# Research Papers — 2026-02 · bundle page 96 of 210 > Full-text markdown of papers #4751–4800 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/96 [← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/95.md) [Next bundle →](https://aipod.dev/papers/archive/2026-02/page/97.md) ### Which Algorithms Can Graph Neural Networks Learn? Authors: Solveig Wittig, Antonis Vasileiou, Robert R. Nerem, Timo Stoll, Floris Geerts, Yusu Wang, Christopher Morris Published: 2026-02-13 Categories: cs.LG, cs.AI, cs.DS, cs.NE arXiv: https://arxiv.org/abs/2602.13106v1 In recent years, there has been growing interest in understanding neural architectures' ability to learn to execute discrete algorithms, a line of work often referred to as neural algorithmic reasoning. The goal is to integrate algorithmic reasoning capabilities into larger neural pipelines. Many such architectures are based on (message-passing) graph neural networks (MPNNs), owing to their permutation equivariance and ability to deal with sparsity and variable-sized inputs. However, existing work is either largely empirical and lacks formal guarantees or it focuses solely on expressivity, leaving open the question of when and how such architectures generalize beyond a finite training set. In this work, we propose a general theoretical framework that characterizes the sufficient conditions under which MPNNs can learn an algorithm from a training set of small instances and provably approximate its behavior on inputs of arbitrary size. Our framework applies to a broad class of algorithms, including single-source shortest paths, minimum spanning trees, and general dynamic programming problems, such as the $0$-$1$ knapsack problem. In addition, we establish impossibility results for a wide range of algorithmic tasks, showing that standard MPNNs cannot learn them, and we derive more expressive MPNN-like architectures that overcome these limitations. Finally, we refine our analysis for the Bellman-Ford algorithm, yielding a substantially smaller required training set and significantly extending the recent work of Nerem et al. (2025) by allowing for a differentiable regularization loss. Empirical results largely support our theoretical findings. --- ### Random Forests as Statistical Procedures: Design, Variance, and Dependence Authors: Nathaniel S. O'Connell Published: 2026-02-13 Categories: stat.ML, cs.LG, math.ST arXiv: https://arxiv.org/abs/2602.13104v3 We develop a finite-sample, design-based theory for random forests in which each tree is a randomized conditional predictor acting on fixed covariates and the forest is their Monte Carlo average. An exact variance identity separates Monte Carlo error from a covariance floor that persists under infinite aggregation. The floor arises through two mechanisms: observation reuse, where the same training outcomes receive weight across multiple trees, and partition alignment, where independently generated trees discover similar conditional prediction rules. We prove the floor is strictly positive under minimal conditions and show that alignment persists even when sample splitting eliminates observation overlap entirely. We introduce procedure-aligned synthetic resampling (PASR) to estimate the covariance floor, decomposing the total prediction uncertainty of a deployed forest into interpretable components. For continuous outcomes, resulting prediction intervals achieve nominal coverage with a theoretically guaranteed conservative bias direction. For classification forests, the PASR estimator is asymptotically unbiased, providing the first pointwise confidence intervals for predicted conditional probabilities from a deployed forest. Nominal coverage is maintained across a range of design configurations for both outcome types, including high-dimensional settings. The underlying theory extends to any tree-based ensemble with an exchangeable tree-generating mechanism. --- ### R-Diverse: Mitigating Diversity Illusion in Self-Play LLM Training Authors: Gengsheng Li, Jinghan He, Shijie Wang, Dan Zhang, Ruiqi Liu, Renrui Zhang, Zijun Yao, Junfeng Fang, Haiyun Guo, Jinqiao Wang Published: 2026-02-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.13103v2 Self-play bootstraps LLM reasoning through an iterative Challenger-Solver loop: the Challenger is trained to generate questions that target the Solver's capabilities, and the Solver is optimized on the generated data to expand its reasoning skills. However, existing frameworks like R-Zero often exhibit non-sustained improvement, where early gains degrade as self-play continues. We identify a key failure mode, Diversity Illusion, where the Solver's training signals appear diverse yet collapse into recurring underlying patterns. It manifests as (1) Local Diversity Illusion, where diversity is enforced only within-batch, inducing cross-iteration mode cycling; and (2) Surface Diversity Illusion, where questions vary superficially but require near-identical reasoning skills. To mitigate them, we propose R-Diverse with two aligned innovations: Memory-Augmented Penalty (MAP), which uses a persistent memory bank to discourage recycling across iterations, and Skill-Aware Measurement (SAM), which evaluates diversity by the reasoning skills exercised rather than surface variation of questions. Across 10 math and general reasoning benchmarks, R-Diverse sustains gains over more iterations and consistently outperforms prior self-play methods. Code is available at https://github.com/Gengsheng-Li/R-Diverse. --- ### Towards interpretable models for language proficiency assessment: Predicting the CEFR level of Estonian learner texts Authors: Kais Allkivi Published: 2026-02-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.13102v2 Using NLP to analyze authentic learner language helps to build automated assessment and feedback tools. It also offers new and extensive insights into the development of second language production. However, there is a lack of research explicitly combining these aspects. This study aimed to classify Estonian proficiency examination writings (levels A2-C1), assuming that careful feature selection can lead to more explainable and generalizable machine learning models for language testing. Various linguistic properties of the training data were analyzed to identify relevant proficiency predictors associated with increasing complexity and correctness, rather than the writing task. Such lexical, morphological, surface, and error features were used to train classification models, which were compared to models that also allowed for other features. The pre-selected features yielded a similar test accuracy but reduced variation in the classification of different text types. The best classifiers achieved an accuracy of around 0.9. Additional evaluation on an earlier exam sample revealed that the writings have become more complex over a 7-10-year period, while accuracy still reached 0.8 with some feature sets. The results have been implemented in the writing evaluation module of an Estonian open-source language learning environment. --- ### Barron-Wiener-Laguerre models Authors: Rahul Manavalan, Filip Tronarp Published: 2026-02-13 Categories: stat.ME, cs.LG arXiv: https://arxiv.org/abs/2602.13098v1 We propose a probabilistic extension of Wiener-Laguerre models for causal operator learning. Classical Wiener-Laguerre models parameterize stable linear dynamics using orthonormal Laguerre bases and apply a static nonlinear map to the resulting features. While structurally efficient and interpretable, they provide only deterministic point estimates. We reinterpret the nonlinear component through the lens of Barron function approximation, viewing two-layer networks, random Fourier features, and extreme learning machines as discretizations of integral representations over parameter measures. This perspective naturally admits Bayesian inference on the nonlinear map and yields posterior predictive uncertainty. By combining Laguerre-parameterized causal dynamics with probabilistic Barron-type nonlinear approximators, we obtain a structured yet expressive class of causal operators equipped with uncertainty quantification. The resulting framework bridges classical system identification and modern measure-based function approximation, providing a principled approach to time-series modeling and nonlinear systems identification. --- ### Consistency of Large Reasoning Models Under Multi-Turn Attacks Authors: Yubo Li, Ramayya Krishnan, Rema Padman Published: 2026-02-13 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.13093v3 Large reasoning models with reasoning capabilities achieve state-of-the-art performance on complex tasks, but their robustness under multi-turn adversarial pressure remains underexplored. We evaluate nine frontier reasoning models under adversarial attacks. Our findings reveal that reasoning confers meaningful but incomplete robustness: most reasoning models studied significantly outperform instruction-tuned baselines, yet all exhibit distinct vulnerability profiles, with misleading suggestions universally effective and social pressure showing model-specific efficacy. Through trajectory analysis, we identify five failure modes (Self-Doubt, Social Conformity, Suggestion Hijacking, Emotional Susceptibility, and Reasoning Fatigue) with the first two accounting for 50% of failures. We further demonstrate that Confidence-Aware Response Generation (CARG), effective for standard LLMs, fails for reasoning models due to overconfidence induced by extended reasoning traces; counterintuitively, random confidence embedding outperforms targeted extraction. Our results highlight that reasoning capabilities do not automatically confer adversarial robustness and that confidence-based defenses require fundamental redesign for reasoning models. --- ### BAAF: Universal Transformation of One-Class Classifiers for Unsupervised Image Anomaly Detection Authors: Declan McIntosh, Alexandra Branzan Albu Published: 2026-02-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.13091v2 Detecting anomalies in images and video is an essential task for multiple real-world problems, including industrial inspection, computer-assisted diagnosis, and environmental monitoring. Anomaly detection is typically formulated as a one-class classification problem, where the training data consists solely of nominal values, leaving methods built on this assumption susceptible to training label noise. We present Bootstrap Aggregation Anomaly Filtering (BAAF), a method that transforms an arbitrary one-class classifier-based anomaly detector into a fully unsupervised method. This is achieved by leveraging the unique intrinsic properties of anomaly detection: anomalies are uncommon in the sampled data and generally heterogeneous. These properties enable us to design a modified Bootstrap Aggregation method that uses multiple independently trained instances of supervised one-class classifiers to filter the training dataset for anomalies. This transformation requires no modifications to the underlying anomaly detector; only the algorithmically selected data bags used for training change. We demonstrate empirically that our method can transform a wide variety of one-class classifier-based image anomaly detectors into unsupervised ones. Consequently, we present the first unsupervised logical anomaly detectors for images. We also demonstrate that our method achieves state-of-the-art performance in fully unsupervised anomaly detection on the MVTec AD, ViSA, and MVTec Loco AD datasets. As improvements to one-class classifiers are made, our method directly transfers those improvements to the unsupervised domain, linking the domains. --- ### Puppets or partners? Governing cyborg propaganda in the digital public square Authors: Jonas R. Kunst, Kinga Bierwiaczonek, Meeyoung Cha, Omid V. Ebrahimi, Marc Fawcett-Atkinson, Asbjørn Følstad, Anton Gollwitzer, Nils Köbis, Gary Marcus, Jon Roozenbeek, Daniel Thilo Schroeder, Jay J. Van Bavel et al. Published: 2026-02-13 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2602.13088v2 The distinction between genuine grassroots activism and automated influence operations is collapsing. While contemporary policy debates prioritize fully autonomous generative agents and synthetic content, this paper offers a conceptual contribution: we develop 'cyborg propaganda,' a closed-loop architecture combining verified human accounts with algorithmic automation to generate personalized content at scale, as a distinct and undertheorized threat to democratic discourse. By relying on verified citizens to ratify AI-generated messages, these campaigns exploit a regulatory gray zone that frameworks built on the human/bot binary (including the EU AI Act and Section 230) are structurally unable to address. Drawing on a conceptual analysis of coordination platforms and comparative examination of governance frameworks across democratic and non-democratic contexts, we analyze this paradox across micro, meso, and macro levels. We examine whether cyborg propaganda democratizes political power by unionizing influence or reduces citizens to cognitive proxies of a hidden directive, arguing that it shifts political discourse from a contest of ideas to a battle of algorithmic campaigns. We propose three regulatory responses: classifying coordination hubs as political action committees to enforce supply-chain transparency; mandating researcher access to platform data through DSA-style mechanisms; and establishing risk standards penalizing amplification of synthetically coordinated content. Comparative analysis reveals that viability varies structurally. Democratic states are simultaneously the most capable of regulation and the most rule-of-law constrained. By contrast, non-democratic actors face no comparable accountability, making international risk standards the primary cross-border enforcement mechanism. --- ### EXCODER: EXplainable Classification Of DiscretE time series Representations Authors: Yannik Hahn, Antonin Königsfeld, Hasan Tercan, Tobias Meisen Published: 2026-02-13 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.13087v1 Deep learning has significantly improved time series classification, yet the lack of explainability in these models remains a major challenge. While Explainable AI (XAI) techniques aim to make model decisions more transparent, their effectiveness is often hindered by the high dimensionality and noise present in raw time series data. In this work, we investigate whether transforming time series into discrete latent representations-using methods such as Vector Quantized Variational Autoencoders (VQ-VAE) and Discrete Variational Autoencoders (DVAE)-not only preserves but enhances explainability by reducing redundancy and focusing on the most informative patterns. We show that applying XAI methods to these compressed representations leads to concise and structured explanations that maintain faithfulness without sacrificing classification performance. Additionally, we propose Similar Subsequence Accuracy (SSA), a novel metric that quantitatively assesses the alignment between XAI-identified salient subsequences and the label distribution in the training data. SSA provides a systematic way to validate whether the features highlighted by XAI methods are truly representative of the learned classification patterns. Our findings demonstrate that discrete latent representations not only retain the essential characteristics needed for classification but also offer a pathway to more compact, interpretable, and computationally efficient explanations in time series analysis. --- ### Exploring a New Competency Modeling Process with Large Language Models Authors: Silin Du, Manqing Xin, Raymond Jia Wang Published: 2026-02-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.13084v1 Competency modeling is widely used in human resource management to select, develop, and evaluate talent. However, traditional expert-driven approaches rely heavily on manual analysis of large volumes of interview transcripts, making them costly and prone to randomness, ambiguity, and limited reproducibility. This study proposes a new competency modeling process built on large language models (LLMs). Instead of merely automating isolated steps, we reconstruct the workflow by decomposing expert practices into structured computational components. Specifically, we leverage LLMs to extract behavioral and psychological descriptions from raw textual data and map them to predefined competency libraries through embedding-based similarity. We further introduce a learnable parameter that adaptively integrates different information sources, enabling the model to determine the relative importance of behavioral and psychological signals. To address the long-standing challenge of validation, we develop an offline evaluation procedure that allows systematic model selection without requiring additional large-scale data collection. Empirical results from a real-world implementation in a software outsourcing company demonstrate strong predictive validity, cross-library consistency, and structural robustness. Overall, our framework transforms competency modeling from a largely qualitative and expert-dependent practice into a transparent, data-driven, and evaluable analytical process. --- ### Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding Authors: Chundong Liang, Yongqi Huang, Dongxiao He, Peiyuan Li, Yawen Li, Di Jin, Weixiong Zhang Published: 2026-02-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.13075v2 Graph pre-training has achieved remarkable success in recent years, delivering transferable representations for downstream adaptation. However, most existing methods are designed for either homogeneous or heterogeneous graphs, thereby hindering unified graph modeling across diverse graph types. This separation contradicts real-world applications, where mixed homogeneous and heterogeneous graphs are ubiquitous, and distribution shifts between upstream pre-training and downstream deployment are common. In this paper, we empirically demonstrate that a balanced mixture of homogeneous and heterogeneous graph pre-training benefits downstream tasks and propose a unified multi-domain \textbf{G}raph \textbf{P}re-training method across \textbf{H}omogeneous and \textbf{H}eterogeneous graphs ($\mathbf{GPH^{2}}$). To address the lack of a unified encoder for homogeneous and heterogeneous graphs, we propose a Unified Multi-View Graph Construction that simultaneously encodes both without explicit graph-type-specific designs. To cope with the increased cross-domain distribution discrepancies arising from mixed graphs, we introduce domain-specific expert encoding. Each expert is independently pre-trained on a single graph to capture domain-specific knowledge, thereby shielding the pre-training encoder from the adverse effects of cross-domain discrepancies. For downstream tasks, we further design a Task-oriented Expert Fusion Strategy that adaptively integrates multiple experts based on their discriminative strengths. Extensive experiments on mixed graphs demonstrate that $\text{GPH}^{2}$ enables stable transfer across graph types and domains, significantly outperforming existing graph pre-training methods. --- ### LCSB: Layer-Cyclic Selective Backpropagation for Memory-Efficient On-Device LLM Fine-Tuning Authors: Juneyoung Park, Eunbeen Yoon, Seongwan Kim. Jaeho Lee Published: 2026-02-13 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2602.13073v1 Memory-efficient backpropagation (MeBP) has enabled first-order fine-tuning of large language models (LLMs) on mobile devices with less than 1GB memory. However, MeBP requires backward computation through all transformer layers at every step, where weight decompression alone accounts for 32--42% of backward time. We propose Layer-Cyclic Selective Backpropagation (LCSB), which computes gradients for only a subset of layers per step. Our key insight is that residual connections guarantee gradient flow through identity paths, while AdamW momentum provides implicit updates for non-selected layers. We interpret LCSB as Block Coordinate Descent on the LoRA parameter space, providing theoretical justification for convergence. LCSB achieves up to 1.40$\times$ speedup with less than 2\% quality degradation across five models and three tasks. Surprisingly, in 4-bit quantized settings, LCSB exhibits superior stability: a 3B model that completely diverges under full backpropagation converges smoothly with LCSB, suggesting an implicit regularization effect from selective gradient computation. --- ### Bus-Conditioned Zero-Shot Trajectory Generation via Task Arithmetic Authors: Shuai Liu, Ning Cao, Yile Chen, Yue Jiang, Gao Cong Published: 2026-02-13 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.13071v1 Mobility trajectory data provide essential support for smart city applications. However, such data are often difficult to obtain. Meanwhile, most existing trajectory generation methods implicitly assume that at least a subset of real mobility data from target city is available, which limits their applicability in data-inaccessible scenarios. In this work, we propose a new problem setting, called bus-conditioned zero-shot trajectory generation, where no mobility trajectories from a target city are accessible. The generation process relies solely on source city mobility data and publicly available bus timetables from both cities. Under this setting, we propose MobTA, the first approach to introduce task arithmetic into trajectory generation. MobTA models the parameter shift from bus-timetable-based trajectory generation to mobility trajectory generation in source city, and applies this shift to target city through arithmetic operations on task vectors. This enables trajectory generation that reflects target-city mobility patterns without requiring any real mobility data from it. Furthermore, we theoretically analyze MobTA's stability across base and instruction-tuned LLMs. Extensive experiments show that MobTA significantly outperforms existing methods, and achieves performance close to models finetuned using target city mobility trajectories. --- ### Memory-Efficient Structured Backpropagation for On-Device LLM Fine-Tuning Authors: Juneyoung Park, Yuri Hong, Seongwan Kim, Jaeho Lee Published: 2026-02-13 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2602.13069v2 On-device fine-tuning enables privacy-preserving personalization of large language models, but mobile devices impose severe memory constraints, typically 6--12GB shared across all workloads. Existing approaches force a trade-off between exact gradients with high memory (MeBP) and low memory with noisy estimates (MeZO). We propose Memory-efficient Structured Backpropagation (MeSP), which bridges this gap by manually deriving backward passes that exploit LoRA's low-rank structure. Our key insight is that the intermediate projection $h = xA$ can be recomputed during backward at minimal cost since rank $r \ll d_{in}$, eliminating the need to store it. MeSP achieves 49\% average memory reduction compared to MeBP on Qwen2.5 models (0.5B--3B) while computing mathematically identical gradients. Our analysis also reveals that MeZO's gradient estimates show near-zero correlation with true gradients (cosine similarity $\approx$0.001), explaining its slow convergence. MeSP reduces peak memory from 361MB to 136MB for Qwen2.5-0.5B, enabling fine-tuning scenarios previously infeasible on memory-constrained devices. --- ### SIEFormer: Spectral-Interpretable and -Enhanced Transformer for Generalized Category Discovery Authors: Chunming Li, Shidong Wang, Tong Xin, Haofeng Zhang Published: 2026-02-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.13067v1 This paper presents a novel approach, Spectral-Interpretable and -Enhanced Transformer (SIEFormer), which leverages spectral analysis to reinterpret the attention mechanism within Vision Transformer (ViT) and enhance feature adaptability, with particular emphasis on challenging Generalized Category Discovery (GCD) tasks. The proposed SIEFormer is composed of two main branches, each corresponding to an implicit and explicit spectral perspective of the ViT, enabling joint optimization. The implicit branch realizes the use of different types of graph Laplacians to model the local structure correlations of tokens, along with a novel Band-adaptive Filter (BaF) layer that can flexibly perform both band-pass and band-reject filtering. The explicit branch, on the other hand, introduces a Maneuverable Filtering Layer (MFL) that learns global dependencies among tokens by applying the Fourier transform to the input ``value" features, modulating the transformed signal with a set of learnable parameters in the frequency domain, and then performing an inverse Fourier transform to obtain the enhanced features. Extensive experiments reveal state-of-the-art performance on multiple image recognition datasets, reaffirming the superiority of our approach through ablation studies and visualizations. --- ### A Calibrated Memorization Index (MI) for Detecting Training Data Leakage in Generative MRI Models Authors: Yash Deo, Yan Jia, Toni Lassila, Victoria J Hodge, Alejandro F Frang, Chenghao Qian, Siyuan Kang, Ibrahim Habli Published: 2026-02-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.13066v1 Image generative models are known to duplicate images from the training data as part of their outputs, which can lead to privacy concerns when used for medical image generation. We propose a calibrated per-sample metric for detecting memorization and duplication of training data. Our metric uses image features extracted using an MRI foundation model, aggregates multi-layer whitened nearest-neighbor similarities, and maps them to a bounded \emph{Overfit/Novelty Index} (ONI) and \emph{Memorization Index} (MI) scores. Across three MRI datasets with controlled duplication percentages and typical image augmentations, our metric robustly detects duplication and provides more consistent metric values across datasets. At the sample level, our metric achieves near-perfect detection of duplicates. --- ### Backdoor Attacks on Contrastive Continual Learning for IoT Systems Authors: Alfous Tim, Kuniyilh Simi D Published: 2026-02-13 Categories: cs.LG, cs.CR, cs.NI arXiv: https://arxiv.org/abs/2602.13062v1 The Internet of Things (IoT) systems increasingly depend on continual learning to adapt to non-stationary environments. These environments can include factors such as sensor drift, changing user behavior, device aging, and adversarial dynamics. Contrastive continual learning (CCL) combines contrastive representation learning with incremental adaptation, enabling robust feature reuse across tasks and domains. However, the geometric nature of contrastive objectives, when paired with replay-based rehearsal and stability-preserving regularization, introduces new security vulnerabilities. Notably, backdoor attacks can exploit embedding alignment and replay reinforcement, enabling the implantation of persistent malicious behaviors that endure through updates and deployment cycles. This paper provides a comprehensive analysis of backdoor attacks on CCL within IoT systems. We formalize the objectives of embedding-level attacks, examine persistence mechanisms unique to IoT deployments, and develop a layered taxonomy tailored to IoT. Additionally, we compare vulnerabilities across various learning paradigms and evaluate defense strategies under IoT constraints, including limited memory, edge computing, and federated aggregation. Our findings indicate that while CCL is effective for enhancing adaptive IoT intelligence, it may also elevate long-lived representation-level threats if not adequately secured. --- ### Native Extrapolation Awareness in Flow-Based Conditional Generation Authors: Constantinos Tsakonas, Serena Ivaldi, Jean-Baptiste Mouret Published: 2026-02-13 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2602.13061v2 The ability of Flow Matching (FM) to model complex conditional distributions has established it as the state-of-the-art for prediction tasks (e.g., robotics, weather forecasting). However, deployment in safety-critical settings is hindered by a critical extrapolation hazard: driven by smoothness biases, flow models yield plausible outputs even for off-manifold conditions, resulting in silent failures indistinguishable from valid predictions. In this work, we introduce Diverging Flows, a novel approach that enables a single model to simultaneously perform conditional generation and native extrapolation detection by structurally enforcing inefficient transport for off-manifold inputs. We evaluate our method on synthetic manifolds, cross-domain style transfer, and weather temperature forecasting, demonstrating that it achieves effective detection of extrapolations without compromising predictive fidelity or inference latency. These results establish Diverging Flows as a robust solution for trustworthy flow models, paving the way for reliable deployment in domains such as medicine, robotics, and climate science. --- ### TraceBack: Multi-Agent Decomposition for Fine-Grained Table Attribution Authors: Tejas Anvekar, Junha Park, Rajat Jha, Devanshu Gupta, Poojah Ganesan, Puneeth Mathur, Vivek Gupta Published: 2026-02-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.13059v1 Question answering (QA) over structured tables requires not only accurate answers but also transparency about which cells support them. Existing table QA systems rarely provide fine-grained attribution, so even correct answers often lack verifiable grounding, limiting trust in high-stakes settings. We address this with TraceBack, a modular multi-agent framework for scalable, cell-level attribution in single-table QA. TraceBack prunes tables to relevant rows and columns, decomposes questions into semantically coherent sub-questions, and aligns each answer span with its supporting cells, capturing both explicit and implicit evidence used in intermediate reasoning steps. To enable systematic evaluation, we release CITEBench, a benchmark with phrase-to-cell annotations drawn from ToTTo, FetaQA, and AITQA. We further propose FairScore, a reference-less metric that compares atomic facts derived from predicted cells and answers to estimate attribution precision and recall without human cell labels. Experiments show that TraceBack substantially outperforms strong baselines across datasets and granularities, while FairScore closely tracks human judgments and preserves relative method rankings, supporting interpretable and scalable evaluation of table-based QA. --- ### Curriculum-DPO++: Direct Preference Optimization via Data and Model Curricula for Text-to-Image Generation Authors: Florinel-Alin Croitoru, Vlad Hondru, Radu Tudor Ionescu, Nicu Sebe, Mubarak Shah Published: 2026-02-13 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.13055v1 Direct Preference Optimization (DPO) has been proposed as an effective and efficient alternative to reinforcement learning from human feedback (RLHF). However, neither RLHF nor DPO take into account the fact that learning certain preferences is more difficult than learning other preferences, rendering the optimization process suboptimal. To address this gap in text-to-image generation, we recently proposed Curriculum-DPO, a method that organizes image pairs by difficulty. In this paper, we introduce Curriculum-DPO++, an enhanced method that combines the original data-level curriculum with a novel model-level curriculum. More precisely, we propose to dynamically increase the learning capacity of the denoising network as training advances. We implement this capacity increase via two mechanisms. First, we initialize the model with only a subset of the trainable layers used in the original Curriculum-DPO. As training progresses, we sequentially unfreeze layers until the configuration matches the full baseline architecture. Second, as the fine-tuning is based on Low-Rank Adaptation (LoRA), we implement a progressive schedule for the dimension of the low-rank matrices. Instead of maintaining a fixed capacity, we initialize the low-rank matrices with a dimension significantly smaller than that of the baseline. As training proceeds, we incrementally increase their rank, allowing the capacity to grow until it converges to the same rank value as in Curriculum-DPO. Furthermore, we propose an alternative ranking strategy to the one employed by Curriculum-DPO. Finally, we compare Curriculum-DPO++ against Curriculum-DPO and other state-of-the-art preference optimization approaches on nine benchmarks, outperforming the competing methods in terms of text alignment, aesthetics and human preference. Our code is available at https://github.com/CroitoruAlin/Curriculum-DPO. --- ### Quantization-Aware Collaborative Inference for Large Embodied AI Models Authors: Zhonghao Lyu, Ming Xiao, Mikael Skoglund, Merouane Debbah, H. Vincent Poor Published: 2026-02-13 Categories: cs.LG, eess.SP arXiv: https://arxiv.org/abs/2602.13052v1 Large artificial intelligence models (LAIMs) are increasingly regarded as a core intelligence engine for embodied AI applications. However, the massive parameter scale and computational demands of LAIMs pose significant challenges for resource-limited embodied agents. To address this issue, we investigate quantization-aware collaborative inference (co-inference) for embodied AI systems. First, we develop a tractable approximation for quantization-induced inference distortion. Based on this approximation, we derive lower and upper bounds on the quantization rate-inference distortion function, characterizing its dependence on LAIM statistics, including the quantization bit-width. Next, we formulate a joint quantization bit-width and computation frequency design problem under delay and energy constraints, aiming to minimize the distortion upper bound while ensuring tightness through the corresponding lower bound. Extensive evaluations validate the proposed distortion approximation, the derived rate-distortion bounds, and the effectiveness of the proposed joint design. Particularly, simulations and real-world testbed experiments demonstrate the effectiveness of the proposed joint design in balancing inference quality, latency, and energy consumption in edge embodied AI systems. --- ### False positive bias in AI-powered speech-based cognitive screening for multilingual English speakers in the UK Authors: Madhurananda Pahar, Caitlin Illingworth, Dorota Braun, Bahman Mirheidari, Lise Sproson, Daniel Blackburn, Heidi Christensen Published: 2026-02-13 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.13047v3 Conversational speech reveals early signs of cognitive decline, including dementia and mild cognitive impairment (MCI). AI models show promise for speech-based screening, yet most research focuses on monolingual groups. In the UK, dementia is projected to rise fastest among Black and Asian communities, where multilingualism is common, making equity assessment critical. We recruited 1,395 participants (monolingual English speakers and multilingual speakers from Sheffield/Bradford) and collected over 263 hours of speech via the CognoMemory agent. Multilingual participants spoke English alongside Somali, Chinese, or South Asian languages (Hindi, Urdu, Punjabi, Mirpuri, Arabic). We evaluated ASR (Whisper, Wav2Vec 2.0, NeMo) and downstream AI models for cognitive classification and MMSE regression. ASR accuracy showed no significant differences across groups. However, downstream models exhibited systematic disparities: multilingual speakers were more often misclassified as impaired, especially in memory, fluency, and reading tasks. False-positive rates were substantially higher for multilingual (28 to 37%) than monolingual (12 to 16%) speakers, meaning multilingual individuals were approximately 2.5 times more likely to receive incorrect impairment labels. These biases worsened when models were trained on DementiaBank. This is the first large-scale analysis of false-positive bias in speech-based AI cognitive screening for UK multilingual ethnic minorities. Despite strong overall performance, current models show measurable disparities affecting multilingual speakers. Addressing these biases is essential for safe, equitable deployment in diverse healthcare settings. --- ### Can we trust AI to detect healthy multilingual English speakers among the cognitively impaired cohort in the UK? An investigation using real-world conversational speech Authors: Madhurananda Pahar, Caitlin Illingworth, Dorota Braun, Bahman Mirheidari, Lise Sproson, Daniel Blackburn, Heidi Christensen Published: 2026-02-13 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.13047v1 Conversational speech often reveals early signs of cognitive decline, such as dementia and MCI. In the UK, one in four people belongs to an ethnic minority, and dementia prevalence is expected to rise most rapidly among Black and Asian communities. This study examines the trustworthiness of AI models, specifically the presence of bias, in detecting healthy multilingual English speakers among the cognitively impaired cohort, to make these tools clinically beneficial. For experiments, monolingual participants were recruited nationally (UK), and multilingual speakers were enrolled from four community centres in Sheffield and Bradford. In addition to a non-native English accent, multilinguals spoke Somali, Chinese, or South Asian languages, who were further divided into two Yorkshire accents (West and South) to challenge the efficiency of the AI tools thoroughly. Although ASR systems showed no significant bias across groups, classification and regression models using acoustic and linguistic features exhibited bias against multilingual speakers, particularly in memory, fluency, and reading tasks. This bias was more pronounced when models were trained on the publicly available DementiaBank dataset. Moreover, multilinguals were more likely to be misclassified as having cognitive decline. This study is the first of its kind to discover that, despite their strong overall performance, current AI models show bias against multilingual individuals from ethnic minority backgrounds in the UK, and they are also more likely to misclassify speakers with a certain accent (South Yorkshire) as living with a more severe cognitive decline. In this pilot study, we conclude that the existing AI tools are therefore not yet reliable for diagnostic use in these populations, and we aim to address this in future work by developing more generalisable, bias-mitigated models. --- ### Geometric Manifold Rectification for Imbalanced Learning Authors: Xubin Wang, Qing Li, Weijia Jia Published: 2026-02-13 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.13045v1 Imbalanced classification presents a formidable challenge in machine learning, particularly when tabular datasets are plagued by noise and overlapping class boundaries. From a geometric perspective, the core difficulty lies in the topological intrusion of the majority class into the minority manifold, which obscures the true decision boundary. Traditional undersampling techniques, such as Edited Nearest Neighbours (ENN), typically employ symmetric cleaning rules and uniform voting, failing to capture the local manifold structure and often inadvertently removing informative minority samples. In this paper, we propose GMR (Geometric Manifold Rectification), a novel framework designed to robustly handle imbalanced structured data by exploiting local geometric priors. GMR makes two contributions: (1) Geometric confidence estimation that uses inverse-distance weighted kNN voting with an adaptive distance metric to capture local reliability; and (2) asymmetric cleaning that is strict on majority samples while conservatively protecting minority samples via a safe-guarding cap on minority removal. Extensive experiments on multiple benchmark datasets show that GMR is competitive with strong sampling baselines. --- ### GPTZero: Robust Detection of LLM-Generated Texts Authors: George Alexandru Adam, Alexander Cui, Edwin Thomas, Emily Napier, Nazar Shmatko, Jacob Schnell, Jacob Junqi Tian, Alekhya Dronavalli, Edward Tian, Dongwon Lee Published: 2026-02-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.13042v1 While historical considerations surrounding text authenticity revolved primarily around plagiarism, the advent of large language models (LLMs) has introduced a new challenge: distinguishing human-authored from AI-generated text. This shift raises significant concerns, including the undermining of skill evaluations, the mass-production of low-quality content, and the proliferation of misinformation. Addressing these issues, we introduce GPTZero a state-of-the-art industrial AI detection solution, offering reliable discernment between human and LLM-generated text. Our key contributions include: introducing a hierarchical, multi-task architecture enabling a flexible taxonomy of human and AI texts, demonstrating state-of-the-art accuracy on a variety of domains with granular predictions, and achieving superior robustness to adversarial attacks and paraphrasing via multi-tiered automated red teaming. GPTZero offers accurate and explainable detection, and educates users on its responsible use, ensuring fair and transparent assessment of text. --- ### Implicit-Scale 3D Reconstruction for Multi-Food Volume Estimation from Monocular Images Authors: Yuhao Chen, Gautham Vinod, Siddeshwar Raghavan, Talha Ibn Mahmud, Bruce Coburn, Jinge Ma, Fengqing Zhu, Jiangpeng He Published: 2026-02-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.13041v1 We present Implicit-Scale 3D Reconstruction from Monocular Multi-Food Images, a benchmark dataset designed to advance geometry-based food portion estimation in realistic dining scenarios. Existing dietary assessment methods largely rely on single-image analysis or appearance-based inference, including recent vision-language models, which lack explicit geometric reasoning and are sensitive to scale ambiguity. This benchmark reframes food portion estimation as an implicit-scale 3D reconstruction problem under monocular observations. To reflect real-world conditions, explicit physical references and metric annotations are removed; instead, contextual objects such as plates and utensils are provided, requiring algorithms to infer scale from implicit cues and prior knowledge. The dataset emphasizes multi-food scenes with diverse object geometries, frequent occlusions, and complex spatial arrangements. The benchmark was adopted as a challenge at the MetaFood 2025 Workshop, where multiple teams proposed reconstruction-based solutions. Experimental results show that while strong vision--language baselines achieve competitive performance, geometry-based reconstruction methods provide both improved accuracy and greater robustness, with the top-performing approach achieving 0.21 MAPE in volume estimation and 5.7 L1 Chamfer Distance in geometric accuracy. --- ### TCRL: Temporal-Coupled Adversarial Training for Robust Constrained Reinforcement Learning in Worst-Case Scenarios Authors: Wentao Xu, Zhongming Yao, Weihao Li, Zhenghang Song, Yumeng Song, Tianyi Li, Yushuai Li Published: 2026-02-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.13040v1 Constrained Reinforcement Learning (CRL) aims to optimize decision-making policies under constraint conditions, making it highly applicable to safety-critical domains such as autonomous driving, robotics, and power grid management. However, existing robust CRL approaches predominantly focus on single-step perturbations and temporally independent adversarial models, lacking explicit modeling of robustness against temporally coupled perturbations. To tackle these challenges, we propose TCRL, a novel temporal-coupled adversarial training framework for robust constrained reinforcement learning (TCRL) in worst-case scenarios. First, TCRL introduces a worst-case-perceived cost constraint function that estimates safety costs under temporally coupled perturbations without the need to explicitly model adversarial attackers. Second, TCRL establishes a dual-constraint defense mechanism on the reward to counter temporally coupled adversaries while maintaining reward unpredictability. Experimental results demonstrate that TCRL consistently outperforms existing methods in terms of robustness against temporally coupled perturbation attacks across a variety of CRL tasks. --- ### Look Inward to Explore Outward: Learning Temperature Policy from LLM Internal States via Hierarchical RL Authors: Yixiao Zhou, Yang Li, Dongzhou Cheng, Hehe Fan, Yu Cheng Published: 2026-02-13 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.13035v1 Reinforcement Learning from Verifiable Rewards (RLVR) trains large language models (LLMs) from sampled trajectories, making decoding strategy a core component of learning rather than a purely inference-time choice. Sampling temperature directly controls the exploration--exploitation trade-off by modulating policy entropy, yet existing methods rely on static values or heuristic adaptations that are decoupled from task-level rewards. We propose Introspective LLM, a hierarchical reinforcement learning framework that learns to control sampling temperature during generation. At each decoding step, the model selects a temperature based on its hidden state and samples the next token from the resulting distribution. Temperature and token policies are jointly optimized from downstream rewards using a coordinate ascent scheme. Experiments on mathematical reasoning benchmarks show that learned temperature policies outperform fixed and heuristic baselines, while exhibiting interpretable exploration behaviors aligned with reasoning uncertainty. --- ### Buy versus Build an LLM: A Decision Framework for Governments Authors: Jiahao Lu, Ziwei Xu, William Tjhi, Junnan Li, Antoine Bosselut, Pang Wei Koh, Mohan Kankanhalli Published: 2026-02-13 Categories: cs.CY, cs.AI, cs.CE, cs.CL, cs.SI arXiv: https://arxiv.org/abs/2602.13033v2 Large Language Models (LLMs) represent a new frontier of digital infrastructure that can support a wide range of public-sector applications, from general purpose citizen services to specialized and sensitive state functions. When expanding AI access, governments face a set of strategic choices over whether to buy existing services, build domestic capabilities, or adopt hybrid approaches across different domains and use cases. These are critical decisions especially when leading model providers are often foreign corporations, and LLM outputs are increasingly treated as trusted inputs to public decision-making and public discourse. In practice, these decisions are not intended to mandate a single approach across all domains; instead, national AI strategies are typically pluralistic, with sovereign, commercial and open-source models coexisting to serve different purposes. Governments may rely on commercial models for non-sensitive or commodity tasks, while pursuing greater control for critical, high-risk or strategically important applications. This paper provides a strategic framework for making this decision by evaluating these options across dimensions including sovereignty, safety, cost, resource capability, cultural fit, and sustainability. Importantly, "building" does not imply that governments must act alone: domestic capabilities may be developed through public research institutions, universities, state-owned enterprises, joint ventures, or broader national ecosystems. By detailing the technical requirements and practical challenges of each pathway, this work aims to serve as a reference for policy-makers to determine whether a buy or build approach best aligns with their specific national needs and societal goals. --- ### Resource-Efficient Gesture Recognition through Convexified Attention Authors: Daniel Schwartz, Dario Salvucci, Yusuf Osmanlioglu, Richard Vallett, Genevieve Dion, Ali Shokoufandeh Published: 2026-02-13 Categories: cs.LG, cs.CV, cs.HC arXiv: https://arxiv.org/abs/2602.13030v1 Wearable e-textile interfaces require gesture recognition capabilities but face severe constraints in power consumption, computational capacity, and form factor that make traditional deep learning impractical. While lightweight architectures like MobileNet improve efficiency, they still demand thousands of parameters, limiting deployment on textile-integrated platforms. We introduce a convexified attention mechanism for wearable applications that dynamically weights features while preserving convexity through nonexpansive simplex projection and convex loss functions. Unlike conventional attention mechanisms using non-convex softmax operations, our approach employs Euclidean projection onto the probability simplex combined with multi-class hinge loss, ensuring global convergence guarantees. Implemented on a textile-based capacitive sensor with four connection points, our approach achieves 100.00\% accuracy on tap gestures and 100.00\% on swipe gestures -- consistent across 10-fold cross-validation and held-out test evaluation -- while requiring only 120--360 parameters, a 97\% reduction compared to conventional approaches. With sub-millisecond inference times (290--296$μ$s) and minimal storage requirements ($<$7KB), our method enables gesture interfaces directly within e-textiles without external processing. Our evaluation, conducted in controlled laboratory conditions with a single-user dataset, demonstrates feasibility for basic gesture interactions. Real-world deployment would require validation across multiple users, environmental conditions, and more complex gesture vocabularies. These results demonstrate how convex optimization can enable efficient on-device machine learning for textile interfaces. --- ### Human-Aligned MLLM Judges for Fine-Grained Image Editing Evaluation: A Benchmark, Framework, and Analysis Authors: Runzhou Liu, Hailey Weingord, Sejal Mittal, Prakhar Dungarwal, Anusha Nandula, Bo Ni, Samyadeep Basu, Hongjie Chen, Nesreen K. Ahmed, Li Li, Jiayi Zhang, Koustava Goswami et al. Published: 2026-02-13 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2602.13028v1 Evaluating image editing models remains challenging due to the coarse granularity and limited interpretability of traditional metrics, which often fail to capture aspects important to human perception and intent. Such metrics frequently reward visually plausible outputs while overlooking controllability, edit localization, and faithfulness to user instructions. In this work, we introduce a fine-grained Multimodal Large Language Model (MLLM)-as-a-Judge framework for image editing that decomposes common evaluation notions into twelve fine-grained interpretable factors spanning image preservation, edit quality, and instruction fidelity. Building on this formulation, we present a new human-validated benchmark that integrates human judgments, MLLM-based evaluations, model outputs, and traditional metrics across diverse image editing tasks. Through extensive human studies, we show that the proposed MLLM judges align closely with human evaluations at a fine granularity, supporting their use as reliable and scalable evaluators. We further demonstrate that traditional image editing metrics are often poor proxies for these factors, failing to distinguish over-edited or semantically imprecise outputs, whereas our judges provide more intuitive and informative assessments in both offline and online settings. Together, this work introduces a benchmark, a principled factorization, and empirical evidence positioning fine-grained MLLM judges as a practical foundation for studying, comparing, and improving image editing approaches. --- ### FedHENet: A Frugal Federated Learning Framework for Heterogeneous Environments Authors: Alejandro Dopico-Castro, Oscar Fontenla-Romero, Bertha Guijarro-Berdiñas, Amparo Alonso-Betanzos, Iván Pérez Digón Published: 2026-02-13 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.13024v1 Federated Learning (FL) enables collaborative training without centralizing data, essential for privacy compliance in real-world scenarios involving sensitive visual information. Most FL approaches rely on expensive, iterative deep network optimization, which still risks privacy via shared gradients. In this work, we propose FedHENet, extending the FedHEONN framework to image classification. By using a fixed, pre-trained feature extractor and learning only a single output layer, we avoid costly local fine-tuning. This layer is learned by analytically aggregating client knowledge in a single round of communication using homomorphic encryption (HE). Experiments show that FedHENet achieves competitive accuracy compared to iterative FL baselines while demonstrating superior stability performance and up to 70\% better energy efficiency. Crucially, our method is hyperparameter-free, removing the carbon footprint associated with hyperparameter tuning in standard FL. Code available in https://github.com/AlejandroDopico2/FedHENet/ --- ### Learning Image-based Tree Crown Segmentation from Enhanced Lidar-based Pseudo-labels Authors: Julius Pesonen, Stefan Rua, Josef Taher, Niko Koivumäki, Xiaowei Yu, Eija Honkavaara Published: 2026-02-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.13022v1 Mapping individual tree crowns is essential for tasks such as maintaining urban tree inventories and monitoring forest health, which help us understand and care for our environment. However, automatically separating the crowns from each other in aerial imagery is challenging due to factors such as the texture and partial tree crown overlaps. In this study, we present a method to train deep learning models that segment and separate individual trees from RGB and multispectral images, using pseudo-labels derived from aerial laser scanning (ALS) data. Our study shows that the ALS-derived pseudo-labels can be enhanced using a zero-shot instance segmentation model, Segment Anything Model 2 (SAM 2). Our method offers a way to obtain domain-specific training annotations for optical image-based models without any manual annotation cost, leading to segmentation models which outperform any available models which have been targeted for general domain deployment on the same task. --- ### Prior-Guided Symbolic Regression: Towards Scientific Consistency in Equation Discovery Authors: Jing Xiao, Xinhai Chen, Jiaming Peng, Qinglin Wang, Menghan Jia, Zhiquan Lai, Guangping Yu, Dongsheng Li, Tiejun Li, Jie Liu Published: 2026-02-13 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.13021v2 Symbolic Regression (SR) aims to discover interpretable equations from observational data, with the potential to reveal underlying principles behind natural phenomena. However, existing approaches often fall into the Pseudo-Equation Trap: producing equations that fit observations well but remain inconsistent with fundamental scientific principles. A key reason is that these approaches are dominated by empirical risk minimization, lacking explicit constraints to ensure scientific consistency. To bridge this gap, we propose PG-SR, a prior-guided SR framework built upon a three-stage pipeline consisting of warm-up, evolution, and refinement. Throughout the pipeline, PG-SR introduces a prior constraint checker that explicitly encodes domain priors as executable constraint programs, and employs a Prior Annealing Constrained Evaluation (PACE) mechanism during the evolution stage to progressively steer discovery toward scientifically consistent regions. Theoretically, we prove that PG-SR reduces the Rademacher complexity of the hypothesis space, yielding tighter generalization bounds and establishing a guarantee against pseudo-equations. Experimentally, PG-SR outperforms state-of-the-art baselines across diverse domains, maintaining robustness to varying prior quality, noisy data, and data scarcity. --- ### DynaGuide: A Generalizable Dynamic Guidance Framework for Unsupervised Semantic Segmentation Authors: Boujemaa Guermazi, Riadh Ksantini, Naimul Khan Published: 2026-02-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.13020v1 Unsupervised image segmentation is a critical task in computer vision. It enables dense scene understanding without human annotations, which is especially valuable in domains where labelled data is scarce. However, existing methods often struggle to reconcile global semantic structure with fine-grained boundary accuracy. This paper introduces DynaGuide, an adaptive segmentation framework that addresses these challenges through a novel dual-guidance strategy and dynamic loss optimization. Building on our previous work, DynaSeg, DynaGuide combines global pseudo-labels from zero-shot models such as DiffSeg or SegFormer with local boundary refinement using a lightweight CNN trained from scratch. This synergy allows the model to correct coarse or noisy global predictions and produce high-precision segmentations. At the heart of DynaGuide is a multi-component loss that dynamically balances feature similarity, Huber-smoothed spatial continuity, including diagonal relationships, and semantic alignment with the global pseudo-labels. Unlike prior approaches, DynaGuide trains entirely without ground-truth labels in the target domain and supports plug-and-play integration of diverse guidance sources. Extensive experiments on BSD500, PASCAL VOC2012, and COCO demonstrate that DynaGuide achieves state-of-the-art performance, improving mIoU by 17.5% on BSD500, 3.1% on PASCAL VOC2012, and 11.66% on COCO. With its modular design, strong generalization, and minimal computational footprint, DynaGuide offers a scalable and practical solution for unsupervised segmentation in real-world settings. Code available at: https://github.com/RyersonMultimediaLab/DynaGuide --- ### Synaptic Activation and Dual Liquid Dynamics for Interpretable Bio-Inspired Models Authors: Mónika Farsang, Radu Grosu Published: 2026-02-13 Categories: cs.NE, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.13017v1 In this paper, we present a unified framework for various bio-inspired models to better understand their structural and functional differences. We show that liquid-capacitance-extended models lead to interpretable behavior even in dense, all-to-all recurrent neural network (RNN) policies. We further demonstrate that incorporating chemical synapses improves interpretability and that combining chemical synapses with synaptic activation yields the most accurate and interpretable RNN models. To assess the accuracy and interpretability of these RNN policies, we consider the challenging lane-keeping control task and evaluate performance across multiple metrics, including turn-weighted validation loss, neural activity during driving, absolute correlation between neural activity and road trajectory, saliency maps of the networks' attention, and the robustness of their saliency maps measured by the structural similarity index. --- ### Multimodal Classification via Total Correlation Maximization Authors: Feng Yu, Xiangyu Wu, Yang Yang, Jianfeng Lu Published: 2026-02-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.13015v2 Multimodal learning integrates data from diverse sensors to effectively harness information from different modalities. However, recent studies reveal that joint learning often overfits certain modalities while neglecting others, leading to performance inferior to that of unimodal learning. Although previous efforts have sought to balance modal contributions or combine joint and unimodal learning, thereby mitigating the degradation of weaker modalities with promising outcomes, few have examined the relationship between joint and unimodal learning from an information-theoretic perspective. In this paper, we theoretically analyze modality competition and propose a method for multimodal classification by maximizing the total correlation between multimodal features and labels. By maximizing this objective, our approach alleviates modality competition while capturing inter-modal interactions via feature alignment. Building on Mutual Information Neural Estimation (MINE), we introduce Total Correlation Neural Estimation (TCNE) to derive a lower bound for total correlation. Subsequently, we present TCMax, a hyperparameter-free loss function that maximizes total correlation through variational bound optimization. Extensive experiments demonstrate that TCMax outperforms state-of-the-art joint and unimodal learning approaches. Our code is available at https://github.com/hubaak/TCMax. --- ### Towards Universal Video MLLMs with Attribute-Structured and Quality-Verified Instructions Authors: Yunheng Li, Hengrui Zhang, Meng-Hao Guo, Wenzhao Gao, Shaoyong Jia, Shaohui Jiao, Qibin Hou, Ming-Ming Cheng Published: 2026-02-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.13013v1 Universal video understanding requires modeling fine-grained visual and audio information over time in diverse real-world scenarios. However, the performance of existing models is primarily constrained by video-instruction data that represents complex audiovisual content as single, incomplete descriptions, lacking fine-grained organization and reliable annotation. To address this, we introduce: (i) ASID-1M, an open-source collection of one million structured, fine-grained audiovisual instruction annotations with single- and multi-attribute supervision; (ii) ASID-Verify, a scalable data curation pipeline for annotation, with automatic verification and refinement that enforces semantic and temporal consistency between descriptions and the corresponding audiovisual content; and (iii) ASID-Captioner, a video understanding model trained via Supervised Fine-Tuning (SFT) on the ASID-1M. Experiments across seven benchmarks covering audiovisual captioning, attribute-wise captioning, caption-based QA, and caption-based temporal grounding show that ASID-Captioner improves fine-grained caption quality while reducing hallucinations and improving instruction following. It achieves state-of-the-art performance among open-source models and is competitive with Gemini-3-Pro. --- ### Probabilistic Wind Power Forecasting with Tree-Based Machine Learning and Weather Ensembles Authors: Max Bruninx, Diederik van Binsbergen, Timothy Verstraeten, Ann Nowé, Jan Helsen Published: 2026-02-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.13010v2 Accurate production forecasts are essential for the integration of renewable energy sources into the power grid. This paper illustrates how to obtain probabilistic forecasts of wind power generation using gradient boosting trees and an ensemble of weather forecasts. To this end, we perform a comparative analysis across three state-of-the-art probabilistic prediction methods-conformalized quantile regression, natural gradient boosting and conditional diffusion models-all of which can be combined with tree-based machine learning. The methods are validated using four years of data for all Belgian offshore wind farms. We benchmark the models against the power curve and a calibrated wake model as well as a probabilistic method using stochastic variational Gaussian process regression. The tree-based models significantly reduce the mean absolute error in comparison to the deterministic baselines. Additionally, all three methods outperform the Gaussian process baseline in probabilistic skill, while two out of the three also improve point forecast accuracy. The conditional diffusion model attains the best performance, with improvements of 5% in mean absolute error and 12% in continuous rank probability score compared to the probabilistic baseline. Last, the results indicate an average improvement in point forecast accuracy of 17% by using an ensemble of weather forecasts instead of a single provider. --- ### Machine Learning-Based Classification of Jhana Advanced Concentrative Absorption Meditation Using 7 Tesla Functional Magnetic Resonance Imaging Authors: Puneet Kumar, Winson F. Z. Yang, Alakhsimar Singh, Xiaobai Li, Matthew D. Sacchet Published: 2026-02-13 Categories: cs.LG, cs.NE arXiv: https://arxiv.org/abs/2602.13008v2 Introduction: Jhana advanced concentrative absorption meditation (ACAM-J) involves profound changes in consciousness, making its neural correlates important for understanding consciousness and well-being. Prior neuroimaging has relied on univariate, group-level contrasts, leaving open whether ACAM-J carries distributed neural signatures decodable from individual scans. This study evaluates whether fMRI-derived regional homogeneity (ReHo) can classify ACAM-J using machine learning. Methods: We analysed 7T fMRI data from 20 advanced meditators who progressed through their standard ACAM-J sequence and two matched control tasks, plus intensive data from one case-study participant held out for final evaluation. ReHo maps were computed per segment and parcellated into 498 regions spanning cortex, subcortex, brainstem, and cerebellum. Within subject-wise stratified cross-validation, feature ranking, recursive feature elimination, and class balancing were applied to training data only; six classifier families were fitted, and the top three per contrast were combined by probability averaging. Results: Across 19 binary comparisons, the ensemble reached an overall average accuracy of 65.87% before and 66.82% after regressing out phenomenology-related variance, with an average Cohen's \k{appa} of 0.2443. Discrimination was strongest for the most separated states (ACAM-J1 vs ACAM-J6, 74.33% accuracy, \k{appa} = 0.5158), while adjacent states were harder to separate. Prefrontal and anterior cingulate areas contributed most to model decisions. Conclusion: ReHo patterns measured at 7T carry information distinguishing ACAM-J from control states and, more modestly, from one another, supporting the feasibility of multivariate decoding of advanced meditation and informing future work on its mechanisms and neuromodulation. --- ### Machine Learning-Based Classification of Jhana Advanced Concentrative Absorption Meditation (ACAM-J) using 7T fMRI Authors: Puneet Kumar, Winson F. Z. Yang, Alakhsimar Singh, Xiaobai Li, Matthew D. Sacchet Published: 2026-02-13 Categories: cs.LG, cs.NE arXiv: https://arxiv.org/abs/2602.13008v1 Jhana advanced concentration absorption meditation (ACAM-J) is related to profound changes in consciousness and cognitive processing, making the study of their neural correlates vital for insights into consciousness and well-being. This study evaluates whether functional MRI-derived regional homogeneity (ReHo) can be used to classify ACAM-J using machine-learning approaches. We collected group-level fMRI data from 20 advanced meditators to train the classifiers, and intensive single-case data from an advanced practitioner performing ACAM-J and control tasks to evaluate generalization. ReHo maps were computed, and features were extracted from predefined brain regions of interest. We trained multiple machine learning classifiers using stratified cross-validation to evaluate whether ReHo patterns distinguish ACAM-J from non-meditative states. Ensemble models achieved 66.82% (p < 0.05) accuracy in distinguishing ACAM-J from control conditions. Feature-importance analysis indicated that prefrontal and anterior cingulate areas contributed most to model decisions, aligning with established involvement of these regions in attentional regulation and metacognitive processes. Moreover, moderate agreement reflected in Cohen's kappa supports the feasibility of using machine learning to distinguish ACAM-J from non-meditative states. These findings advocate machine-learning's feasibility in classifying advanced meditation states, future research on neuromodulation and mechanistic models of advanced meditation. --- ### Towards Uncertainty-Aware Federated Granger Causal Learning Authors: Ayush Mohanty, Nazal Mohamed, Nagi Gebraeel Published: 2026-02-13 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2602.13004v2 Granger causality recovers directed interactions from time-series data, but in many distributed systems, the data are vertically partitioned across clients, with each client observing only the variables of its own subsystem. Federated Granger causality (FedGC) recovers cross-client interactions without sharing raw data. Existing FedGC methods, however, return deterministic point estimates with no calibrated measure of uncertainty, leaving operators without a principled basis for identifying reliable cross-client interactions. We address this limitation by characterizing how uncertainty propagates through the FedGC framework. We derive closed-form covariance recursions for the cross-covariances induced by the coupled client-server feedback loop, and establish spectral-radius-based convergence conditions yielding closed-form expressions for the steady-state variances at both the client and server. Under mild stability conditions, we prove that the steady-state uncertainty depends only on client data statistics (aleatoric) and is independent of the priors placed on the model parameters (epistemic). Building on this asymptotic characterization, we construct a post-training hypothesis testing procedure that separates genuine cross-client interactions from spurious edges. Experiments on synthetic and real-world datasets show that the predicted uncertainty propagation matches the theory across multiple operating regimes, while consistently outperforming the state-of-the-art federated causal structure learning baselines. --- ### MASAR: Motion-Appearance Synergy Refinement for Joint Detection and Trajectory Forecasting Authors: Mohammed Amine Bencheikh Lehocine, Julian Schmidt, Frank Moosmann, Dikshant Gupta, Fabian Flohr Published: 2026-02-13 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.13003v1 Classical autonomous driving systems connect perception and prediction modules via hand-crafted bounding-box interfaces, limiting information flow and propagating errors to downstream tasks. Recent research aims to develop end-to-end models that jointly address perception and prediction; however, they often fail to fully exploit the synergy between appearance and motion cues, relying mainly on short-term visual features. We follow the idea of "looking backward to look forward", and propose MASAR, a novel fully differentiable framework for joint 3D detection and trajectory forecasting compatible with any transformer-based 3D detector. MASAR employs an object-centric spatio-temporal mechanism that jointly encodes appearance and motion features. By predicting past trajectories and refining them using guidance from appearance cues, MASAR captures long-term temporal dependencies that enhance future trajectory forecasting. Experiments conducted on the nuScenes dataset demonstrate MASAR's effectiveness, showing improvements of over 20% in minADE and minFDE while maintaining robust detection performance. Code and models are available at https://github.com/aminmed/MASAR. --- ### Know More, Know Clearer: A Meta-Cognitive Framework for Knowledge Augmentation in Large Language Models Authors: Hao Chen, Ye He, Yuchun Fan, Yukun Yan, Zhenghao Liu, Qingfu Zhu, Maosong Sun, Wanxiang Che Published: 2026-02-13 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.12996v2 Knowledge augmentation has significantly enhanced the performance of Large Language Models (LLMs) in knowledge-intensive tasks. However, existing methods typically operate on the simplistic premise that model performance equates with internal knowledge, overlooking the knowledge-confidence gaps that lead to overconfident errors or uncertain truths. To bridge this gap, we propose a novel meta-cognitive framework for reliable knowledge augmentation via differentiated intervention and alignment. Our approach leverages internal cognitive signals to partition the knowledge space into mastered, confused, and missing regions, guiding targeted knowledge expansion. Furthermore, we introduce a cognitive consistency mechanism to synchronize subjective certainty with objective accuracy, ensuring calibrated knowledge boundaries. Extensive experiments demonstrate the our framework consistently outperforms strong baselines, validating its rationality in not only enhancing knowledge capabilities but also fostering cognitive behaviors that better distinguish knowns from unknowns. All codes are available at https://github.com/AI9Stars/Know-More-Know-Clearer. --- ### Evaluating the Homogeneity of Keyphrase Prediction Models Authors: Maël Houbre, Florian Boudin, Beatrice Daille Published: 2026-02-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.12989v1 Keyphrases which are useful in several NLP and IR applications are either extracted from text or predicted by generative models. Contrarily to keyphrase extraction approaches, keyphrase generation models can predict keyphrases that do not appear in a document's text called `absent keyphrases`. This ability means that keyphrase generation models can associate a document to a notion that is not explicitly mentioned in its text. Intuitively, this suggests that for two documents treating the same subjects, a keyphrase generation model is more likely to be homogeneous in their indexing i.e. predict the same keyphrase for both documents, regardless of those keyphrases appearing in their respective text or not; something a keyphrase extraction model would fail to do. Yet, homogeneity of keyphrase prediction models is not covered by current benchmarks. In this work, we introduce a method to evaluate the homogeneity of keyphrase prediction models and study if absent keyphrase generation capabilities actually help the model to be more homogeneous. To our surprise, we show that keyphrase extraction methods are competitive with generative models, and that the ability to generate absent keyphrases can actually have a negative impact on homogeneity. Our data, code and prompts are available on huggingface and github. --- ### Represent Micro-Doppler Signature in Orders Authors: Weicheng Gao Published: 2026-02-13 Categories: eess.SP, cs.CV arXiv: https://arxiv.org/abs/2602.12985v1 Non-line-of-sight sensing of human activities in complex environments is enabled by multiple-input multiple-output through-the-wall radar (TWR). However, the distinctiveness of micro-Doppler signature between similar indoor human activities such as gun carrying and normal walking is minimal, while the large scale of input images required for effective identification utilizing time-frequency spectrograms creates challenges for model training and inference efficiency. To address this issue, the Chebyshev-time map is proposed in this paper, which is a method characterizing micro-Doppler signature using polynomial orders. The parametric kinematic models for human motion and the TWR echo model are first established. Then, a time-frequency feature representation method based on orthogonal Chebyshev polynomial decomposition is proposed. The kinematic envelopes of the torso and limbs are extracted, and the time-frequency spectrum slices are mapped into a robust Chebyshev-time coefficient space, preserving the multi-order morphological detail information of time-frequency spectrum. Numerical simulations and experiments are conducted to verify the effectiveness of the proposed method, which demonstrates the capability to characterize armed and unarmed indoor human activities while effectively compressing the scale of the time-frequency spectrum to achieve a balance between recognition accuracy and input data dimensions. The open-source code of this paper can be found in: https://github.com/JoeyBGOfficial/Represent-Micro-Doppler-Signature-in-Orders. --- ### SciAgentGym: Benchmarking Multi-Step Scientific Tool-use in LLM Agents Authors: Yujiong Shen, Yajie Yang, Zhiheng Xi, Binze Hu, Huayu Sha, Jiazheng Zhang, Qiyuan Peng, Junlin Shang, Jixuan Huang, Yutao Fan, Jingqi Tong, Shihan Dou et al. Published: 2026-02-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.12984v2 Scientific reasoning inherently demands integrating sophisticated toolkits to navigate domain-specific knowledge. Yet, current benchmarks largely overlook agents' ability to orchestrate tools for such rigorous workflows. To bridge this gap, we introduce SciAgentGym, a scalable interactive environment featuring 1,780 domain-specific tools across four natural science disciplines, supported by a robust execution infrastructure. Complementing this, we present SciAgentBench, a tiered evaluation suite designed to stress-test agentic capabilities from elementary actions to long-horizon workflows. Our evaluation identifies a critical bottleneck: state-of-the-art models still struggle with complex scientific tool-use, and their performance degrades substantially as interaction horizons extend. To address this, we propose SciForge, a data synthesis method that models the tool action space as a dependency graph to generate logic-aware training trajectories. By fine-tuning on these trajectories, our SciAgent-8B outperforms the significantly larger Qwen3-VL-235B-Instruct while exhibiting positive cross-domain transfer of scientific tool-use capabilities. These results underscore the promising potential of next-generation autonomous scientific agents. --- ### Detecting Object Tracking Failure via Sequential Hypothesis Testing Authors: Alejandro Monroy Muñoz, Rajeev Verma, Alexander Timans Published: 2026-02-13 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.12983v1 Real-time online object tracking in videos constitutes a core task in computer vision, with wide-ranging applications including video surveillance, motion capture, and robotics. Deployed tracking systems usually lack formal safety assurances to convey when tracking is reliable and when it may fail, at best relying on heuristic measures of model confidence to raise alerts. To obtain such assurances we propose interpreting object tracking as a sequential hypothesis test, wherein evidence for or against tracking failures is gradually accumulated over time. Leveraging recent advancements in the field, our sequential test (formalized as an e-process) quickly identifies when tracking failures set in whilst provably containing false alerts at a desired rate, and thus limiting potentially costly re-calibration or intervention steps. The approach is computationally light-weight, requires no extra training or fine-tuning, and is in principle model-agnostic. We propose both supervised and unsupervised variants by leveraging either ground-truth or solely internal tracking information, and demonstrate its effectiveness for two established tracking models across four video benchmarks. As such, sequential testing can offer a statistically grounded and efficient mechanism to incorporate safety assurances into real-time tracking systems. --- ### Multi-Dimensional Visual Data Recovery: Scale-Aware Tensor Modeling and Accelerated Randomized Computation Authors: Wenjin Qin, Hailin Wang, Jiangjun Peng, Jianjun Wang, Tingwen Huang Published: 2026-02-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.12982v1 The recently proposed fully-connected tensor network (FCTN) decomposition has demonstrated significant advantages in correlation characterization and transpositional invariance, and has achieved notable achievements in multi-dimensional data processing and analysis. However, existing multi-dimensional data recovery methods leveraging FCTN decomposition still have room for further enhancement, particularly in computational efficiency and modeling capability. To address these issues, we first propose a FCTN-based generalized nonconvex regularization paradigm from the perspective of gradient mapping. Then, reliable and scalable multi-dimensional data recovery models are investigated, where the model formulation is shifted from unquantized observations to coarse-grained quantized observations. Based on the alternating direction method of multipliers (ADMM) framework, we derive efficient optimization algorithms with convergence guarantees to solve the formulated models. To alleviate the computational bottleneck encountered when processing large-scale multi-dimensional data, fast and efficient randomized compression algorithms are devised in virtue of sketching techniques in numerical linear algebra. These dimensionality-reduction techniques serve as the computational acceleration core of our proposed algorithm framework. Theoretical results on approximation error upper bounds and convergence analysis for the proposed method are derived. Extensive numerical experiments illustrate the effectiveness and superiority of the proposed algorithm over other state-of-the-art methods in terms of quantitative metrics, visual quality, and running time. --- ### MAUNet-Light: A Concise MAUNet Architecture for Bias Correction and Downscaling of Precipitation Estimates Authors: Sumanta Chandra Mishra Sharma, Adway Mitra, Auroop Ratan Ganguly Published: 2026-02-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.12980v1 Satellite-derived data products and climate model simulations of geophysical variables like precipitation, often exhibit systematic biases compared to in-situ measurements. Bias correction and spatial downscaling are fundamental components to develop operational weather forecast systems, as they seek to improve the consistency between coarse-resolution climate model simulations or satellite-based estimates and ground-based observations. In recent years, deep learning-based models have been increasingly replaced traditional statistical methods to generate high-resolution, bias free projections of climate variables. For example, Max-Average U-Net (MAUNet) architecture has been demonstrated for its ability to downscale precipitation estimates. The versatility and adaptability of these neural models make them highly effective across a range of applications, though this often come at the cost of high computational and memory requirements. The aim of this research is to develop light-weight neural network architectures for both bias correction and downscaling of precipitation, for which the teacher-student based learning paradigm is explored. This research demonstrates the adaptability of MAUNet to the task of bias correction, and further introduces a compact, lightweight neural network architecture termed MAUNet-Light.The proposed MAUNet-Light model is developed by transferring knowledge from the trained MAUNet, and it is designed to perform both downscaling and bias correction with reduced computational requirements without any significant loss in accuracy compared to state-of-the-art. ---