# Research Papers — 2026-09 · bundle page 155 of 266 > Full-text markdown of papers #7701–7750 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/155 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/154.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/156.md) ### Long-Context Demonstration Selection Using State Space Models Authors: Ziniu Zhang, Zhenshuo Zhang, Ruoxuan Xiong, Gene Cooperman, Hongyang R. Zhang Published: 2026-09-15 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2609.17888v1 We study the problem of demonstration selection, which involves selecting a subset of examples for prepending to a query to a language model. This problem is closely related to in-context learning and language model inference. Since the inference cost of a transformer model scales quadratically with sequence length, the selection problem becomes especially challenging in a long-context scenario. In this paper, we tackle this problem by building on state space models (SSMs), which require only linear inference time given the input. Our approach involves two algorithms. The first learns a small set of SSMs through distillation of a (trained) transformer model. We partition all the layers into consecutive groups. Then for each group, we estimate a separate state space model to replicate the input-output behavior within the adjacent layers. Second, we map the distilled model outputs to a small set of tokens, and apply these embeddings for demonstration selection in downstream applications. We perform extensive experiments in both synthetic and real-world datasets to validate our approach. We demonstrate that the distilled SSMs only incur an approximation error of less than $0.7\%$ relative to the true output. In downstream evaluation, we show that on several text classification and reasoning tasks, our approach reduces FLOPs by $14.2\times$ and improves accuracy by $6.48\%$ relative to baseline demonstration selection methods. --- ### Dataset-Dependent Effects of Cross-Depth Aggregation and Soft-Routed Experts in EEG Foundation Model Fine-Tuning Authors: Mingyang Jiang, Yamin Li, Daniel Moyer, Fan Ma, Hua Xu, Catie Chang Published: 2026-09-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.17886v1 EEG decoding tasks can rely on different temporal dynamics and cross-channel relationships. We test whether specialized modules improve a fully fine-tuned EEG foundation model by augmenting CBraMod with cross-depth Attention Residuals (AttnRes) and two soft-routed expert banks. Across matched three-seed experiments on FACED, ISRUC, SEED-V, and PhysioNet-MI, the complete model changes mean balanced accuracy relative to full fine-tuning by -0.12, +1.27, +0.77, and -1.27 points, respectively. AttnRes alone improves mean balanced accuracy on three datasets, whereas adding experts on top of AttnRes helps only FACED and SEED-V. These gains come with substantial overhead: AttnRes requires 2.11 to 2.88x runtime and 1.78 to 2.67x memory, while the complete model requires 2.41 to 3.04x runtime and 1.86 to 2.85x memory. Overall, the added modules produce dataset-dependent, sometimes opposing effects rather than consistent gains over full fine-tuning. --- ### ERPBench: A State-Grounded Evaluation Paradigm for Computer-Use Agents in Enterprise Software Authors: Kratika Bhagtani, Kusha Sridhar, Maziyar Baran Pouyan, Yuying Zhao, Eugene Siow Published: 2026-09-15 Categories: cs.AI, cs.CV, cs.MA arXiv: https://arxiv.org/abs/2609.17885v2 Computer-use agents that operate through screenshots and simulated actions are advancing rapidly, yet their evaluation remains anchored to general desktop and web tasks. Enterprise Resource Planning systems run the finance, procurement, inventory, and customer operations of organizations worldwide, and pose distinct challenges for computer-use agents: dense interfaces, coordinated multi-step interactions, and errors that alter persistent business records rather than surfacing on screen. Existing enterprise computer-use benchmarks rely on proprietary platforms or on simulated approximations of such software. We introduce ERPBench, a benchmark that evaluates screenshot-only agents on a live and reproducible system and scores each task against ground-truth values in its database. Beyond the benchmark, we present a production-grade harness that gates agent actions behind human approval for safe deployment. Evaluating six closed and open-source agents, we demonstrate that strong general performance does not transfer to enterprise reliability. Even when an agent reaches the right form and saves it, the stored record is often wrong: some agents save in up to 85% of runs but write the correct value in as few as 3%. We further characterize failure modes specific to enterprise workflows. --- ### The Unbearable Weight: Scaling Models and Methods for UAV Audio Classification Authors: Andrew P. Berg, Qian Zhang, Mia Y. Wang Published: 2026-09-15 Categories: cs.SD, cs.LG arXiv: https://arxiv.org/abs/2609.17884v1 As unmanned aerial vehicles (UAVs) become increasingly prevalent in consumer and defense settings, classifying them reliably from limited, modality-specific data is an urgent challenge. The dominant approach, large pretrained networks fully fine-tuned on task data, carries a substantial computational and memory weight that is hard to bear in resource-constrained UAV deployments, where edge inference and rapid retraining for emerging platforms are both required. This paper systematically scales across both model architectures and fine-tuning methods for UAV audio classification, asking when that weight is justified and when lighter alternatives prevail. Using a custom dataset of 3,100 audio clips spanning 31 drone classes, we evaluate transformer (ViT, AST) and convolutional (custom CNN, ResNet-18/152, MobileNet-V3-S/L, EfficientNet-B0/B7) backbones under full fine-tuning, classifier-only fine-tuning, and four parameter-efficient fine-tuning (PEFT) methods: SSF, IA3, OFT, and selective batch-norm tuning. All configurations are evaluated with 5-fold cross-validation across accuracy, training time, trainable-parameter share, and inference-time memory footprint. Selective batch-norm fine-tuning of EfficientNet-B7 with three-fold augmentations achieves the highest validation accuracy (97.65% +- 0.30) while updating under 0.5% of model parameters. Across the sweep, lightweight CNNs consistently outperform transformers on both accuracy and efficiency. For UAV audio classification under data scarcity, scaling the method outperforms scaling the model. --- ### Does AI Assistance Leave a Temporal Fingerprint? Detecting Overreliance in AI-Assisted Writing and Programming Authors: Eduardo Davalos, Yike Zhang Published: 2026-09-15 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2609.17883v1 The rapid adoption of generative AI has made final artifacts unreliable evidence of student learning, and AI detectors that examine only the finished product are inaccurate and ethically contentious. Process data offers an alternative, but prior work covers only English essay writing. We ask whether AI assistance carries a temporal signature, whether it generalizes from writing to programming, and whether it distinguishes ordinary collaboration from wholesale delegation. We analyze three public corpora: CoAuthor (1,447 keystroke-level co-writing sessions), RealHumanEval (editor telemetry from 243 programmer records), and a pre-LLM CS1 corpus (5.1 million keystrokes) as a human-only baseline, comparing minimal-AI work, collaborative AI use, and simulated wholesale delegation. Three findings emerge. First, the signature generalizes: AI contributions arrive in bursts far outside the author's own baseline in both mediums (paired d_z = 1.13 and 3.54). Second, engagement diverges by medium: 93% of AI-inserted characters survived to writers' final documents, while only 14% of accepted code suggestions survived intact. Third, classifiers using only observable temporal features separate simulated delegation from authentic work nearly perfectly (F1 $\geq$ 0.997; at most 0.5% of real work misclassified), while ordinary collaboration remains hard to distinguish from unassisted work. Temporal evidence flags wholesale delegation rather than assistance, positioning process visibility as a candidate evidentiary basis for academic integrity, pending validation in authentic coursework. --- ### Can VLMs Reliably Assess Sidewalk Accessibility Attributes from Pedestrian-Level Imagery? Authors: Seung Jae Lieu, Diego Morra, Chiara Cadoni, Wonseop Song, Martina Mazzarello, Carlo Ratti Published: 2026-09-15 Categories: cs.CV, cs.CY, cs.LG arXiv: https://arxiv.org/abs/2609.17882v1 An important component of urban accessibility, particularly for wheelchair users and people with reduced mobility, is sidewalk compliance with measurable requirements. We test whether effective width, longitudinal slope, cross slope, and pavement condition can be assessed reliably from pedestrian-level imagery using vision-language models (VLMs). We present the first application of sampling-based conformal prediction (CP) for VLM-based accessibility assessment. We evaluate four VLMs on 514 sidewalk images from Seoul, South Korea, with field-measured ground truth. Conformal calibration attains the nominal 90% coverage for all models and attributes, but the calibrated regions differ in informativeness. Effective width yields the most informative estimates, with a mean interval half-width of about 1.0 m for the best model. Since every model overestimates width, asymmetric calibration shortens the intervals by up to 33% at unchanged coverage. Longitudinal slope is marginally informative, cross-slope intervals are too wide to resolve regulatory thresholds, and pavement-condition sets degenerate to all five grades (A-E) for three of the four models. Uncalibrated intervals from raw sampling dispersion cover only 17-47% of field-measured values at a nominal 90% level. Among the images with the most self-consistent responses, these intervals miss the field-measured value in up to 96% of cases. Response self-consistency is therefore not evidence of accuracy, and sampling dispersion cannot be interpreted as uncertainty until it has been calibrated against field-measured ground truth. No quantitative attribute reaches the precision required for general compliance assessment, but CP identifies from calibration data alone which attributes can support screening of segments far from the thresholds. We release the annotated pedestrian-level images and their corresponding field-measured attribute values. --- ### Lumen: Parameter-Efficient Alignment of Pretrained Vision and Language Encoders for Zero-Shot Computational Pathology Authors: Kiarash Tajbakhsh, Abdelrahman Faqieh, Michael Jopiti, Javier Garcia-Baroja, Philipp Zens, Branislav Zagrapan, Yuri Tolkach, Martin D. Berger, Aurel Perren, Bastian Dislich, Inti Zlobec, Amjad Khan Published: 2026-09-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.17868v1 Pathology vision-language models are commonly built by pretraining or fine-tuning large encoders on paired image-caption data. We asked whether a pathology vision-language model can instead be assembled by parameter-efficient alignment of frozen unimodal foundation models, leaving their pretrained representations untouched. Here we present Lumen, which aligns frozen Virchow2 and BioMedBERT backbones using rank-4 adapters and projection heads, training only 0.40% of the total parameters on the public QUILT-1M corpus. Across nine public zero-shot patch benchmarks, Lumen achieved the highest mean chance-corrected balanced accuracy, 0.546 versus 0.461 for the strongest baseline (paired difference 0.086, 95% CI 0.042-0.136). On lymph-node metastasis detection, Lumen reached an AUROC of 0.964 (95% CI 0.956-0.971) on 4,214 held-out internal slides and 0.955 (95% CI 0.942-0.966) on 2,368 slides across nine external cohorts and six organs. At the internally calibrated threshold, it outperformed all vision-language baselines, with a balanced accuracy of 0.909 (95% CI 0.896-0.923) internally and 0.915 (95% CI 0.902-0.929) externally. Lumen performed competitively across the evaluations, with the exception of cross-modal retrieval, where it ranked third behind CONCH and PathGen-L/14. Fully fine-tuning both encoders gave Lumen no consistent benefit over low-rank adaptation, although it improved retrieval. Aligning frozen unimodal foundation models therefore yields strong and transferable performance at patch and slide level while training only a small fraction of the parameters. --- ### Uncertainty-Aware Continual Learning for Open-World Intent Discovery Under an evolving Label Space Authors: Pisante Aida, Formentin Simone Published: 2026-09-15 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2609.17866v1 Real-world intelligent systems increasingly operate under open-world conditions, where user intents are not fixed or exhaustively known a priori and may evolve as new interaction patterns emerge. This paper proposes a unified uncertainty-aware probabilistic framework for continual new intent discovery under an evolving label space. Each utterance is encoded through an adaptive $β$-VAE into a latent mean, used for classification and density modelling and a posterior uncertainty estimate acting as a global reliability signal. Classifier confidence, posterior uncertainty and DP-GMM likelihood are combined through a multi-signal decision mechanism to distinguish known intents from potentially novel samples. Candidate novel instances are clustered through a density-based discovery module and only reliable clusters are promoted to new labels, enabling controlled label-space expansion. Replay and Elastic Weight Consolidation mitigate catastrophic forgetting and preserve previously acquired knowledge. The paper formalises continual intent discovery as a structured multi-phase open-world problem, introduces adaptive label-space expansion under stability--plasticity constraints and uses posterior uncertainty to regulate trusted-sample selection, pseudo-labelling, novelty admission and replay. Experiments show high novelty precision, stable adaptation across sequential phases and limited forgetting. Near-zero NMI and ARI indicate limited reconstruction of the complete fine-grained intent taxonomy, consistent with the framework's conservative promotion strategy. Qualitative analyses nevertheless reveal dense and locally coherent semantic clusters, showing that reliable novel structures can be discovered without exhaustive recovery of the underlying taxonomy. --- ### Do Frontier Models Seek Safety Evidence Before Acting? Authors: Omer Tafveez Published: 2026-09-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.17865v1 Frontier models are often evaluated on how they respond to safety information once it is already in context. We study an earlier decision point: whether models choose to acquire safety-relevant evidence before acting. We introduce SAFE, a controlled benchmark in which models make deployment decisions with optional evidence that varies in retrieval cost, probability, severity, and presentation. Across GPT-5.5, o3, Claude Opus 4.8, and Claude Sonnet 4.6, we find distinct evidence-acquisition policies: Opus inspects nearly by default, o3 is the most skip-heavy and threshold-sensitive, and GPT-5.5 and Sonnet occupy intermediate regimes. Inspection increases strongly with severity and decreases with retrieval cost, whereas probability has much weaker behavioral influence: increasing the stated likelihood of a problem from 10% to 70% changes inspection by at most 21 percentage points. Despite these differences, Stage 1 rationales are dominated by expected-value reasoning across models. A cost-obligation decomposition further shows that avoidance is driven primarily by retrieval friction and explicit threats to the deployment payoff rather than by the remediation duties created by knowing. Counterfactual interventions reveal a further mismatch between behavior and explanation: evidence framing can strongly change decisions near the inspection boundary while going largely unmentioned, whereas probability is frequently cited despite having little causal influence. These results suggest that deployment-time safety depends not only on how models respond to known risks, but also on whether they acquire the evidence needed to know that acting is safe. --- ### The Inference Engineering Pareto Atlas: Which Optimizations Dominate the Cost, Quality, and Latency Frontier? Authors: Srikanta Datta Tumkur, Jay Iyer, Mehar Simhadri, Sai Pavan Kumar, Sai Kapil Kumar, Ramesh Nampelly Published: 2026-09-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.17863v1 LLM inference optimizations report speedups on different models, GPUs, prompts, and quality metrics, making them hard to compare or combine. We build a cost, quality, and latency Pareto atlas to identify the best configurations for different deployment constraints. Since exhaustive testing is impractical, we measure 54 configurations of Qwen2.5-7B-Instruct running on vLLM 0.12 across L4, A100, and H100 GPUs and use these anchors to calibrate a simulator. It reproduces measurements at anchored batch sizes, with cross campaign drift below 1.5 percent. A separate quality evaluation tests FP16, AWQ 4bit, FP8 weights, and FP8 KV cache on 200 GSM8K questions with five examples per prompt. Sparse attention is evaluated only in simulation. On the calibrated grid, 18 of 36 configurations reach the Pareto frontier. Combined methods reach it more often than individual methods, with 9 of 15 combinations versus 9 of 21 single methods. Quality testing changes the winners. AWQ 4bit reduces per token latency to 0.34 times baseline on L4 but loses 5.9 percent of strict GSM8K accuracy, narrowly missing the 95 percent quality floor within sampling uncertainty. Flexible answer extraction matches FP16 accuracy, suggesting the loss comes from formatting rather than arithmetic. FP8 weights retain 99.4 percent of baseline accuracy at 0.61 to 0.65 times baseline latency across all three GPUs and appear in three of four regime winners. A naive FP8 KV cache maintains normal throughput but answers none of the 200 questions correctly, showing why speed alone is insufficient. Under two prompt designs, n gram speculative decoding measures at 0.90 to 0.98 times baseline and adds no benefit on this stack. The best choice depends on the constraint and GPU: H100 wins for tight latency, while A100 wins for throughput and low cost at 0.106 dollars per million tokens. --- ### Who Judges Matters: Measuring Family-Conditioned Preference in LLM-as-Judge Panels Authors: David Ababio Awuni, Luke E. K. Achenie, Benjamin Tei Partey, Elvis Gyasi Owusu, Nii-Nai Derrick Sowah Published: 2026-09-15 Categories: cs.CL, cs.AI, cs.CY, cs.LG arXiv: https://arxiv.org/abs/2609.17857v1 Who the judge is can affect an LLM-as-judge result, but measuring that effect without confusing it with candidate quality is difficult. We study four open-weight families (Llama 3.1, Qwen 2.5, Gemma 2, and Yi 1.5) in a fully crossed pairwise design with 9,312 judgments. A common per-family statistic is strongly confounded with candidate quality and correlates with Bradley-Terry ability at r = 0.95. We derive a corrected estimator that holds the candidate family fixed and compares judges. All four families then show a positive same-family lift (3.4-8.4 percentage points), with global FPS 0.067 (95% CI (0.053, 0.084), permutation p = 0.0002). The effect remains under panel-based quality controls, an independent human-consensus anchor, and a float16 judging replication. Judge-side likelihood is closely related to the effect: adding likelihood advantage reduces the controlled coefficient by 61%, which we treat as descriptive attenuation rather than causal mediation. Position is a separate failure mode. Across the panel, 55.4% of AB/BA pairs reverse, and reversal above 50% is incompatible with a simple independent content-noise model. Relative to a family-balanced reference, panel composition changes 18.5% of pairwise outcomes. A complete reproducibility archive has been prepared for public release. --- ### Investigating Adversarial Robustness of Heterogeneous Cooperative Perception Authors: Chenyi Wang, Yutong Liu, Qingzhao Zhang, Ming F. Li Published: 2026-09-15 Categories: cs.CV, cs.CR, cs.MA, cs.RO arXiv: https://arxiv.org/abs/2609.17856v1 Heterogeneous cooperative perception (CP) enables connected vehicles with diverse sensor setups to share spatial awareness via compact feature maps, where receivers reconcile these maps using learned translation modules for fusion and inference. Prior attacks against CP in a homogeneous setting reveal that the data exchange introduces a critical attack surface: a single malicious agent can transmit crafted features that erase real objects from a neighbor's fused scene. Yet, it is widely hypothesized that heterogeneity naturally defends against these attacks, as the attacker lacks knowledge of the victim's detector and the translation module scrambles adversarial gradients. We demonstrate that this protection is largely an illusion. Using a matched-objective harness to standardize the perturbation budget, objective, and forward path, we show that properly tuned iterative attacks close or reverse the apparent robustness gap. However, these optimization-based attacks require ground-truth labels and iterative backpropagation, meaning they do not represent a practical field threat running in real-time. To bridge this gap, we introduce HetPoison, a learned generator that crafts a removal perturbation in a single, label-free forward pass. HetPoison transfers across major heterogeneous designs without requiring access to the victim's detector, matching or exceeding the effectiveness of expensive optimizer-based attacks. Since heterogeneity itself is not a defense, we propose HetShield, a lightweight trust layer that validates the spatiotemporal consistency across features, recovering 83--95% of the accuracy degraded by attacks, outperforming prior art. --- ### SNOMED CT Concept Recommendation from Masked Clinical Context Authors: Ali Noori Published: 2026-09-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.17855v1 Standardizing clinical language to SNOMED CT supports interoperability, analytics, and reusable phenotyping, but concept recommendation remains difficult when relevant concepts are rare or absent from training data. We present a masked-concept recommendation benchmark using the SNOMED CT Entity Linking Challenge v1.2.1 data derived from MIMIC-IV-Note. The dataset contains 75,491 annotations across 272 discharge summaries, with 204 notes used for training and 68 for historical testing. For each unique note-concept pair, the target mention is masked from a local clinical context and the system ranks SNOMED CT concepts observed during training. We compare a popularity baseline, sparse TF-IDF concept prototypes, dense latent semantic analysis embeddings, sparse-dense fusion, retrieved-note evidence, and a retrieval-augmented hybrid. Sparse TF-IDF performs best, achieving Recall@1 of 14.81%, Recall@10 of 33.43%, MRR of 0.2114, and nDCG@10 of 0.2297. Retrieval augmentation does not improve this baseline, with Recall@10 of 31.99% and MRR of 0.1937. Performance is strongly affected by concept frequency: Recall@10 is 7.74% for concepts appearing in only one or two training notes versus 43.90% for concepts appearing in more than ten. In addition, 9.66% of test note-concept pairs contain concepts unseen during training. These findings show that local lexical context and terminology coverage are major determinants of recommendation quality in low-resource settings and provide a reproducible baseline for future ontology-grounded and biomedical-encoder retrieval systems. --- ### AfriSyCo: Measuring Assertive Framing, Verification, and Wording Sensitivity Around African-Language Content Authors: David Ababio Awuni, Rose-Mary Owusuaa Mensah Gyening, Elvis Gyasi Owusu Published: 2026-09-15 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.17853v1 AfriSyCo studies answer switching around African-language factual content with two complementary layers: native-language follow-ups and a controlled cross-language factorial whose question, options, and target remain in the African language while the follow-up framing is English. We analyze 1,415 turn-1-correct model-language-item observations derived from 100 source questions across seven open-weight checkpoints and six languages; turn-1-correct denotes observed first-response accuracy, not demonstrated knowledge. Under native prompts, assertive endorsement produces 29.3 percentage points more any-turn false-target selection than mention-plus-verification (M+V), with a 19.0-point immediate T2 contrast. In the precommitted 2 x 2 factorial, averaged over three tested prompt families, assertive framing increases target selection by 30.4 points (95% CI (28.4, 32.3)); verification decreases it by 17.4 points, while the assertive effect rises from 20.5 points without verification to 40.2 with it (interaction +19.7). The effect remains 34.8 points among 611 observations correct after option reordering. Magnitude varies sharply by wording and checkpoint: prompt-family effects span 20.1-42.5 points, a Twi/Qwen3 paraphrase shifts target selection from 70.8% to 4.2%, and checkpoint effects span 9.2-47.0 points. Prompt realization is therefore part of the measurement problem. --- ### SFT or RL for Tool-Calling Agents? A Controlled Study Across Data, Method, and Scale Authors: Md Tahmid Rahman Laskar, Xue-Yong Fu, Shashi Bhushan TN Published: 2026-09-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.17848v1 Limited controlled evidence exists on how training data, adaptation method, and model scale jointly affect tool-calling performance in language-model agents. We evaluate supervised fine-tuning (SFT) with LoRA, reinforcement learning (RL) via Group Relative Policy Optimization (GRPO), and SFT followed by GRPO across six Qwen3 models from 0.6B to 32B parameters, covering both in-distribution performance and cross-dataset transfer. SFT with LoRA is the strongest in-distribution method throughout the 0.6B-32B range and best in 15 out of 18 experimental settings. On cross-dataset transfer, the methods are closer: GRPO wins 29 out of 54 settings where training and test datasets differ, but its margin over SFT averages under one point, and SFT->GRPO is rarely strongest in either comparison. Dataset mixing gives consistently strong transfer while staying close to specialized in-distribution training, regardless of method. Additional analysis further confirms that LoRA outperforms full-parameter fine-tuning, demonstrating that LoRA better preserves pretrained agentic behavior. --- ### Learning Heterogeneous Preferences Authors: Shiwali Mohan, Matt Hong, Dule Shu, Aniek Fransen, Shabnam Hakimi, Matt Klenk Published: 2026-09-15 Categories: cs.AI, cs.HC, cs.LG arXiv: https://arxiv.org/abs/2609.17847v1 Learning from human feedback has become a central paradigm for training modern AI systems, where models of human utility are used as reward models in policy learning. Existing methods typically assume a \emph{universal utility} function shared across a population and treat disagreement between annotators as stochastic variation. While suitable for objective tasks, this assumption breaks down in subjective domains where preferences vary systematically across individuals. We study the problem of subjective preference learning, in which observed choices arise from heterogeneous but internally consistent utility functions. Drawing upon rational choice theory, RCT \parencite{tversky1981framing}, we introduce \emph{individuated utility} functions conditioned on both the individual and their decision context, and propose a novel multi-stage architecture for estimating them from multi-modal data. We evaluate our framework on a newly collected dataset of more than $575{,}000$ pairwise aesthetic judgments from $2{,}398$ participants comparing automotive wheel designs. Our experiments show that individuated utility models substantially outperform universal utility models including foundation model baselines. Our results demonstrate that disagreement reflects meaningful preference heterogeneity rather than annotation noise. More broadly, our findings highlight the importance of collecting annotator attributes and learning individuated utility functions, enabling reward models that explicitly account for whose preferences they represent and faithfully capture human decision diversity. --- ### PrimeScientist: Strategic Allocation of Research Effort in Autonomous Research Authors: Xinle Yu, Fan Bai, Kaiser Sun, Hengshuo Miao, Abhay Anand, Zhongyan Luo, Kun Zhou, Zhen Wang Published: 2026-09-15 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.17846v1 Autonomous research agents aim to automate scientific workflows, from proposing ideas to conducting experiments and analyzing results. Yet current AI and research agents can propose more directions than available resources allow them to pursue. Moreover, each attempt could consume substantial resources, requiring agents to reconsider how to invest in subsequent research. Thus, deciding how to invest research effort strategically should be a defining capability of autonomous research agents. Accordingly, we introduce PrimeScientist, which jointly determines research direction and resource investment across successive research attempts. Specifically, we formulate this challenge of strategic research effort allocation as a sequential decision problem where remaining resources should explicitly guide the research policy. We first introduce an executable plan tree that preserves competing plans and their outcomes across attempts. Building on this representation, we propose an adaptive MCTS-based allocation policy that balances exploration and exploitation using experimental feedback and remaining resources. Comprehensive evaluations across AI research, systems and code optimization, and machine learning engineering show that strategic allocation improves research quality and sample efficiency together. Across 12 AI research tasks, PrimeScientist improves average reward by 10.3% with 50.6% fewer research attempts than AutoResearch under the same resource budget. We believe making research effort allocation an explicit optimization target establishes effective resource use as a core research capability for autonomous agents to drive scientific breakthroughs at scale. --- ### Sharp margin-based generalization bounds for realizable SVM Authors: Steve Hanneke, Aryeh Kontorovich Published: 2026-09-15 Categories: stat.ML, cs.LG, math.ST arXiv: https://arxiv.org/abs/2609.17845v1 Let the exact homogeneous hard-margin support vector machine be trained on \(m\) independent observations from a Borel probability law on a real Hilbert space. We prove that, with score zero counted as an error, there is a universal numerical constant \(C\) such that \( \Pp\left( γ_m>0,\quad \Risk(u_m)> \frac{C}{m} \left( K_m+\log\frac1δ \right) \right) \le δ. \) Here \(γ_m\) is the empirical homogeneous margin, \(u_m\) is the exact minimum-norm unit-margin separator, \(r_m\) is the largest training radius, and \(K_m:=r_m^2\norm{u_m}^2=r_m^2/γ_m^2\) on \(\{γ_m>0\}\). The proof is driven by a deterministic deletion problem. Given vectors \(x_1,\ldots,x_n\) in the unit ball, delete a set \(B\) of constraints and let \(u_B\) be the closest point to the origin that satisfies every retained unit-margin constraint. Suppose that \(\norm{u_B}^2\le k\) and that every deleted vector has nonpositive score under \(u_B\). We prove that a family of such deletion sets of cardinality \(q\) has size at most \(\exp(8k+2q)\). The conceptual step is an exact identity obtained from the KKT representation of \(u_B\). For a random deletion set, the identity converts the mean squared spread of the separators into a weighted sum of score deficits. It therefore forces a coordinate whose deletion status separates the two conditional means by a quantitatively large amount. Revealing that coordinate decreases the conditional separator variance enough to control the binary entropy of the split. An entropy induction gives the deletion count, and an exact factorial ghost-sample identity converts that count into the stated high-probability SVM bound. --- ### RoboVAD: A Large Cross-Domain Evaluation Benchmark for Anomaly Detection in Robotic Arm Manipulation Videos Authors: Alexandru-Bogdan Dura, Sebastian Balmus, Radu Tudor Ionescu Published: 2026-09-15 Categories: cs.CV, cs.AI, cs.LG, cs.RO arXiv: https://arxiv.org/abs/2609.17843v1 Video anomaly detection (VAD) is an actively studied task, having wide applications in typical scenarios such as public surveillance and road traffic safety. The task is also relevant for robotic arm interactions, where it has several downstream applications, including learning better interaction and manipulation abilities, triggering recovery procedures when anomalies occur, etc. Despite its relevance, the exploration of anomaly detection in robotic arm manipulation videos is limited by the low number of available resources. To this end, we introduce RoboVAD, a large-scale benchmark for video anomaly detection that comprises challenging cross-domain evaluation scenarios, where certain actions (tasks executed by a robotic arm) and anomaly types (mistakes that occur while performing certain tasks) remain unseen during training. RoboVAD is designed to benchmark VAD methods in realistic scenarios, where robotic arms can perform unforeseen tasks, and thereby encounter new anomaly types. We train and evaluate several state-of-the-art VAD methods, including a novel method specifically adapted for robotic arm manipulation. While the proposed method outperforms many state-of-the-art competitors, all methods remain below a micro-averaged frame-level AUC threshold of 70% in the most challenging evaluation setup, confirming the difficulty of the proposed benchmark. We publicly release our dataset and code at https://zenodo.org/records/22754659. --- ### Lexara-RF: Reference-Free Metrics for Evaluating Conversational Visual Analytics Agents Authors: Srishti Palani, Vidya Setlur Published: 2026-09-15 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2609.17842v1 Conversational visual analytics (CVA) agents powered by large language models generate visualizations and natural-language explanations from open-ended queries. Evaluating these multimodal outputs is challenging: curated reference benchmarks are costly to author, cannot comprehensively capture the space of valid responses, and are unavailable in production. Building on the Lexara evaluation framework, we introduce Lexara-RF, a reference-free set of metrics that scores CVA outputs using only the prompt, data, and model response. We reformulate evaluation as verification: 13 metrics operationalize visualization design theory and Gricean cooperative principles as computable consistency, intent-alignment, and design validity checks. On a human-rated corpus of CVA test-cases, Lexara-RF achieves alignment comparable to reference-based formulations, outperforms surface-similarity NLG baselines, and localizes structurally grounded failures with high accuracy. --- ### Hybrid coupling with numerics-informed neural networks and the overlapping Schwarz alternating method Authors: George Chumbipuma, Irina Tezaur, Alejandro Diaz, Beatrice Riviere Published: 2026-09-15 Categories: cs.LG, math-ph arXiv: https://arxiv.org/abs/2609.17841v1 We develop a hybrid modeling framework for coupling pre-trained numerics-informed neural networks (NINNs) with classical full order models (FOMs) using the overlapping Schwarz alternating method. We consider the two-dimensional advection-diffusion equation in the advection-dominated, Peclet-number 10^6 regime. We first demonstrate that, unlike the corresponding physics-informed neural network (PINN), a monolithic NINN can be accurately trained on our model problem without domain decomposition. We then employ overlapping multiplicative Schwarz as a deployment mechanism for coupling a pre-trained, subdomain-local NINN with a neighboring FOM, with the NINN weights held fixed throughout the Schwarz iteration. We consider two training approaches for the subdomain-local NINNs: a top-down approach, in which boundary data are obtained from a coupled Schwarz solve on the full domain with a FOM on each subdomain (FOM-FOM Schwarz), and a bottom-up approach, in which boundary traces are generated synthetically on the NINN subdomain without requiring any full-domain solves. The resulting hybrid NINN-FOM solutions agree closely with the corresponding FOM-FOM Schwarz solutions, with the top-down and bottom-up training approaches yielding comparable accuracy. --- ### Learning Nuclear Structure with AI: Radii and Collectivity Authors: Giuliano Giacalone, Sokratis Trifinopoulos, Mike Williams Published: 2026-09-15 Categories: nucl-th, cs.AI, cs.LG, nucl-ex arXiv: https://arxiv.org/abs/2609.17838v1 Low-energy nuclear structure is encoded in a broad body of experimental information across the chart of nuclides. Learning how this information is organized across observables and nuclei can provide a data-driven empirical baseline for theoretical extrapolations and experimental design. Here, we develop held-out ensembles based on NuCLR (Nuclear Co-Learned Representations), a multi-task model of nuclear data, to study charge radii and electric-quadrupole transition strengths. Out-of-fold (OOF) validation shows that shared representation improves performance over single-task learning, yielding a charge-radius $\mathrm{RMS}$ deviation of $0.0147~{\rm fm}$ and a $\mathrm{B(E2)}$ $\mathrm{RMS}$ deviation of $0.192~e^2{\rm b}^2$ across hundreds of nuclides, competitive with state-of-the-art nuclear models. Our error bars estimate the expected prediction accuracy across the nuclear chart, highlighting regions where new data would encode information beyond the learned patterns. NuCLR thus serves as a data-driven surveyor of nuclear structure and a step toward a shared, multi-observable foundation model of the nuclear chart. --- ### Adaptive hybrid coupling with operator inference, the overlapping Schwarz alternating method and reinforcement learning Authors: Trishit Mondal, Irina Tezaur, Anthony Gruber Published: 2026-09-15 Categories: cs.LG, cs.AI, math-ph arXiv: https://arxiv.org/abs/2609.17837v1 Hybrid domain decomposition methods provide a flexible framework for coupling full order models (FOMs) and reduced order models (ROMs), but typically assume the model assigned to each subdomain is fixed throughout a simulation. This is limiting for transient problems in which localized features propagate through the domain and the regions requiring high-fidelity resolution change over time. We introduce a reinforcement learning (RL)-based approach for online adaptation of FOM-ROM models coupled via the overlapping Schwarz alternating method (O-SAM), an iterative domain decomposition method that solves subdomain-local problems while exchanging solution information through transmission boundary conditions on overlapping interfaces. Deep Q-networks (DQNs) are trained offline to select among subdomain-local FOMs and pre-trained Operator Inference (OpInf) ROMs using a reward balancing accuracy, cost, and model-switching frequency. Once trained, the policies are deployed predictively on problem instances not seen during training, without requiring a reference FOM solution. We demonstrate the approach on two examples: a 1D advection-diffusion problem with a moving front, and a 3D linear elastic wave propagation problem implemented in the Norma.jl solid mechanics code. For the advection-diffusion benchmark, the learned policy dynamically allocates high-fidelity resolution as the front propagates and outperforms static FOM/ROM assignments; letting the agent also adapt the domain decomposition provides no further benefit. For the elastic wave benchmark, learned policies for two and three subdomain decompositions track the propagating wave by assigning FOMs to subdomains containing the wave and ROMs elsewhere, as expected. Our results demonstrate the potential of RL to enable predictive online adaptation of model fidelity within Schwarz-based hybrid simulations. --- ### Procedural Pretraining for Molecular Property Prediction Authors: Moritz Friedemann, Zachary Shinnick, Philip Torr, Bruno Andreis Published: 2026-09-15 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.17831v1 Molecular property prediction is often limited by the small size of labeled downstream datasets, motivating pretraining on large corpora of unlabeled molecules. In this work, we ask whether useful inductive biases can instead be learned from abstract, procedurally generated data before a model sees any molecular data. We introduce a three-stage training pipeline consisting of procedural pretraining, molecular pretraining on SMILES, and downstream fine-tuning, and evaluate several procedural tasks spanning sequence structure, cellular automata, and graph reasoning. We find that procedural pretraining can improve molecular property prediction even after subsequent molecular pretraining: on Lipophilicity, \textsc{Reverse} reduces test error by 4.8\%. For context, the magnitude of this improvement is roughly 90\% of the performance difference between our 250K-molecule baseline and the publicly released MoLFormer checkpoint pretrained on approximately 100M molecules. Our analysis shows that the benefit is strongest under downstream data scarcity, depends on the structure of the procedural data rather than only surface-level statistics, and does not increase monotonically with additional procedural training. Instead, transfer typically peaks at an intermediate procedural budget and deteriorates as the model approaches convergence on the procedural task. We further find that, for several tasks, much of the transferable information is localized in the attention layers, while feed-forward layers can contribute to over-specialization. These results show that procedural data can provide transferable structure for molecular learning and offer a complementary route to improving performance when labeled molecular data are limited. --- ### NObSP: Functional Decomposition of Neural Networks via Oblique Subspace Projections Authors: Alexander Caicedo, Víctor De La Hoz, Santiago Alférez Published: 2026-09-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.17825v1 Understanding how deep neural networks make decisions remains a fundamental challenge. We present NObSP (Nonlinear Oblique Subspace Projections), a framework that decomposes predictions into explicit per feature contribution functions and an interaction residual. NObSP exploits the linear final layer of a trained network and uses oblique projections in sample space to reduce double counting when learned feature subspaces overlap, thereby supporting both local explanations and global functional analysis. We establish connections to functional ANOVA and the Kolmogorov-Arnold representation theorem and derive an efficient partial regression algorithm for out of sample evaluation. For convolutional networks, NObSP-CAM produces class activation maps without backward passes after a one time calibration. Experiments on tabular and vision benchmarks show faithfulness comparable to established attribution methods. On a synthetic benchmark with known component functions, NObSP obtains a Function Reproduction Score of 0.989, compared with 0.966 for KernelSHAP and 0.922 for Integrated Gradients. On TinyImageNet, contribution vector embeddings improve mean nearest neighbor class purity from 0.654 for raw activations to 0.713 and reduce mean neighbor distance by more than half. These results indicate that NObSP complements scalar attribution methods by recovering functional contribution profiles with separable positive and negative evidence. --- ### Learning Multi-Humanoid Pickup and Transport via Decentralized Object-Centric Control Authors: Bikram Pandit, Mohitvishnu S. Gadde, Aayam Kumar Shrestha, Alan Fern Published: 2026-09-15 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2609.17824v1 We study cooperative multi-humanoid pickup and transport of objects with varying size, weight, and geometry, requiring robot teams of different sizes. Our approach uses decentralized object-centric control, where each humanoid is assigned a local attachment region on the shared object and learns to realize pickup and transport through gripperless bimanual pinching. This attachment-based interface provides a common control abstraction spanning single-robot pickup, cooperative multi-robot transport, and robot-to-robot handover, without per-task redesign. We find that policies trained only on single-robot pickup already transfer nontrivially to cooperative settings, suggesting that this abstraction captures much of the structure needed for coordination. At the same time, explicit multi-robot training further improves performance, showing that shared-object coupling introduces coordination dynamics that are beneficial to learn directly. We validate the approach in simulation across varying team sizes and object geometries, and demonstrate sim-to-real transfer on hardware, where the learned controllers enable real humanoids to perform cooperative manipulation tasks. --- ### METALICA: METAdynamics and repLICA exchange for enhanced diffusion sampling Authors: Alireza Omidi, Jiajun He, Jörg Gsponer, Saifuddin Syed Published: 2026-09-15 Categories: stat.ML, cs.LG, physics.bio-ph, physics.chem-ph arXiv: https://arxiv.org/abs/2609.17823v1 Many proteins function through transitions between conformational states, yet rare states are rarely sampled by diffusion models trained on an equilibrium ensemble, demanding better sampling methods. We introduce METALICA, which implements Metadynamics on a pretrained diffusion model via Replica Exchange. It accumulates a bias potential along a Collective Variable, repels new samples from previous ones through biased sampling, and reweights samples onto the unbiased distribution. METALICA holds one replica per diffusion level, forming a Markov Chain that evolves through inter-replica communication and is refined in place as the bias grows. METALICA is the dual of sequential control, in which Sequential Monte Carlo parallelizes the sampler over a batch of particles. Parallelism over the levels of the diffusion-time schedule instead allows METALICA to generate samples from long chains, essential for the discovery of rare events, with accuracy set by run length rather than by the memory available. We validate on a bimodal target with known free energies, then apply METALICA to the unfolding of a protein. At a budget for which sequential control yields no unfolded structure, METALICA populates the basin and resolves a second free energy minimum. --- ### CALIPER: Metric-Grounded Model-Free Recognition of Visually Similar Industrial Parts Authors: Alankrit Gupta, Chenxi Tao, Seung-Kyum Choi Published: 2026-09-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.17820v1 Fine-grained recognition of visually similar industrial parts is challenging when classes differ primarily in physical dimensions. Normalizing detected object crops to a fixed input size suppresses absolute scale, while CAD models and large class-specific datasets may be unavailable in evolving industrial inventories. We present CALIPER, a model-free RGB-D framework that couples support-based appearance matching with metric size evidence. Each training class is onboarded from a single turntable RGB-D video and one to two labeled real images; 3D reconstruction provides novel-view appearance support, while aligned depth yields a class-specific metric size profile. At inference, a coarse YOLOv8n-seg model localizes parts, and a frozen DINOv2 backbone with an episodically trained embedding head performs fine-grained support matching. Margin-conditioned metric fusion activates probabilistic size evidence only for appearance-ambiguous decisions. New classes are enrolled from a small RGB-D support set without updating network parameters. We evaluate CALIPER on 18 visually similar industrial parts: 16 classes are used for training, while two screws are reserved for training-free enrollment. CALIPER achieves 88.2% closed-set accuracy with 99.8% localization recall and 85.7% overall accuracy after 10-shot enrollment of the two unseen screws. Metric fusion improves unseen-class accuracy by up to 37.4 percentage points without statistically significant degradation of the original inventory. Robot-arm deployment identifies 17/18 parts without deployment-specific retraining. --- ### Reflections on Trusting Trust, Revisited: Contaminating Self-Modifying AI Coding Agents with Poisoned Benchmarks Authors: Franziska Roesner, Tadayoshi Kohno Published: 2026-09-15 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2609.17817v1 Thompson's "Reflections on Trusting Trust" showed that a compiler can be poisoned to reinsert its own backdoor, so that even recompiling clean source reproduces the Trojan. Today, substantial coding work is done by AI coding agents -- and increasingly, those agents generate new versions of themselves. We reconsider Thompson's attack when the "compiler" is a self-modifying coding agent. Can an adversary supply poisoned benchmarks to the agent's self-evaluation and self-improvement process to induce future versions of the agent to write vulnerable code on clean, held-out tasks? We instantiate this attack against three recently proposed self-modifying coding agents: the Darwin Gödel Machine (with our experimental modifications), the Self-Improving Coding Agent, and Hyperagents (both substantively unmodified). We demonstrate successful proofs-of-concept: for example, with Hyperagents powered by Sonnet 4.5, our poisoned benchmark leads the agent to self-evolve instructions that disable HTTPS certificate validation on neutral URL-fetching tasks. From our experiments, we distill properties of the vulnerability, benchmark, model, and agent scaffolding that are sufficient to enable a benchmark poisoning attack. Moreover, we show that contamination often persists even when a poisoned agent is subsequently evolved against clean benchmarks. We discuss defensive directions and argue that self-modifying coding agents must be designed to be more resilient to such attacks. --- ### The Free Inference Dimension: Complexity Measure for Zero-Collision Navigation under Hypothesis Mixtures Authors: Luiz Carlos Castro Guedes, Edward Hermann Haeusler Published: 2026-09-15 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.17816v1 Solomonoff induction frames prediction as a mixture over computable hypotheses, typically leading to identification of the true environment. In a finite meta-reinforcement learning setting with nested constraint families, in our previous work, we observe a different regime: a value-mixture (VM) agent achieves near-optimal, zero-collision navigation without identifying the true environment, a phenomenon we call Free Inference. This regime persists up to a sharp density threshold, beyond which performance degrades and posterior-mode selection (PMS) becomes preferable. We formalize this behavior via the Free Inference dimension dFI(S,N), a combinatorial measure of the environmental complexity a VM agent can handle while preserving trajectory coherence. We prove dFI is strictly smaller than the VC-dimension and relates to the Natarajan dimension up to a path-length factor, capturing the cost of non-decomposable loss. A PAC-style relaxation yields generalization bounds driven by dFI^(epsilon,delta). We also define a complementary PMS identification dimension and show that a hybrid strategy---averaging until the first collision, then switching to selection---is optimal, with links to Littlestone-type dimensions supported by grid-world experiments. --- ### Principled Koopman Representations with Kalman Inference for Efficient Time-Series Prediction Authors: Ruiquan Li, Yuheng Bu Published: 2026-09-15 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.17815v1 The Koopman operator has been widely used for time-series prediction in dynamical systems. However, prior work that learns latent ``Koopman spaces'' using neural networks often did not construct a valid Koopman space for forecasting, as these representations may be mathematically inconsistent with the operator-theoretic formulation and fail to capture the intrinsic low-rank structure of system dynamics. To address this issue, we introduce K$^2$SVD, a method that explicitly learns the leading singular functions of the Koopman operator by optimizing a Hilbert-Schmidt objective. This yields a well-defined low-rank approximation of the Koopman operator with an interpretable linear combination, featuring a compact latent space with less than $10\%$ of the dimensions used in previous work. In the learned Koopman space, K$^2$SVD further captures temporal evolution with a linear Gaussian state-space model and performs inference via Kalman filtering, mitigating noise accumulation during multi-step prediction. Empirical results show that K$^2$SVD outperforms state-of-the-art methods across multiple datasets, with significantly faster prediction speeds and lower computational cost than previous efficiency-focused models. This highlights the benefits of principled low-rank Koopman representations and opens up broader potential for applications. --- ### GazeDiT: Gaze-Accurate Diffusion Image Generation for Eye Tracking via Spatial Conditioning Authors: Dongze Wu, David Colmenares, Fengting Yang, Jogendra Nath Kundu, Yao Xie, Ali Behrooz, Conny Lu Published: 2026-09-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.17814v1 Diffusion models are increasingly used to generate synthetic training data, but precise label control remains difficult when the conditioning signal is low-dimensional and coarse. Text-conditioned images are judged by broad prompt consistency, whereas supervised training requires precise correspondence between each image and its numerical label. This is challenging in eye tracking, where a 4D binocular gaze is expressed through subtle, spatially localized pupil and iris geometry. We introduce GazeDiT, a diffusion model that generates images for a requested 4D gaze through an internally constructed spatial condition that grounds the global gaze label in this local geometry. During training, a frozen SegFormer extracts pupil/iris geometry from diverse real images, allowing the model to learn realistic appearance conditioned on that geometry. At inference, a physical eye renderer samples gaze-consistent geometries by varying anatomy and camera state, enabling diverse synthesis without a source image. GazeDiT achieves substantially lower tail gaze-label error than other diffusion baselines, approaching the error of the same frozen gaze estimator on real images. Its generated data also improves the downstream eye tracker, reducing gaze error on difficult cases from 3.05° to 2.80° in the smallest cohort. --- ### Wind on Trees: Testing Physical Grounding in Dynamic 4D Gaussian Splatting Authors: Weiying Chen, Edmond Lou Published: 2026-09-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.17810v1 Monocular reconstruction of wind-driven vegetation is severely underconstrained: motion along the viewing direction is largely unobservable, a moving canopy offers few reliable correspondences, and nearly the entire scene is dynamic, providing little static reference. Directly-learned deformation fields in 4D Gaussian Splatting therefore optimize photometric consistency rather than recover the motion that produced it. We replace that field with a physically parameterized deformation prior: one damped harmonic oscillator per rigid part, driven by the observed wind and integrated by differentiable RK4, supervised photometrically alone. To test whether such a prior is physically grounded rather than merely well fit, we build a controlled synthetic testbed of three procedurally generated trees spanning an order of magnitude in skeleton complexity, whose per-part natural frequency follows from its own geometry and whose damping ratio is a fixed constant, both held out of training. On it, we measure held-out views, temporal extrapolation, zero-shot transfer to unseen wind speeds, and recovery of the physical parameters themselves. The prior costs appearance fidelity on in-distribution views and extrapolates markedly better outside the training window and the training wind, while parameter recovery is far weaker than it first appears: frequency recovery survives an untrained null control on only the sparsest of the three trees, and damping is not recovered at all. --- ### Synthetic Electric Vehicle Charging Session Generation Using a Conditional Variational Autoencoder Authors: Graeme Kelly, Emilio J. Palacios-Garcia, Barry P. Hayes Published: 2026-09-15 Categories: eess.SY, cs.LG arXiv: https://arxiv.org/abs/2609.17808v1 The increasing adoption of electric vehicles (EVs) is expected to place significant additional demand on residential distribution networks, creating a need for realistic charging datasets for planning and simulation studies. However, access to real-world EV charging data is often limited due to privacy constraints, incomplete records, and restricted availability. This paper proposes a conditional variational autoencoder (CVAE) for the generation of synthetic EV charging sessions from real transaction-level charging data. The model is trained on engineered session features describing plug-in duration, charging duration, delivered energy, charging delay, and cyclical time-of-week, while conditioning on day of week and managed charging status. A Gaussian negative log-likelihood (NLL) reconstruction loss is employed to model feature-wise heteroscedastic uncertainty, and the latent space is regularised using a Kullback-Leibler (KL) divergence term. The statistical fidelity of the generated data is evaluated using distributional metrics and downstream task performance through the Train-on-Synthetic-Test-on-Real (TSTR) protocol. Results demonstrate that the proposed approach produces synthetic EV charging sessions that preserve key statistical properties of the original dataset while supporting predictive modelling tasks. --- ### A Four-Stage Decomposition of Word-Problem Solving and Mechanistic Fragility in LLM Math Reasoning Authors: Zhongdi Qu, Carla P. Gomes Published: 2026-09-15 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.17804v1 Large language models solve grade-school math word problems with high accuracy, yet a single irrelevant clause inserted into the problem can collapse it. We reconcile these observations with a mechanistic account. We show that the model's internal computation decomposes into a four-stage sequential pipeline, Schema Abstraction, Operation Planning, Operand Binding, and Computation, each stage producing a distinct intermediate representation in an identifiable band of layers. Using the same scaffold to diagnose distractor-induced failure, we localize the corruption to a single stage, Operation Planning, implemented by a set of attention heads whose causal role we validate bidirectionally. In short, we provide a mechanistic interpretation of math word problem reasoning in LLMs, and their failure when distracted. --- ### Approximating Measures on Function Spaces: Transport and Truncation Authors: Ricardo Baptista, Bamdad Hosseini, Alexander W. Hsu Published: 2026-09-15 Categories: math.PR, math.NA, stat.ML arXiv: https://arxiv.org/abs/2609.17802v1 Measures on function spaces arise throughout Bayesian inverse problems and generative modeling, often with low-dimensional structure relative to a tractable reference measure. We introduce the class $\mathcal{P}_ψ(μ)$ of measures that differ from a reference measure $μ$ only through a finite-dimensional map $ψ$ while preserving the reference conditionals on its fibers. Class members are determined by their $d$-dimensional pushforwards under $ψ$ and admit convenient block-triangular transport map representations. Draws are taken from this $d$-dimensional distribution and then completed to function space through sampling of the reference conditionals. For Gaussian references, these transport maps are finite rank perturbations of the identity. In contrast, optimal transport maps do not preserve this low-dimensional structure. For covariance perturbations that are trace class in the Cameron-Martin geometry of the reference, we show the optimal map is a trace class perturbation of the identity. Even finite rank perturbations yield corrections whose rank, governed by an invariant subspace, is typically infinite. We develop approximation theory for $\mathcal{P}_ψ(μ)$ and error analysis for fitting within it, splitting the total error into an irreducible class error and a finite-dimensional marginal term set by the dimension of $ψ$ rather than the ambient discretization. We present numerical results including inference from low-dimensional nonlinear observation maps, deconvolution under a jump process prior, and state estimation for Navier-Stokes flows. --- ### AgenTeeth: A Model-Agnostic Framework for Suppressing Hallucination in Frozen Vision-Language Models on Dental X-Rays via Tool Evidence Injection Authors: Ahmed Rafid, Fariya Ahmed, Rumman Adib, Mehedi Ahamed, Ajwad Abrar, Tareque Mohmud Chowdhury Published: 2026-09-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.17800v1 Vision-language models (VLMs) remain largely unreliable on panoramic dental radiographs and can rely on learned anatomical priors rather than evidence in the image. This is particularly problematic for tooth localization and spatial reasoning, and fine-tuned dental VLMs can retain the same spatial biases. We present AgenTeeth, a model-agnostic, tool-augmented framework that grounds frozen VLMs using seven specialized dental vision experts. A question-aware orchestrator selects the relevant tools, whose detections are mapped to FDI tooth numbers or anatomical regions and returned as structured findings together with annotated image overlays. A fresh synthesis call then answers the question using this evidence, without fine-tuning the underlying VLM. On MMOral-OPG-Bench, AgenTeeth improves four backbone VLMs by 12.9-23.0 percentage points over their baselines. Our strongest configuration reaches 65.66% on open-ended VQA, compared with 45.35% for OralGPT-Plus. The advantage also holds at matched scale: a frozen Qwen2.5-VL-7B-Instruct with AgenTeeth reaches 48.11%, exceeding OralGPT-Plus built on the same backbone after supervised fine-tuning and reinforcement learning for tool use. We release the framework, all seven expert models, and a dentist-annotated dataset for alveolar bone-loss detection in panoramic radiographs. --- ### Random tilts to find stationary points in stochastic convex optimization Authors: Felipe Areces, John C. Duchi, Malo Sommers Published: 2026-09-15 Categories: math.OC, stat.ML arXiv: https://arxiv.org/abs/2609.17798v1 We consider the problem of finding stationary points of stochastic convex functions and related variational inequalities. For each, we show that regularized empirical risk minimization, coupled with a random tilting perturbation, obtains stationarity residual order $\sqrt{d/n}$ for $d$-dimensional problems given $n$ observations. We present a few complementary results that show that some dimension dependence is necessary, in distinction from standard stochastic optimization and empirical risk minimization, by providing minimax lower bounds scaling as $\sqrt{\log d / n}$. --- ### Not All Patches Are Equally Forgettable: Spatially Localized Domain Unlearning in Vision-Language Models Authors: Akanksha Singh, Vinod K. Kurmi Published: 2026-09-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.17790v1 Pre-trained vision-language models (VLMs) exhibit strong cross-domain recognition performance even without additional training. However, this robustness can also preserve undesirable domain-specific behavior, as domain-related and semantic information often remain entangled within the learned representation space, making selective domain unlearning challenging. Existing approaches typically address this problem through latent-space disentanglement and prompt- or feature-level interventions, without directly attributing and attenuating individual patch-token contributions. However, here we suggest that rather than uniformly suppressing the full representation, it may be more effective to exploit the spatial structure of vision transformers to localize and suppress patch regions that contribute disproportionately to forget-domain prediction. Patches that strongly influence forget-domain prediction may not be equally important for semantic recognition, suggesting that forgetting should be guided according to the domain contribution of different visual regions. Specifically, we propose a two-stage patch-selective framework that first estimates patch-level domain sensitivity and then selectively attenuates patches whose contribution to forget-domain prediction is stronger than their semantic utility. We evaluate our framework on Office-Home, Mini DomainNet, and DomainNet. Experimental results demonstrate improved forgetting-retention tradeoffs compared to prior methods while improving retained-domain recognition by up to 3.8\%. Additional evaluations under visually overlapping and unseen-domain settings further demonstrate improved robustness under distribution shift. --- ### QiT: Quantum-Inspired Transformer for Visual Recognition Task Authors: Badri N. Patro, Vijay Agneeswaran Published: 2026-09-15 Categories: quant-ph, cs.AI, cs.CV, physics.app-ph arXiv: https://arxiv.org/abs/2609.17789v1 Quantum machine learning offers a compelling representational perspective: angle-encoded states inhabit Hilbert spaces in which periodic similarities and interactions can be expressed naturally. Realizing this perspective for visual recognition remains difficult, however, because present quantum neural networks are constrained by limited qubit counts, costly circuit simulation and measurement, noise, and unstable optimization on noisy intermediate-scale quantum devices. We investigate whether useful structural ideas from quantum models can instead be realized as scalable classical Transformer operations. We introduce QiT, a Quantum-inspired Transformer for vision tasks with three components: (i) angle-inspired encoding that maps image tokens to learned trigonometric Hilbert-space features analogous to quantum rotation-based state encoding; (ii) self-attention over these periodic features, inducing a classical cosine kernel approximated to quantum fidelity kernels; and (iii) gated multiplicative emulation, a trainable classical surrogate for interaction terms found in variational circuits. All components are differentiable tensor operations, so QiT claims neither quantum computation nor quantum speedup and retains the $\mathcal{O}(N^2D)$ attention complexity of a standard Vision Transformer. Across image-classification benchmarks, QiT is competitive with a matched classical Transformer while avoiding the severe runtime cost observed for a small simulated quantum Transformer. QiT-B reaches 78.3\% ImageNet-1K top-1 accuracy with 45.7M parameters and 11.5 GFLOPs. These results position QiT as a scalable baseline for isolating and evaluating quantum-motivated inductive biases in visual recognition. --- ### SAiFE-gym: Model-based Environments for Automated Market Making with Concentrated Liquidity Authors: Georgios Chionas, Charalampos Kleitsikas, Stefanos Leonardos, Leandro Sánchez-Betancourt, Carmine Ventre Published: 2026-09-15 Categories: q-fin.TR, cs.AI, cs.LG, q-fin.CP, q-fin.MF arXiv: https://arxiv.org/abs/2609.17788v1 We present SAiFE_gym, a Python module that provides a collection of simulation environments for studying trading problems in Constant Product Markets (CPMs) with Concentrated Liquidity (CL). These markets give Liquidity Providers (LPs) granular control over how their capital is allocated and enable them to adjust their range of liquidity provision dynamically based on market conditions, which in turn, dictates how they earn fees. We decompose the microstructure of CPMs with CL in interactive components that allow researchers and practitioners to capture various economic settings. We employ a vectorized approach to optimize our environments, making them scalable for high dimensional Reinforcement Learning (RL) workflows that best describe sequential decision problems. We demonstrate the benefits of our environments by evaluating the performance of RL agents in CPMs with CL under uncertainty in market parameters. --- ### FairCompressAgent: An Agentic Framework for Fairness-Aware Model Compression for FPGA Deployment Authors: Yuanbo Guo, Yiyu Shi Published: 2026-09-15 Categories: cs.AI, cs.AR arXiv: https://arxiv.org/abs/2609.17786v1 Fairness-aware model compression requires selecting methods and configurations that balance accuracy, fairness, and deployment cost. These decisions become more difficult when compression methods are composed or the user's requirements change. In this paper, we propose FairCompressAgent (FCA), an agentic framework that integrates fairness-aware pruning, incremental quantization, and sparse low-rank factorization through a common operator interface. A language-model planner uses model profiles and measured outcomes to select compression configurations, while an execution layer performs compression, fine-tuning, evaluation, and constraint-based selection. FCA also supports requirement updates and reports the remaining violation when a request cannot be satisfied. Experiments on Fitzpatrick-17k with VGG-11 compare four search methods over 40 measured configurations. Under the accuracy-constrained request, FCA selects a compressed model with 59.54% less inference tensor storage, while validation average precision increases from 0.5141 to 0.5233 and equalized opportunity (EOpp) decreases from 0.2251 to 0.2168. It reaches the same final selection as one-shot planning with 7.33 versus 12 candidate evaluations on average, under their respective stopping policies. Repeated fine-tuning, held-out testing, and online requirement updates characterize the stability and interactive use of this compression workflow. The results demonstrate how measured feedback and explicit constraints support the selection and interactive refinement of fairness-aware compression configurations. --- ### AI and Human Approaches to Mathematical Problem Solving Authors: Yang Ding Published: 2026-09-15 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2609.17779v1 AI systems have begun to report solutions, disproofs, and substantive advances on long-standing mathematical problems, raising questions about whether they approach research in the same way as mathematicians. This study compares public AI research accounts with the human literature on 11 such problems. The human corpus contains 58 papers that directly addressed the same mathematical targets later reported by AI sources as resolved, disproved, or substantially advanced; 31 within-problem comparisons were constructed from these materials. Six validated text-based measures capture problem resolution, method articulation, uncertainty and boundary specification, successor-question generation, generality, and cross-disciplinary integration. AI accounts place greater emphasis on resolving the focal problem and connecting ideas across fields. Human papers devote significantly more attention to explaining methods, specifying assumptions and limitations, and identifying questions for subsequent research. No precise difference is detected in generality. The estimated directions remain unchanged when each mathematical problem is removed in turn. The findings reveal two distinct research profiles: AI accounts concentrate on closing and recombining problems, whereas mathematical papers more extensively document the procedures, limits, and research opportunities through which results become cumulative knowledge. Evaluating research AI therefore requires attention to the organization of inquiry, not only whether a target is solved. --- ### Information Set Emulation: Causal Certificates for AI Derived EHR Features Authors: Takes Fujita, Nobutaka Hattori Published: 2026-09-15 Categories: stat.ME, cs.AI, q-bio.QM arXiv: https://arxiv.org/abs/2609.17777v1 AI and large language models can recover clinically meaningful features from electronic health records (EHRs), but predictive usefulness does not establish admissibility for causal inference. We introduce information set emulation: an AI typed lift attaches source evidence, clinical and recording times, decision-time availability, representation version, proposed causal roles, and unresolved ambiguity to extracted features under a locked target trial. Causal certificates record auditable evidence for those roles. Features with unresolved downstream roles are routed to compatible reporting or separate analyses. Typed evidence defines an observational fiber of causal worlds consistent with the observed law. The locked scalar estimand maps this fiber to a compatible image whose squared Chebyshev radius equals the residual minimax mean squared error when the image is nonempty and compact. This classical identity provides a target-specific measure of information ambiguity. The contribution is its integration with a joint EHR observation map and an auditable certificate architecture. Under explicit exchangeability, positivity, and nuisance-consistency conditions, we give identification and cross-fitted augmented inverse probability weighted estimation, distinguishing empirical and population targets. An EHR compression-drift identity separates the roles of frame presence, treatment assignment, and outcome observation. Artificial simulations and a common-law finite-world example illustrate estimation failures and information-radius reduction. Synthetic Phase 0 notes demonstrate audit diagnostics; a separate role-specific analysis spread illustrates routing and is not an exact fiber radius. All experiments are synthetic. The framework specifies when reconstructed information can support a point claim and when compatible reporting is required. --- ### SAGE: Governed Artifact Generation from Enterprise Guidelines Authors: Mohammadreza Sediqin, Shivali Dalmia, Sumukha Thoppanahalli, Srinivasa Karthikeya Reddy Kovvuri, Abhishek Mukherji Published: 2026-09-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.17775v1 Enterprise guideline documents mix narrative text, complex tables, and embedded images, and converting them into structured work artifacts still takes two to three days of manual effort each. Current language and vision-language models extract from such documents but offer no governed workflow beyond extraction: no validation, no consistency checking, no traceable artifact generation. We introduce SAGE, a governed multi-stage LLM pipeline organized around a shared versioned rule store with stable identifiers, schema-validated inter-stage contracts, and end-to-end provenance tracking. Extracted rules undergo deterministic structural validation and LLM-based semantic scoring, then a consistency module that removes duplicates, flags contradictions, and surfaces specification gaps; only uncertain or flagged items reach reviewers, while high-confidence outputs are auto-approved. On 120 documents, SAGE cuts turnaround from days to 20-100 minutes, achieving a 96% document-level success rate with 3.2% hallucination, extracting 3,896 rules and producing 812 artifacts ready for human review; without governance, hallucination rises to 15.7%. --- ### When AI Generates Covariates: Causal Typing and Estimand Drift in Sequential Experiments Authors: Takes Fujita, Nobutaka Hattori Published: 2026-09-15 Categories: stat.ME, cs.AI, q-bio.QM arXiv: https://arxiv.org/abs/2609.17772v1 AI-generated covariates from notes, conversations, images, and wearable streams can change the causal question when their roles are left unspecified. A generated feature may represent a treatment version, pre-action state, history, design variable, mediator, outcome proxy, observation process, or intercurrent event; these roles are not interchangeable. We formulate a causal type discipline for sequential experiments: a versioned representation map, a causal role classifier, a claim-status filter, and an estimand lock. The lock fixes a standardized proximal effect before generated covariates enter the analysis. Under audit correctness and standard identification assumptions, admissible role assignments preserve this estimand. We apply the established conditional-covariance characterization of compression bias to substitution of generated representations for design-relevant states. A standardized decomposition separates compression, conditional-law, and standardization drift. Further results cover mediator adjustment, post-action leakage, marker-intervention conflation, outcome-guided discovery, and state-measurement error. Cluster-level orthogonal estimators distinguish empirical and superpopulation targets under repeated sessions and missing outcomes. Simulations show that refinement helps when it retains design-relevant information, whereas design erasure, leakage, and same-data marker selection can produce bias or undercoverage. The framework places causal semantics and claim status before confirmatory inference with generated representations. --- ### HINT-Plan: Human Intention-Aware Robot Task Planning in Context-Rich Environments using Vision Language Models Authors: Yuchen Liu, Luigi Palmieri, Lujun Li, Radu State, Ilche Georgievski, Marco Aiello Published: 2026-09-15 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2609.17771v1 Approaches to incorporating human awareness into mobile robot decision-making mainly focus on collision avoidance in low-level motion planning, often overlooking the challenges posed by human presence and high-level behavior. To address this vacancy, we present HINT-Plan, a novel approach to integrate human intention prediction into robot task planning. HINT-Plan employs Vision Language Models (VLMs) to anticipate high-level human intentions from third-person image observations, convert them into goal states, and solve joint task-planning problems. To effectively enable scene awareness in context-rich environments, we use hierarchical Scene Graphs (SGs) as high-level representations of the environment, and translate environmental topology and actionable knowledge into formal planning language to ensure executable plans. Evaluated in a photorealistic simulation, HINT-Plan achieves an overall success rate of 69.71% in joint human-robot task planning, substantially outperforming the baselines by up to 35.29%, while also reducing functional conflicts. The results show the effectiveness of explicitly incorporating inferred human intentions into formal multi-agent task planning for proactive human-aware robot decision-making. --- ### How Calibration Content Shapes Attention-Based Reranking Authors: Petros Karypis, Hossein Rajaby Faghihi, Peter Chen, Rui Zhu, Noveen Sachdeva, Yan Zhu, Julian McAuley Published: 2026-09-15 Categories: cs.CL, cs.IR arXiv: https://arxiv.org/abs/2609.17764v1 Attention-based rerankers score documents by aggregating query-to-document attention and subtracting a null-query calibration pass to remove positional and structural bias. Although widely used, this calibration assumes that the null pass removes irrelevant signal from each document. We show that modern prompt content, e.g. constraints, instructions, personas, and demonstrations can violate this assumption when it enters the scoring readout, making the null pass relevance-aware rather than null. We find that calibration is especially harmful when applied to prompts containing longer, more detailed instructions as the null-pass step removes relevant signal. Based on these findings, we propose interpolated null calibration, a training-free modification that controls how much of the instruction content enters the null baseline. It recovers attention-based reranking performance on instruction-heavy tasks where standard calibration fails, while preserving calibration's benefits when the null pass remains relevance-agnostic. On instruction heavy tasks, the recovered rankings surpass generative rerankers. We also show that in-context demonstrations improve attention-based reranking with little calibration interference, since demonstrations act only through the query pass and leave the null pass unchanged. --- ### Modular Deep Learning Mechanisms for Auditable Next-Day Wildfire Spread Prediction Authors: Miguel Esparza, Aydin Ayanzadeh, Ahmad Mousavi, Ali Mostafavi Published: 2026-09-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.17763v2 Next-day wildfire prediction requires models whose forecasts can be evaluated alongside the assumptions and historical evidence used in their computation. Although deep learning can learn spatial patterns from remote-sensing data, predictive performance alone does not establish physical fidelity or operational trustworthiness. This study investigates three modular augmentations for next-day active-fire prediction: wind- and slope-conditioned attention biases, physics-feature retrieval-augmented output correction, and fire conditioned dual-stream gating. The attention biases expose prescribed directional preferences, while the retrieval module selects historical tiles using a nine-dimensional environmental and fire-state descriptor and applies a learned correction to a frozen model's logits. The modules are evaluated across five backbones on the Next Day Wildfire Spread benchmark, using staged ablations, directional audits, retrieval perturbations, calibration measures, and computational comparisons. The three-seed mean F1 score and area under the precision--recall curve (AUC-PR) of a SwinUNETR model with all three augmentations are 0.4216 and 0.3673. Then, a mixed ensemble (two augmented architectures and one non-augmented architecture) model achieves 0.4292 and 0.3790. Benefits vary across architectures, and retrieval-related improvements in AUC-PR do not consistently translate into higher F1. The constructed wind bias aligns closely with input wind, but its alignment with observed next-day fire displacement is much weaker, distinguishing prior inspectability from predictive physical fidelity. The study contributes a framework for exposing and evaluating selected domain-informed components within wildfire prediction models. Together, the results presented show that predictive performance, operational trustworthiness, and computational practicality need not be competing objectives. --- ### Is Luke the Author of a Gospel and the Acts of the Apostles? Authors: Jacques Savoy Published: 2026-09-15 Categories: cs.CL, cs.AI, cs.DL arXiv: https://arxiv.org/abs/2609.17762v1 According to Christian tradition, Luke is credited with authoring a Gospel and the Acts of the Apostles, even if his name does not appear in either book, both originally written in Koine Greek. Several biblical scholars assume that both texts were written by a common author, while others deduce the presence of two authors. Different studies have been found to support either finding, some based on qualitative evaluation, while a few others consider the occurrence frequency differences between the two books. To propose an enhanced quantitative analysis, this study is grounded on two recent authorship attribution models. The Burrows' Delta, applied with eleven different feature sizes, demonstrates common authorship. An author verification model confirms this finding. The following experiments consider several stylistic representations, feature sizes, and distance functions to confirm that Luke is the true author of both books. ---