# Research Papers — 2026-09 · bundle page 201 of 266 > Full-text markdown of papers #10001–10050 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/201 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/200.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/202.md) ### Context operations to architecture modelling output from large language models and evaluation criteria for their use in systems engineering design Authors: Vinicius Kaster Marini, Petter Krus Published: 2026-09-09 Categories: eess.SY, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2609.10132v1 The development of generative artificial intelligence resources enables opportunities of speeding up systems and engineering design work. This contribution introduces a framework of formal operations for assembling context in LLM-based engineering design. This framework involves the assembly of modular context units, including policy prompts, reference units with persistence, and user questions with prompt vectoring. This approach enables the systematic structuring of interactions with generative models. A formal method for evaluating modelling-as-code LLM outputs is also presented, which enables the evaluation of compliance to intent from LLM answers and thereby asses the support from LLMs for systems architecture modelling. --- ### SA-Profile: Automated Sulcus Angle Profiling from Super-Resolution MRI Authors: Michael Wehrli, Leo Widmer, Edwin Li, Noel Fiechter, Lorenzo Pettinari, Sidaty El Hadramy, Carol C. Hasler, Philippe C. Cattin Published: 2026-09-09 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.10125v1 Trochlear dysplasia (TD) is an abnormality of the femoral trochlea associated with anterior knee pain and patellar instability. The sulcus angle (SA) is used to assess trochlear morphology, but it is typically measured on a single axial MR slice with no clear guidance on which to select, making it sensitive to slice selection and landmark placement. We propose an automatic framework for continuous SA profiling from super-resolved MR volumes. Clinically acquired axial, coronal, and sagittal MR scans are combined using implicit neural representations to reconstruct a high-resolution volume. SA measurements are computed across the trochlear region using two landmark detection U-Net models. The approach was evaluated on the public fastMRI dataset and a small in-house cohort of patients with TD. Compared with conventional manual single-slice SA measurements, the proposed automated method yielded a mean absolute error of 11.6$^\circ$ while providing continuous characterization of trochlear morphology. Population-level analysis demonstrated distinct mean SA profiles between the public cohort and the in-house TD cohort, highlighting the potential of profile-based assessment to characterize TD. By reducing reliance on a single manually selected axial slice, the proposed framework extends conventional SA assessment to a continuous profile-based description of trochlear morphology without additional imaging, while remaining conceptually linked to current clinical assessment. Further validation is required. The code is available: https://github.com/wehrlimi/SA_Profile. --- ### If It's Not Buggy, Don't Fix It: On the Dynamics of Iterative Bug-fixing with LLMs Authors: Xietao Wang-Lin, Anton Isopoussu, Louis Mahon Published: 2026-09-09 Categories: cs.SE, cs.CL arXiv: https://arxiv.org/abs/2609.10123v1 Large language models (LLMs) have become ubiquitous in software development, with LLM-based automated program repair tools increasingly used during code review. In this report, we explore the iterative blind use of LLMs as bug-fixers. Across multiple models and repair environments, we find that LLMs consistently claim to detect bugs in entirely bug-free programs while the rate of repair of buggy programs is less than that of the damage to correct programs. We also explore the long-term dynamics of this iterative process, and find that this frequently reaches a pseudo-bug-fixing cycle where the same changes are added and removed again ad infinitum. Lastly, via mechanistic probing, we unveil the existence of a steering vector which controls the editing propensity, suggesting that LLMs have an internal representation of ``buggy code", and that this representation is what is falsely activated to induce pseudo-bug fixing. These results provide insight towards the dynamics of fully autonomous bug-fixing systems, as well as stopping conditions under ambiguous goals. --- ### ProbPlug: A Plugin Uncertainty Network for Reliable Confidence in LLM Binary Classification Authors: Jianzong Wang, Chuhang Liu, Botao Zhao, Zuheng Kang, Xulong Zhang, Xiaoyang Qu, Junqing Peng, Zhiewei Ye, Yayun He Published: 2026-09-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.10122v1 Large language models (LLMs) have achieved strong performance across a broad range of classification settings, yet the reliability of their predictions remains a major obstacle to deployment in high-stakes scenarios. Although confidence estimation for LLMs has been widely studied, confidence calibration for LLM-based classification remains underexplored. We introduce ProbPlug, a lightweight confidence estimation framework for LLM-based binary classification, which predicts whether an output is correct using internal token features extracted from a frozen LLM. ProbPlug employs a self-attention module to aggregate hidden representations and can be integrated into the original inference pipeline without modifying the base model. Experiments across multiple tasks involving both text-based and multimodal large models show that ProbPlug provides more reliable confidence estimates, improves classification performance with negligible additional overhead, and exhibits strong generalization across tasks. These results indicate that ProbPlug serves as a practical solution for confidence estimation in LLM-based classification. Our code is publicly available at Github. --- ### Data-Centric Post-Training for Financial Reasoning: Mining, Distillation, and Verifiable Learning Authors: Zhirayr Hayrapetyan, Andrei Kalmykov, Denis Kokosinskii, Dmitry Stanishevskii, Dmitry Zmitrovich Published: 2026-09-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.10113v1 Financial text, textbooks, and question-answer pairs are abundant, but only a small fraction is directly usable for reasoning-focused post-training. Existing QA pairs often lack explicit reasoning, sufficient context, or reliably verifiable answers, while textbooks must first be transformed into synthetic training examples. We present a data-centric pipeline that constructs complementary corpora by mining open-source reasoning traces, distilling financial instruction data, and generating knowledge-graph-guided question-answer pairs from financial educational material. After semantic deduplication, three lightweight sequence classifiers select finance-relevant examples, reject under-specified questions, and identify tasks suitable for reinforcement learning with compact rule-based verifiers. For model adaptation, we study supervised fine-tuning and reinforcement learning, while self-distilled fine-tuning and post-training model merging are used to prevent the loss of financial capabilities already present in the starting model. We evaluate the adapted language models using FINESSE-Bench, reporting aggregate performance and changes relative to their starting checkpoints. Across the selected comparisons, ordinary SFT reduces FINESSE-Bench accuracy by 3.2-4.0 percentage points, whereas self-distilled SFT improves over the corresponding starting models by 1.0-2.8 points. Equal-weight merging recovers 3.0 points over its SFT parent and finishes 0.9 points above the original model; GRPO on hard tasks adds 0.4 points after self-distilled SFT or 3.0 points when applied directly to verifiable tasks. These results show that retention-aware adaptation can improve financial reasoning without the regressions observed after ordinary SFT. --- ### Storage-Scalable Progressive Semantic Communication via Knowledge-Base Reuse Authors: Heng Zhu, Ye Liu, Kun Zhu, Feifei Song Published: 2026-09-09 Categories: cs.LG, cs.NI, eess.IV arXiv: https://arxiv.org/abs/2609.10112v1 Existing knowledge-base-assisted semantic communication schemes commonly adopt either single knowledge-base quantization (SKBQ) or multi-knowledge-base residual quantization (MKBQ). SKBQ incurs limited storage overhead but has restricted quantization capacity, whereas MKBQ supports progressive refinement by assigning an independent knowledge base (KB) to each stage, causing the KB storage to grow linearly with the transmission depth. To address this problem, we propose storage-scalable knowledge-base reuse quantization (SSKBQ), which reuses a compact set of KBs across multiple residual refinement stages and thereby decouples the number of transmission stages from the number of maintained KBs. A stage-aware residual supervision mechanism is further introduced to regularize intermediate quantized representations and encourage progressive refinement. Experimental results demonstrate that KB reuse provides an effective solution to the storage scalability problem while maintaining competitive progressive reconstruction performance. --- ### A Trust-Network-Based Federated Learning Framework for Multi-Center Aging Clock Prediction Authors: Chunxu Zhang, Bo Li, Wenliang Wang, Yang Liu, Di Jiang, Yuan Huang, Yo-ichi Nabeshima, Akinori Yamamura, Bo Yang, Qiang Yang Published: 2026-09-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.10108v1 Aging clocks quantify biological aging and help characterize individual health status. What protein interactions are important for accurate aging clocks, and are they zeroth-order or higher-order? Addressing these questions requires learning from large molecular datasets distributed across medical centers, where privacy constraints prevent centralized data sharing. Federated learning offers a natural solution but faces four challenges in this setting: limited local sample sizes, sparse and directional inter-center trust, the need to retain discriminative age prediction while supporting interpretation, and model drift and forgetting under heterogeneous cross-center data. We propose TNFL, a trust-network-based federated learning framework that progressively propagates models along directed pairwise trust relations without centralized aggregation. TNFL combines an age-aware mixture-of-experts model with generative replay to preserve previously learned information and reduce forgetting and drift. Experiments across multiple molecular datasets show that TNFL enables effective aging-clock prediction with limited local data, provides interpretable age-dependent prediction patterns, and maintains stable performance across interaction orders. To investigate the biological questions, we analyze TNFL-identified pairwise protein interactions and their higher-order organization through functional and network analyses. The identified interactions repeatedly form coordinated higher-order subnetworks spanning multiple aging-related biological systems, with several proteins recurring across subnetworks. These findings suggest that TNFL captures molecular relationships beyond isolated pairwise associations and reveals coherent higher-order biological organization associated with aging. --- ### Beyond Training: A Feasibility Taxonomy for Inference-Time AI Governance Authors: Samar Ansari Published: 2026-09-09 Categories: cs.CY, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2609.10105v1 Compute governance today is a governance of training: the thresholds, reporting requirements, and frontier-AI regimes now in force attach to training compute and treat the trained model as the regulatory unit. That picture is incomplete: capability increasingly migrates to the deployment stage through inference-time scaling, agentic scaffolding, and compression onto consumer hardware. This paper asks which mechanisms are available once the regulatory object shifts from the training run to the inference call. We develop a feasibility taxonomy of twenty inference-time mechanisms across monitoring, verification, and enforcement, each rated on a four-point readiness scale against a documented four-vendor evidence base. We then stress the taxonomy against a two-dimensional adversary model (three capability tiers crossed with four adversary roles) and map each mechanism to four governance scenarios (domestic regulation, bilateral or multilateral coordination, industry self-regulation, and compute-marketplace governance). Fifteen of the twenty mechanisms have commercial technical substrates in production today, although governance-grade assurance and adversarial robustness vary substantially. The adversary analysis shows that this readiness holds only against a cooperative deployer and a low-to-medium-capability user: no mechanism rates adequate against a high-capability state-level deployer, and fine-tuning removes the model-internal components of the enforcement cluster, although platform-external controls can persist. A substitution analysis connects the taxonomy to a companion hardware paper as a conditional substitution principle describing when inference-stage and hardware-stage mechanisms provide comparable regulatory coverage under stated conditions. A second-rater reliability check on a random subset of the readiness ratings returned a quadratic-weighted Cohen's kappa of 0.74. --- ### A Systematic Evaluation of Molecule Generation Models for De Novo Drug Design: From Benchmarks to Practical Insights Authors: Xinrui Xu, Xueer Wang, Dan Luo, Sisi Yuan, Xuan Lin Published: 2026-09-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.10099v1 Molecule generation has emerged as a powerful computational tool for de novo drug design, enabling the exploration of chemical space beyond the limits of conventional virtual screening. The field has progressed rapidly, driven by advances in molecular representations, generative architectures, and target-aware modeling strategies. However, existing reviews typically address specific model families or application scenarios in isolation, rather than offering an integrated perspective on how these components collectively form a coherent generation workflow. In this review, we present a comprehensive evaluation of molecule generation models for de novo drug design, covering 82 methods across five deep generative frameworks, including recurrent neural network (RNN)- and Transformer-based models, variational autoencoders (VAEs), generative adversarial networks (GANs), flow-based models, and diffusion models. We first summarize widely used benchmarks and molecular representations, and then examine the methodological principles underlying both general and pocket-conditioned generation. A central contribution of this work is a systematic synthesis and comparative analysis of reported performance across commonly used benchmarks and evaluation metrics. We also summarize representative experimentally validated case studies. Looking ahead, we discuss future directions in standardized 3D data, interaction-aware generation, receptor flexibility, and multi-objective molecular design, with the aim of improving the reliability and experimental relevance of molecule generation. All collected benchmark resources, evaluation metrics, and model references are provided in a publicly accessible repository at https://github.com/JacklinGroup/molecule-generation-review. --- ### LinearMask-GS: Stable-Mask Importance Pruning for Compact 3D Gaussian Splatting Authors: Donghun Ryu, Minhyeok Lee Published: 2026-09-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.10095v1 3D Gaussian Splatting (3DGS) enables real-time novel view synthesis but produces millions of primitives through adaptive densification, leading to significant storage overhead. Learned-mask pruning methods such as LP-3DGS address this by assigning each Gaussian a learnable mask to identify and prune redundant primitives. However, we identify a limitation of this paradigm: the steep slope of the Gumbel-Sigmoid activation drives mask values to the extremes within the short mask-training window, before the importance ranking has stabilized, producing a sharply bimodal distribution from which that ranking can no longer be reliably recovered. We propose LinearMask-GS, which replaces Gumbel-Sigmoid with a linear increment activation that keeps mask values in a mid-confidence regime throughout mask training, producing a stable, unimodal mask distribution whose ranking tracks importance. On Mip-NeRF 360, our method achieves 3.6x and 1.6x Gaussian reductions over 3DGS and LP-3DGS, respectively, while maintaining or improving rendering quality. For outdoor scenes, it yields a 1.6x reduction (from 2.18M to 1.36M) with notable gains in PSNR (+0.38 dB), SSIM (+0.025), and LPIPS (-0.029). --- ### RAP: Research Attention Prediction Reveals Target-Conditioned Evidence Acquisition Biases Authors: Yingqian Wu, Jingcong Liang, Siyuan Wang, Zhenfei Yin, Philip Torr, Junchi Yu, Zhongyu Wei Published: 2026-09-09 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.10092v1 Large language models (LLMs) increasingly act as research agents, yet their ability to track shifts in research attention is difficult to evaluate because reviews and research ideas lack uniquely verifiable outcomes. We introduce Research Attention Prediction (RAP), a rolling benchmark covering 278 AI/ML fields and 1,390 episodes. At each cut-off, an LLM agent searches a temporally restricted arXiv corpus and predicts the next six months' paper shares across eight frozen research directions. Search generally helps, but all four diagnostic models perform worse than an exact-count exponentially weighted moving average (EWMA) baseline in compositional accuracy. We identify two linked bottlenecks. Under cumulative-history access, State carry-forward outperforms direct Forecast for all four diagnostic models; frozen-evidence replay links a shared component of this reversal to Forecast-oriented policies retrieving a smaller share of recent evidence. Even with exact historical activity, future-specific updating remains limited, with only GPT-5.5 plus reopened Search slightly surpassing EWMA. Fine-tuning on realised outcomes improves Qwen3-4B's forecast Spearman correlation by 0.105 on held-out fields at later origins, with gains also on change-rich episodes. --- ### Hybrid Quantum-Classical NLP Classification with Compact Semantic Representations: An Experimental Analysis of Representation Compression Authors: Ali Hassan, Zijia Zhao, Maha A. Metawei Published: 2026-09-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.10089v1 Large language and sentence-embedding models provide rich semantic representations, but their high dimensionality poses a challenge for near-term quantum machine learning (QML), where quantum circuits can process only a limited number of input features. We investigate a hybrid quantum-classical pipeline that transforms high-dimensional sentence embeddings into compact representations for variational quantum classification. The workflow combines a pretrained sentence-embedding model, dimensionality reduction, angle encoding, a variational quantum circuit (VQC), and a classical decision layer. We systematically compare principal component analysis (PCA), neighborhood components analysis (NCA), and linear discriminant analysis (LDA), covering both unsupervised and supervised dimensionality reduction. Using the TREC question-classification dataset, we study the relationship between representation dimensionality, information retention, qubit count, and classification performance. Preliminary PCA experiments reveal a strong information bottleneck: reducing 768-dimensional embeddings to 3, 4, 5, and 8 dimensions retains about 8.2%, 10.2%, 11.9%, and 16.4% of the variance, with corresponding classification accuracies of 50.3%, 51.2%, 57.9%, and 63.4%. In contrast, supervised reduction is substantially more efficient. LDA reaches 85.3% accuracy and NCA reaches 83.1% using only 5 dimensions, under a leakage-free cross-validation protocol, compared with 85.1% for a full 384-dimensional classical baseline. These results indicate that supervised dimensionality reduction can preserve task-relevant information far more effectively than variance-based compression, making compact representations a promising route toward practical hybrid quantum-classical NLP models. --- ### A statistical approach to bias in zero-shot learning: the lens of handwriting recognition Authors: Clarence Chew, Gim Siang Chia, Sukalpa Chanda, Subhroshekhar Ghosh, Soumendu Sundar Mukherjee Published: 2026-09-09 Categories: stat.ML, cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.10084v1 Generalized zero-shot learning (GZSL) has emerged as an important paradigm for visual recognition systems that must generalize to classes that were not observed during training. Traditional GZSL techniques are limited by their applicability to a relatively small number of such unseen classes, scalability beyond which is challenging due to its well-known misclassification bias towards classes observed during training. In this work, we investigate the GZSL paradigm through the lens of zero-shot handwritten word recognition over extremely large vocabularies. We propose a statistical approach to rectifying this bias, which views any classical GZSL feature learner as a black box mechanism whose intrinsic bias in identifying the training status (seen vs. unseen) of a typical data point we aim to correct, similar to an out of distribution inferential problem. Our method leverages a simple two-stage hierarchical architecture, combining a classical GZSL blackbox in the first stage and an ensemble of lightweight Monte Carlo bias-correctors in the second. Once debiased, the classification of test data is undertaken only restricted to its predicted training status via well-founded statistical methods (eg nearest neighbour, logistic regression and random forests). We achieve relative accuracy improvements of over 20% in the classification of unseen words compared to established techniques. A key outcome is that word recognition over large scale vocabularies is amenable to a much lower dimensional representation (~15 dimensions). Our approach is underpinned by mathematical analysis that captures the essence of the statistical approach to bias correction. Our approach to bias rectification can be combined in a turn-key fashion with any classical GZSL learner as a blackbox, thereby suggesting a wide scope of applicability of this method for a wide variety of GZSL implementations in different domains. --- ### Automatic Reproducible Camera Intrinsic Calibration Authors: Xiangcheng Hu Published: 2026-09-09 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2609.10082v1 Accurate camera intrinsic calibration is fundamental to robot perception, and the accuracy depends on the quality of the collected images. However, existing target-based calibration methods often require the practitioner to manually filter out high-quality images and to specify an appropriate radial distortion order. This paper presents a fully automatic intrinsic calibration pipeline that determines both from the collected data. We adopt an iterative rejection scheme that estimates parameters on a candidate image set and removes views whose mean residual exceeds a multiple of the median. Crucially, this process runs independently under each candidate distortion order, so that the retained image set is consistent with the residual scale of that order. Further, the distortion order is selected on held-out images, with the intrinsics and distortion fixed and only the board pose re-estimated, ensuring that an added coefficient is supported by independent observations. Finally, we integrate both steps into an interactive calibration tool that supports full-pipeline data inspection and parameter estimation. Experiments on our own camera data and five public real-world datasets show that image filtering reduces the held-out reprojection error by 25\%, the order selection further by 5\%, achieving the lowest held-out mean among four compared configurations without manual image selection. We will release the code and data to facilitate future research. --- ### Physics-Informed Multi-Task Surrogate Model for the Martian Nightside Thermosphere Authors: Sergey Nikiforov Published: 2026-09-09 Categories: astro-ph.EP, cs.LG arXiv: https://arxiv.org/abs/2609.10077v1 Modeling the Martian nightside thermosphere remains challenging due to sparse in situ sampling and strong coupling among transport, magnetic, and seasonal processes. Purely data-driven models can produce non-physical artifacts, such as density inversions, in poorly sampled altitude regimes. We present a multi-task physics-informed neural network that simultaneously predicts the base-10 logarithmic densities of four neutral species (O, CO$_2$, N$_2$, and Ar) using more than a decade of MAVEN/NGIMS observations (MY 32-38, 2014-2025). A shared backbone learns a common representation of the nightside thermospheric state and branches into species-specific output heads. A weak monotonicity prior is incorporated via automatic differentiation by penalizing positive vertical gradients in logarithmic density. Experiments using an orbit-disjoint train/validation/test split show that physics-informed regularization substantially reduces non-physical inversions while preserving predictive skill and slightly improving it in the best-performing configuration, as measured by RMSE, MAE, and $R^2$. The resulting model provides a computationally efficient surrogate for nightside thermospheric reconstruction with improved vertical consistency. --- ### Reference-Based Bias Detection in LLMs via Relative Representations of Hidden States Authors: Marek Jeliński, Jan Dubiński, Maciej Chrabaszcz, Sebastian Cygert Published: 2026-09-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.10060v1 Existing bias auditing methods typically rely on model outputs, requiring costly benchmarks or judge models and potentially missing internal shifts that never appear in generated text. We propose a reference-based method that audits bias in hidden-state representations across related model variants, for example before and after fine-tuning. Because fine-tuning reshapes representation geometry, absolute hidden states are not directly comparable, so we encode each sentence by its similarities to a fixed set of anchor sentences, yielding relative representations in a shared comparison space. There we measure how target groups shift in their association with positive and negative attributes, a quantity we call the Representational Bias Shift $ΔB$. Across three model families and the WildGuardMix, DecodingTrust and ToxiGen benchmarks, $ΔB$ correlates with output-level bias change in 15 of the 18 settings we test, reaching $|r| = 0.84$ ($p < 0.001$) under full fine-tuning and becoming more model-dependent under parameter-efficient adaptation. Thresholding $ΔB$ detects checkpoints whose bias increased with ROC AUC between $0.65$ and $0.99$, and on WildGuardMix and DecodingTrust it separates them better than a SEAT-based baseline for all three families. $ΔB$ is also stable under changes to the anchor set, attribute sets and target templates. Our method requires no task-specific evaluation data and audits a model in about three minutes, using $3$-$50\times$ less compute than the output-level benchmarks considered here. We view it as complementary to output-based auditing rather than a replacement for it. --- ### NOPE-HYPE: A Structured Simulation Workflow for Robust Speech-to-Text Across Diverse Acoustic Environments Authors: Niramay M. Patel, Bibek Behera, Raksha Sharma Published: 2026-09-09 Categories: cs.SD, cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.10058v1 Robust speech-to-text translation systems should perform reliably across diverse acoustic conditions, yet practical pipelines lack controllable tools for systematic environment exploration. Large speech models remain sensitive to unseen acoustic conditions, as training data rarely cover the full range of real environments.We present NOPEHYPE, a structured training workflow that combines a controllable environment simulator, coverage-optimal environment reduction on Power Spectral Density (PSD) templates, and a small, interpretable hyperparameter search over simulator knobs. We show that simulator-generated noise achieves performance comparable to balanced realnoise training across Whisper and SeamlessM4T models, provide principled environment prototype sets, and identify practical default simulator configurations from a structured 27-run hyperparameter sweep. --- ### OntologyAligner: Ontology-Aligned Retrieval and Hierarchy-Guided Large Language Model Reranking for Biomedical Ontology Normalization Authors: Jie Song, Zhichuan Xu, Ziyu Lu, Meng Xiao, Cheng Bi, Yuxin Zhang, Xin Zheng, Xiaoran Li, Qiongfang Cao, Hao Yang, Bairong Shen Published: 2026-09-09 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.10055v1 Biomedical ontology normalization maps free-text expressions to standardized concepts, enabling consistent integration and analysis of biomedical data. This task remains challenging because lexical variation and subtle distinctions among hierarchically related concepts can obscure concept boundaries. We present OntologyAligner, a three-stage framework that combines ontology-aligned retrieval, large language model candidate reranking, and selective hierarchy-guided refinement. We also construct PhenoNormBench, a unified benchmark comprising 13,390 samples from seven Human Phenotype Ontology datasets. OntologyAligner achieved state-of-the-art performance on HPO normalization, with 88.78% Macro Top-1 Accuracy and 86.75% Micro Top-1 Accuracy, exceeding the strongest baseline by 4.85 and 5.07 percentage points, respectively. Ablation analyses showed complementary contributions from all three stages, and sensitivity analyses demonstrated stability across candidate-set sizes and model backbones. Applications to MONDO, MEDIC, and NCBITaxon further established portability to other ontologies. OntologyAligner offers a generalizable framework for accurate mapping of biomedical text to structured ontology concepts. PhenoNormBench and the code are publicly available at https://github.com/zhelishisongjie/OntologyAligner. --- ### Orukeet: Multilingual ASR with Frozen Gabor Kernels Authors: Nathan Roll, Irene Yi, Büşra Marşan, Vianney Grenez, Gabriel Stein, Momcilo Mrkaic, Pavle Padjin, Vladimir Zeljkovic, Calbert Graham Published: 2026-09-09 Categories: cs.SD, cs.LG, eess.AS arXiv: https://arxiv.org/abs/2609.10054v1 Orukeet replaces half of an adapted Parakeet encoder's temporal filters with 12,288 fitted Gabor kernels, freezes these replacements, and trains the remaining parameters on multilingual and multi-accent data. Final adaptation and checkpoint selection use LibriSpeech test-other. Across 20,146 FLEURS recordings in 25 languages, pooled word error rate (WER) falls from Parakeet's 11.01% to Orukeet's 9.85%, a 10.6% relative reduction. Orukeet has lower WER on 23 of the 25 languages. Orukeet outperforms Parakeet on 61 out of 74 tested splits, including LibriSpeech test-clean (1.46% vs. 1.53% WER), test-other (2.86% vs. 3.14%), and FLEURS English (3.82% vs. 4.28%). All comparisons decode the same audio with matched NeMo settings. The fitted kernels are stored as ordinary convolution weights, retaining Parakeet's architecture and inference operators. --- ### Direct Diversity Optimization for Diverse Successful Trajectories in Preference Post-Training Authors: Junwon Ko, Dong-Jae Lee, Minchan Kwon, Sunghyun Baek, Junmo Kim Published: 2026-09-09 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.10052v1 LLM agents for sequential decision tasks are often post-trained with trajectory-level outcome labels, but such labels provide little supervision for preserving multiple successful branches from the same decision state. We study this problem as successful strategy coverage: how broadly a model realizes distinct successful strategies under a fixed rollout budget. We present Direct Diversity Optimization (DDO), an offline post-training method that combines Divergence-Tree Collection (DTC) with the Reference-Relative Target-Odds Objective (RTO). DTC constructs state-aligned branch sets rooted at shared decision states, and RTO trains the model to match reference-relative targets over successful alternatives. DDO achieves the strongest task success and successful strategy coverage among the compared post-training methods across BabyAI, BabaIsAI, and WebShop. It also achieves the highest recovery rate after local action replacement and higher task success and coverage than successful-only imitation and decoding-time diversification controls. --- ### Zero-Shot Temporal Localisation of Audio Deepfakes in Multi-Speaker Conversations Authors: Soumyadeep Roy Published: 2026-09-09 Categories: cs.SD, cs.LG arXiv: https://arxiv.org/abs/2609.10051v1 Voice-cloning fraud increasingly relies on surgical injection: a genuine conversation in which only one or two sentences are replaced by synthetic speech. Utterance-level deepfake detectors emit a single real/fake label per clip and cannot report where the synthetic speech lies. We formalise this as Temporal Deepfake Localisation in Multi-Speaker Conversations (TDLMC), show that equal error rate and min-DCF are ill-posed once a file contains both classes, and propose temporal metrics for this regime. Our contribution is a training-free five-stage pipeline that wraps a frozen binary detector and adds segment-level output with no retraining, using a two-threshold hysteresis finitestate-machine decoder to turn noisy window scores into coherent intervals. On 180 constructed multi-speaker conversations from ASVspoof 5, the system attains temporal intersection-over-union 0.90, temporal detection rate 0.95, and MS-DCF 0.26 with a strong backbone, and its false-alarm rate on genuine speech is below 6%, falling under 2% on genuine real multi-speaker dialogue (AMI). Under an identical pipeline, a trained localiser improves temporal IoU by only about 0.04, bounding the cost of forgoing supervision. Evaluated across three frozen detectors under one decoder whose constants are selected on a held-out calibration split, and with a controlled analysis attributing the residual false-alarm rate to a backbone domain gap rather than to the decoder, this provides the first zero-shot baseline and a reusable benchmark for TDLMC. --- ### MedDeID enables locally governed clinical-text de-identification from real or synthetic training data Authors: Stig Hellemans, Tom Stroobants, Elyne Scheurwegs, Pieter Meysman, Philippe G. Jorens, Kris Laukens Published: 2026-09-09 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.10049v1 Clinical notes contain personally identifiable information (PII), restricting reuse for research and medical AI, especially when data cannot leave an institution. We developed MedDeID, an on-premises framework combining in-house annotation and synthetic-note generation with model training, inference, pseudonymisation and evaluation. On an independently annotated, adjudicated 300-note Dutch hospital benchmark, a hospital-trained compact transformer detected 98.9% of identifying text while redacting 0.24% of text outside annotated identifiers; a synthetic-only counterpart detected 96.1%. On 100 primary-care notes, the synthetic-trained model achieved higher recall than the hospital-trained model (90.3% versus 87.0%) and greater robustness to identifier-format perturbations. An English instantiation trained without real text detected 99.7% and 98.9% of annotated identifier characters on two external synthetic benchmarks. These results demonstrate transfer of the workflow to another language, but not clinical English performance. MedDeID provides a route to locally governed de-identification using real or synthetic training data. --- ### Belief-State Engine: Augmenting LLMs for Principled Planning Under Partial Observability Authors: Arnab Chattopadhayay, Debdipta Halder Published: 2026-09-09 Categories: cs.AI, cs.LG, cs.RO arXiv: https://arxiv.org/abs/2609.10036v1 Large language model agents produce fluent action sequences across a wide range of tasks, yet they fail in characteristic ways once the environment becomes partially observable. Ambiguous feedback pushes them into premature commitments. A single informative observation can collapse their uncertainty onto the wrong hypothesis. Policies drift as the history grows. We trace these symptoms to a common structural cause. An LLM agent, as commonly deployed, is a history-conditioned policy with no explicit belief over hidden state. We propose an architectural fix. The Belief-State Engine (BSE) is an inference module placed outside the LLM. It maintains a Bayesian posterior over the latent states of a given POMDP (Partially Observable Markov Decision Process) model, and at each decision step it exposes only that posterior to the LLM. The raw action-observation log is not shown. We set out a minimal four-axiom specification of what a belief-consistent internal state must satisfy, and prove that the LLM paired with the BSE is a sound Markov policy on the belief MDP induced by the underlying POMDP. It therefore inherits the Bellman optimality guarantees of classical POMDP theory, provided the LLM is never exposed to the raw history. We evaluate the architecture on the Tiger POMDP and a red-team attack-graph task, against six baselines: a reactive LLM, Chain-of-Thought, ReAct, a natural-language belief tracker, QMDP, and POMCP. Across both domains, the BSE-augmented agent improves task return, belief calibration, and decision consistency. Ten targeted ablations isolate the contribution of each architectural choice confirms that the effect is not specific to any one model. Code, environment specifications, prompt templates, and seed logs accompany this paper. --- ### Field-level prediction of mid-plane stress tensor fields in concrete target penetration: a cross-velocity graph neural operator surrogate Authors: Wenpu Du, Peng Zhou, Yunlong Xia, Sinuo Xin, Congcong Zhang, Boyang Zhang, Yi Zhang, Wenzheng Xu Published: 2026-09-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.10032v1 Although the impact resistance of concrete has been studied extensively, a framework linking mesoscale heterogeneity to full-field stress-tensor prediction has been lacking. Data were generated with a full-scale aggregate-resolved LS-DYNA model (projectile diameter 45 mm, mass 2.13 kg, target diameter 500 mm x thickness 200 mm, mesh 10 mm), verified against published penetration experiments (Frew 2006, Hanchak 1992, Forrestal 1996) by configuration similarity. The dataset contains six-component stress-tensor fields on the X-Z mid-plane for 400 cases (4 impact velocities x 100 aggregate seeds). Three contributions are reported. First, case-by-case verification of the terminal penetration state delimited the rest-state validity of penetration depth and anchored reliable observables to rigid-body motion and field-level stress evolution. Second, a field-level graph neural operator surrogate learned the time-varying stress-field evolution and evaluated cross-velocity leave-one-out extrapolation. Third, the full-scale, aggregate-resolved, cross-velocity, per-seed database was established as a reproducible resource. Cases at 100, 135 and 200 m/s still moved at window end (negative velocity, i.e. rebound), and only one 165 m/s case arrested. Penetration depth is therefore not reported as a rest-state scalar except for the single arrested case (69.33 mm); nose-node depth differences were confirmed as numerical artifacts of displacement integration after erosion. The single-step relative L2 error was 0.6977, reported honestly; autoregressive rollout from frame 11 to 39 took about 144 ms, a speedup of about 3.6x10^3 to 4.3x10^3 relative to single-core LS-DYNA, reported as application value. Validation is bounded by configuration similarity and field-level self-consistency; the framework is a simulation-trained decision-support method within the studied parameter space. --- ### Dynamical Non-compensatory Multidimensional IRT Model Using Variational Approximation Authors: Hiroshi Tamano, Daichi Mochihashi Published: 2026-09-09 Categories: stat.ME, cs.LG arXiv: https://arxiv.org/abs/2609.10028v1 Multidimensional item response theory (MIRT) is a statistical test theory that precisely estimates multiple latent skills of learners from the responses in a test. Both compensatory and non-compensatory models have been proposed for MIRT: the former assumes that each skill can complement other skills, whereas the latter assumes they cannot. This non-compensatory assumption is convincing in many tests that measure multiple skills; therefore, applying non-compensatory models to such data is crucial for achieving unbiased and accurate estimation. In contrast to tests, latent skills will change over time in daily learning. To monitor the growth of skills, dynamical extensions of MIRT models have been investigated. However, most of them assumed compensatory models, and a model that can reproduce continuous latent states of skills under the non-compensatory assumption has not been proposed thus far. To enable accurate skill tracing under the non-compensatory assumption, we propose a dynamical extension of non-compensatory MIRT models by combining a linear dynamical system and a non-compensatory model. This results in a complicated posterior of skills, which we approximate with a Gaussian distribution by minimizing the Kullback-Leibler divergence between the approximated posterior and the true posterior. The learning algorithm for the model parameters is derived through Monte Carlo expectation maximization. Simulation studies verify that the proposed method is able to reproduce latent skills accurately, whereas the dynamical compensatory model suffers from significant underestimation errors. Furthermore, experiments on an actual data set demonstrate that our dynamical non-compensatory model can infer practical skill tracing and clarify differences in skill tracing between non-compensatory and compensatory models. --- ### Beyond Contact Sensors: Deep learning with Pseudo-Labeling for remote Photoplethysmography Authors: Bhargav Acharya, Barbara Hammer, Hanna Drimalla Published: 2026-09-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.10026v1 Heart rate is a critical biomarker of health, and remote photoplethysmography (rPPG) enables its contactless estimation from video data for telemedicine applications. Recent advancements in deep learning based rPPG methods achieve state-of-the-art results, outperforming classical signal-processing methods in complex scenarios. However, deep learning methods depend on datasets with precise synchronization between videos and ground truth signals collected via contact sensors, whereas signal-processing-based methods do not. To address this dependence on labeled datasets, which are labor-intensive to collect, we investigate under which circumstances pseudo-labels extracted using unsupervised signal-processing methods can replace contact sensors labels for training deep learning methods. Our systematic evaluations found that for datasets with imperfect synchronization, the pseudo-label approach outperforms supervised training on contact sensors. For datasets with good synchronization, results are mixed: within-dataset evaluation shows no significant difference between training methods, while cross-dataset evaluation favors supervised training. However, removing a single outlier participant significantly improves the pseudo-label approach's cross-dataset performance, highlighting the importance of label quality. These results demonstrate that signal-processing methods can generate valid training signals for deep learning models, reducing dependency on labor-intensive dataset collection while maintaining competitive performance. --- ### Deterministic Prompting for Speaker-Stable Low-Resource Greek TTS Authors: Georgios Syllas, Efthymios Georgiou, Kosmas Kritsis, Alexandros Potamianos Published: 2026-09-09 Categories: cs.SD, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.10022v1 Modern TTS systems approach human quality for high-resource languages but degrade when clean speech data is scarce. Modern Greek exemplifies this, lacking the curated corpora behind state-of-the-art synthesis. We propose a data curation recipe that transforms audiobook recordings into TTS-ready data via WhisperX alignment and filtering. Then we fine-tune Parler-TTS (880M), a prompt-based multilingual model whose pre-training encodes phonetic priors transferable to Greek. During development, we find that LLM-generated style prompts introduce speaker drift at inference. Replacing them with deterministic prompts resolves this, and a speaker-specific LoRA stage trained on 3.5 h of single-speaker data anchors identity while updating ~5% of parameters. Our system achieves WER 10.7% (2.9 above the ASR floor), MOS-I 4.00 (vs. 4.36 human speech), and near-human speaker consistency (MOS-C 4.24 vs. 4.30), showing that robust single-speaker Greek TTS is achievable with limited curated data. --- ### Elastoformer: Enabling Dynamic Adaptivity via Elastic Model Transformation Authors: Sudaksh Kalra, Dolly Sapra Published: 2026-09-09 Categories: cs.CV, cs.AI, cs.PF, eess.SY arXiv: https://arxiv.org/abs/2609.10018v1 EdgeAI systems are increasingly employing computer vision applications to enable intelligent, on-device decision-making in real-time. However, these deployments face highly dynamic operational conditions, with fluctuating constraints on latency, power availability, and memory resources. Deep Neural Networks (DNN), which follow fixed computational execution flows, lack the flexibility to adapt to such variability, resulting in inefficient and suboptimal performance in edge scenarios. This underscores the need for architectures that are not only efficient but also dynamically scalable at runtime. In this paper, we propose Elastoformer: A framework that transforms conventional neural networks (NN) into Elastic NN capable of real-time elastic inference. Unlike the conventional bag-of-models approach, which requires maintaining multiple independent models for different operating conditions, Elastoformer offers a single, modular solution that dynamically switches between multiple modes of operation at runtime, adapting efficiently to the changing computational budgets of edge devices without the overhead of managing separate models. Experiments reveal that our framework achieves up to 85% reduction in computation FLOPs, 50% reduction in latency and 76% reduction in memory overhead, while showcasing the architecture agnostic nature of the framework across both Vision Transformers and CNNs. Our code is available at https://github.com/sudaksh14/Elastoformer. --- ### Structure-Aware Unsupervised Anomaly Detection for Spacecraft Telemetry with Adaptive EVT Thresholding Authors: Óscar Alcarria, Rafael Sánchez, Javier Sempere, Pablo Torrijos, Juan C. Alfaro, Juan M. Auñón, José A. Gámez, José M. Puerta Published: 2026-09-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.10017v1 Operational anomaly detection in spacecraft telemetry typically requires labeled historical anomalies or extended warm-up periods. These requirements are rarely met in practice. We propose an unsupervised, deployment-ready framework that produces predictions from the second month of operation without any labels, prior fault knowledge, or mission-specific tuning. The approach combines incremental monthly retraining, statistical model selection, and adaptive Extreme Value Theory (EVT) thresholding for false alarm control. On the ESA Anomalies Dataset (ESA-AD), it achieves $F_{0.5}=0.700$ on Mission~1 and $F_{0.5}=0.698$ on Mission~2 under strict chronological evaluation. --- ### MetroLLM-Bench: Evaluating Language Models as Transit Kiosk Runtimes Authors: Remco Hendriks Published: 2026-09-09 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.10016v1 We introduce MetroLLM-Bench, a 955-case benchmark for testing language models as the policy layer of a transit kiosk. It covers six real metro systems, ranging from 37 to 414 stations, and eleven categories that include routing, fare calculation, disruptions, accessibility, and adversarial input. In each case, the model must call structured tools and submit a machine-renderable terminal state containing an outcome, a per-ticket fare quote when applicable, and a kiosk action. Fourteen deterministic scoring components form Tier 1; eight semantic-quality components form Tier 2, six of which use a language-model judge. We report Tier 1 and the combined score of both tiers. A stratified 75/25 split reserves 717 cases for training-data generation and 238 for held-out evaluation. We evaluate twenty-six models from six vendors, of which twenty-three are ranked. On the held-out partition, a 4B Qwen 3.5 student trained through parameter-efficient fine-tuning (PEFT) exceeds both GPT-5.6 tiers on Tier 1 (91.3 against 90.6 and 90.0) and matches GPT-5.4 full at maximum reasoning effort (91.4), with a 2.6 GB Q4_K_M footprint. Larger 9B and 27B students provide no further Tier 1 improvement over the 4B student at this training scale. Across the four Qwen sizes, the PEFT gain over the corresponding base model decreases from +7.03 points at 2B (three training seeds) to -0.91 at 27B; every seed shows the same direction at every size. A deterministic rule-based baseline reaches 84.6 on Tier 1, with the remaining language-model advantage concentrated in policy adaptation, compound scenarios, accessibility, and temporal reasoning. Muse Glimmer 30B leads the composite ranking, and serving configuration alone moves the Qwen 3.5-to-3.8 comparison by 2.7 Tier 1 points. The benchmark, harness, reproduction guide, and fine-tuned students are released at https://github.com/continker/metrollm-bench. --- ### An Explainable Machine Learning Framework for Predicting Blood-Brain Barrier Permeability Using Molecular Descriptors Authors: Fatemeh Mahmoudi Published: 2026-09-09 Categories: cs.LG, cond-mat.mtrl-sci arXiv: https://arxiv.org/abs/2609.10012v1 Blood-brain barrier (BBB) permeability is a critical determinant in the development of central nervous system therapeutics because it directly influences the ability of drug candidates to reach their target sites within the brain. In this study, an explainable machine learning framework was developed to predict BBB permeability using molecular descriptors generated from the MoleculeNet BBBP dataset with the RDKit cheminformatics toolkit. Fifteen physicochemical descriptors extracted from 2,039 compounds were used to train four supervised machine learning algorithms, including Logistic Regression, Support Vector Machine (SVM), Random Forest, and Extreme Gradient Boosting (XGBoost). Hyperparameter optimization was performed using GridSearchCV, while model interpretability was investigated using SHapley Additive exPlanations (SHAP). Among the evaluated models, the optimized XGBoost classifier achieved the best predictive performance, with an accuracy of 88.97%, a precision of 88.92%, a recall of 97.76%, an F1-score of 93.13%, and a ROC-AUC of 0.9282. Stratified five-fold cross-validation further demonstrated the robustness of the proposed model, yielding a mean ROC-AUC of 0.8982 +/- 0.0130. Feature importance and SHAP analyses consistently identified TPSA, HBD, and LogP as the most influential molecular descriptors governing BBB permeability prediction. Overall, the proposed framework provides an accurate, interpretable, and computationally efficient approach for BBB permeability prediction and may serve as a valuable tool for the early-stage screening of CNS drug candidates. --- ### Beyond Similarity: Foundation Models as an Efficient Backbone for Training-Free Composed Video Retrieval Authors: Dmitry Demidov, Muhammad Zaigham Zaheer, Omkar Thawakar, Abdelrahman Mohamed Shaker, Rao Anwer Published: 2026-09-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.10008v1 Composed video retrieval (CoVR) searches a gallery for the target video that realizes a natural-language modification of a source clip. However, at gallery scale, this creates a fundamental tension: compact embeddings enable efficient, reusable search but can miss the transient actions, state changes, and subtle constraints that demand fine-grained video reasoning, whereas applying large multimodal models uniformly sacrifices scalability. To address these limitations, we propose that frozen foundation models should instead occupy complementary roles, with inference depth adapted to query difficulty. Based on this premise, we introduce \methodname{}, a framework for training-free \methodexpansion{}. Specifically, a composed-query embedding first searches reusable video-only gallery representations; uncertain queries undergo bounded reranking and candidate expansion; ambiguous edits trigger target-description generation; and only close leading candidates reach multimodal verification. To support these roles, frame selection, spatial resolution, and time cues are adapted to each stage. Across complete target-gallery evaluations, our method reaches state-of-the-art performance among training-free approaches, with 89.55 and 93.43 R@1 on Dense-WebVid-CoVR and CoVR-R, respectively (with more than +35\% and +25\% absolute margins to the closest counterpart). These results show that adaptively orchestrating foundation-model capabilities can combine scalable retrieval with fine-grained reasoning without task-specific training. The source code and all relevant guidelines are available on https://github.com/demidovd98/CoVRAGE. --- ### What Makes Adversarial Examples Transfer Across Deepfake Detectors? Authors: Rafael M. Mamede, Pedro C. Neto, Ana F. Sequeira Published: 2026-09-09 Categories: cs.CV, cs.AI, cs.CR, cs.LG arXiv: https://arxiv.org/abs/2609.10002v1 Deepfake detectors remain vulnerable to transfer-based black-box attacks, in which adversarial examples are generated on a source surrogate model and transferred to a target model, unknown to the attacker. Yet how source--target compatibility shapes attack success remains poorly understood. Prior studies evaluate limited detector pools and rarely disentangle architectural from training factors. We conduct a controlled evaluation of adversarial transferability across 60 detectors spanning six backbones, two pretraining regimes, and five training-data configurations, using two attack procedures: AutoAttack (AA) and the Carlini--Wagner attack with Expectation over Transformation (CW--EOT). Matched comparisons reveal significantly higher transfer when source and target share an exact backbone, architecture family, pretraining regime, or training data. This compatibility structure is attack-dependent: exact backbone compatibility has the largest effect under AA, whereas shared pretraining and training data have the largest effects under CW--EOT. When transfer is averaged across non-target sources, mean attack success rate (ASR) is $7.21\%$ under AA and $19.52\%$ under CW--EOT. By contrast, a multi-source oracle combining both attacks attains a \(64.48\%\) mean ASR after excluding exact backbone and training-data matches, showing that source averaging can substantially understate target vulnerability. We release 240,000 adversarially perturbed images, complete pairwise transfer results, detector configurations, and evaluation code. These findings establish source--target compatibility and source-model selection as central dimensions of credible transfer-based black-box robustness evaluation. --- ### From Few-Shot Segmentation to Clinician-in-the-Loop Medical Image Analysis Authors: Yazhou Zhu Published: 2026-09-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.10001v2 Few-shot medical image segmentation (FSMIS) seeks to delineate unseen structures from a small support set, but its standard formulation fixes task-defining evidence before inference. This assumption is fragile under acquisition shift, atypical pathology, ambiguous boundaries, and poor image quality. Adding clinician interaction and rapid adaptation is not sufficient: the binding constraint is deciding when asking or changing is warranted. We therefore reframe FSMIS as a three-layer sequential decision problem. First, decidable self-assessment separates errors that a bounded intervention can repair from those that no admissible intervention can reach. We formalize this distinction through a correctable set defined by the update operator and remaining interaction budget. Second, selective interaction allocates a distinct expert-attention budget by response-conditioned net expected value of information, yielding explicit accept, query, and defer actions. Third, bounded adaptation emphasizes reversibility and independent safety reassessment rather than speed. A complementary cross-case memory stores reproducible correction priors over failure modes instead of disease-specific mask priors. This structure links sparse support representation, cross-domain robustness, multi-level risk estimation, clinician feedback, and governed experience transfer. We state six hypotheses with an explicit dependency order and propose a minimal pilot that can falsify the foundational self-assessment claim before a clinician study. The central claim is not that interaction resolves domain shift, but that scarce expert attention should be used only when a bounded intervention is expected to reach a clinically better outcome. --- ### SalamandraTA at WMT 2026 Terminology Shared Task: Hard Examples Are Better Teachers Authors: Xixian Liao, Maite Melero Published: 2026-09-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.09999v2 Terminology-aware translation asks for more than a correct translation: the output must use the exact terms a glossary prescribes. The standard recipe, fine-tuning on glossary-annotated translation pairs, hides an inefficiency: for most examples the glossary prescribes exactly what the model would have produced anyway, so they teach nothing about following a glossary. We therefore keep only the examples where the model's own translation contradicts the glossary. In a controlled study at fixed data volume, this selection alone raises term accuracy from 78.7% to 89.9%. The filtered data, built by a two-way synthetic pipeline on open models, is part of the instruction-tuning mixture of our public release SalamandraTA-7b-instruct v3.0, which, used exactly as released and wrapped in a document-level inference pipeline, forms the BSC submission to the WMT26 Terminology Shared Task Track 1. At the official WMT26 evaluation, our system achieves 94.2% term success at 74.6 chrF++, with only two of the twenty-two submissions outperforming it on both metrics. On last year's benchmark, it also surpasses our GRPO-based system, despite being trained solely with ordinary supervised fine-tuning. --- ### Stable Answers, Unfinished Reasoning: Why Self-Consensus Is Not a Safe Early-Exit Signal Authors: Yunxiang Mo, Donghao Zhao, Hejia Geng Published: 2026-09-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.09989v1 A natural way to cut reasoning-model inference cost is to repeatedly probe a single partial trajectory for its current answer and stop once probes agree -- self-consensus. We ask whether any such rule is both safe and token-saving, and whether one can be selected once and reused. A preregistered sweep of 3,520 consensus rules, replayed on frozen trajectories from two models and three benchmarks, clears none of three acceptance gates fixed in advance; the frontier reproduces on a held-out split and on two unseen models -- while a boundary-confidence control (DEER) swept through the same pipeline clears all three. The reason lies in the signal: agreement establishes that the current answer persists under a fixed probing procedure, not that the reasoning has terminated -- a consensus-termination gap. Stopping on it commits non-terminal answers. At a rule still saving 32% of the tokens, one stop in nine fires on an answer the trajectory itself later abandons, and most of those stops cut off a correction it would otherwise have made. Widening the agreement window does not remove them: the share levels off near 7%, and by then the saving has fallen to 8%. Probe re-wording and a hand-labelled error taxonomy show the agreed answer is often a placeholder the model had not settled on. Used on its own as the stop signal, agreement fails not because it is insufficiently strict, but because it repeatedly measures the wrong object. --- ### A Sharp Barrier for Consistent Submodular Maximization: Any Improvement over $2-\sqrt{2}$ Entails Exponential Queries or Linear Recourse Authors: Shi Fu, Qixin Zhang, Dacheng Tao Published: 2026-09-09 Categories: cs.DS, cs.LG arXiv: https://arxiv.org/abs/2609.09986v1 Consistent submodular maximization studies the tradeoff between solution quality and stability when elements arrive over time. For a monotone submodular objective, which models diminishing returns, an algorithm maintains a set of at most $k$ available elements and changes only $O(1)$ elements after each insertion. Dütting et al. (2025) established a tight $2/3$ approximation with unrestricted computation and a polynomial-time $0.51$ approximation. They left open at STOC 2025 whether efficient algorithms can match the offline $1-1/e$ guarantee. We resolve this problem by proving that the supremum approximation achievable with polynomially many value queries and worst-case constant recourse is \( β=2-\sqrt2\approx0.5858<1-1/e. \) For every $\varepsilon>0$, our randomized algorithm attains $β-\varepsilon$ with $O(\varepsilon^{-2})$ changes per insertion. Any fixed improvement requires exponentially many queries before one critical insertion or linear recourse of $Ω(k)$ changes at that insertion, even with unlimited queries afterwards. This gap quantifies the cost of consistency: the current oracle hides which elements will be needed after an arrival. We also determine the exact curvature-dependent threshold $1-(\sqrt2-1)\vartheta$, attain $1-1/e-\varepsilon$ for weighted coverage with $O(\varepsilon^{-1})$ recourse, and separate the existence of universal future-price certificates from their efficient computation. Our algorithm has a bounded-bit polynomial-time implementation for polynomial-bit rational oracle answers; the lower bound uses only logarithmic-bit rational answers. --- ### VLX-VR: An Agentic-Aware Video Reasoning Model Authors: Sheng Li, Peng Liu, Qianqian Zhang, Tiancheng Zhao Published: 2026-09-09 Categories: cs.CL, cs.CV arXiv: https://arxiv.org/abs/2609.09985v1 Real-world video understanding requires integrating visual, audio, textual, and temporal evidence distributed across a video. Yet many pipelines use a fixed video context and single-pass inference, limiting adaptive evidence acquisition when observations are incomplete, ambiguous, or conflicting. We present VLX-VR, an agentic-aware video reasoning model trained within a video reasoning framework defined by a Think--Memory--Observation loop. At each step, VLX-VR determines the needed evidence, invokes read_memory or write_memory, incorporates the returned Observation, and decides whether to continue or produce the task output. We train VLX-VR with multimodal data, including videos and agent trajectories, using reinforcement learning to learn evidence acquisition, memory use, and termination. On MINERVA, VLX-VR achieves state-of-the-art performance among the models included in our comparison, with 78.79% accuracy. Under the original three duration groups, its accuracies are 76.70%, 78.73%, and 80.92%, with a cross-duration accuracy variance of 2.97~$\mathrm{pp}^2$. On correctly answered samples, 96.20% of VLX-VR's reasoning traces are consistent with the MINERVA reference reasoning traces and the evidence described by them, while approximately 75.80% of all evaluated samples satisfy both answer correctness and this evidence-grounded trace criterion. These results show strong performance and broadly stable behavior across durations, while counting, state changes, causal reasoning, and spatial perception remain challenging. --- ### Multi-Functional Embedding Models for Funder Name Disambiguation in Scientific Publication Records Authors: Kanyao Han, Zhiwen You, Jinseok Kim, Jana Diesner Published: 2026-09-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.09984v1 Understanding the historical allocation and distribution of research funding advances our knowledge of how scientific research is supported across fields, institutions, and regions. However, large-scale analyses are hindered by the lack of comprehensive funder name disambiguation solutions, as funder names often exhibit spelling variations, translations, abbreviations, and inconsistent levels of granularity. In this paper, we present a framework for developing multilingual, multi-functional funder name disambiguation models and demonstrate its application to research publications in biodiversity conservation. To construct a training dataset, we integrated the Research Organization Registry (ROR), which provides unique identifiers for research organizations, with two publication datasets: the Web of Science (WoS) and the Crossref Open Funder Registry (OFR). We used multi-task learning with Contrastive Loss and Multiple Negatives Ranking Loss to fine-tune three open-weight embedding models from the Sentence Transformer, Gemma, and Qwen3 families. The best-performing models achieved accuracy above 0.90 when matching WoS funder names to ROR identifiers, outperforming general-purpose LLMs, including GPT-5.2, Claude-Sonnet-4.6, and Gemini-2.5-Flash, by more than 0.1. For funder names not indexed in ROR, we constructed a similarity network among funder names and identified clusters within it. Finally, we analyzed the disambiguation results and highlighted challenges arising from limited knowledge of smaller funders and funders from non-English-speaking countries. This work provides a reusable framework for funder name disambiguation with potential applicability across different model architectures and datasets, featuring cost-effective training data creation and multi-task learning and disambiguation. --- ### Optimal Value Inference for Reinforcement Learning Authors: Nan Lu, Ethan Lee, James M. Robins, David Simchi-Levi, Junwei Lu Published: 2026-09-09 Categories: stat.ML, cs.LG, stat.ME arXiv: https://arxiv.org/abs/2609.09981v2 We study offline inference for the optimal value in reinforcement learning under finite state and action spaces. Two new nuisances are derived as fixed points of a self-induced Bellman equation, in which we approximate the maximum Bellman operator by its softmax correspondence. We propose a debiased estimator through the Neyman orthogonality and establish its asymptotic normality under diverging horizons even when the behavior policy changes with time, as long as the nuisances have the statistical rates that can be achieved by many machine learning methods. We provide a concrete estimating procedure for these nuisances and show they can lead to valid inference. Synthetic experiments validate the numerical performance of our inference method, and we implement it in real-life decision-making problems, including bike repositioning and AI agentic tool use. --- ### Fidelity-Aware Scheduling of Quantum Circuits on Multi-QPU Systems Authors: Innocenzo Fulginiti, Antonio Tudisco, Salvatore Zammuto, Patrick Hopf, Deborah Volpe, Helmut Seidl, Giovanna Turvani, Robert Wille, Christian B. Mendl, Martin Schulz Published: 2026-09-09 Categories: quant-ph, cs.AI, cs.ET arXiv: https://arxiv.org/abs/2609.09980v2 High Performance Computing-Quantum Computing (HPCQC) platforms expose multiple Quantum Processing Units (QPUs) that may differ in size, topology, native gates, and noise characteristics. For current noisy devices, errors compound along the compiled circuits quickly, and minimizing them, that is, maximizing the circuits' execution fidelity, is essential for reliable results. Fidelity depends on the compilation to a specific target device: the same high-level circuit may produce different executables and, therefore, different expected fidelities across QPUs. We present a low-overhead fidelity-aware scheduling framework for multi-QPU systems based on a Graph Neural Network (GNN) that estimates, before compilation, the expected fidelity of each circuit on each available QPU. Then, a tunable scheduler uses these estimates to control the trade-off between execution fidelity and parallelism. Results show that this framework allows for approximating an exhaustive fidelity-based assignment, saving computational resources compared to a brute-force approach that compiles each circuit on every device. --- ### Towards Stress-Aware Sentence-Level Filipino G2P With Weakly-Supervised ByT5 Fine-Tuning Authors: Lorenz Bernard Marqueses, Paulo Grane Gabriel Silva, Chastine Cabatay, Ericson Adler Tan, Ann Franchesca Laguna Published: 2026-09-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.09974v1 Grapheme-to-phoneme conversion (G2P) refers to the task of converting a sequence of graphemes to a corresponding sequence of phonemes. While Filipino G2P is fairly straightforward due to its shallow orthography, the inclusion of prosodic features such as stress adds a layer of complexity that requires sentence-level context instead of single-word inputs. However, sentence-level data for Filipino typically do not include phoneme transcriptions, posing a challenge for training G2P models. As such, we investigate how to obtain sentence-level phoneme data for Filipino using available data and compare the resulting models with multilingual word-level G2P as well as measure how accurately they predict stress marker position for Filipino. We propose fine-tuning a ByT5-based model, pre-trained on multilingual word-level G2P data, on three sentence-level G2P datasets annotated with an LLM-assisted pipeline guided by data from Wiktionary. This approach produces models that perform well on the G2P task, achieving at best around 0.54% PER and 2.50% CER, a significant decrease compared to base model PER at around 19.74%, on a manually-corrected test set. The model is able to correctly classify most of the main stress classes in Filipino, but struggles particularly with malumi words. We show that a ByT5-based model performs well at sentence-level Filipino G2P and offers strong potential for Filipino homograph disambiguation. --- ### Putting Captions to the Test: Evaluating Video Caption Quality through Multiple-Choice Question Answering Authors: Zizhen Wang, Bo Feng, Zhengfeng Lai, Shiyu Li, Yang Lu, Meng Cao, Ping Huang, Xiaoming Simon Wang Published: 2026-09-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.09973v1 Evaluating video captioning remains a critical challenge for Visual Large Language Models (VLLMs). Existing metrics primarily rely on matching generated text against ground-truth references. This paradigm suffers from the ``one-to-many'' nature of video description, where high-quality captions are often penalized for lexical mismatches or valid shifts in visual focus. Furthermore, such assessments are typically one-dimensional, failing to provide a fine-grained analysis of caption quality. To address this, we redefine caption quality through the lens of information fidelity: A caption must maximize the coverage of salient visual information while ensuring strict factuality. We introduce CapQuiz, a novel reference-free benchmark that assesses captions based on their utility in answering human-verified, fine-grained, multiple-choice questions derived from the video. CapQuiz features a hierarchical taxonomy of 10 question types (spanning Descriptive and Inferential categories) across 24 diverse video domains. Extensive experiments demonstrate that CapQuiz correlates significantly better with human judgments than existing metrics and offers interpretable insights into model performance. --- ### Deep Neural Networks for Learning Intent from sEMG Signals to Support Hardware Devices for Post-Stroke Neurorehabilitation Authors: Zakariyya Brewster, Divy Wadhwani, Emily Yan, Aidan Wang, Karma Namgyal, Shuting Xie, Markiyan Konyk, Tala Abdelmaguid Published: 2026-09-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.09971v1 Finger-specific motor intent is a clinically meaningful control signal for post-stroke neurorehabilitation, where residual muscle activity may remain measurable despite weak or incomplete movement. We study five-finger multilabel intent decoding from impaired-arm high-density surface electromyography (sEMG) in PhysioMio, a bilateral longitudinal dataset collected from stroke patients. A common processing protocol aligns movement labels, applies 20--450 Hz Butterworth filtering and Symlet-4 wavelet denoising, segments overlapping 200 ms windows, and extracts twelve time- and frequency-domain descriptors per channel. Direct LSTM, CNN, and GNN baselines reveal complementary behavior: the LSTM attains the highest subset accuracy (0.545), whereas the GNN attains the highest macro F1 (0.706) and macro AUPRC (0.776). Architecture search then identifies CNN-Large as the strongest single-split CNN, with 0.593 subset accuracy and 0.714 macro F1, while CNN-Micro provides a compact architecture for embedded inference. To match a four-sensor hardware design, we retrain CNN-Micro using channels associated with ECRB, ECRL, FDS, and FDP and exclude the ground electrode from model input. Across five seeds, cross-channel knowledge distillation improves the four-channel student over direct training, reaching $0.5219 \pm 0.0114$ subset accuracy, $0.7612 \pm 0.0038$ finger accuracy, and $0.6095 \pm 0.0058$ macro F1. The selected 123K-parameter model accepts nine windows of 48 features and has been exported to ONNX. These results establish a reproducible software path from post-stroke sEMG to compact five-finger intent prediction for subsequent hardware-in-the-loop evaluation. --- ### 5-Dialects-BN: Unmasking the Impact of Transliteration on Bangla Dialectal LLMs Authors: Md Mahir Jawad, Galib Mahmud Jim, Rafid Ahmed, Mir Sazzat Hossain, Md Fahim, Md Farhad Alam Bhuiyan Published: 2026-09-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.09964v1 Large Language Models (LLMs) have achieved remarkable progress across natural language processing (NLP) tasks, yet their capabilities degrade sharply for low-resource languages and dialectally diverse settings. Bangla, the world's sixth most spoken language, exemplifies this gap: existing resources overwhelmingly target Standard Bangla, leaving its regional dialects without the benchmarks needed to develop or evaluate dialect-aware systems. We address this gap with 5-Dialects-BN, the first multi-annotation Bangla dialect benchmark to align Romanized transliteration with dialectal text, Standard Bangla, English, and subjectivity labels across five regional varieties. The dataset comprises 6,000 manually annotated entries spanning five major dialects: Chittagong, Barisal, Noakhali, Sylhet, and Rangpur (Chittagong 1,900; Noakhali 1,500; Sylhet 1,200; Barisal 700; Rangpur 700), reflecting natural online availability. Each entry is enriched with five aligned annotations: the original dialectal text, a Romanized transliteration, an English translation, a Standard Bangla translation, and a subjectivity label (subjective vs. objective). Annotations were produced and cross-validated by native speakers and undergraduate linguistics students to ensure dialectal authenticity and semantic fidelity. The resulting resource supports a diverse suite of tasks, including dialect identification, dialect-to-standard normalization, machine translation, subjectivity classification, and parameter-efficient fine-tuning (e.g., LoRA) of multilingual LLMs. By providing a standardized, multi-annotation benchmark, 5-Dialects-BN enables principled evaluation of LLMs on dialectally diverse Bangla and lays a foundation for further research in low-resource, dialect-aware NLP. --- ### Beyond Verified Answers: Solver-Informed Self-Distillation for Bootstrapping Operations Research Language Models Authors: Rui Zhu, Minglong Cao, Chenyu Zhou, Jianghao Lin, Dongdong Ge Published: 2026-09-09 Categories: math.OC, cs.AI arXiv: https://arxiv.org/abs/2609.09957v1 Modern large language models (LLMs) can translate natural-language descriptions into operations research (OR) formulations. Post-training techniques including reinforcement learning and on-policy self-distillation have further improved this capability. However, three limitations remain in training LLMs for OR formulations. First, training commonly relies on synthetic formulations validated by human experts or stronger models, constraining scalable supervision. Second, credit assignment is either coarse or costly: outcome rewards score an entire trajectory without locating the responsible modeling decision, whereas process-level supervision requires an additional evaluator. Third, privileged self-distillation can induce style mismatch by using solver context unavailable at deployment. We find that a model can improve from solver-artifact feedback generated by its own rollouts, making self-distillation a practical, evaluator-free source of dense supervision. Therefore, we propose SOLID: Solver-Informed On-Policy LearnIng through Self-Distillation, a novel framework for self-improving OR language models without verified answers or external evaluators. SOLID executes candidate programs from multiple rollouts, clusters their objectives, and selects a majority-group artifact as a pseudo-reference. The model then performs updates using group-relative advantages and dense self-supervision signals. Across multiple OR benchmarks, SOLID improves solution accuracy for both general-purpose and OR-tuned models over outcome-only group-relative training. These results show that solver artifacts can support scalable self-improvement without trusted answers. --- ### Improving Cross-Lingual Token Representations by Adding a Pinch of SALT Authors: Guillem Ramírez Published: 2026-09-09 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.09953v1 Cross-lingual sentence encoders enable scalable transfer across hundreds of languages, powering applications such as translation mining and zero-shot learning in low-resource settings. Although trained for sentence-level alignment, they are increasingly also applied to token-level tasks such as hallucination detection and sequence tagging, exposing a mismatch between training and usage. We propose SALT, a lightweight post-training method that improves token representations by injecting span-level supervision into existing sentence encoders. Across five multilingual token-level benchmarks, SALT achieves the best overall results on four of them, outperforming alternative fine-tuning strategies and competitive encoders. It also improves sentence-level performance on cross-lingual retrieval and classification tasks. These results demonstrate that span-level supervision is an effective signal for improving both token and sentence representations. --- ### Vague2Detect: Handling Ambiguous Prompts in Knowledge-Based Open-World Detection Authors: Ibrohimjon Muminov, Jihie Kim Published: 2026-09-09 Categories: cs.CV, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.09949v1 Real-world detectors must often interpret functional or ambiguous prompts, yet conventional models such as YOLO remain restricted to fixed class lists. Even open-vocabulary models like YOLO-World frequently misalign vague language with the intended objects. Building on our prior work Commonsense-Guided Open-World Object Detection Using LLMs and Visual-Semantic Matching, we address YOLO-World's limitations in grounding task-driven queries. We propose Vague2Detect, a hybrid pipeline in which a fine-tuned Sentence-BERT retrieves candidates from a structured household Knowledge Base (KB), and YOLO-World verifies their presence in the image. For prompts outside the KB, a large language model (GPT-3.5-turbo) generates candidate descriptions, dynamically expanding the KB to cover novel concepts. On a benchmark of household scenes using custom images and an Open Images V7 subset, YOLO-World alone achieves only 32% Vague Prompt Success Rate (VPSR), the ability to map ambiguous queries to correct detections. In contrast, Vague2Detect improves performance to 61% VPSR with high precision, and up to 85% when augmented with GPT fallback. --- ### Adversarial Training for Tabular Credit Scoring: A Multi-Attack Robustness Evaluation in P2P Lending Authors: Gijs A. F. Niewzwaag, Marijn G. S. Veth, Manuele Massei, Marcos R. Machado Published: 2026-09-09 Categories: cs.LG, q-fin.RM, stat.ML arXiv: https://arxiv.org/abs/2609.09945v1 Machine learning-based credit scoring is increasingly central to Peer-to-Peer (P2P) lending, yet its resilience to adversarial manipulation, where applicants strategically alter self-reported inputs to secure favourable decisions, remains poorly understood. Most adversarial-robustness evidence comes from image and text domains and evaluates a single attack against a matching defence, offering little guidance on how defences generalise across attack types in tabular credit data. We address this with a systematic train-test robustness benchmark on a large Lending Club subset, spanning three model families (logistic regression, a feed-forward neural network, and a transformer for tabular data) and four attacks confined to applicant-mutable features: Fast Gradient Sign Method (FGSM), Projected Gradient Descent (PGD), Salt-and-Pepper (S&P) noise, and DeepFool, plus a mixed-attack regime. Across a full grid evaluated with stratified cross-validation, adversarial training sharply improves robustness against the attack it is trained on and transfers well within the gradient-based family, but transfers weakly to non-gradient corruption, so single-attack defences overstate real-world resilience. Mixed training delivers the most balanced robustness across heterogeneous attacks while preserving clean-test performance, supporting multi-attack stress testing in credit-model governance. --- ### Structural Process Supervision for Latent Chain-of-Thought Reasoning Authors: Yiqi Li, Xu Chen, Chen Ju, Jiangchao Yao, Zhaoyang Li, Jinsong Lan, Xiaoyong Zhu, Yu Wang Published: 2026-09-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.09928v2 Latent reasoning approaches enhance token-level efficiency and robustness by replacing verbose, explicit chain-of-thought (CoT) tokens with compact continuous-space embeddings. However, existing methods lack efficient process supervision over these embeddings, which often leads to representation collapse and uneven information distribution. % However, supervising these latent embeddings is challenging because a fixed number of latent states must capture information from variable-length reasoning traces. To address this, we propose Prototype-Mediated Process Supervision (PMPS), which introduces learnable reasoning prototypes as semantic anchors to provide structural process-level supervision for latent reasoning. PMPS projects latent embeddings and explicit CoT embeddings into a shared prototype space, achieving many-to-many soft alignment between unequal-length representations through prototype assignment. Meanwhile, we introduce a Progressive Sequential Alignment (PSA) module to further guide training: positional priors initially encourage sequential alignment structure, then gradually relax to permit adaptive matching. Experimental results show that PMPS compresses output token length to under 50% of explicit CoT on GSM8K-Aug. Compared to leading baseline SIM-CoT, our method achieves average accuracy gains of 2.51% across different model families. On GPT-2, accuracy of PMPS even surpasses CoT-SFT. On larger models and a more challenging task, PMPS consistently attains the highest accuracy among all latent reasoning methods with comparable output length. ---