraction (SER) were recorded at baseline, 6, 12, and 24 months. An automated segmentation model extracted vascular parameters, main vessel angle (MA), branching angle (BA), bifurcation edge angle (BEA), crossover point (COP), and terminal vessel count (TVC). Repeated-measures ANOVA assessed temporal changes. Pearson or Spearman correlations evaluated associations between AL and vascular metrics. Results: Over 24 months, the OK group exhibited significantly slower axial elongation than the Defocus group (0.214 mm and 0.522 mm, p < 0.01). In the OK group, MA and BA decreased modestly, BEA in arteries declined gradually, but COP and TVC remained relatively stable. The Defocus group demonstrated more pronounced decreases in MA and BA, an increase in BEA, and significant reductions in COP and TVC (p < 0.05). Correlation analysis revealed stronger associations between AL and vascular parameters, especially COP and TVC, in the Defocus group at all time points, whereas only BA and BEA correlated with AL in the OK group. Conclusions: OK lenses mitigate axial elongation and induce milder retinal vascular remodeling compared to Defocus lenses. Distinct temporal patterns of vascular metrics changes were observed between the two interventions, and correlate differentially with axial growth. --- ### Discovery-Driven Integration of Disjoint Tables via Text Authors: Md Ataur Rahman, Dimitris Sacharidis, Oscar Romero, Sergi Nadal Published: 2026-09-22 Categories: cs.IR, cs.CL, cs.DB, cs.LG arXiv: https://arxiv.org/abs/2609.26658v1 Integrating heterogeneous datasets within data lakes is a critical challenge, particularly for semantically related tables that lack the explicit attributes needed to be joined. We study Discovery-Driven Integration, where the relevant sources and their missing relational structure must be discovered before integration. In this setting, unstructured text provides the evidence that connects otherwise disjoint tables. The fundamental challenge is to discover the relationships at a fine-grained level that connect individual rows from different tables through specific sentences. We formalize this task as Text-Mediated Join Path Discovery and propose a horizontal bidirectional cross-attention architecture called LOKI Latent-space Optimization for Knowledge Integration) that learns contextualized representations of table rows and sentences. Through a global table-text contrastive objective, fine-grained row-sentence associations emerge without explicit local supervision. Existing multi-modal discovery methods largely retrieve coarse-grained column-text associations, whereas integration systems assume supplied row-text links, schemas, or queries. LOKI instead transforms these implicit associations into explicit, interpretable join paths, organizes them into relation-consistent groups, and materializes them as typed integrated tables with sentence-level provenance. Comprehensive evaluations on real-world benchmarks demonstrate that LOKI consistently outperforms state-of-the-art multi-modal data discovery approaches, and materializes typed integrated tables with 0.982 macro typed-pair precision while being up to 40 times cheaper in LLM API cost than direct prompting. --- ### Context-Adaptive Thresholding for Conditionally Representative Monitoring and Classification Authors: Ansgar Steland Published: 2026-09-22 Categories: math.ST, stat.ML arXiv: https://arxiv.org/abs/2609.26652v1 Commonly, classifiers and monitoring procedures are trained from labeled data by optimizing an objective such as the misclassification rate. This may lead to unrepresentative conditional distributions of the outcome (the labels) given important external variables, different from the conditional laws in the population. We show how to modify any given threshold-type classifier resp. monitoring rule to achieve representative conditional label prediction by using adapting the threshold to a covariate $Z$ (the context) to distribute sensitivity while maintaining the false alarm rate. In case that the alarm event is unknown, this approach also allows to (approximately) infer the event in terms of a thresholding rule. The approach is implemented by a computationally cheap nonparametric estimation procedure, and its properties are studied in terms of nonasymptotic error bounds and asymptotic distribution theory including empirical process theory. These results allow to construct uniform confidence bands, functional hypothesis tests and change-detection procedures. For the well known FICOS credit scoring example, often used in interpretable machine learning, threshold adaptation leads to an easily interpretable decision rule which can compete with state of the art methods including transformers, in terms of common classification metrics. --- ### ROAM-ASD: Robust Open-World Active Speaker Detection with Flexible Multimodal Fusion Authors: Pu Wang, Hugo Van hamme Published: 2026-09-22 Categories: cs.MM, cs.CV, cs.SD, eess.AS, eess.IV arXiv: https://arxiv.org/abs/2609.26648v2 Active speaker detection (ASD) requires reliable association between visible faces and acoustic speech, yet existing systems often degrade under challenging domains or incomplete observations. We introduce ROAM-ASD, a robust audiovisual framework that jointly models audio, full-face, and fine-grained mouth representations. A unified joint self-attention mechanism processes all input streams together with modality-agnostic query tokens, enabling direct interaction among available modality inputs. Modality dropout further improves robustness when input streams are unavailable. ROAM-ASD achieves state-of-the-art performance across five ASD benchmarks: 98.8% mAP on WASD, 87.9% on UniTalk, 96.5% on AVA, 99.3% on ASW, and 98.2% on Talkies, improving over previous best systems by 5.1, 4.7, 0.9, 1.0, and 2.1 mAP points, respectively. ROAM-ASD also substantially improves zero-shot cross-dataset generalization and remains robust to missing observations. --- ### ROAM-ASD: Robust Open-World Active Speaker Detection with Flexible Multimodal Fusion Authors: Pu Wang, Yujun Wang, Hugo Van hamme Published: 2026-09-22 Categories: cs.MM, cs.CV, cs.SD, eess.AS, eess.IV arXiv: https://arxiv.org/abs/2609.26648v1 Active speaker detection (ASD) requires reliable association between visible faces and acoustic speech, yet existing systems often degrade under challenging domains or incomplete observations. We introduce ROAM-ASD, a robust audiovisual framework that jointly models audio, full-face, and fine-grained mouth representations. A unified joint self-attention mechanism processes all input streams together with modality-agnostic query tokens, enabling direct interaction among available modality inputs. Modality dropout further improves robustness when input streams are unavailable. ROAM-ASD achieves state-of-the-art performance across five ASD benchmarks: 98.8% mAP on WASD, 87.9% on UniTalk, 96.5% on AVA, 99.3% on ASW, and 98.2% on Talkies, improving over previous best systems by 5.1, 4.7, 0.9, 1.0, and 2.1 mAP points, respectively. ROAM-ASD also substantially improves zero-shot cross-dataset generalization and remains robust to missing observations. --- ### Statistical Rates for Entropic Optimal Transport in the Discrete to SubGaussian Regime Authors: Tomas Gonzalez, Gonzalo Mena Published: 2026-09-22 Categories: math.ST, cs.LG arXiv: https://arxiv.org/abs/2609.26647v1 We study statistical rates in entropic optimal transport in the semi-discrete regime where one measure has finite support and the other is subGaussian. Our main result establishes parametric convergence rates for the empirical dual potentials to their population counterparts, with no dimension dependence in the leading term. Our result relies on tailored strong concavity analysis of the semi-dual objective, coupled with specialized bounds for the semi-discrete potentials. As a consequence, we obtain fast rates for downstream quantities derived from the optimal coupling. Chiefly, the empirical barycentric projection achieves a squared-error rate $n^{-1}$, matching the fully compact case and improving over the less favorable $n^{-1/2}$ rate known for fully subGaussian settings. Altogether, these results may indicate a lower complexity adaptation phenomenon whereby the statistical complexity of the barycentric projection is governed by the discrete measure. As an application, we analyze Sinkhorn-EM, an EM-type algorithm in which the E-step is replaced by an entropic optimal transport problem. In a well-specified and balanced two-component Gaussian mixture model, we prove $\sqrt{n}$-consistency of the empirical iterates to their population counterparts for any fixed number of iterations, matching classical EM rates up to a $\sqrt{\log n}$ factor. Simulations support the theory. --- ### The Delegation Blind Spot: Auditing Product Decisions from Agent Choices Authors: Shivam Gupta Published: 2026-09-22 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.26642v1 Successful agent execution need not identify which future product improvement its user would value. We present a decision-specific audit that maps a declared observation channel and product-value contrast to compatible intervals and witness populations. Its foundations are established identification and decision theory; the contribution is an executable measurement workflow and a controlled study of its limits. A frozen experiment makes 4,800 requests to two pinned model snapshots on shared synthetic tasks. All 36 conservative primary intervals remain unresolved despite different execution accuracy. An exploratory 2,400-call follow-up records supplied preferences and resolves three of nine comparisons per model. A deterministic extractor resolves seven of nine without model calls or calibration observations, exposing unnecessary uncertainty introduced by model-generated reports. A further 14,400 controlled multinomial simulations distinguish structural ambiguity from weak identification and finite calibration precision. We propose a source-labeled decision receipt and provide an offline viewer for inspecting the audit. These results motivate preserving decision-relevant structured input and diagnosing why a decision is unresolved before collecting more telemetry. The study contains no human participants or real customer outcomes. Full proofs, raw model provenance, controlled experiments, and reproducible analyses accompany the report. --- ### Diffusion Drafts, AR Verifies: Accelerating Document OCR with Self-Speculative Decoding Authors: Dohyun Kim, Sungjun Han, Hyungguk Kim, Yusik Kim, Jamin Shin, Paul Hongsuck Seo, Hongjoon Ahn Published: 2026-09-22 Categories: cs.CL, cs.CV arXiv: https://arxiv.org/abs/2609.26638v1 Autoregressive OCR vision-language models accurately convert document images into text and structured markup, but require one sequential decoding step per output token, limiting inference speed. Unlike open-ended text generation, OCR outputs are strongly grounded in the input image, making diffusion-based parallel generation promising. However, when several tokens are predicted in one diffusion step, each is predicted before the others are known. Committing them directly can therefore introduce errors. We therefore introduce GravityOCR, a parameter-shared AR-block-diffusion model jointly trained for parallel drafting and causal AR verification. Verifying drafts before commitment lets the model commit multiple output tokens per round without a separate drafting network. The causal AR path also enables GRPO with sequence- and structure-level OCR rewards, avoiding diffusion-trajectory likelihood estimation while updating the shared drafter parameters. On OmniDocBench v1.6, AR-path GRPO improves the Overall score from 94.92 to 95.16 without reducing diffusion drafting efficiency, while the final model remains close to the original GLM-OCR score of 95.48. In an SGLang serving deployment, GravityOCR commits an average of 9.7 output tokens per forward pass and achieves a $3.94\times$ decode-only speedup on region crops and a $1.32\times$ end-to-end page-processing speedup over AR decoding. --- ### Capable yet Parsimonious: Extracting and Characterizing Hidden Chain-of-Thought in Frontier Models Authors: Xiaoyu Luo, Tao Ren, Wenrui Yu, Xiao Li, Qiongxiu Li, Johannes Bjerva Published: 2026-09-22 Categories: cs.CL, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2609.26637v1 The rapid capability gains of frontier language models are widely attributed to improved reasoning abilities, yet this cannot be verified as raw CoT traces in closed-source systems are hidden. By registering a simple custom tool through a standard API feature, we induce frontier models to externalize intermediate reasoning. Because these traces may reflect post-hoc rationalization rather than genuine reasoning, we first evaluate against native CoT on open-source models and extend to closed-source frontier models including GPT-6 Astra. We find that the extracted reasoning matches native reasoning performance and substantially outperforms no-reasoning baselines, across competition mathematics, science, and code generation. We then characterize how frontier models structure their intermediate reasoning. Across token efficiency, reasoning-step types, and induced reasoning trees, we identify systematic differences in how models externalize, compress, and organize reasoning. We find that Astra exhibits token-efficient directed reasoning, selecting a correct trajectory earlier, while resolving elementary steps internally and externalizing only crucial reasoning. These findings provide a behavioral lens on frontier-model reasoning beyond benchmark scores. --- ### Laryngeal Structure Segmentation in High-Speed Videoendoscopy Using Deep Learning Authors: Sardar Nafis Bin Ali, Mohsen Zayernouri, Dimitar D. Deliyski, Maryam Naghibolhosseini Published: 2026-09-22 Categories: cs.CV, eess.IV arXiv: https://arxiv.org/abs/2609.26636v1 Laryngeal high-speed videoendoscopy (HSV) offers an effective means of observing the motion of different laryngeal structures along with vibratory behaviors of the vocal folds under various voicing conditions. Segmentation of laryngeal tissues enables analysis of different tissue structures and their dynamics, helping characterize the involvement of laryngeal muscles in voice production. Given the large number of HSV frames, automating this task is imperative. While deep learning-based methods have been implemented in previous studies to segment laryngeal structures, they have not been applied to HSV data during connected speech, which poses significant challenges due to excessive tissue movements and image quality limitations associated with fiberoptic image acquisition. The application of deep learning to connected speech data is critical for capturing nonstationary laryngeal behaviors and identifying anomalous patterns associated with voice disorders. The present study aims to address these gaps by training U-Net models to detect the aryepiglottic folds and arytenoid cartilages, vocal folds, epiglottis, and glottal area, using HSV data from both sustained vowel phonation and connected speech obtained from normophonic and disordered voices. Image pre-processing techniques, including noise removal and histogram equalization, were applied to improve the quality of the training HSV images and enhance network performance. Finally, to evaluate the accuracy and reliability of the networks, quantitative performance metrics were used alongside qualitative visual inspection of the test images. The high performance of the developed networks, with overall accuracies exceeding 95%, establishes their potential as reliable tools for automated laryngeal image analysis, quantitative characterization of laryngeal dynamics, and future detection of anomalous laryngeal behaviors in clinical settings. --- ### Knowledge Pull Requests for Continual Document Authoring Authors: Alexander Martin, Benjamin Van Durme Published: 2026-09-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.26634v1 We introduce Knowledge Pull Requests (KPRs), a framework for continual document authoring that makes each change interpretable. Documents require ongoing revision as new knowledge surfaces from other sources, languages, or times, but existing approaches either edit with no account of what knowledge changed or regenerate from scratch. A KPR integrates new knowledge into a document by extracting claims, filtering and routing them to sections, and flagging conflicts with existing content, producing a ChangeLog that separates what knowledge changes (claim proposal) from how the text changes (document diff). We evaluate KPRs on revising Wikipedia across languages and updating query-driven reports on RAGTIME. KPRs integrate more information and better preserve existing content than rewriting from sources or regenerating from scratch, while adding the most information per token generated. A KPR-revised article also grounds question answering better than a frontier model with search, which does not surface knowledge documented only in other languages. --- ### Label-Efficient Learning for Ground-Based Sky-Image Classification: A Benchmark of Transfer Learning, Active Learning, and Pseudo-Labeling on GCD Authors: Esther Bou Dagher, Viktoriya Bu-Dager, Boguslaw Zegarlinski Published: 2026-09-22 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2609.26631v1 Accurate ground-based cloud classification is important for atmospheric monitoring, solar-energy forecasting, aviation weather assessment, and climate observation systems. However, reliable sky-image annotation is time-consuming, especially when cloud types are visually similar or mixed. We study the label efficiency of deep learning for ground-based cloud classification using the Ground-based Cloud Dataset (GCD). Rather than proposing a new architecture, we benchmark three practical strategies under limited annotation budgets: supervised transfer learning, uncertainty-based active learning, and high-confidence pseudo-labeling. An ImageNet-pretrained ResNet50 is used as a common frozen backbone, with experiments repeated over five random seeds for label budgets from $1\%$ to $100\%$ of the training labels. Supervised transfer learning is already highly label-efficient: test accuracy increases from $0.635 \pm 0.018$ with $1\%$ labels to $0.730 \pm 0.002$ with $40\%$ labels, approaching the full-label result of $0.735 \pm 0.003$. Active learning and pseudo-labeling are competitive with supervised sampling and provide small improvements for some metrics and budgets, but neither gives a large or consistent aggregate gain. Diagnostic analyses show that accepted pseudo-labels are reliable, with accuracy from $0.946$ to $0.977$, but biased toward easier high-confidence sky-type groups. In contrast, uncertainty sampling preferentially queries visually challenging groups, including Mixed and the confusable Stratocumulus and Cumulonimbus groups, but these targeted acquisitions yield only modest gains. Overall, transfer learning substantially reduces annotation requirements for GCD, while simple active and semi-supervised strategies provide limited additional benefit over a strong supervised baseline. --- ### PERSONAWEAVER: Controllable Diversity Beyond Conventional Archetypes in Procedural Character Generation Authors: Maan Qraitem, Kate Saenko, Bryan A. Plummer Published: 2026-09-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.26629v1 Procedural character generation aims to populate games, simulations, and other virtual worlds with diverse characters. Large language models (LLMs) offer a promising foundation for scaling this task. However, LLM-based procedural character generation remains at an early stage: existing methods either generate characters directly or adapt profiles retrieved from persona banks. As we show, both approaches produce behaviorally homogeneous populations: characters overwhelmingly agree with positive moral norms and respond to questions with helpful, assistant-like reactions. To mitigate this homogenization, we introduce PersonaWeaver, which disentangles world building from behavioral specification and models behavior through setting general, diverse, manually curated banks of moral positions and conversational reactions. This design allows us to test how far LLM(s) can be pushed beyond their default behavioral patterns across settings. Across ten realistic and fantastical settings and three LLM(s), PersonaWeaver produces broader moral and interactional response distributions than prior work. Its guidance also diversifies interpersonal language, response length, and sentiment. It also produces less archetypal combinations of world attributes. Code is available at https://github.com/mqraitem/PersonaWeaver. --- ### On Basis Function Selection for Sparse Gaussian Process Regression Authors: Marnix Van Soom, Ivan De Boi Published: 2026-09-22 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2609.26624v2 Sparse Gaussian processes achieve $O(N)$ inference by replacing the kernel with an appropriate expansion in a fixed basis $\{φ_j\}$ on the input space. Given a compute budget $M \ll N$, practitioners conventionally truncate the basis to its first $M$ entries. Nothing in the formalism, however, prevents one from selecting only those $M$ basis functions that matter for the data at hand. This would avoid spending budget on basis functions where there is no signal, but it requires a criterion for ranking the candidates. We propose three such criteria derived from an information-theoretic view of the basis-function selection problem. Each criterion matches a different state of knowledge at selection time: a no-data state, a no-prior state, and an in-between state. We then study the performance of truncation versus selection strategies on six UCI regression benchmarks across three basis families: Hilbert-space Gaussian processes (HSGP), variational Fourier features (VFF), and variational inducing spherical harmonics (VISH). We observe that the no-data criterion is a safe default, matching or improving on truncation for HSGP, VFF and VISH, with substantial gains for VISH and improvements over a recently developed selection heuristic for that basis family. The data-aware no-prior and in-between criteria provide substantial gains over truncation specifically for HSGP, which is the most broadly used of the three families in practice. --- ### On Basis Function Selection for Sparse Gaussian Process Regression Authors: Marnix Van Soom, Ivan De Boi Published: 2026-09-22 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2609.26624v1 Sparse Gaussian processes achieve $O(N)$ inference by replacing the kernel with an appropriate expansion in a fixed basis $\{φ_j\}$ on the input space. Given a compute budget $M \ll N$, practitioners conventionally truncate the basis to its first $M$ entries. Nothing in the formalism, however, prevents one from selecting only those $M$ basis functions that matter for the data at hand. This would avoid spending budget on basis functions where there is no signal, but it requires a criterion for ranking the candidates. We propose three such criteria derived from an information-theoretic view of the basis-function selection problem. Each criterion matches a different state of knowledge at selection time: a no-data state, a no-prior state, and an in-between state. We then study the performance of truncation versus selection strategies on six UCI regression benchmarks across three basis families: Hilbert-space Gaussian processes (HSGP), variational Fourier features (VFF), and variational inducing spherical harmonics (VISH). We observe that the no-data criterion is a safe default, matching or improving on truncation for HSGP, VFF and VISH, with substantial gains for VISH and improvements over a recently developed selection heuristic for that basis family. The data-aware no-prior and in-between criteria provide substantial gains over truncation specifically for HSGP, which is the most broadly used of the three families in practice. --- ### A Data-Interventional Framework for Auditing Privacy and Fairness in Generative Medical Imaging Authors: Mischa Dombrowski, Bernhard Kainz Published: 2026-09-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.26623v1 Diffusion-based synthetic data generation offers a promising route for sharing medical imaging data without releasing sensitive patient records. However, generative models face a fundamental tension between privacy and fairness: they may memorize rare training samples, leading to privacy risks, or fail to reproduce underrepresented features, resulting in unfair synthetic distributions. While prior work has largely focused on either memorization or fairness in isolation, their interaction remains insufficiently understood. In this work, we introduce a data-interventional framework to systematically analyze privacy and fairness in diffusion models. We discuss synthetic anatomical fingerprints (SAFs), rare and manually injected image features, as controlled probes to study whether models generalize sensitive attributes across identities, memorize training samples, or suppress rare signals entirely. Across multiple conditioning modalities, we observe a consistent behavior: models either forget these fingerprints or memorize the entire image in which they appear, but do not generalize them to novel images. To support large-scale auditing where explicit sample extraction is infeasible, we further introduce the indicator metric t', which estimates a model's susceptibility to memorization by exploiting the internal structure of the diffusion process. By comparing conditioning signals of varying surprisal, we reveal a clear relationship between conditioning rarity and memorization behavior. Highly surprising conditioning signals act as retrieval keys that amplify memorization, whereas low-surprisal conditioning signals systematically suppress rare features, even when these appear repeatedly in the training data. Our findings provide actionable insights and concrete mitigation strategies for safe and fair synthetic medical data sharing. Code is available at https://github.com/MischaD/Privacy. --- ### Greedy Decoding Is Not Precision-Invariant: Cross-Precision Output Divergence in LLM Inference Authors: Gaoyuan Du, Anam Nawaz Khan, Rex Zhou, Xiaoyang Liu, Deepayan Chakrabarti, Fnu Suya, Xueping Li Published: 2026-09-22 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.26621v1 Greedy decoding from large language models is commonly treated as deterministic. We show it is not precision-invariant: the same model, prompt, and decoding algorithm produce different outputs in BF16 versus FP16 on identical hardware. Across our evaluations of six models (1.1B-7B parameters, four families; divergence additionally characterised at 12B) and three benchmarks, 49-100\% of prompts diverge; a single token flip often cascades into trajectory-level divergence. We develop an empirical error-propagation analysis and find that 22 layers of accumulated body error do not distinguish flipping from non-flipping steps; the outcome depends primarily on the top-two logit margin at the LM head relative to the directional perturbation between the top-two candidates. The analysis makes five testable predictions about intervention outcomes, including that applying more FP32 compute (broader scope) makes agreement worse. The experiments match all five predictions. The best-performing low-overhead intervention we evaluate, selective FP32 LM head recomputation, triggered only when the margin falls below a threshold, delivers +22-36 pp exact agreement on A10G (+12-21 pp on L4 and A100) at less than 4\% latency overhead in low-batch (batch size <=4) single-stream inference. We map the applicability boundary across six models and four batch sizes, and hypothesise that training-time precision stability is a determining factor. The method is a partial mitigation rather than a universal determinism guarantee: its benefit vanishes when body-originated error dominates, including at batch size >=8 and under end-to-end FP8 in our tests. --- ### GeoComposer: Geometry-Grounded Photographic Composition Instruction Authors: Shuangzhi Li, Qiaoqiao Jia, Xingxin Chen, Guile Wu, Dongfeng Bai Published: 2026-09-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.26620v1 Photographic composition aims to provide visual guidance for improving the framing, viewpoint, and spatial arrangement of an image. Early methods primarily rely on image cropping to enhance composition, which is restricted to the viewpoint and spatial arrangement of the input image. Recent methods have explored image understanding and editing to improve composition, but they mainly focus on instruction following and aesthetic quality, overlooking the importance of 3D scene geometry consistency for photographic composition. In this work, we propose GeoComposer, a novel geometry-grounded photographic composition framework that analyzes the composition of a given image to generate textual guidance and synthesizes a visual exemplar that enhances the composition of the given image. To promote geometry-grounded composition, we propose a geometry-aware representation learning mechanism that leverages geometric priors from a visual geometry foundation model to shape the intermediate representations of the composition editing model. This mechanism preserves both global structural relationships and local fine-grained correspondences for geometry-grounded composition. Furthermore, we propose a reinforcement learning strategy guided by a hybrid reward that jointly optimizes instruction following, aesthetic quality, and geometric consistency. This enables the model to generate visual exemplars that faithfully follow the composition instructions while remaining visually appealing and geometrically consistent. Extensive experiments show the superiority of our approach over state-of-the-art methods, highlighting its effectiveness in generating visually appealing and geometrically consistent composition. --- ### MMAP: Multimodal Missing-Aware Pretraining for Longitudinal Alzheimer's Prediction Authors: Fiona Kekwick, Matthew Baugh, Bernhard Kainz, Paul M. Matthews, Wenjia Bai Published: 2026-09-22 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.26617v1 Clinical decision making heavily relies on predicting the disease progression trajectory by seeking to understand patient's health status which is characterised by multimodal medical data. AI holds great potential for learning useful representations from multimodal medical data to predict disease progression and aid clinical decision making. However, development of predictive AI models is constrained by missing modalities and incomplete tabular data frequently occurring in medical datasets. In addition, disease labels alone may only provide limited supervisory signals for learning representations from high-dimensional multimodal data. Here, we present MMAP, a novel Multimodal Missing-aware Alignment Pretraining method for learning image-tabular representations from incomplete data. An image encoder is pretrained with efficient sigmoid contrastive learning combined with generative reconstruction. A tabular encoder is built upon a tabular foundation model. A missing token generator enables the two encoders to take incomplete data as input, enabling the model to be robust against missing modalities, either with missing images or missing tabular data. We evaluate the clinical usefulness of the learnt multimodal representations on two challenging longitudinal clinical tasks for Alzheimer's disease: predicting disease stage conversion and predicting amyloid status. The proposed method outperforms strong multimodal and unimodal baselines. --- ### Semantic Abstraction for Natural Language Inference: a Methodological Framework for Discovering and Compensating Semantic Knowledge and Reasoning Gaps in Large Language Models Authors: David Torres-Moreno, Jorge Hermosillo-Valadez Published: 2026-09-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.26610v1 Despite their outstanding performance on many NLP tasks, LLMs face serious challenges related to semantic abstraction. In this study, we are interested in understanding how LLMs leverage abstract semantic knowledge in natural language inference (NLI), which requires sophisticated linguistic capabilities to interpret implicit meanings, contextual conceptual relationships, and semantic connections between words and phrases. To this end, we propose a methodological framework for constructing new semantic knowledge at a higher level of abstraction, which we define under the notions of semantic compatibility and incompatibility for NLI. In this framework, the meaning of the lexical-semantic relations between the premise and the hypothesis is reconfigured to achieve a more flexible semantic network that induces different reasoning paths in LLMs. These new pathways show a consistent pattern of responses that allows agreement on a single response. The results demonstrate that our proposal allows to discover and compensate for LLMs' semantic knowledge gaps in NLI, achieving significant improvements in accuracy, exceeding 10% for some models, and in particular for the non-entailment class. It is essential to note that LLMs need structured knowledge and not just more data to bridge reasoning gaps. Our hybrid approach directs attention to overlooked word relationships, allowing models to synthesize missing information. We believe that the future lies not in increasing model size, but in creating a semantic scafolding that mimics the flexibility of human thinking. Hopefully, our proposal will enable the development of more robust agents and interpretable reasoning, guiding AI toward reliable language understanding. --- ### Foundation model embeddings capture pre-diagnostic changes on screening mammograms Authors: Kalina P. Slavkova, Eric Brattain, Aditya Gowd, Akash Pattnaik, Jean-Benoit Delbrouck, Matthew Morgan, Julie Bauml, Javid Abderezaei, Khan Siddiqui Published: 2026-09-22 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.26605v1 Foundation model embeddings of screening mammograms may encode pre-diagnostic tissue change without task-specific adaptation. We tested whether embeddings move faster along a data-derived "cancer direction" in women later biopsied for cancer than in matched screen-negative controls, and whether this depends on pretraining domain. We studied 1,773 biopsied women (785 malignant, 988 biopsy-negative) and 1,773 matched controls, each with at least two annual screening exams before their index exam. An identical pipeline was applied to four 2D models: Mammo-CLIP (MC, out-of-distribution mammography), HOPPR (in-distribution mammography), MedImageInsight (MII, general medical imaging), and BiomedCLIP (biomedical vision-language pretraining on literature figures). Breast-level embeddings quantified longitudinal movement along the cancer direction. We compared cases and controls using a between-patient design with complementary mixed-effects analysis, and biopsied versus healthy contralateral breasts within patients. Under matched modality in MII embedding space, malignant cases drifted significantly faster than controls in the first two screening intervals preceding the index exam; biopsy-negative cases showed significance only in the first. MC differences were significant in the first interval for both biopsy groups. Within-patient comparisons showed a broadly similar pattern, with MC significance extending to the second interval in both groups and HOPPR showing significance at interval 1. BiomedCLIP showed no significant differences in either design or biopsy group. Overall, directional embedding velocity emerges as a property of clinically grounded rather than general biomedical pretraining, showing that foundation model embeddings can encode pre-diagnostic mammographic change without task-specific adaptation. --- ### Hierarchical GNNs for power flow: letting physics shape the hierarchy Authors: Carmine Delle Femine, Leire Garin Atxaga, Asier Diaz-Iglesias, Juan Pablo Maroto Herrera, Ane Miren Florez-Tapia, Marco Quartulli, Izaro Goienetxea Urziku Published: 2026-09-22 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.26603v2 Hierarchical latent communication improves the generalization of a power-flow model, shared across three grids, to new operating scenarios. The module exchanges information through two reduced graphs inside the corrective network of GENCO, replacing two of its local correction steps. We compare Kron-derived transports, a same-anchor Quotient construction and the flat GENCO Base architecture, all trained under one protocol of our own with about a hundred times fewer optimizer updates per grid than GENCO's reference training: 200 epochs on three grid topologies, fewer than 1,900 training scenarios per grid and three initialization seeds per model. Evaluation uses 200 newly generated, preselected scenarios per grid. On the training topologies, Kron reaches a macro family-balanced voltage error of $0.851\pm0.110$, 51.3% below a per-bus mean fitted on training solutions (1.747). Kron is below this reference on 98.5% of the 600 fresh scenarios, and both hierarchical models outperform it on every training topology in all three seeds. The flat baseline reaches $5.660\pm0.899$ and does not outperform the reference on any training topology, so Kron's 85.0% reduction relative to it compares architectures within our training regime. Kron is also 31.0% below Quotient ($1.235\pm0.225$). These results demonstrate generalization across operating scenarios within the studied topologies, with one set of learned parameters shared across grids. On two topologies unseen in training, the current models do not yet outperform the fitted reference in calibrated transfer; extrapolation to new topologies is the next development objective. --- ### Towards Hierarchical GNNs for multi-grid power flow: generalization across operating scenarios Authors: Carmine Delle Femine, Leire Garin Atxaga, Asier Diaz-Iglesias, Juan Pablo Maroto Herrera, Ane Miren Florez-Tapia, Marco Quartulli. Izaro Goienetxea Urziku Published: 2026-09-22 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.26603v1 Hierarchical latent communication improves the generalization of a multi-grid power-flow model to new operating scenarios. The module exchanges information through two reduced graphs within a GENCO-based corrective network. We compare Kron-derived transports, a same-anchor Quotient construction and a flat backbone in preliminary trainings of 200 epochs on three grid topologies, with three initialization seeds per model. Evaluation uses 200 newly generated, preselected scenarios per grid. On the training topologies, Kron reduces the macro family-balanced voltage error from 5.660 +- 0.899 to 0.851 +- 0.110: an 85.0% reduction relative to Flat GENCO and 31.0% relative to Quotient, which reaches 1.235 +- 0.225. Both hierarchical models outperform a per-bus mean fitted on training solutions on every training topology in all three seeds. These results demonstrate generalization across operating scenarios within the studied topologies, with one set of learned parameters shared across grids. Evaluation on two additional topologies distinguishes this achievement from cross-topology generalization: the current models do not yet outperform the fitted reference in that calibrated- transfer setting. This preprint presents the architecture and preliminary evidence for hierarchical communication as a component of multi-grid power-flow learning, with generalization to unseen topologies as the next development objective. --- ### Unlocking Cross-Scenario Physical Layer Security: A Mixture-of-Experts Framework with Generative Diffusion Models Authors: Xiao Tang, Tong Hui, Chao Shen, Yichen Wang, Qinghe Du, Li Sun, Zhu Han Published: 2026-09-22 Categories: eess.SP, cs.IT, cs.LG arXiv: https://arxiv.org/abs/2609.26598v1 The future 6G networks are expected to incorporate a proliferation of wireless services in diverse environments, which presents a significant challenge for information security. Conventionally optimization always requires recalculation and learning strategy often suffers poor generalization, which are thus incapable for the security provisioning with wide scenario coverage. In this paper, we propose an adaptive and robust learning framework that leverages a mixture-of-experts (MoE) architecture to achieve cross-scenario physical layer security guarantee. Specifically, we first select a few representative scenarios and establish the scenario-specific generative diffusion model (GDM)-based experts for secure transmission beamforming with artificial noise. The diffusion nature of experts learns the overall probability distribution of security strategy solution landscape and the Transformer-based denoising process enhances the ability to generalize across varying network configurations. Then, a lightweight gating network is constructed to identify the scenarios by engineering the channel features and select the most relevant experts. Finally, an attention-based combiner is introduced to synthesize the security proposals from the top-rated experts to produce a high-fidelity security strategy to cover the unseen scenarios. Simulation results demonstrate that the proposed GDM-based MoE framework can accurately recognize the scenarios and properly select the experts, maintaining near-optimal secrecy rates across a continuum of wireless scenarios and outperforming traditional single-model paradigms. --- ### GTR: Gated Token Recurrence for Efficient Dense Prediction Authors: Zhe Feng, Longfei Liu, Wei Liu, Kai Chen, Jiangang Kong, Wei Zhou, Yifeng Qian, Dexiong Chen, Xuanlong Yu, Xi Shen Published: 2026-09-22 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.26590v2 Self-attention-based vision backbones perform well on dense prediction, but the quadratic computational cost of global softmax attention limits their efficiency as image resolution increases. We introduce Gated Token Recurrence (GTR), a softmax-free recurrent vision backbone that combines gated linear attention, alternating spatial scan directions, and spatially enhanced SwiGLU blocks. GTR is distilled from a detection-specialized DINOv3 teacher using only final-layer patch-token alignment through a linear projection and squared $\ell_2$ loss, without masked-token prediction or intermediate-layer supervision. With Objects365 detector pre-training, GTR-L achieves 58.9 box AP on COCO \texttt{val2017} with 1.908\,ms median batch-one latency under compiled FP16 execution on an RTX~4090. The same backbone also transfers to instance segmentation, pose estimation, oriented detection, semantic segmentation, and monocular depth estimation. In an isolated kernel benchmark, our specialized chunkwise CUDA operator is $4.0\times$ faster than FLA v0.5.0 at 1.6K tokens on RTX~4090. TensorRT deployment on DRIVE AGX Thor achieves 2.282--8.769\,ms median batch-one latency across the evaluated models. These results show that recurrent token mixing can provide an efficient alternative to global softmax attention for high-resolution dense prediction and edge deployment. Project page: https://intellindust-ai-lab.github.io/projects/GTR/ --- ### GTR: Gated Token Recurrence for Efficient Dense Prediction Authors: Zhe Feng, Longfei Liu, Wei Liu, Kai Chen, Jiangjiang Kong, Wei Zhou, Yifeng Qian, Dexiong Chen, Xuanlong Yu, Xi Shen Published: 2026-09-22 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.26590v1 Self-attention-based vision backbones perform well on dense prediction, but the quadratic computational cost of global softmax attention limits their efficiency as image resolution increases. We introduce Gated Token Recurrence (GTR), a softmax-free recurrent vision backbone that combines gated linear attention, alternating spatial scan directions, and spatially enhanced SwiGLU blocks. GTR is distilled from a detection-specialized DINOv3 teacher using only final-layer patch-token alignment through a linear projection and squared $\ell_2$ loss, without masked-token prediction or intermediate-layer supervision. With Objects365 detector pre-training, GTR-L achieves 58.9 box AP on COCO \texttt{val2017} with 1.908\,ms median batch-one latency under compiled FP16 execution on an RTX~4090. The same backbone also transfers to instance segmentation, pose estimation, oriented detection, semantic segmentation, and monocular depth estimation. In an isolated kernel benchmark, our specialized chunkwise CUDA operator is $4.0\times$ faster than FLA v0.5.0 at 1.6K tokens on RTX~4090. TensorRT deployment on DRIVE AGX Thor achieves 2.282--8.769\,ms median batch-one latency across the evaluated models. These results show that recurrent token mixing can provide an efficient alternative to global softmax attention for high-resolution dense prediction and edge deployment.Project page: https://intellindust-ai-lab.github.io/projects/GTR/ --- ### Polyak-Type Extragradient Methods for Monotone Root-Finding Problems Authors: TaeHo Yoon, Sayantan Choudhury, Ezra Greenberg, Nicolas Loizou Published: 2026-09-22 Categories: math.OC, cs.LG arXiv: https://arxiv.org/abs/2609.26581v1 We study Polyak-type step-size selection for extragradient methods for solving deterministic and stochastic monotone root-finding problems. We show that the known projection-type correction for deterministic extragradient arises from minimizing an upper bound on the distance to a solution, paralleling the classical Polyak step-size construction. Using this viewpoint, we provide a unified deterministic analysis of the Polyak-type Extragradient Method (PolyakEG), based on a local critical condition controlling the variation of operator $F$ along the extrapolation direction. This analysis does not require global Lipschitz continuity, and covers sublinear convergence under broader conditions such as Hölder continuity or $(L_0, L_1)$-Lipschitzness and linear convergence under additional strong monotonicity, all through a single framework. We then study the stochastic extensions of this approach. We first prove convergence of a direct stochastic variant, PolyakSEG, when all stochastic component operators share a common solution. We also show that, without this condition, PolyakSEG with nonvanishing step-sizes may fail to converge to a zero of the mean operator. To address this limitation, we propose DecPolyakSEG, which combines decreasing step-sizes with Polyak-type updates, and establish a sublinear residual convergence result without requiring a common solution across the component operators. These results parallel recent developments in stochastic Polyak step-sizes from the convex minimization literature and establish an analogous research avenue in the broader root-finding regime. --- ### Receptiveness, Not Sycophancy: Distinguishing Engagement from Deference in Language Models Authors: Calvin Isley, Johann Gaebler, Max Lamparth, Julia Minson, Sharad Goel Published: 2026-09-22 Categories: cs.CL, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2609.26579v1 A central concern with language models is sycophancy: their tendency to defer to users' views at the expense of independent substantive judgment. In parallel, work on social sycophancy has focused on behaviors such as validation and positivity that may signal inappropriate deference. Yet the markers of social sycophancy are also characteristic of conversational receptiveness, a construct from social psychology shown to improve interactions across disagreement. We argue that this overlap creates a construct-validity problem for social sycophancy evaluations. Using a popular moral-advice dataset, we find that responses classified as more socially sycophantic are also more receptive. Further, increasing the receptiveness of human-written responses---while preserving their substantive conclusions---causes them to be classified as more socially sycophantic. This tight coupling raises the possibility that social sycophancy evaluations inadvertently penalize desirable behavior. In a preregistered experiment comparing substantively equivalent responses, participants prefer the more receptive responses, expect users to be more likely to listen to them, and are more willing to seek advice from their authors. The same overall pattern persists even among participants who believe the original question asker is in the wrong. Finally, we introduce a simple approach that substantially increases receptiveness without increasing substantive deference, demonstrating that conversational receptiveness and substantive independence can be achieved together. --- ### Radiomics--Foundation Fusion for Interpretable RCC Classification: Internal Benchmarking and Exploratory External Transfer Authors: Yuan Liang, Fangyijie Wang, Kathleen M. Curran, Guénolé Silvestre, Sourav Bhattacharjee, Abraham Campbell Published: 2026-09-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.26578v1 Accurate preoperative subtype classification of renal cell carcinoma (RCC) from contrast-enhanced CT remains clinically challenging because clear cell RCC (ccRCC) and non-clear cell RCC often show overlapping imaging appearances. This study evaluates whether foundation representations reduce reliance on handcrafted radiomics, or whether radiomics remains complementary for interpretable tumour characterisation. We compared radiomics, conventional CNN features, MedicalNet-pretrained features, MedVAE representations, and fusion variants for binary ccRCC classification on KiTS23, reporting area under the receiver operating characteristic curve (AUC) with bootstrap confidence intervals and average precision (AP) as a complementary class-imbalance-sensitive metric. We further assessed branch-removal ablation, TCGA/AIMI external transfer, and interpretability using radiomics permutation importance and gate-level analysis. Internally, 3D MedVAE gated fusion achieved the best performance, with an AUC of 82.7% and AP of 92.2%. On the external TCGA cohort, the same model achieved an AUC of 79.5% and AP of 98.9%, although specificity remains uncertain because only two external non-ccRCC cases were available. Gate analysis showed a radiomics-dominant fusion regime, suggesting that foundation representations acted as case-dependent refinement signals rather than replacements for structured tumour descriptors. These findings support radiomics as a complementary and clinically interpretable component of CT-based RCC characterisation in the foundation-model era. --- ### Beyond End-Task Success: How to Audit Visual Experience Retrieval in Robotics Authors: Eshika Pathak, Leela Krishna Published: 2026-09-22 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2609.26567v2 Robots that store past experiences must select which one to reuse in a new scene. Most systems select by visual similarity, and most evaluations report only the success of the selected experience. That number does not show whether the selection was good: a rule can score well by repeatedly using one broadly transferable experience, or poorly because its preferred experience is weak. Since robots increasingly adapt by reuse rather than retraining, a score that describes the library rather than the rule misleads what the field builds next. We contribute an audit methodology: execute every stored experience in every query scene, over two manipulation tasks, three reuse mechanisms, and libraries of $K=3$, $10$, and $50$. Because every alternative's outcome is known, a score can be traced to per-scene selection or to library quality. The audited rules select by nearest-neighbor distance in five visual embeddings, from raw pixels to CLIP. (1) One fixed experience, chosen with hindsight, captures 30-58% of the gap between random selection and an oracle; per-scene selection competes for the remaining 0.07-0.15 in success rate. (2) At $K\ge10$, visual rules concentrate on one experience 1.5-3 times more than the oracle does, and their scores then follow that experience's quality. (3) Wherever a rule differs significantly from a shuffle that keeps its selection rates but pairs them with scenes at random, the rule is worse, for every learned image policy. (4) Visual distance predicts well whether a given pair will succeed (AUROC up to 0.96), yet ranks the candidates within one scene no better than chance for four of five embeddings at $K=50$ (AUROC 0.45-0.52). Exhaustive execution is usually infeasible, so the audit reduces to two cheap reports any study can give: the distribution of selected experiences, and the success of the best single experience in hindsight. --- ### Beyond End-Task Success: How to Audit Visual Experience Retrieval in Robotics Authors: Eshika Pathak, Leela Krishna Published: 2026-09-22 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2609.26567v1 Robots that store past experiences must select which one to reuse in a new scene. Most systems select by visual similarity, and most evaluations report only the success of the selected experience. That number does not show whether the selection was good: a rule can score well by repeatedly using one broadly transferable experience, or poorly because its preferred experience is weak. Since robots increasingly adapt by reuse rather than retraining, a score that describes the library rather than the rule misleads what the field builds next. We contribute an audit methodology: execute every stored experience in every query scene, over two manipulation tasks, three reuse mechanisms, and libraries of $K=3$, $10$, and $50$. Because every alternative's outcome is known, a score can be traced to per-scene selection or to library quality. The audited rules select by nearest-neighbor distance in five visual embeddings, from raw pixels to CLIP. (1) One fixed experience, chosen with hindsight, captures 30-58% of the gap between random selection and an oracle; per-scene selection competes for the remaining 0.07-0.15 in success rate. (2) At $K\ge10$, visual rules concentrate on one experience 1.5-3 times more than the oracle does, and their scores then follow that experience's quality. (3) Wherever a rule differs significantly from a shuffle that keeps its selection rates but pairs them with scenes at random, the rule is worse, for every learned image policy. (4) Visual distance predicts well whether a given pair will succeed (AUROC up to 0.96), yet ranks the candidates within one scene no better than chance for four of five embeddings at $K=50$ (AUROC 0.45-0.52). Exhaustive execution is usually infeasible, so the audit reduces to two cheap reports any study can give: the distribution of selected experiences, and the success of the best single experience in hindsight. --- ### Quantum-Aided Active Device Detection in Energy-Harvesting Symbiotic Radio Networks Authors: Remon Polus, Deemah Tashman, Soumaya Cherkaoui Published: 2026-09-22 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.26565v1 Massive connectivity in next-generation networks demands energy- and spectrum-efficient solutions for large-scale Internet of Things (IoT) deployments. Symbiotic radio (SR) enables passive IoT devices to communicate by backscattering existing cellular transmissions. A key challenge in uplink SR is active device detection (ADD), which directly affects decoding reliability, interference management, and system throughput. We propose an energy-harvesting code-domain non-orthogonal multiple access (NOMA)-SR system in which IoT devices harvest energy from ambient uplink signals and backscatter information using low-density spreading (LDS) codes. To reduce the complexity of ADD, Grover's quantum search algorithm is employed, providing a quadratic reduction in oracle-query complexity over exhaustive maximum-likelihood (ML) search. Numerical results show that the proposed approach closely approaches ML performance while substantially reducing the number of search iterations, demonstrating its potential for scalable ambient IoT systems. --- ### The Disciplinary Language Transfer Problem: How Psychological Vocabulary Produces Governance Failures in AI Agent Deployment Authors: Kymberly Lasser-Chere, Tyler Akidau, Marc Millstone Published: 2026-09-22 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2609.26562v1 The vocabulary used to describe AI agents in governance contexts -- learning, memory, values, compliance, identity, trust -- is borrowed from psychological and organizational science, contributing to systematic failures in how organizations deploy, oversee, and hold agents accountable. This paper argues that the problem is not merely terminological but epistemological: psychological vocabulary carries an "invisible grammar" of its home discipline into governance discourse, calibrating frameworks to a metaphysical entity that does not exist in current AI architectures. We call this the disciplinary language transfer problem. Drawing on Wittgenstein's concept of language games, Kuhn's paradigm-laden observation, Haraway's situated knowledge, and Star and Griesemer's boundary object theory, we show that the transfer operates at three levels (epistemological assumptions, theoretical constructs, and surface vocabulary), each requiring a different remediation. We characterize six foundational epistemological assumptions embedded in Western psychological governance discourse, trace their origin in specific philosophical traditions, and show why each fails when applied to systems without developmental continuity. The paper's practical output is an actionable Disciplinary Audit: a six-question governance document scan operationalized through a translation taxonomy of thirty-seven terms mapping operational constructs to agent-appropriate replacements, presented here in abridged form and openly archived in full. The vocabulary reform proposed here is not merely terminological; it is the condition of possibility for governance frameworks that correctly identify what they are governing. ---