# Research Papers — 2026-02 · bundle page 98 of 210 > Full-text markdown of papers #4851–4900 of 10493 published in 2026-02, newest first. AI-readable mirrors of the full 10493-paper 2026-02 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-02/page/98 [← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/97.md) [Next bundle →](https://aipod.dev/papers/archive/2026-02/page/99.md) ### AIWizards at MULTIPRIDE: A Hierarchical Approach to Slur Reclamation Detection Authors: Luca Tedeschini, Matteo Fasulo Published: 2026-02-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.12818v1 Detecting reclaimed slurs represents a fundamental challenge for hate speech detection systems, as the same lexcal items can function either as abusive expressions or as in-group affirmations depending on social identity and context. In this work, we address Subtask B of the MultiPRIDE shared task at EVALITA 2026 by proposing a hierarchical approach to modeling the slur reclamation process. Our core assumption is that members of the LGBTQ+ community are more likely, on average, to employ certain slurs in a eclamatory manner. Based on this hypothesis, we decompose the task into two stages. First, using a weakly supervised LLM-based annotation, we assign fuzzy labels to users indicating the likelihood of belonging to the LGBTQ+ community, inferred from the tweet and the user bio. These soft labels are then used to train a BERT-like model to predict community membership, encouraging the model to learn latent representations associated with LGBTQ+ identity. In the second stage, we integrate this latent space with a newly initialized model for the downstream slur reclamation detection task. The intuition is that the first model encodes user-oriented sociolinguistic signals, which are then fused with representations learned by a model pretrained for hate speech detection. Experimental results on Italian and Spanish show that our approach achieves performance statistically comparable to a strong BERT-based baseline, while providing a modular and extensible framework for incorporating sociolinguistic context into hate speech modeling. We argue that more fine-grained hierarchical modeling of user identity and discourse context may further improve the detection of reclaimed language. We release our code at https://github.com/LucaTedeschini/multipride. --- ### Left-right asymmetry in predicting brain activity from LLMs' representations emerges with their formal linguistic competence Authors: Laurent Bonnasse-Gahot, Christophe Pallier Published: 2026-02-13 Categories: cs.CL, cs.AI, q-bio.NC arXiv: https://arxiv.org/abs/2602.12811v2 When humans and large language models (LLMs) process the same text, activations in the LLMs correlate with brain activity measured, e.g., with functional magnetic resonance imaging (fMRI). Moreover, it has been shown that, as the training of an LLM progresses, the performance in predicting brain activity from its internal activations improves more in the left hemisphere than in the right one. The aim of the present work is to understand which kind of competence acquired by the LLMs underlies the emergence of this left-right asymmetry. Using the OLMo-2 7B language model at various training checkpoints and fMRI data from English participants, we compare the evolution of the left-right asymmetry in the correlation between brain activity and model predictions alongside performance on several benchmarks. We observe that the asymmetry co-emerges with the formal linguistic abilities of the LLM. These abilities are demonstrated in two ways: by the model's capacity to assign a higher probability to an acceptable sentence than to a grammatically unacceptable one within a minimal contrasting pair, and by its ability to produce well-formed text. By contrast, the left-right asymmetry does not align with the performance on arithmetic or Dyck language tasks; nor with text-based tasks involving world knowledge and reasoning. We generalize these results to another family of LLMs (Pythia) and two other languages, French and Chinese. Our observations indicate that the left-right asymmetry in brain predictivity matches the progress in formal linguistic competence. --- ### RAT-Bench: A Comprehensive Benchmark for Text Anonymization Authors: Nataša Krčo, Zexi Yao, Matthieu Meeus, Yves-Alexandre de Montjoye Published: 2026-02-13 Categories: cs.CL, cs.AI, cs.CR, cs.LG arXiv: https://arxiv.org/abs/2602.12806v1 Data containing personal information is increasingly used to train, fine-tune, or query Large Language Models (LLMs). Text is typically scrubbed of identifying information prior to use, often with tools such as Microsoft's Presidio or Anthropic's PII purifier. These tools have traditionally been evaluated on their ability to remove specific identifiers (e.g., names), yet their effectiveness at preventing re-identification remains unclear. We introduce RAT-Bench, a comprehensive benchmark for text anonymization tools based on re-identification risk. Using U.S. demographic statistics, we generate synthetic text containing various direct and indirect identifiers across domains, languages, and difficulty levels. We evaluate a range of NER- and LLM-based text anonymization tools and, based on the attributes an LLM-based attacker is able to correctly infer from the anonymized text, we report the risk of re-identification in the U.S. population, while properly accounting for the disparate impact of identifiers. We find that, while capabilities vary widely, even the best tools are far from perfect in particular when direct identifiers are not written in standard ways and when indirect identifiers enable re-identification. Overall we find LLM-based anonymizers, including new iterative anonymizers, to provide a better privacy-utility trade-off albeit at a higher computational cost. Importantly, we also find them to work well across languages. We conclude with recommendations for future anonymization tools and will release the benchmark and encourage community efforts to expand it, in particular to other geographies. --- ### Can Neural Networks Provide Latent Embeddings for Telemetry-Aware Greedy Routing? Authors: Andreas Boltres, Niklas Freymuth, Gerhard Neumann Published: 2026-02-13 Categories: cs.LG, cs.AI, cs.NI arXiv: https://arxiv.org/abs/2602.12798v1 Telemetry-Aware routing promises to increase efficacy and responsiveness to traffic surges in computer networks. Recent research leverages Machine Learning to deal with the complex dependency between network state and routing, but sacrifices explainability of routing decisions due to the black-box nature of the proposed neural routing modules. We propose \emph{Placer}, a novel algorithm using Message Passing Networks to transform network states into latent node embeddings. These embeddings facilitate quick greedy next-hop routing without directly solving the all-pairs shortest paths problem, and let us visualize how certain network events shape routing decisions. --- ### GSM-GS: Geometry-Constrained Single and Multi-view Gaussian Splatting for Surface Reconstruction Authors: Xiao Ren, Yu Liu, Ning An, Jian Cheng, Xin Qiao, He Kong Published: 2026-02-13 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2602.12796v1 Recently, 3D Gaussian Splatting has emerged as a prominent research direction owing to its ultrarapid training speed and high-fidelity rendering capabilities. However, the unstructured and irregular nature of Gaussian point clouds poses challenges to reconstruction accuracy. This limitation frequently causes high-frequency detail loss in complex surface microstructures when relying solely on routine strategies. To address this limitation, we propose GSM-GS: a synergistic optimization framework integrating single-view adaptive sub-region weighting constraints and multi-view spatial structure refinement. For single-view optimization, we leverage image gradient features to partition scenes into texture-rich and texture-less sub-regions. The reconstruction quality is enhanced through adaptive filtering mechanisms guided by depth discrepancy features. This preserves high-weight regions while implementing a dual-branch constraint strategy tailored to regional texture variations, thereby improving geometric detail characterization. For multi-view optimization, we introduce a geometry-guided cross-view point cloud association method combined with a dynamic weight sampling strategy. This constructs 3D structural normal constraints across adjacent point cloud frames, effectively reinforcing multi-view consistency and reconstruction fidelity. Extensive experiments on public datasets demonstrate that our method achieves both competitive rendering quality and geometric reconstruction. See our interactive project page --- ### SQuTR: A Robustness Benchmark for Spoken Query to Text Retrieval under Acoustic Noise Authors: Yuejie Li, Ke Yang, Yueying Hua, Berlin Chen, Jianhao Nie, Yueping He, Caixin Kang Published: 2026-02-13 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2602.12783v3 Spoken query retrieval is an important interaction mode in modern information retrieval. However, existing evaluation datasets are often limited to simple queries under constrained noise conditions, making them inadequate for assessing the robustness of spoken query retrieval systems under complex acoustic perturbations. To address this limitation, we present SQuTR, a robustness benchmark for spoken query retrieval that includes a large-scale dataset and a unified evaluation protocol. SQuTR aggregates 37,317 unique queries from six commonly used English and Chinese text retrieval datasets, spanning multiple domains and diverse query types. We synthesize speech using voice profiles from 200 real speakers and mix 17 categories of real-world environmental noise under controlled SNR levels, enabling reproducible robustness evaluation from quiet to highly noisy conditions. Under the unified protocol, we conduct large-scale evaluations on representative cascaded and end-to-end retrieval systems. Experimental results show that retrieval performance decreases as noise increases, with substantially different drops across systems. Even large-scale retrieval models struggle under extreme noise, indicating that robustness remains a critical bottleneck. Overall, SQuTR provides a reproducible testbed for benchmarking and diagnostic analysis, and facilitates future research on robustness in spoken query to text retrieval. --- ### Aspect-Based Sentiment Analysis for Future Tourism Experiences: A BERT-MoE Framework for Persian User Reviews Authors: Hamidreza Kazemi Taskooh, Taha Zare Harofte Published: 2026-02-13 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2602.12778v1 This study advances aspect-based sentiment analysis (ABSA) for Persian-language user reviews in the tourism domain, addressing challenges of low-resource languages. We propose a hybrid BERT-based model with Top-K routing and auxiliary losses to mitigate routing collapse and improve efficiency. The pipeline includes: (1) overall sentiment classification using BERT on 9,558 labeled reviews, (2) multi-label aspect extraction for six tourism-related aspects (host, price, location, amenities, cleanliness, connectivity), and (3) integrated ABSA with dynamic routing. The dataset consists of 58,473 preprocessed reviews from the Iranian accommodation platform Jabama, manually annotated for aspects and sentiments. The proposed model achieves a weighted F1-score of 90.6% for ABSA, outperforming baseline BERT (89.25%) and a standard hybrid approach (85.7%). Key efficiency gains include a 39% reduction in GPU power consumption compared to dense BERT, supporting sustainable AI deployment in alignment with UN SDGs 9 and 12. Analysis reveals high mention rates for cleanliness and amenities as critical aspects. This is the first ABSA study focused on Persian tourism reviews, and we release the annotated dataset to facilitate future multilingual NLP research in tourism. --- ### Bootstrapping MLLM for Weakly-Supervised Class-Agnostic Object Counting Authors: Xiaowen Zhang, Zijie Yue, Yong Luo, Cairong Zhao, Qijun Chen, Miaojing Shi Published: 2026-02-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.12774v1 Object counting is a fundamental task in computer vision, with broad applicability in many real-world scenarios. Fully-supervised counting methods require costly point-level annotations per object. Few weakly-supervised methods leverage only image-level object counts as supervision and achieve fairly promising results. They are, however, often limited to counting a single category, e.g. person. In this paper, we propose WS-COC, the first MLLM-driven weakly-supervised framework for class-agnostic object counting. Instead of directly fine-tuning MLLMs to predict object counts, which can be challenging due to the modality gap, we incorporate three simple yet effective strategies to bootstrap the counting paradigm in both training and testing: First, a divide-and-discern dialogue tuning strategy is proposed to guide the MLLM to determine whether the object count falls within a specific range and progressively break down the range through multi-round dialogue. Second, a compare-and-rank count optimization strategy is introduced to train the MLLM to optimize the relative ranking of multiple images according to their object counts. Third, a global-and-local counting enhancement strategy aggregates and fuses local and global count predictions to improve counting performance in dense scenes. Extensive experiments on FSC-147, CARPK, PUCPR+, and ShanghaiTech show that WS-COC matches or even surpasses many state-of-art fully-supervised methods while significantly reducing annotation costs. Code is available at https://github.com/viscom-tongji/WS-COC. --- ### PixelRush: Ultra-Fast, Training-Free High-Resolution Image Generation via One-step Diffusion Authors: Hong-Phuc Lai, Phong Nguyen, Anh Tran Published: 2026-02-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.12769v2 Pre-trained diffusion models excel at generating high-quality images but remain inherently limited by their native training resolution. Recent training-free approaches have attempted to overcome this constraint by introducing interventions during the denoising process; however, these methods incur substantial computational overhead, often requiring more than five minutes to produce a single 4K image. In this paper, we present PixelRush, the first tuning-free framework for practical high-resolution text-to-image generation. Our method builds upon the established patch-based inference paradigm but eliminates the need for multiple inversion and regeneration cycles. Instead, PixelRush enables efficient patch-based denoising within a low-step regime. To address artifacts introduced by patch blending in few-step generation, we propose a seamless blending strategy. Furthermore, we mitigate over-smoothing effects through a noise injection mechanism. PixelRush delivers exceptional efficiency, generating 4K images in approximately 20 seconds representing a 10$\times$ to 35$\times$ speedup over state-of-the-art methods while maintaining superior visual fidelity. Extensive experiments validate both the performance gains and the quality of outputs achieved by our approach. --- ### "Not Human, Funnier": How Machine Identity Shapes Humor Perception in Online AI Stand-up Comedy Authors: Xuehan Huang, Canwen Wang, Yifei Hao, Daijin Yang, Ray LC Published: 2026-02-13 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2602.12763v1 Chatbots are increasingly applied to domains previously reserved for human actors. One such domain is comedy, whereby both the general public working with ChatGPT and research-based LLM-systems have tried their hands on making humor. In formative interviews with professional comedians and video analyses of stand-up comedy in humans, we found that human performers often use their ethnic, gender, community, and demographic-based identity to enable joke-making. This suggests whether the identity of AI itself can empower AI humor generation for human audiences. We designed a machine-identity-based agent that uses its own status as AI to tell jokes in online performance format. Studies with human audiences (N=32) showed that machine-identity-based agents were seen as funnier than baseline-GPT agent. This work suggests the design of human-AI integrated systems that explicitly utilize AI as its own unique identity apart from humans. --- ### Towards complete digital twins in cultural heritage with ART3mis 3D artifacts annotator Authors: Dimitrios Karamatskos, Vasileios Arampatzakis, Vasileios Sevetlidis, Stavros Nousias, Athanasios Kalogeras, Christos Koulamas, Aris Lalos, George Pavlidis Published: 2026-02-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.12761v1 Archaeologists, as well as specialists and practitioners in cultural heritage, require applications with additional functions, such as the annotation and attachment of metadata to specific regions of the 3D digital artifacts, to go beyond the simplistic three-dimensional (3D) visualization. Different strategies addressed this issue, most of which are excellent in their particular area of application, but their capacity is limited to their design's purpose; they lack generalization and interoperability. This paper introduces ART3mis, a general-purpose, user-friendly, feature-rich, interactive web-based textual annotation tool for 3D objects. Moreover, it enables the communication, distribution, and reuse of information as it complies with the W3C Web Annotation Data Model. It is primarily designed to help cultural heritage conservators, restorers, and curators who lack technical expertise in 3D imaging and graphics, handle, segment, and annotate 3D digital replicas of artifacts with ease. --- ### Towards a Diagnostic and Predictive Evaluation Methodology for Sequence Labeling Tasks Authors: Elena Alvarez-Mellado, Julio Gonzalo Published: 2026-02-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.12759v2 Standard evaluation in NLP typically indicates that system A is better on average than system B, but it provides little info on how to improve performance and, what is worse, it should not come as a surprise if B ends up being better than A on outside data. We propose an evaluation methodology for sequence labeling tasks grounded on error analysis that provides both quantitative and qualitative information on where systems must be improved and predicts how models will perform on a different distribution. The key is to create test sets that, contrary to common practice, do not rely on gathering large amounts of real-world in-distribution scraped data, but consists in handcrafting a small set of linguistically motivated examples that exhaustively cover the range of span attributes (such as shape, length, casing, sentence position, etc.) a system may encounter in the wild. We demonstrate this methodology on a benchmark for anglicism identification in Spanish. Our methodology provides results that are diagnostic (because they help identify systematic weaknesses in performance), actionable (because they can inform which model is better suited for a given scenario) and predictive: our method predicts model performance on external datasets with a median correlation of 0.85. --- ### VineetVC: Adaptive Video Conferencing Under Severe Bandwidth Constraints Using Audio-Driven Talking-Head Reconstruction Authors: Vineet Kumar Rakesh, Soumya Mazumdar, Tapas Samanta, Hemendra Kumar Pandey, Amitabha Das, Sarbajit Pal Published: 2026-02-13 Categories: eess.IV, cs.AI, cs.CV, cs.MM arXiv: https://arxiv.org/abs/2602.12758v1 Intense bandwidth depletion within consumer and constrained networks has the potential to undermine the stability of real-time video conferencing: encoder rate management becomes saturated, packet loss escalates, frame rates deteriorate, and end-to-end latency significantly increases. This work delineates an adaptive conferencing system that integrates WebRTC media delivery with a supplementary audio-driven talking-head reconstruction pathway and telemetry-driven mode regulation. The system consists of a WebSocket signaling service, an optional SFU for multi-party transmission, a browser client capable of real-time WebRTC statistics extraction and CSV telemetry export, and an AI REST service that processes a reference face image and recorded audio to produce a synthesized MP4; the browser can substitute its outbound camera track with the synthesized stream with a median bandwidth of 32.80 kbps. The solution incorporates a bandwidth-mode switching strategy and a client-side mode-state logger. --- ### Closing the Loop: A Control-Theoretic Framework for Provably Stable Time Series Forecasting with LLMs Authors: Xingyu Zhang, Jingyao Wang, Zeen Song, Changwen Zheng, Wenwen Qiang Published: 2026-02-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.12756v2 Large Language Models (LLMs) have recently shown exceptional potential in time series forecasting (TSF), leveraging their inherent sequential reasoning capabilities to model complex temporal dynamics. Existing approaches typically employ an autoregressive generation strategy to adapt LLMs for TSF. However, we identify a theoretical flaw in this paradigm: during inference, the model operates in an open-loop manner, recursively consuming its own generated outputs. This leads to error accumulation, where minor early deviations cascade into significant rollout drift over long horizons. In this paper, we reformulate autoregressive forecasting through the lens of control theory, proposing Feedback-driven LLM (F-LLM), a novel closed-loop framework. Unlike standard methods that passively propagate errors, F-LLM actively stabilizes the trajectory via a learnable residual estimator functioning as a system observer. Furthermore, we provide a mathematical proof that, under explicit contraction assumptions, this closed-loop mechanism guarantees a uniformly bounded step-wise error sequence within the local surrogate dynamics. Extensive experiments demonstrate that F-LLM significantly mitigates error propagation, achieving good performance on time series benchmarks. Our code is publicly available at https://github.com/Zh-XY22/F-LLM. --- ### Closing the Loop: A Control-Theoretic Framework for Provably Stable Time Series Forecasting with LLMs Authors: Xingyu Zhang, Hanyun Du, Zeen Song, Jianqi Zhang, Changwen Zheng, Wenwen Qiang Published: 2026-02-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.12756v1 Large Language Models (LLMs) have recently shown exceptional potential in time series forecasting, leveraging their inherent sequential reasoning capabilities to model complex temporal dynamics. However, existing approaches typically employ a naive autoregressive generation strategy. We identify a critical theoretical flaw in this paradigm: during inference, the model operates in an open-loop manner, consuming its own generated outputs recursively. This leads to inevitable error accumulation (exposure bias), where minor early deviations cascade into significant trajectory drift over long horizons. In this paper, we reformulate autoregressive forecasting through the lens of control theory, proposing \textbf{F-LLM} (Feedback-driven LLM), a novel closed-loop framework. Unlike standard methods that passively propagate errors, F-LLM actively stabilizes the trajectory via a learnable residual estimator (Observer) and a feedback controller. Furthermore, we provide a theoretical guarantee that our closed-loop mechanism ensures uniformly bounded error, provided the base model satisfies a local Lipschitz constraint. Extensive experiments demonstrate that F-LLM significantly mitigates error propagation, achieving good performance on time series benchmarks. --- ### Towards reconstructing experimental sparse-view X-ray CT data with diffusion models Authors: Nelas J. Thomsen, Xinyuan Wang, Felix Lucka, Ezgi Demircan-Tureyen Published: 2026-02-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.12755v3 Diffusion-based image generators are promising priors for ill-posed inverse problems like sparse-view X-ray Computed Tomography (CT). As most studies consider synthetic data, it is not clear whether training data mismatch (``domain shift'') or forward model mismatch complicate their successful application to experimental data. We measured CT data from a physical phantom resembling the synthetic Shepp-Logan phantom and trained diffusion priors on synthetic image data sets with different degrees of domain shift towards it. Then, we employed the priors in a Decomposed Diffusion Sampling scheme on sparse-view CT data sets with increasing difficulty leading to the experimental data. Our results reveal that domain shift plays a nuanced role: while severe mismatch causes model collapse and hallucinations, diverse priors match or exceed well-matched but narrow priors. Forward model mismatch pulls the image samples away from the prior manifold, which causes artifacts but can be mitigated with annealed likelihood weight schedules that also increase computational efficiency. Overall, we demonstrate that performance gains do not immediately translate from synthetic to experimental data, and future development must validate against real-world benchmarks. --- ### Hierarchical Successor Representation for Robust Transfer Authors: Changmin Yu, Máté Lengyel Published: 2026-02-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.12753v2 The successor representation (SR) provides a powerful framework for decoupling predictive dynamics from rewards, enabling rapid generalisation across reward configurations. However, the classical SR is limited by its inherent policy dependence: policies change due to ongoing learning, environmental non-stationarities, and changes in task demands, making established predictive representations obsolete. Furthermore, in topologically complex environments, SRs suffer from spectral diffusion, leading to dense and overlapping features that scale poorly. Here we propose the Hierarchical Successor Representation (HSR) for overcoming these limitations. By incorporating temporal abstractions into the construction of predictive representations, HSR learns stable state features which are robust to task-induced policy changes. Applying non-negative matrix factorisation (NMF) to the HSR yields a sparse, low-rank state representation that facilitates highly sample-efficient transfer to novel tasks in multi-compartmental environments. Further analysis reveals that HSR-NMF discovers interpretable topological structures, providing a policy-agnostic hierarchical map that effectively bridges model-free optimality and model-based flexibility. Beyond providing a useful basis for task-transfer, we show that HSR's temporally extended predictive structure can also be leveraged to drive efficient exploration, effectively scaling to large, procedurally generated environments. --- ### ReBA-Pred-Net: Weakly-Supervised Regional Brain Age Prediction on MRI Authors: Shuai Shao, Yan Wang, Shu Jiang, Shiyuan Zhao, Xinzhe Luo, Di Yang, Jiangtao Wang, Yutong Bai, Jianguo Zhang Published: 2026-02-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.12751v1 Brain age has become a prominent biomarker of brain health. Yet most prior work targets whole brain age (WBA), a coarse paradigm that struggles to support tasks such as disease characterization and research on development and aging patterns, because relevant changes are typically region-selective rather than brain-wide. Therefore, robust regional brain age (ReBA) estimation is critical, yet a widely generalizable model has yet to be established. In this paper, we propose the Regional Brain Age Prediction Network (ReBA-Pred-Net), a Teacher-Student framework designed for fine-grained brain age estimation. The Teacher produces soft ReBA to guide the Student to yield reliable ReBA estimates with a clinical-prior consistency constraint (regions within the same function should change similarly). For rigorous evaluation, we introduce two indirect metrics: Healthy Control Similarity (HCS), which assesses statistical consistency by testing whether regional brain-age-gap (ReBA minus chronological age) distributions align between training and unseen HC; and Neuro Disease Correlation (NDC), which assesses factual consistency by checking whether clinically confirmed patients show elevated brain-age-gap in disease-associated regions. Experiments across multiple backbones demonstrate the statistical and factual validity of our method. --- ### Lung nodule classification on CT scan patches using 3D convolutional neural networks Authors: Volodymyr Sydorskyi Published: 2026-02-13 Categories: eess.IV, cs.CV, eess.SY arXiv: https://arxiv.org/abs/2602.12750v1 Lung cancer remains one of the most common and deadliest forms of cancer worldwide. The likelihood of successful treatment depends strongly on the stage at which the disease is diagnosed. Therefore, early detection of lung cancer represents a critical medical challenge. However, this task poses significant difficulties for thoracic radiologists due to the large number of studies to review, the presence of multiple nodules within the lungs, and the small size of many nodules, which complicates visual assessment. Consequently, the development of automated systems that incorporate highly accurate and computationally efficient lung nodule detection and classification modules is essential. This study introduces three methodological improvements for lung nodule classification: (1) an advanced CT scan cropping strategy that focuses the model on the target nodule while reducing computational cost; (2) target filtering techniques for removing noisy labels; (3) novel augmentation methods to improve model robustness. The integration of these techniques enables the development of a robust classification subsystem within a comprehensive Clinical Decision Support System for lung cancer detection, capable of operating across diverse acquisition protocols, scanner types, and upstream models (segmentation or detection). The multiclass model achieved a Macro ROC AUC of 0.9176 and a Macro F1-score of 0.7658, while the binary model reached a Binary ROC AUC of 0.9383 and a Binary F1-score of 0.8668 on the LIDC-IDRI dataset. These results outperform several previously reported approaches and demonstrate state-of-the-art performance for this task. --- ### X-SYS: A Reference Architecture for Interactive Explanation Systems Authors: Tobias Labarta, Nhi Hoang, Maximilian Dreyer, Jim Berend, Oleg Hein, Jackie Ma, Wojciech Samek, Sebastian Lapuschkin Published: 2026-02-13 Categories: cs.AI, cs.HC, cs.SE arXiv: https://arxiv.org/abs/2602.12748v3 The explainable AI (XAI) research community has proposed numerous technical methods, yet deploying explainability as systems remains challenging: Interactive explanation systems require both suitable algorithms and system capabilities that maintain explanation usability across repeated queries, evolving models and data, and governance constraints. We argue that operationalizing XAI requires treating explainability as an information systems problem where user interaction demands induce specific system requirements. We introduce X-SYS, a reference architecture for interactive explanation systems, that guides (X)AI researchers, developers and practitioners in connecting interactive explanation user interfaces (XUI) with system capabilities. X-SYS organizes around four quality attributes named STAR (scalability, traceability, responsiveness, and adaptability), and specifies a five-component decomposition (XUI Services, Explanation Services, Model Services, Data Services, Orchestration and Governance). It maps interaction patterns to system capabilities to decouple user interface evolution from backend computation. We implement X-SYS through SemanticLens, a system for semantic search and activation steering in vision-language models. SemanticLens demonstrates how contract-based service boundaries enable independent evolution, offline/online separation ensures responsiveness, and persistent state management supports traceability. Together, this work provides a reusable blueprint and concrete instantiation for interactive explanation systems supporting end-to-end design under operational constraints. --- ### Lamer-SSL: Layer-aware Mixture of LoRA Experts for Continual Multilingual Expansion of Self-supervised Models without Forgetting Authors: Jing Xu, Minglin Wu, Xueyuan Chen, Xixin Wu, Helen Meng Published: 2026-02-13 Categories: cs.CL, eess.AS arXiv: https://arxiv.org/abs/2602.12746v1 Despite their impressive performance, self-supervised speech models often struggle to generalize to new languages and tend to forget previously acquired knowledge during continual training. To address this, we propose Lamer-SSL, a parameter-efficient framework that integrates a Layer-Aware MixturE of LoRA Experts (Lamer) module with a replay strategy. The Lamer module enables flexible balancing between shared and language-specific representations, while layer-aware expert allocation assigns more experts to deeper layers where semantic information is richer. Meanwhile, the replay strategy retains prior knowledge using minimal data, mitigating forgetting during continual training. Experiments on automatic speech recognition (ASR) and language identification (LID) demonstrate that Lamer-SSL extends self-supervised models to new languages effectively while maintaining strong performance on previously learned languages with only 2.14% parameters being trainable. --- ### Adaptive Structured Pruning of Convolutional Neural Networks for Time Series Classification Authors: Javidan Abdullayev, Maxime Devanne, Cyril Meyer, Ali Ismail-Fawaz, Jonathan Weber, Germain Forestier Published: 2026-02-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.12744v1 Deep learning models for Time Series Classification (TSC) have achieved strong predictive performance but their high computational and memory requirements often limit deployment on resource-constrained devices. While structured pruning can address these issues by removing redundant filters, existing methods typically rely on manually tuned hyperparameters such as pruning ratios which limit scalability and generalization across datasets. In this work, we propose Dynamic Structured Pruning (DSP), a fully automatic, structured pruning framework for convolution-based TSC models. DSP introduces an instance-wise sparsity loss during training to induce channel-level sparsity, followed by a global activation analysis to identify and prune redundant filters without needing any predefined pruning ratio. This work tackles computational bottlenecks of deep TSC models for deployment on resource-constrained devices. We validate DSP on 128 UCR datasets using two different deep state-of-the-art architectures: LITETime and InceptionTime. Our approach achieves an average compression of 58% for LITETime and 75% for InceptionTime architectures while maintaining classification accuracy. Redundancy analyses confirm that DSP produces compact and informative representations, offering a practical path for scalable and efficient deep TSC deployment. --- ### Synthetic Craquelure Generation for Unsupervised Painting Restoration Authors: Jana Cuch-Guillén, Antonio Agudo, Raül Pérez-Gonzalo Published: 2026-02-13 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.12742v1 Cultural heritage preservation increasingly demands non-invasive digital methods for painting restoration, yet identifying and restoring fine craquelure patterns from complex brushstrokes remains challenging due to scarce pixel-level annotations. We propose a fully annotation-free framework driven by a domain-specific synthetic craquelure generator, which simulates realistic branching and tapered fissure geometry using Bézier trajectories. Our approach couples a classical morphological detector with a learning-based refinement module: a SegFormer backbone adapted via Low-Rank Adaptation (LoRA). Uniquely, we employ a detector-guided strategy, injecting the morphological map as an input spatial prior, while a masked hybrid loss and logit adjustment constrain the training to focus specifically on refining candidate crack regions. The refined masks subsequently guide an Anisotropic Diffusion inpainting stage to reconstruct missing content. Experimental results demonstrate that our pipeline significantly outperforms state-of-the-art photographic restoration models in zero-shot settings, while faithfully preserving the original paint brushwork. --- ### SPRig: Self-Supervised Pose-Invariant Rigging from Mesh Sequences Authors: Ruipeng Wang, Langkun Zhong, Miaowei Wang Published: 2026-02-13 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2602.12740v2 State-of-the-art rigging methods typically assume a predefined canonical rest pose. However, this assumption does not hold for dynamic mesh sequences such as DyMesh or DT4D, where no canonical T-pose is available. When applied independently frame-by-frame, existing methods lack pose invariance and often yield temporally inconsistent topologies. To address this limitation, we propose SPRig, a general fine-tuning framework that enforces cross-frame consistency across a sequence to learn pose-invariant rigs on top of existing models, covering both skeleton and skinning generation. For skeleton generation, we introduce novel consistency regularization in both token space and geometry space. For skinning, we improve temporal stability through an articulation-invariant consistency loss combined with consistency distillation and structural regularization. Extensive experiments show that SPRig achieves superior temporal coherence and significantly reduces artifacts in prior methods, without sacrificing and often even enhancing per-frame static generation quality. The code is available in the supplemental material and will be made publicly available upon publication. --- ### VimRAG: Navigating Massive Visual Context in Retrieval-Augmented Generation via Multimodal Memory Graph Authors: Qiuchen Wang, Shihang Wang, Yu Zeng, Qiang Zhang, Fanrui Zhang, Zhuoning Guo, Bosi Zhang, Wenxuan Huang, Lin Chen, Zehui Chen, Pengjun Xie, Ruixue Ding Published: 2026-02-13 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2602.12735v2 Effectively retrieving, reasoning, and understanding multimodal information remains a critical challenge for agentic systems. Traditional Retrieval-augmented Generation (RAG) methods rely on linear interaction histories, which struggle to handle long-context tasks, especially those involving information-sparse yet token-heavy visual data in iterative reasoning scenarios. To bridge this gap, we introduce VimRAG, a framework tailored for multimodal Retrieval-augmented Reasoning across text, images, and videos. Inspired by our systematic study, we model the reasoning process as a dynamic directed acyclic graph that structures the agent states and retrieved multimodal evidence. Building upon this structured memory, we introduce a Graph-Modulated Visual Memory Encoding mechanism, with which the significance of memory nodes is evaluated via their topological position, allowing the model to dynamically allocate high-resolution tokens to pivotal evidence while compressing or discarding trivial clues. To implement this paradigm, we propose a Graph-Guided Policy Optimization strategy. This strategy disentangles step-wise validity from trajectory-level rewards by pruning memory nodes associated with redundant actions, thereby facilitating fine-grained credit assignment. Extensive experiments demonstrate that VimRAG consistently achieves state-of-the-art performance on diverse multimodal RAG benchmarks. The code is available at https://github.com/Alibaba-NLP/VRAG. --- ### ART3mis: Ray-Based Textual Annotation on 3D Cultural Objects Authors: Vasileios Arampatzakis, Vasileios Sevetlidis, Fotis Arnaoutoglou, Athanasios Kalogeras, Christos Koulamas, Aris Lalos, Chairi Kiourt, George Ioannakis, Anestis Koutsoudis, George Pavlidis Published: 2026-02-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.12725v1 Beyond simplistic 3D visualisations, archaeologists, as well as cultural heritage experts and practitioners, need applications with advanced functionalities. Such as the annotation and attachment of metadata onto particular regions of the 3D digital objects. Various approaches have been presented to tackle this challenge, most of which achieve excellent results in the domain of their application. However, they are often confined to that specific domain and particular problem. In this paper, we present ART3mis - a general-purpose, user-friendly, interactive textual annotation tool for 3D objects. Primarily attuned to aid cultural heritage conservators, restorers and curators with no technical skills in 3D imaging and graphics, the tool allows for the easy handling, segmenting and annotating of 3D digital replicas of artefacts. ART3mis applies a user-driven, direct-on-surface approach. It can handle detailed 3D cultural objects in real-time and store textual annotations for multiple complex regions in JSON data format. --- ### ADEPT: RL-Aligned Agentic Decoding of Emotion via Evidence Probing Tools -- From Consensus Learning to Ambiguity-Driven Emotion Reasoning Authors: Esther Sun, Bo-Hao Su, Abinay Reddy Naini, Shinji Watanabe, Carlos Busso Published: 2026-02-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.12714v1 Speech Large Language Models (SLLMs) enable high-level emotion reasoning but often produce ungrounded, text-biased judgments without verifiable acoustic evidence. In contrast, self-supervised speech encoders such as WavLM provide strong acoustic representations yet remain opaque discriminative models with limited interpretability. To bridge this gap, we introduce ADEPT (Agentic Decoding of Emotion via Evidence Probing Tools), a framework that reframes emotion recognition as a multi-turn inquiry process rather than a single-pass prediction. ADEPT transforms an SLLM into an agent that maintains an evolving candidate emotion set and adaptively invokes dedicated semantic and acoustic probing tools within a structured pipeline of candidate generation, evidence collection, and adjudication. Crucially, ADEPT enables a paradigm shift from consensus learning to ambiguity-driven emotion reasoning. Since human affect exhibits inherent complexity and frequent co-occurrence of emotions, we treat minority annotations as informative perceptual signals rather than discarding them as noise. Finally, we integrate Group Relative Policy Optimization (GRPO) with an Evidence Trust Gate to explicitly couple tool-usage behaviors with prediction quality and enforce evidence-grounded reasoning. Experiments show that ADEPT improves primary emotion accuracy in most settings while substantially improving minor emotion characterization, producing explanations grounded in auditable acoustic and semantic evidence. --- ### Reverse Delegated Training and Private Inference via Perfectly-Secure Quantum Homomorphic Encryption Authors: Sergio A. Ortega, Miguel A. Martin-Delgado Published: 2026-02-13 Categories: quant-ph, cs.NE arXiv: https://arxiv.org/abs/2602.12712v1 Quantum machine learning in cloud environments requires protecting sensitive data while enabling remote computation. Here we demonstrate the first realistic implementations of a perfectly-secure quantum homomorphic encryption (QHE) scheme applied to quantum neural networks (QNN). Using efficient Clifford+$T$ decomposition, we implement quantum convolutional neural networks for two complementary scenarios: (i) reverse delegated training, where encrypted data from multiple providers trains a user's network via federated aggregation; (ii) private inference, where users process encrypted data with remote quantum networks. Moreover, analysis of server circuit privacy reveals probabilistic model protection through Pauli gate concealment. These results establish perfectly-secure QHE as a practical framework for multi-party quantum machine learning. --- ### ReFilter: Improving Robustness of Retrieval-Augmented Generation via Gated Filter Authors: Yixin Chen, Ying Xiong, Shangyu Wu, Xiangrui Ke, Nan Guan, Chun Jason Xue Published: 2026-02-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.12709v1 Retrieval-augmented generation (RAG) has become a dominant paradigm for grounding large language models (LLMs) with external evidence in knowledge-intensive question answering. A core design choice is how to fuse retrieved samples into the LLMs, where existing internal fusion approaches broadly fall into query-based fusion, parametric fusion, and latent-based fusion. Despite their effectiveness at modest retrieval scales, these methods often fail to scale gracefully as the number of retrieved candidates k increases: Larger k improves evidence coverage, yet realistic top-k retrieval inevitably contains irrelevant or redundant content and increases the inference cost. To address these limitations, we propose ReFilter, a novel latent-based fusion framework that performs token-level filtering and fusion. ReFilter consists of three key components: a context encoder for encoding context features, a gated filter for weighting each token, and a token fusion module for integrating the weighted token feature into the LLM's hidden states. Our experiments across four general-domain QA benchmarks show that ReFilter consistently achieves the best average performance under both in-domain adaptation and out-of-domain transfer. ReFilter further generalizes to five biomedical QA benchmarks in zero-shot transfer without domain fine-tuning, reaching 70.01% average accuracy with Qwen2.5-14B-Instruct. --- ### Mixture of Predefined Experts: Maximizing Data Usage on Vertical Federated Learning Authors: Jon Irureta, Gorka Azkune, Jon Imaz, Aizea Lojo, Javier Fernandez-Marques Published: 2026-02-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.12708v2 Vertical Federated Learning (VFL) has emerged as a critical paradigm for collaborative model training in privacy-sensitive domains such as finance and healthcare. However, most existing VFL frameworks rely on the idealized assumption of full sample alignment across participants, a premise that rarely holds in real-world scenarios. To bridge this gap, this work introduces Split-MoPE, a novel framework that integrates Split Learning with a specialized Mixture of Predefined Experts (MoPE) architecture. Unlike standard Mixture of Experts (MoE), where routing is learned dynamically, MoPE uses predefined experts to process specific data alignments, effectively maximizing data usage during both training and inference without requiring full sample overlap. By leveraging pretrained encoders for target data domains, Split-MoPE achieves state-of-the-art performance in a single communication round, significantly reducing the communication footprint compared to multi-round end-to-end training. Furthermore, unlike existing proposals that address sample misalignment, this novel architecture provides inherent robustness against malicious or noisy participants and offers per-sample interpretability by quantifying each collaborator's contribution to each prediction. Extensive evaluations on vision (CIFAR-10/100) and tabular (Breast Cancer Wisconsin) datasets demonstrate that Split-MoPE consistently outperforms state-of-the-art systems such as LASER and Vertical SplitNN, particularly in challenging scenarios with high data missingness. --- ### Physics-Informed Laplace Neural Operator for Solving Partial Differential Equations Authors: Heechang Kim, Qianying Cao, Hyomin Shin, Seungchul Lee, George Em Karniadakis, Minseok Choi Published: 2026-02-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.12706v2 Neural operators have emerged as fast surrogate solvers for parametric partial differential equations (PDEs). However, purely data-driven models often require extensive training data and can generalize poorly, especially in small-data regimes and under unseen (out-of-distribution) input functions that are not represented in the training data. To address these limitations, we propose the Physics-Informed Laplace Neural Operator (PILNO), which enhances the Laplace Neural Operator (LNO) by embedding governing physics into training through PDE, boundary condition, and initial condition residuals. To improve expressivity, we first introduce an Advanced LNO (ALNO) backbone that retains a pole-residue transient representation while replacing the steady-state branch with an FNO-style Fourier multiplier. To make physics-informed training both data-efficient and robust, PILNO further leverages (i) virtual inputs: an unlabeled ensemble of input functions spanning a broad spectral range that provides abundant physics-only supervision and explicitly targets out-of-distribution (OOD) regimes; and (ii) temporal-causality weighting: a time-decaying reweighting of the physics residual that prioritizes early-time dynamics and stabilizes optimization for time-dependent PDEs. Across four representative benchmarks -- Burgers' equation, Darcy flow, a reaction-diffusion system, and a forced KdV equation -- PILNO consistently improves accuracy in small-data settings (e.g., N_train <= 27), reduces run-to-run variability across random seeds, and achieves stronger OOD generalization with respect to input function statistics than purely data-driven baselines. --- ### Physics-Informed Laplace Neural Operator for Solving Partial Differential Equations Authors: Heechang Kim, Qianying Cao, Hyomin Shin, Seungchul Lee, George Em Karniadakis, Minseok Choi Published: 2026-02-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.12706v1 Neural operators have emerged as fast surrogate solvers for parametric partial differential equations (PDEs). However, purely data-driven models often require extensive training data and can generalize poorly, especially in small-data regimes and under unseen (out-of-distribution) input functions that are not represented in the training data. To address these limitations, we propose the Physics-Informed Laplace Neural Operator (PILNO), which enhances the Laplace Neural Operator (LNO) by embedding governing physics into training through PDE, boundary condition, and initial condition residuals. To improve expressivity, we first introduce an Advanced LNO (ALNO) backbone that retains a pole-residue transient representation while replacing the steady-state branch with an FNO-style Fourier multiplier. To make physics-informed training both data-efficient and robust, PILNO further leverages (i) virtual inputs: an unlabeled ensemble of input functions spanning a broad spectral range that provides abundant physics-only supervision and explicitly targets out-of-distribution (OOD) regimes; and (ii) temporal-causality weighting: a time-decaying reweighting of the physics residual that prioritizes early-time dynamics and stabilizes optimization for time-dependent PDEs. Across four representative benchmarks -- Burgers' equation, Darcy flow, a reaction-diffusion system, and a forced KdV equation -- PILNO consistently improves accuracy in small-data settings (e.g., N_train <= 27), reduces run-to-run variability across random seeds, and achieves stronger OOD generalization than purely data-driven baselines. --- ### MedXIAOHE: A Comprehensive Recipe for Building Medical MLLMs Authors: Baorong Shi, Bo Cui, Boyuan Jiang, Deli Yu, Fang Qian, Haihua Yang, Huichao Wang, Jiale Chen, Jianfei Pan, Jieqiong Cao, Jinghao Lin, Kai Wu et al. Published: 2026-02-13 Categories: cs.CL, cs.AI, cs.CV, eess.IV arXiv: https://arxiv.org/abs/2602.12705v4 We present MedXIAOHE, a medical vision-language foundation model designed to advance general-purpose medical understanding and reasoning in real-world clinical applications. MedXIAOHE achieves state-of-the-art performance across diverse medical benchmarks and surpasses leading closed-source multimodal systems on multiple capabilities. To achieve this, we propose an entity-aware continual pretraining framework that organizes heterogeneous medical corpora to broaden knowledge coverage and reduce long-tail gaps (e.g., rare diseases). For medical expert-level reasoning and interaction, MedXIAOHE incorporates diverse medical reasoning patterns via reinforcement learning and tool-augmented agentic training, enabling multi-step diagnostic reasoning with verifiable decision traces. To improve reliability in real-world use, MedXIAOHE integrates user-preference rubrics, evidence-grounded reasoning, and low-hallucination long-form report generation, with improved adherence to medical instructions. We release this report to document our practical design choices, scaling insights, and evaluation framework, hoping to inspire further research. --- ### QTabGAN: A Hybrid Quantum-Classical GAN for Tabular Data Synthesis Authors: Subhangi Kumari, Rakesh Achutha, Vignesh Sivaraman Published: 2026-02-13 Categories: cs.LG, quant-ph arXiv: https://arxiv.org/abs/2602.12704v2 Synthesizing realistic tabular data is challenging due to heterogeneous feature types and high dimensionality. We introduce QTabGAN, a hybrid quantum-classical generative adversarial framework for tabular data synthesis. QTabGAN is especially designed for settings where real data are scarce or restricted by privacy constraints. The model exploits the expressive power of quantum circuits to learn complex data distributions, which are then mapped to tabular features using classical neural networks. We evaluate QTabGAN on multiple classification and regression datasets and benchmark it against leading state-of-the-art generative models. Experiments show that QTabGAN achieves up to 54.07% improvement across various classification datasets and evaluation metrics, thus establishing a scalable quantum approach to tabular data synthesis and highlighting its potential for quantum-assisted generative modelling. --- ### SWING: Unlocking Implicit Graph Representations for Graph Random Features Authors: Alessandro Manenti, Avinava Dubey, Arijit Sehanobish, Cesare Alippi, Krzysztof Choromanski Published: 2026-02-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.12703v2 We propose SWING: Space Walks for Implicit Network Graphs, a new class of algorithms for computations involving Graph Random Features on graphs given by implicit representations (i-graphs), where edge-weights are defined as bi-variate functions of feature vectors in the corresponding nodes. Those classes of graphs include several prominent examples, such as: $ε$-neighborhood graphs, used on regular basis in machine learning. Rather than conducting walks on graphs' nodes, those methods rely on walks in continuous spaces, in which those graphs are embedded. To accurately and efficiently approximate original combinatorial calculations, SWING applies customized Gumbel-softmax sampling mechanism with linearized kernels, obtained via random features coupled with importance sampling techniques. This algorithm is of its own interest. SWING relies on the deep connection between implicitly defined graphs and Fourier analysis, presented in this paper. SWING is accelerator-friendly and does not require input graph materialization. We provide detailed analysis of SWING and complement it with thorough experiments on different classes of i-graphs. --- ### Channel-Aware Probing for Multi-Channel Imaging Authors: Umar Marikkar, Syed Sameed Husain, Muhammad Awais, Sara Atito Published: 2026-02-13 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.12696v1 Training and evaluating vision encoders on Multi-Channel Imaging (MCI) data remains challenging as channel configurations vary across datasets, preventing fixed-channel training and limiting reuse of pre-trained encoders on new channel settings. Prior work trains MCI encoders but typically evaluates them via full fine-tuning, leaving probing with frozen pre-trained encoders comparatively underexplored. Existing studies that perform probing largely focus on improving representations, rather than how to best leverage fixed representations for downstream tasks. Although the latter problem has been studied in other domains, directly transferring those strategies to MCI yields weak results, even worse than training from scratch. We therefore propose Channel-Aware Probing (CAP), which exploits the intrinsic inter-channel diversity in MCI datasets by controlling feature flow at both the encoder and probe levels. CAP uses Independent Feature Encoding (IFE) to encode each channel separately, and Decoupled Pooling (DCP) to pool within channels before aggregating across channels. Across three MCI benchmarks, CAP consistently improves probing performance over the default probing protocol, matches fine-tuning from scratch, and largely reduces the gap to full fine-tuning from the same MCI pre-trained checkpoints. Code can be found in https://github.com/umarikkar/CAP. --- ### Leverage-Weighted Conformal Prediction Authors: Shreyas Fadnavis Published: 2026-02-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.12693v1 Split conformal prediction provides distribution-free prediction intervals with finite-sample marginal coverage, but produces constant-width intervals that overcover in low-variance regions and undercover in high-variance regions. Existing adaptive methods require training auxiliary models. We propose Leverage-Weighted Conformal Prediction (LWCP), which weights nonconformity scores by a function of the statistical leverage -- the diagonal of the hat matrix -- deriving adaptivity from the geometry of the design matrix rather than from auxiliary model fitting. We prove that LWCP preserves finite-sample marginal validity for any weight function; achieves asymptotically optimal conditional coverage at essentially no width cost when heteroscedasticity factors through leverage; and recovers the form and width of classical prediction intervals under Gaussian assumptions while retaining distribution-free guarantees. We further establish that randomized leverage approximations preserve coverage exactly with controlled width perturbation, and that vanilla CP suffers a persistent, sample-size-independent conditional coverage gap that LWCP eliminates. The method requires no hyperparameters beyond the choice of weight function and adds negligible computational overhead to vanilla CP. Experiments on synthetic and real data confirm the theoretical predictions, demonstrating substantial reductions in conditional coverage disparity across settings. --- ### ALOE: Action-Level Off-Policy Evaluation for Vision-Language-Action Model Post-Training Authors: Rushuai Yang, Hecheng Wang, Zhichao Wu, Chiming Liu, Xiaohan Yan, Xuan Du, Shuoyu Yue, Chuheng Zhang, Yunlong Wang, Yongcheng Liu, Lizhe Qi, Yi Chen et al. Published: 2026-02-13 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2602.12691v3 We study how to improve large foundation vision-language-action (VLA) systems through human-in-the-loop reinforcement learning (RL) in real-world environments. A key challenge is learning reliable value functions from heterogeneous real-world experience, as value estimation provides the primary learning signal for VLA training. In practice, replay buffers contain trajectories collected from historical policies, online rollouts, demonstrations, and intermittent human interventions. Because replay buffers mix trajectories generated by different behaviors, the observed returns can be mismatched with the quality of the current policy. Prior VLA post-training methods often rely on progress-style value signals, which reflect the average quality of historical behaviors, leading to mismatched learning signals for the current policy. In this paper, we propose ALOE, an off-policy evaluation framework whose value function directly evaluates current-policy behavior for each iteration. Specifically, ALOE combines chunked temporal-difference bootstrapping and conservative value aggregation to perform stable current-policy evaluation, then uses these estimates for advantage-weighted policy improvement. This design improves credit assignment to critical action chunks under sparse rewards and supports stable policy improvement. We evaluate ALOE on four real-world manipulation tasks encompassing long-horizon and high-precision scenarios: smartphone packing, laundry folding, multi-object sorting, and phone assembly. Across all tasks, ALOE outperforms other VLA post-training methods, highlighting the benefit of off-policy value estimates for real-world VLA post-training. Videos are available at our project website https://rooshy-yang.github.io/aloe. --- ### Trust the uncertain teacher: distilling dark knowledge via calibrated uncertainty Authors: Jeonghyun Kim, SooKyung Kim, Richeng Xuan, Hyunsoo Cho Published: 2026-02-13 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.12687v2 The core of knowledge distillation lies in transferring the teacher's rich 'dark knowledge'-subtle probabilistic patterns that reveal how classes are related and the distribution of uncertainties. While this idea is well established, teachers trained with conventional cross-entropy often fail to preserve such signals. Their distributions collapse into sharp, overconfident peaks that appear decisive but are in fact brittle, offering little beyond the hard label or subtly hindering representation-level transfer. This overconfidence is especially problematic in high-cardinality tasks, where the nuances among many plausible classes matter most for guiding a compact student. Moreover, such brittle targets reduce robustness under distribution shift, leaving students vulnerable to miscalibration in real-world conditions. To address this limitation, we revisit distillation from a distributional perspective and propose Calibrated Uncertainty Distillation (CUD), a framework designed to make dark knowledge more faithfully accessible. Instead of uncritically adopting the teacher's overconfidence, CUD encourages teachers to reveal uncertainty where it is informative and guides students to learn from targets that are calibrated rather than sharpened certainty. By directly shaping the teacher's predictive distribution before transfer, our approach balances accuracy and calibration, allowing students to benefit from both confident signals on easy cases and structured uncertainty on hard ones. Across diverse benchmarks, CUD yields students that are not only more accurate, but also more calibrated under shift and more reliable on ambiguous, long-tail inputs. --- ### Xiaomi-Robotics-0: An Open-Sourced Vision-Language-Action Model with Real-Time Execution Authors: Rui Cai, Jun Guo, Xinze He, Piaopiao Jin, Jie Li, Bingxuan Lin, Futeng Liu, Wei Liu, Fei Ma, Kun Ma, Feng Qiu, Heng Qu et al. Published: 2026-02-13 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2602.12684v2 In this report, we introduce Xiaomi-Robotics-0, an advanced vision-language-action (VLA) model optimized for high performance and fast and smooth real-time execution. The key to our method lies in a carefully designed training recipe and deployment strategy. Xiaomi-Robotics-0 is first pre-trained on large-scale cross-embodiment robot trajectories and vision-language data, endowing it with broad and generalizable action-generation capabilities while avoiding catastrophic forgetting of the visual-semantic knowledge of the underlying pre-trained VLM. During post-training, we propose several techniques for training the VLA model for asynchronous execution to address the inference latency during real-robot rollouts. During deployment, we carefully align the timesteps of consecutive predicted action chunks to ensure continuous and seamless real-time rollouts. We evaluate Xiaomi-Robotics-0 extensively in simulation benchmarks and on two challenging real-robot tasks that require precise and dexterous bimanual manipulation. Results show that our method achieves state-of-the-art performance across all simulation benchmarks. Moreover, Xiaomi-Robotics-0 can roll out fast and smoothly on real robots using a consumer-grade GPU, achieving high success rates and throughput on both real-robot tasks. To facilitate future research, code and model checkpoints are open-sourced at https://xiaomi-robotics-0.github.io --- ### Flow Matching from Viewpoint of Proximal Operators Authors: Kenji Fukumizu, Wei Huang, Han Bao, Shuntuo Xu, Nisha Chandramoorthy Published: 2026-02-13 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2602.12683v2 We reformulate Optimal Transport Conditional Flow Matching (OT-CFM), a class of dynamical generative models, showing that it admits an exact proximal formulation via an extended Brenier potential, without assuming that the target distribution has a density. In particular, the mapping to recover the target point is exactly given by a proximal operator, which yields an explicit proximal expression of the vector field. We also discuss the convergence of minibatch OT-CFM to the population formulation as the batch size increases. Finally, using second epi-derivatives of convex potentials, we prove that, for manifold-supported targets, OT-CFM is terminally normally hyperbolic: after time rescaling, the dynamics contracts exponentially in directions normal to the data manifold while remaining neutral along tangential directions. --- ### Fool Me If You Can: On the Robustness of Binary Code Similarity Detection Models against Semantics-preserving Transformations Authors: Jiyong Uhm, Minseok Kim, Michalis Polychronakis, Hyungjoon Koo Published: 2026-02-13 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2602.12681v1 Binary code analysis plays an essential role in cybersecurity, facilitating reverse engineering to reveal the inner workings of programs in the absence of source code. Traditional approaches, such as static and dynamic analysis, extract valuable insights from stripped binaries, but often demand substantial expertise and manual effort. Recent advances in deep learning have opened promising opportunities to enhance binary analysis by capturing latent features and disclosing underlying code semantics. Despite the growing number of binary analysis models based on machine learning, their robustness to adversarial code transformations at the binary level remains underexplored. We evaluate the robustness of deep learning models for the task of binary code similarity detection (BCSD) under semantics-preserving transformations. The unique nature of machine instructions presents distinct challenges compared to the typical input perturbations found in other domains. We introduce asmFooler, a system that evaluates the resilience of BCSD models using a diverse set of adversarial code transformations that preserve functional semantics. We construct a dataset of 9,565 binary variants from 620 baseline samples by applying eight semantics-preserving transformations across six representative BCSD models. Our major findings highlight several key insights: i) model robustness relies on the processing pipeline, including code pre-processing, architecture, and feature selection; ii) adversarial transformation effectiveness is bounded by a budget shaped by model-specific constraints like input size and instruction expressive capacity; iii) well-crafted transformations can be highly effective with minimal perturbations; and iv) such transformations efficiently disrupt model decisions (e.g., misleading to false positives or false negatives) by focusing on semantically significant instructions. --- ### A Regularization-Sharpness Tradeoff for Linear Interpolators Authors: Qingyi Hu, Liam Hodgkinson Published: 2026-02-13 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2602.12680v1 The rule of thumb regarding the relationship between the bias-variance tradeoff and model size plays a key role in classical machine learning, but is now well-known to break down in the overparameterized setting as per the double descent curve. In particular, minimum-norm interpolating estimators can perform well, suggesting the need for new tradeoff in these settings. Accordingly, we propose a regularization-sharpness tradeoff for overparameterized linear regression with an $\ell^p$ penalty. Inspired by the interpolating information criterion, our framework decomposes the selection penalty into a regularization term (quantifying the alignment of the regularizer and the interpolator) and a geometric sharpness term on the interpolating manifold (quantifying the effect of local perturbations), yielding a tradeoff analogous to bias-variance. Building on prior analyses that established this information criterion for ridge regularizers, this work first provides a general expression of the interpolating information criterion for $\ell^p$ regularizers where $p \ge 2$. Subsequently, we extend this to the LASSO interpolator with $\ell^1$ regularizer, which induces stronger sparsity. Empirical results on real-world datasets with random Fourier features and polynomials validate our theory, demonstrating how the tradeoff terms can distinguish performant linear interpolators from weaker ones. --- ### Motion Prior Distillation in Time Reversal Sampling for Generative Inbetweening Authors: Wooseok Jeon, Seunghyun Shin, Dongmin Shin, Hae-Gon Jeon Published: 2026-02-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.12679v2 Recent progress in image-to-video (I2V) diffusion models has significantly advanced the field of generative inbetweening, which aims to generate semantically plausible frames between two keyframes. In particular, inference-time sampling strategies, which leverage the generative priors of large-scale pre-trained I2V models without additional training, have become increasingly popular. However, existing inference-time sampling, either fusing forward and backward paths in parallel or alternating them sequentially, often suffers from temporal discontinuities and undesirable visual artifacts due to the misalignment between the two generated paths. This is because each path follows the motion prior induced by its own conditioning frame. In this work, we propose Motion Prior Distillation (MPD), a simple yet effective inference-time distillation technique that suppresses bidirectional mismatch by distilling the motion residual of the forward path into the backward path. Our method can deliberately avoid denoising the end-conditioned path which causes the ambiguity of the path, and yield more temporally coherent inbetweening results with the forward motion prior. We not only perform quantitative evaluations on standard benchmarks, but also conduct extensive user studies to demonstrate the effectiveness of our approach in practical scenarios. --- ### SLA2: Sparse-Linear Attention with Learnable Routing and QAT Authors: Jintao Zhang, Haoxu Wang, Kai Jiang, Kaiwen Zheng, Youhe Jiang, Ion Stoica, Jianfei Chen, Jun Zhu, Joseph E. Gonzalez Published: 2026-02-13 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2602.12675v1 Sparse-Linear Attention (SLA) combines sparse and linear attention to accelerate diffusion models and has shown strong performance in video generation. However, (i) SLA relies on a heuristic split that assigns computations to the sparse or linear branch based on attention-weight magnitude, which can be suboptimal. Additionally, (ii) after formally analyzing the attention error in SLA, we identify a mismatch between SLA and a direct decomposition into sparse and linear attention. We propose SLA2, which introduces (I) a learnable router that dynamically selects whether each attention computation should use sparse or linear attention, (II) a more faithful and direct sparse-linear attention formulation that uses a learnable ratio to combine the sparse and linear attention branches, and (III) a sparse + low-bit attention design, where low-bit attention is introduced via quantization-aware fine-tuning to reduce quantization error. Experiments show that on video diffusion models, SLA2 can achieve 97% attention sparsity and deliver an 18.6x attention speedup while preserving generation quality. --- ### $\mathcal{X}$-KD: General Experiential Knowledge Distillation for Large Language Models Authors: Yuang Cai, Yuyu Yuan Published: 2026-02-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.12674v1 Knowledge Distillation (KD) for Large Language Models (LLMs) has become increasingly important as models grow in size and complexity. While existing distillation approaches focus on imitating teacher behavior, they often overlook the original learning environment that shaped the teacher's knowledge. Inspired by the experiential learning theory and inverse reinforcement learning, we propose Experiential Knowledge Distillation ($\mathcal{X}$-KD), a novel and general framework that enables student models to learn in the teacher's original learning environment. $\mathcal{X}$-KD adopts the Approximated Variational Reward Imitation Learning (AVRIL) framework to jointly model the teacher's original reward function and perform policy distillation, encouraging consistency between the student policy and the original reward function. Our derivation demonstrates that $\mathcal{X}$-KD follows the supervised learning framework and applies to both sequence-level and divergence-based distillation methods, underlining the simplicity and flexibility of our approach. Empirical results show that $\mathcal{X}$-KD outperforms the generalized KD and MiniLLM baselines on abstractive summarization, machine translation, and arithmetic reasoning tasks. Additionally, $\mathcal{X}$-KD achieves better performance-diversity trade-off and data efficiency than baseline KD approaches. --- ### SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks Authors: Xiangyi Li, Yimin Liu, Wenbo Chen, Bingran You, Zonglin Di, Yifeng He, Shenghan Zheng, Kyoung Whan Choe, Jiankai Sun, Shuyi Wang, Chujun Tao, Binxu Li et al. Published: 2026-02-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.12670v4 Agent Skills are structured packages of procedural knowledge that augment large language model (LLM) agents at inference time. Despite rapid adoption, there is no standard way to measure whether they actually help. We present SkillsBench, a benchmark whose current inventory contains 87 tasks across 8 domains paired with curated Skills and deterministic verifiers. Our latest aggregate evaluation runs the 87-task benchmark under matched no-Skills and curated-Skills conditions for 18 model-harness configurations. Curated Skills raise the average pass rate from 33.9% to 50.5% (+16.6 percentage points; 25.5% normalized gain), with configuration-level gains ranging from +4.1 to +25.7 pp. Focused Skills with at most three modules outperform larger or exhaustive bundles, and smaller models with Skills can match larger models without them. SkillsBench establishes paired evaluation as the foundation for rigorous measurement of Skill efficacy on agentic, expertise-heavy work. --- ### Evaluating Robustness of Reasoning Models on Parameterized Logical Problems Authors: Naïm Es-sebbani, Esteban Marquer, Yakoub Salhi, Zied Bouraoui Published: 2026-02-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.12665v1 Logic provides a controlled testbed for evaluating LLM-based reasoners, yet standard SAT-style benchmarks often conflate surface difficulty (length, wording, clause order) with the structural phenomena that actually determine satisfiability. We introduce a diagnostic benchmark for 2-SAT built from parameterized families of structured 2--CNF formulas, where satisfiability is characterized by the implication graph and can be tuned along interpretable axes. Our generators isolate distinct competencies and failure modes: (i) contradiction-cycle UNSAT cores with controllable size and imbalance, (ii) SAT instances with a prescribed fraction of free variables to control solution multiplicity, (iii) planted backbones that modulate propagation, (iv) late bridge clauses that couple otherwise monotone regions to probe sensitivity to ordering and revision, and (v) symmetry/duplication variants that test abstraction under renaming and redundant structure. We evaluate LLM-based reasoners on decision accuracy and assignment validity, and quantify robustness under semantics-preserving perturbations such as clause reordering, filler clauses, and variable renaming. Across models, we observe sharp performance transitions under targeted structural interventions even when surface statistics are held fixed, revealing brittleness regimes that are invisible to aggregate SAT accuracy. --- ### Think Fast and Slow: Step-Level Cognitive Depth Adaptation for LLM Agents Authors: Ruihan Yang, Fanghua Ye, Xiang We, Ruoqing Zhao, Kang Luo, Xinbo Xu, Bo Zhao, Ruotian Ma, Shanyi Wang, Zhaopeng Tu, Xiaolong Li, Deqing Yang et al. Published: 2026-02-13 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.12662v1 Large language models (LLMs) are increasingly deployed as autonomous agents for multi-turn decision-making tasks. However, current agents typically rely on fixed cognitive patterns: non-thinking models generate immediate responses, while thinking models engage in deep reasoning uniformly. This rigidity is inefficient for long-horizon tasks, where cognitive demands vary significantly from step to step, with some requiring strategic planning and others only routine execution. In this paper, we introduce CogRouter, a framework that trains agents to dynamically adapt cognitive depth at each step. Grounded in ACT-R theory, we design four hierarchical cognitive levels ranging from instinctive responses to strategic planning. Our two-stage training approach includes Cognition-aware Supervised Fine-tuning (CoSFT) to instill stable level-specific patterns, and Cognition-aware Policy Optimization (CoPO) for step-level credit assignment via confidence-aware advantage reweighting. The key insight is that appropriate cognitive depth should maximize the confidence of the resulting action. Experiments on ALFWorld and ScienceWorld demonstrate that CogRouter achieves state-of-the-art performance with superior efficiency. With Qwen2.5-7B, it reaches an 82.3% success rate, outperforming GPT-4o (+40.3%), OpenAI-o3 (+18.3%), and GRPO (+14.0%), while using 62% fewer tokens. --- ### Learning Ordinal Probabilistic Reward from Preferences Authors: Longze Chen, Lu Wang, Renke Shan, Ze Gong, Run Luo, Jiaming Li, Jing Luo, Qiyao Wang, Min Yang Published: 2026-02-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.12660v2 Reward models are crucial for aligning large language models (LLMs) with human values and intentions. Existing approaches follow either Generative (GRMs) or Discriminative (DRMs) paradigms, yet both suffer from limitations: GRMs typically demand costly point-wise supervision, while DRMs produce uncalibrated relative scores that lack probabilistic interpretation. To address these challenges, we introduce a novel reward modeling paradigm: Probabilistic Reward Model (PRM). Instead of modeling reward as a deterministic scalar, our approach treats it as a random variable, learning a full probability distribution for the quality of each response. To make this paradigm practical, we present its closed-form, discrete realization: the Ordinal Probabilistic Reward Model (OPRM), which discretizes the quality score into a finite set of ordinal ratings. Building on OPRM, we propose a data-efficient training strategy called Region Flooding Tuning (RgFT). It enables rewards to better reflect absolute text quality by incorporating quality-level annotations, which guide the model to concentrate the probability mass within corresponding rating sub-regions. Experiments on various reward model benchmarks show that our method improves accuracy by $\textbf{2.9%}\sim\textbf{7.4%}$ compared to prior reward models, demonstrating strong performance and data efficiency. Analysis of the score distribution provides evidence that our method captures not only relative rankings but also absolute quality. ---