# Research Papers — 2026-02 · bundle page 28 of 210 > Full-text markdown of papers #1351–1400 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/28 [← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/27.md) [Next bundle →](https://aipod.dev/papers/archive/2026-02/page/29.md) ### Learning Unknown Interdependencies for Decentralized Root Cause Analysis in Nonlinear Dynamical Systems Authors: Ayush Mohanty, Paritosh Ramanan, Nagi Gebraeel Published: 2026-02-25 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2602.21928v1 Root cause analysis (RCA) in networked industrial systems, such as supply chains and power networks, is notoriously difficult due to unknown and dynamically evolving interdependencies among geographically distributed clients. These clients represent heterogeneous physical processes and industrial assets equipped with sensors that generate large volumes of nonlinear, high-dimensional, and heterogeneous IoT data. Classical RCA methods require partial or full knowledge of the system's dependency graph, which is rarely available in these complex networks. While federated learning (FL) offers a natural framework for decentralized settings, most existing FL methods assume homogeneous feature spaces and retrainable client models. These assumptions are not compatible with our problem setting. Different clients have different data features and often run fixed, proprietary models that cannot be modified. This paper presents a federated cross-client interdependency learning methodology for feature-partitioned, nonlinear time-series data, without requiring access to raw sensor streams or modifying proprietary client models. Each proprietary local client model is augmented with a Machine Learning (ML) model that encodes cross-client interdependencies. These ML models are coordinated via a global server that enforces representation consistency while preserving privacy through calibrated differential privacy noise. RCA is performed using model residuals and anomaly flags. We establish theoretical convergence guarantees and validate our approach on extensive simulations and a real-world industrial cybersecurity dataset. --- ### Bridging Through Absence: How Comeback Researchers Bridge Knowledge Gaps Through Structural Re-emergence Authors: Somyajit Chakraborty, Angshuman Jana, Avijit Gayen Published: 2026-02-25 Categories: cs.SI, cs.DL, cs.LG, physics.soc-ph arXiv: https://arxiv.org/abs/2602.21926v1 Understanding the role of researchers who return to academia after prolonged inactivity, termed "comeback researchers", is crucial for developing inclusive models of scientific careers. This study investigates the structural and semantic behaviors of comeback researchers, focusing on their role in cross-disciplinary knowledge transfer and network reintegration. Using the AMiner citation dataset, we analyze 113,637 early-career researchers and identify 1,425 comeback cases based on a three-year-or-longer publication gap followed by renewed activity. We find that comeback researchers cite 126% more distinct communities and exhibit 7.6% higher bridging scores compared to dropouts. They also demonstrate 74% higher gap entropy, reflecting more irregular yet strategically impactful publication trajectories. Predictive models trained on these bridging- and entropy-based features achieve a 97% ROC-AUC, far outperforming the 54% ROC-AUC of baseline models using traditional metrics like publication count and h-index. Finally, we substantiate these results via a multi-lens validation. These findings highlight the unique contributions of comeback researchers and offer data-driven tools for their early identification and institutional support. --- ### Learning in the Null Space: Small Singular Values for Continual Learning Authors: Cuong Anh Pham, Praneeth Vepakomma, Samuel Horváth Published: 2026-02-25 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2602.21919v1 Alleviating catastrophic forgetting while enabling further learning is a primary challenge in continual learning (CL). Orthogonal-based training methods have gained attention for their efficiency and strong theoretical properties, and many existing approaches enforce orthogonality through gradient projection. In this paper, we revisit orthogonality and exploit the fact that small singular values correspond to directions that are nearly orthogonal to the input space of previous tasks. Building on this principle, we introduce NESS (Null-space Estimated from Small Singular values), a CL method that applies orthogonality directly in the weight space rather than through gradient manipulation. Specifically, NESS constructs an approximate null space using the smallest singular values of each layer's input representation and parameterizes task-specific updates via a compact low-rank adaptation (LoRA-style) formulation constrained to this subspace. The subspace basis is fixed to preserve the null-space constraint, and only a single trainable matrix is learned for each task. This design ensures that the resulting updates remain approximately in the null space of previous inputs while enabling adaptation to new tasks. Our theoretical analysis and experiments on three benchmark datasets demonstrate competitive performance, low forgetting, and stable accuracy across tasks, highlighting the role of small singular values in continual learning. The code is available at https://github.com/pacman-ctm/NESS. --- ### Scan Clusters, Not Pixels: A Cluster-Centric Paradigm for Efficient Ultra-high-definition Image Restoration Authors: Chen Wu, Ling Wang, Zhuoran Zheng, Yuning Cui, Zhixiong Yang, Xiangyu Chen, Yue Zhang, Weidong Jiang, Jingyuan Xia Published: 2026-02-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.21917v2 Ultra-High-Definition (UHD) image restoration is trapped in a scalability crisis: existing models, bound to pixel-wise operations, demand unsustainable computation. While state space models (SSMs) like Mamba promise linear complexity, their pixel-serial scanning remains a fundamental bottleneck for the millions of pixels in UHD content. We ask: must we process every pixel to understand the image? This paper introduces C$^2$SSM, a visual state space model that breaks this taboo by shifting from pixel-serial to cluster-serial scanning. Our core discovery is that the rich feature distribution of a UHD image can be distilled into a sparse set of semantic centroids via a neural-parameterized mixture model. C$^2$SSM leverages this to reformulate global modeling into a novel dual-path process: it scans and reasons over a handful of cluster centers, then diffuses the global context back to all pixels through a principled similarity distribution, all while a lightweight modulator preserves fine details. This cluster-centric paradigm achieves a decisive leap in efficiency, slashing computational costs while establishing new state-of-the-art results across five UHD restoration tasks. More than a solution, C$^2$SSM charts a new course for efficient large-scale vision: scan clusters, not pixels. --- ### Protein Graph Neural Networks for Heterogeneous Cryo-EM Reconstruction Authors: Jonathan Krook, Axel Janson, Joakim Andén, Melanie Weber, Ozan Öktem Published: 2026-02-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.21915v1 We present a geometry-aware method for heterogeneous single-particle cryogenic electron microscopy (cryo-EM) reconstruction that predicts atomic backbone conformations. To incorporate protein-structure priors, we represent the backbone as a graph and use a graph neural network (GNN) autodecoder that maps per-image latent variables to 3D displacements of a template conformation. The objective combines a data-discrepancy term based on a differentiable cryo-EM forward model with geometric regularization, and it supports unknown orientations via ellipsoidal support lifting (ESL) pose estimation. On synthetic datasets derived from molecular dynamics trajectories, the proposed GNN achieves higher accuracy compared to a multilayer perceptron (MLP) of comparable size, highlighting the benefits of a geometry-informed inductive bias. --- ### The Error of Deep Operator Networks Is the Sum of Its Parts: Branch-Trunk and Mode Error Decompositions Authors: Alexander Heinlein, Johannes Taraz Published: 2026-02-25 Categories: cs.LG, math.NA arXiv: https://arxiv.org/abs/2602.21910v2 Operator learning has the potential to strongly impact scientific computing by learning solution operators for differential equations, potentially accelerating multi-query tasks such as design optimization and uncertainty quantification by orders of magnitude. Despite proven universal approximation properties, deep operator networks (DeepONets) often exhibit limited accuracy and generalization in practice, which hinders their adoption. Understanding these limitations is therefore crucial for further advancing the approach. This work analyzes performance limitations of the classical DeepONet architecture. It is shown that the approximation error is dominated by the branch network when the internal dimension is sufficiently large, and that the learned trunk basis can often be replaced by classical basis functions without a significant impact on performance. To investigate this further, a modified DeepONet is constructed in which the trunk network is replaced by the left singular vectors of the training solution matrix. This modification yields several key insights. First, for examples involving the KdV and Burgers equations, a spectral bias in the branch network is observed, with coefficients of dominant, low-frequency modes learned more effectively. Second, through the interplay of the singular-value weighting and the optimizer's neglect of small modes, the branch error is dominated by modes with large and intermediate singular values. Third, using a shared branch network for all mode coefficients, as in the standard architecture, improves generalization of small modes compared to a stacked architecture in which coefficients are computed separately. Finally, detrimental coupling between modes in parameter space is identified, which weakens with increasing network width. --- ### The Error of Deep Operator Networks Is the Sum of Its Parts: Branch-Trunk and Mode Error Decompositions Authors: Alexander Heinlein, Johannes Taraz Published: 2026-02-25 Categories: cs.LG, math.NA arXiv: https://arxiv.org/abs/2602.21910v1 Operator learning has the potential to strongly impact scientific computing by learning solution operators for differential equations, potentially accelerating multi-query tasks such as design optimization and uncertainty quantification by orders of magnitude. Despite proven universal approximation properties, deep operator networks (DeepONets) often exhibit limited accuracy and generalization in practice, which hinders their adoption. Understanding these limitations is therefore crucial for further advancing the approach. This work analyzes performance limitations of the classical DeepONet architecture. It is shown that the approximation error is dominated by the branch network when the internal dimension is sufficiently large, and that the learned trunk basis can often be replaced by classical basis functions without a significant impact on performance. To investigate this further, a modified DeepONet is constructed in which the trunk network is replaced by the left singular vectors of the training solution matrix. This modification yields several key insights. First, a spectral bias in the branch network is observed, with coefficients of dominant, low-frequency modes learned more effectively. Second, due to singular-value scaling of the branch coefficients, the overall branch error is dominated by modes with intermediate singular values rather than the smallest ones. Third, using a shared branch network for all mode coefficients, as in the standard architecture, improves generalization of small modes compared to a stacked architecture in which coefficients are computed separately. Finally, strong and detrimental coupling between modes in parameter space is identified. --- ### TIRAuxCloud: A Thermal Infrared Dataset for Day and Night Cloud Detection Authors: Alexis Apostolakis, Vasileios Botsos, Niklas Wölki, Andrea Spichtinger, Nikolaos Ioannis Bountos, Ioannis Papoutsis, Panayiotis Tsanakas Published: 2026-02-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.21905v2 Clouds are a major obstacle in Earth observation, limiting the usability and reliability of critical remote sensing applications such as fire disaster response, urban heat island monitoring, and snow and ice cover mapping. Therefore, the ability to detect clouds 24/7 is of paramount importance. While visible and near-infrared bands are effective for daytime cloud detection, their dependence on solar illumination makes them unsuitable for nighttime monitoring. In contrast, thermal infrared (TIR) imagery plays a crucial role in detecting clouds at night, when sunlight is absent. Due to their generally lower temperatures, clouds emit distinct thermal signatures that are detectable in TIR bands. Despite this, accurate nighttime cloud detection remains challenging due to limited spectral information and the typically lower spatial resolution of TIR imagery. To address these challenges, we present TIRAuxCloud, a multi-modal dataset centered around thermal spectral data to facilitate cloud segmentation under both daytime and nighttime conditions. The dataset comprises a unique combination of multispectral data (TIR, optical, and near-infrared bands) from Landsat and VIIRS, aligned with auxiliary information layers. Elevation, land cover, meteorological variables, and cloud-free reference images are included to help reduce surface-cloud ambiguity and cloud formation uncertainty. To overcome the scarcity of manual cloud labels, we include a large set of samples with automated cloud masks and a smaller manually annotated subset to further evaluate and improve models. Comprehensive benchmarks are presented to establish performance baselines through supervised and transfer learning, demonstrating the dataset's value in advancing the development of innovative methods for day and night time cloud detection. --- ### UNet-Based Keypoint Regression for 3D Cone Localization in Autonomous Racing Authors: Mariia Baidachna, James Carty, Aidan Ferguson, Joseph Agrane, Varad Kulkarni, Aubrey Agub, Michael Baxendale, Aaron David, Rachel Horton, Elliott Atkinson Published: 2026-02-25 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2602.21904v1 Accurate cone localization in 3D space is essential in autonomous racing for precise navigation around the track. Approaches that rely on traditional computer vision algorithms are sensitive to environmental variations, and neural networks are often trained on limited data and are infeasible to run in real time. We present a UNet-based neural network for keypoint detection on cones, leveraging the largest custom-labeled dataset we have assembled. Our approach enables accurate cone position estimation and the potential for color prediction. Our model achieves substantial improvements in keypoint accuracy over conventional methods. Furthermore, we leverage our predicted keypoints in the perception pipeline and evaluate the end-to-end autonomous system. Our results show high-quality performance across all metrics, highlighting the effectiveness of this approach and its potential for adoption in competitive autonomous racing systems. --- ### EndoDDC: Learning Sparse to Dense Reconstruction for Endoscopic Robotic Navigation via Diffusion Depth Completion Authors: Yinheng Lin, Yiming Huang, Beilei Cui, Long Bai, Huxin Gao, Hongliang Ren, Jiewen Lai Published: 2026-02-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.21893v2 Accurate depth estimation plays a critical role in the navigation of endoscopic surgical robots, forming the foundation for 3D reconstruction and safe instrument guidance. Fine-tuning pretrained models heavily relies on endoscopic surgical datasets with precise depth annotations. While existing self-supervised depth estimation techniques eliminate the need for accurate depth annotations, their performance degrades in environments with weak textures and variable lighting, leading to sparse reconstruction with invalid depth estimation. Depth completion using sparse depth maps can mitigate these issues and improve accuracy. Despite the advances in depth completion techniques in general fields, their application in endoscopy remains limited. To overcome these limitations, we propose EndoDDC, an endoscopy depth completion method that integrates images, sparse depth information with depth gradient features, and optimizes depth maps through a diffusion model, addressing the issues of weak texture and light reflection in endoscopic environments. Extensive experiments on two publicly available endoscopy datasets show that our approach outperforms state-of-the-art models in both depth accuracy and robustness. This demonstrates the potential of our method to reduce visual errors in complex endoscopic environments. Our code will be released at https://github.com/yinheng-lin/EndoDDC. --- ### 2-Step Agent: A Framework for the Interaction of a Decision Maker with AI Decision Support Authors: Otto Nyberg, Fausto Carcassi, Davide Tugnoli, Giovanni Cinà Published: 2026-02-25 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.21889v3 Predictions from ML models support human decision making in several fields, including high-stakes ones such as healthcare and the judiciary. Yet, we still lack a clear understanding of how decision makers learn from ML-based decision support (ML-DS). In this paper, we introduce a general computational framework, the 2-Step Agent, to capture this process. As a prediction from an ML model contains information about the training data, a prediction can also be used for inference. Our framework models (i) how a prediction for a new observation affects the beliefs of a rational Bayesian agent, and (ii) how this change in beliefs affects the estimation of causal effect, the downstream decision, and the subsequent outcome. In addition to the framework itself, we make three contributions. First, for the linear Gaussian setting, we derive a tractable solution for the challenging Bayesian inference problem we introduced, i.e. one in which the agent infers from an ML prediction. Second, we experimentally identify conditions under which ML-DS is beneficial. Third, we show that a single misaligned prior belief can be sufficient for ML-DS to lead to worse downstream outcomes compared to no decision support even when the ML model is well-specified and the agent is perfectly rational. Hence, even under ideal conditions, ML-DS can do more harm than good. --- ### ExpLang: Improved Exploration and Exploitation in LLM Reasoning with On-Policy Thinking Language Selection Authors: Changjiang Gao, Zixian Huang, Kaichen Yang, Jiajun Chen, Jixing Li, Shujian Huang Published: 2026-02-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.21887v1 Current large reasoning models (LRMs) have shown strong ability on challenging tasks after reinforcement learning (RL) based post-training. However, previous work mainly focuses on English reasoning in expectation of the strongest performance, despite the demonstrated potential advantage of multilingual thinking, as well as the requirement for native thinking traces by global users. In this paper, we propose ExpLang, a novel LLM post-training pipeline that enables on-policy thinking language selection to improve exploration and exploitation during RL with the use of multiple languages. The results show that our method steadily outperforms English-only training with the same training budget, while showing high thinking language compliance for both seen and unseen languages. Analysis shows that, by enabling on-policy thinking language selection as an action during RL, ExpLang effectively extends the RL exploration space with diversified language preference and improves the RL exploitation outcome with leveraged non-English advantage. The method is orthogonal to most RL algorithms and opens up a new perspective on using multilinguality to improve LRMs. --- ### How to Take a Memorable Picture? Empowering Users with Actionable Feedback Authors: Francesco Laiti, Davide Talon, Jacopo Staiano, Elisa Ricci Published: 2026-02-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.21877v2 Image memorability, i.e., how likely an image is to be remembered, has traditionally been studied in computer vision either as a passive prediction task, with models regressing a scalar score, or with generative methods altering the visual input to boost the image likelihood of being remembered. Yet, none of these paradigms supports users at capture time, when the crucial question is how to improve a photo memorability. We introduce the task of Memorability Feedback (MemFeed), where an automated model should provide actionable, human-interpretable guidance to users with the goal to enhance an image future recall. We also present MemCoach, the first approach designed to provide concrete suggestions in natural language for memorability improvement (e.g., "emphasize facial expression," "bring the subject forward"). Our method, based on Multimodal Large Language Models (MLLMs), is training-free and employs a teacher-student steering strategy, aligning the model internal activations toward more memorable patterns learned from a teacher model progressing along least-to-most memorable samples. To enable systematic evaluation on this novel task, we further introduce MemBench, a new benchmark featuring sequence-aligned photoshoots with annotated memorability scores. Our experiments, considering multiple MLLMs, demonstrate the effectiveness of MemCoach, showing consistently improved performance over several zero-shot models. The results indicate that memorability can not only be predicted but also taught and instructed, shifting the focus from mere prediction to actionable feedback for human creators. --- ### GFPL: Generative Federated Prototype Learning for Resource-Constrained and Data-Imbalanced Vision Task Authors: Shiwei Lu, Yuhang He, Jiashuo Li, Qiang Wang, Yihong Gong Published: 2026-02-25 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.21873v1 Federated learning (FL) facilitates the secure utilization of decentralized images, advancing applications in medical image recognition and autonomous driving. However, conventional FL faces two critical challenges in real-world deployment: ineffective knowledge fusion caused by model updates biased toward majority-class features, and prohibitive communication overhead due to frequent transmissions of high-dimensional model parameters. Inspired by the human brain's efficiency in knowledge integration, we propose a novel Generative Federated Prototype Learning (GFPL) framework to address these issues. Within this framework, a prototype generation method based on Gaussian Mixture Model (GMM) captures the statistical information of class-wise features, while a prototype aggregation strategy using Bhattacharyya distance effectively fuses semantically similar knowledge across clients. In addition, these fused prototypes are leveraged to generate pseudo-features, thereby mitigating feature distribution imbalance across clients. To further enhance feature alignment during local training, we devise a dual-classifier architecture, optimized via a hybrid loss combining Dot Regression and Cross-Entropy. Extensive experiments on benchmarks show that GFPL improves model accuracy by 3.6% under imbalanced data settings while maintaining low communication cost. --- ### DynamicGTR: Leveraging Graph Topology Representation Preferences to Boost VLM Capabilities on Graph QAs Authors: Yanbin Wei, Jiangyue Yan, Chun Kang, Yang Chen, Hua Liu, James Kwok, Yu Zhang Published: 2026-02-25 Categories: cs.CV, cs.AI, cs.CL, cs.GR arXiv: https://arxiv.org/abs/2602.21864v1 Vision-Language Models (VLMs) have emerged as versatile solutions for zero-shot question answering (QA) across various domains. However, enabling VLMs to effectively comprehend structured graphs and perform accurate, efficient QA remains challenging. Existing approaches typically rely on one single graph topology representation (GTR), such as fixed-style visual images or unified text descriptions. This ``one-size-fits-all'' strategy often neglects model-specific and task-specific preferences, resulting in inaccurate or over-lengthy responses to graph-related queries. To address this, we propose the $\mbox{DynamicGTR}$ framework, which dynamically selects the optimal GTR for each query during inference, thereby enhancing the zero-shot graph QA capabilities of VLMs with a customizable accuracy and brevity trade-off. Extensive experiments show that DynamicGTR not only improves VLM-based graph algorithm QA performance but also successfully transfers the experience trained from synthetic graph algorithm tasks to real-world applications like link prediction and node classification, without any additional training. Additionally, DynamicGTR demonstrates strong transferability across tasks, domains, and models, suggesting its potential as a flexible solution for broad graph scenarios. --- ### Personalized Graph-Empowered Large Language Model for Proactive Information Access Authors: Chia Cheng Chang, An-Zi Yen, Hen-Hsen Huang, Hsin-Hsi Chen Published: 2026-02-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.21862v1 Since individuals may struggle to recall all life details and often confuse events, establishing a system to assist users in recalling forgotten experiences is essential. While numerous studies have proposed memory recall systems, these primarily rely on deep learning techniques that require extensive training and often face data scarcity due to the limited availability of personal lifelogs. As lifelogs grow over time, systems must also adapt quickly to newly accumulated data. Recently, large language models (LLMs) have demonstrated remarkable capabilities across various tasks, making them promising for personalized applications. In this work, we present a framework that leverages LLMs for proactive information access, integrating personal knowledge graphs to enhance the detection of access needs through a refined decision-making process. Our framework offers high flexibility, enabling the replacement of base models and the modification of fact retrieval methods for continuous improvement. Experimental results demonstrate that our approach effectively identifies forgotten events, supporting users in recalling past experiences more efficiently. --- ### ProactiveMobile: A Comprehensive Benchmark for Boosting Proactive Intelligence on Mobile Devices Authors: Dezhi Kong, Zhengzhao Feng, Qiliang Liang, Hao Wang, Haofei Sun, Changpeng Yang, Yang Li, Peng Zhou, Shuai Nie, Hongzhen Wang, Linfeng Zhou, Hao Jia et al. Published: 2026-02-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.21858v4 Multimodal large language models (MLLMs) have made significant progress in mobile agent development, yet their capabilities are predominantly confined to a reactive paradigm, where they merely execute explicit user commands. The emerging paradigm of proactive intelligence, where agents autonomously anticipate needs and initiate actions, represents the next frontier for mobile agents. However, its development is critically bottlenecked by the lack of benchmarks that can address real-world complexity and enable objective, executable evaluation. To overcome these challenges, we introduce ProactiveMobile, a comprehensive benchmark designed to systematically advance research in this domain. ProactiveMobile formalizes the proactive task as inferring latent user intent across four dimensions of on-device contextual signals and generating an executable function sequence from a comprehensive function pool of 63 APIs. The benchmark features over 3,660 instances of 14 scenarios that embrace real-world complexity through multi-answer annotations. To ensure quality, a team of 30 experts conducts a final audit of the benchmark, verifying factual accuracy, logical consistency, and action feasibility, and correcting any non-compliant entries. Extensive experiments demonstrate that our fine-tuned Qwen2.5-VL-7B-Instruct achieves a success rate of 19.15%, outperforming o1 (15.71%) and GPT-5 (7.39%). This result indicates that proactivity is a critical competency widely lacking in current MLLMs, yet it is learnable, emphasizing the importance of the proposed benchmark for proactivity evaluation. --- ### Distill and Align Decomposition for Enhanced Claim Verification Authors: Jabez Magomere, Elena Kochkina, Samuel Mensah, Simerjot Kaur, Fernando Acero, Arturo Oncevay, Charese H. Smiley, Xiaomo Liu, Manuela Veloso Published: 2026-02-25 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2602.21857v1 Complex claim verification requires decomposing sentences into verifiable subclaims, yet existing methods struggle to align decomposition quality with verification performance. We propose a reinforcement learning (RL) approach that jointly optimizes decomposition quality and verifier alignment using Group Relative Policy Optimization (GRPO). Our method integrates: (i) structured sequential reasoning; (ii) supervised finetuning on teacher-distilled exemplars; and (iii) a multi-objective reward balancing format compliance, verifier alignment, and decomposition quality. Across six evaluation settings, our trained 8B decomposer improves downstream verification performance to (71.75%) macro-F1, outperforming prompt-based approaches ((+1.99), (+6.24)) and existing RL methods ((+5.84)). Human evaluation confirms the high quality of the generated subclaims. Our framework enables smaller language models to achieve state-of-the-art claim verification by jointly optimising for verification accuracy and decomposition quality. --- ### Understanding Annotation Error Propagation and Learning an Adaptive Policy for Expert Intervention in Barrett's Video Segmentation Authors: Lokesha Rasanjalee, Jin Lin Tan, Dileepa Pitawela, Rajvinder Singh, Hsiang-Ting Chen Published: 2026-02-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.21855v1 Accurate annotation of endoscopic videos is essential yet time-consuming, particularly for challenging datasets such as dysplasia in Barrett's esophagus, where the affected regions are irregular and lack clear boundaries. Semi-automatic tools like Segment Anything Model 2 (SAM2) can ease this process by propagating annotations across frames, but small errors often accumulate and reduce accuracy, requiring expert review and correction. To address this, we systematically study how annotation errors propagate across different prompt types, namely masks, boxes, and points, and propose Learning-to-Re-Prompt (L2RP), a cost-aware framework that learns when and where to seek expert input. By tuning a human-cost parameter, our method balances annotation effort and segmentation accuracy. Experiments on a private Barrett's dysplasia dataset and the public SUN-SEG benchmark demonstrate improved temporal consistency and superior performance over baseline strategies. --- ### FewMMBench: A Benchmark for Multimodal Few-Shot Learning Authors: Mustafa Dogan, Ilker Kesen, Iacer Calixto, Aykut Erdem, Erkut Erdem Published: 2026-02-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.21854v1 As multimodal large language models (MLLMs) advance in handling interleaved image-text data, assessing their few-shot learning capabilities remains an open challenge. In this paper, we introduce FewMMBench, a comprehensive benchmark designed to evaluate MLLMs under few-shot conditions, with a focus on In-Context Learning (ICL) and Chain-of-Thought (CoT) prompting. Covering a diverse suite of multimodal understanding tasks, from attribute recognition to temporal reasoning, FewMMBench enables systematic analysis across task types, model families, and prompting strategies. We evaluate 26 open-weight MLLMs from six model families across zero-shot, few-shot, and CoT-augmented few-shot settings. Our findings reveal that instruction-tuned models exhibit strong zero-shot performance but benefit minimally, or even regress, with additional demonstrations or CoT reasoning. Retrieval-based demonstrations and increased context size also yield limited gains. These results highlight FewMMBench as a rigorous testbed for diagnosing and advancing few-shot capabilities in multimodal LLMs. The data is available at: https://huggingface.co/datasets/mustafaa/FewMMBench --- ### Meta-FC: Meta-Learning with Feature Consistency for Robust and Generalizable Watermarking Authors: Yuheng Li, Weitong Chen, Chengcheng Zhu, Jiale Zhang, Chunpeng Ge, Di Wu, Guodong Long Published: 2026-02-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.21849v1 Deep learning-based watermarking has made remarkable progress in recent years. To achieve robustness against various distortions, current methods commonly adopt a training strategy where a \underline{\textbf{s}}ingle \underline{\textbf{r}}andom \underline{\textbf{d}}istortion (SRD) is chosen as the noise layer in each training batch. However, the SRD strategy treats distortions independently within each batch, neglecting the inherent relationships among different types of distortions and causing optimization conflicts across batches. As a result, the robustness and generalizability of the watermarking model are limited. To address this issue, we propose a novel training strategy that enhances robustness and generalization via \underline{\textbf{meta}}-learning with \underline{\textbf{f}}eature \underline{\textbf{c}}onsistency (Meta-FC). Specifically, we randomly sample multiple distortions from the noise pool to construct a meta-training task, while holding out one distortion as a simulated ``unknown'' distortion for the meta-testing phase. Through meta-learning, the model is encouraged to identify and utilize neurons that exhibit stable activations across different types of distortions, mitigating the optimization conflicts caused by the random sampling of diverse distortions in each batch. To further promote the transformation of stable activations into distortion-invariant representations, we introduce a feature consistency loss that constrains the decoded features of the same image subjected to different distortions to remain consistent. Extensive experiments demonstrate that, compared to the SRD training strategy, Meta-FC improves the robustness and generalization of various watermarking models by an average of 1.59\%, 4.71\%, and 2.38\% under high-intensity, combined, and unknown distortions. --- ### Scalable Kernel-Based Distances for Statistical Inference and Integration Authors: Masha Naslidnyk Published: 2026-02-25 Categories: stat.ML, cs.LG, math.ST, stat.ME arXiv: https://arxiv.org/abs/2602.21846v1 Representing, comparing, and measuring the distance between probability distributions is a key task in computational statistics and machine learning. The choice of representation and the associated distance determine properties of the methods in which they are used: for example, certain distances can allow one to encode robustness or smoothness of the problem. Kernel methods offer flexible and rich Hilbert space representations of distributions that allow the modeller to enforce properties through the choice of kernel, and estimate associated distances at efficient nonparametric rates. In particular, the maximum mean discrepancy (MMD), a kernel-based distance constructed by comparing Hilbert space mean functions, has received significant attention due to its computational tractability and is favoured by practitioners. In this thesis, we conduct a thorough study of kernel-based distances with a focus on efficient computation, with core contributions in Chapters 3 to 6. Part I of the thesis is focused on the MMD, specifically on improved MMD estimation. In Chapter 3 we propose a theoretically sound, improved estimator for MMD in simulation-based inference. Then, in Chapter 4, we propose an MMD-based estimator for conditional expectations, a ubiquitous task in statistical computation. Closing Part I, in Chapter 5 we study the problem of calibration when MMD is applied to the task of integration. In Part II, motivated by the recent developments in kernel embeddings beyond the mean, we introduce a family of novel kernel-based discrepancies: kernel quantile discrepancies. These address some of the pitfalls of MMD, and are shown through both theoretical results and an empirical study to offer a competitive alternative to MMD and its fast approximations. We conclude with a discussion on broader lessons and future work emerging from the thesis. --- ### xai-cola: A Python library for sparsifying counterfactual explanations Authors: Lin Zhu, Lei You Published: 2026-02-25 Categories: cs.LG, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2602.21845v1 Counterfactual explanation (CE) is an important domain within post-hoc explainability. However, the explanations generated by most CE generators are often highly redundant. This work introduces an open-source Python library xai-cola, which provides an end-to-end pipeline for sparsifying CEs produced by arbitrary generators, reducing superfluous feature changes while preserving their validity. It offers a documented API that takes as input raw tabular data in pandas DataFrame form, a preprocessing object (for standardization and encoding), and a trained scikit-learn or PyTorch model. On this basis, users can either employ the built-in or externally imported CE generators. The library also implements several sparsification policies and includes visualization routines for analysing and comparing sparsified counterfactuals. xai-cola is released under the MIT license and can be installed from PyPI. Empirical experiments indicate that xai-cola produces sparser counterfactuals across several CE generators, reducing the number of modified features by up to 50% in our setting. The source code is available at https://github.com/understanding-ml/COLA. --- ### JSAM: Privacy Straggler-Resilient Joint Client Selection and Incentive Mechanism Design in Differentially Private Federated Learning Authors: Ruichen Xu, Ying-Jun Angela Zhang, Jianwei Huang Published: 2026-02-25 Categories: cs.LG, cs.DC, cs.GT arXiv: https://arxiv.org/abs/2602.21844v1 Differentially private federated learning faces a fundamental tension: privacy protection mechanisms that safeguard client data simultaneously create quantifiable privacy costs that discourage participation, undermining the collaborative training process. Existing incentive mechanisms rely on unbiased client selection, forcing servers to compensate even the most privacy-sensitive clients ("privacy stragglers"), leading to systemic inefficiency and suboptimal resource allocation. We introduce JSAM (Joint client Selection and privacy compensAtion Mechanism), a Bayesian-optimal framework that simultaneously optimizes client selection probabilities and privacy compensation to maximize training effectiveness under budget constraints. Our approach transforms a complex 2N-dimensional optimization problem into an efficient three-dimensional formulation through novel theoretical characterization of optimal selection strategies. We prove that servers should preferentially select privacy-tolerant clients while excluding high-sensitivity participants, and uncover the counter-intuitive insight that clients with minimal privacy sensitivity may incur the highest cumulative costs due to frequent participation. Extensive evaluations on MNIST and CIFAR-10 demonstrate that JSAM achieves up to 15% improvement in test accuracy compared to existing unbiased selection mechanisms while maintaining cost efficiency across varying data heterogeneity levels. --- ### Resilient Federated Chain: Transforming Blockchain Consensus into an Active Defense Layer for Federated Learning Authors: Mario García-Márquez, Nuria Rodríguez-Barroso, M. Victoria Luzón, Francisco Herrera Published: 2026-02-25 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2602.21841v1 Federated Learning (FL) has emerged as a key paradigm for building Trustworthy AI systems by enabling privacy-preserving, decentralized model training. However, FL is highly susceptible to adversarial attacks that compromise model integrity and data confidentiality, a vulnerability exacerbated by the fact that conventional data inspection methods are incompatible with its decentralized design. While integrating FL with Blockchain technology has been proposed to address some limitations, its potential for mitigating adversarial attacks remains largely unexplored. This paper introduces Resilient Federated Chain (RFC), a novel blockchain-enabled FL framework designed specifically to enhance resilience against such threats. RFC builds upon the existing Proof of Federated Learning architecture by repurposing the redundancy of its Pooled Mining mechanism as an active defense layer that can be combined with robust aggregation rules. Furthermore, the framework introduces a flexible evaluation function in its consensus mechanism, allowing for adaptive defense against different attack strategies. Extensive experimental evaluation on image classification tasks under various adversarial scenarios, demonstrates that RFC significantly improves robustness compared to baseline methods, providing a viable solution for securing decentralized learning environments. --- ### UniVBench: Towards Unified Evaluation for Video Foundation Models Authors: Jianhui Wei, Xiaotian Zhang, Yichen Li, Yuan Wang, Yan Zhang, Ziyi Chen, Zhihang Tang, Wei Xu, Zuozhu Liu Published: 2026-02-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.21835v2 Video foundation models aim to integrate video understanding, generation, editing, and instruction following within a single framework, making them a central direction for next-generation multimodal systems. However, existing evaluation benchmarks remain fragmented and limited in scope, as they each target a single task, rely on task-specific metrics, and typically use short or simple video clips. As a result, they do not capture the unified capabilities that these models are designed to deliver. To address this gap, we introduce UniVBench, a benchmark purpose-built for evaluating video foundation models across four core abilities: video understanding, video generation, video editing, and a newly proposed task, video reconstruction, which assesses how faithfully a model can reproduce video content it has encountered. Our benchmark substantially expands the complexity of evaluation by incorporating 200 high-quality, diverse and multi-shot videos, each paired with detailed captions, multi-format editing instructions, and reference images. All videos are human-created and carefully validated, offering richer cinematic information than prior benchmarks. In addition, we develop a unified agentic evaluation system (UniV-Eval) that standardizes prompting, instruction parsing, and scoring across all tasks, enabling fair, scalable, and reproducible comparisons of unified video models. By grounding evaluation in instruction-based multi-shot video tasks, UniVBench provides the first framework for measuring the integrated capabilities that video foundation models aim to achieve. Extensive human annotations ensure our evaluation aligns with human judgment, enabling rigorous assessment and accelerating progress toward robust video intelligence. --- ### StoryMovie: A Dataset for Semantic Alignment of Visual Stories with Movie Scripts and Subtitles Authors: Daniel Oliveira, David Martins de Matos Published: 2026-02-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.21829v1 Visual storytelling models that correctly ground entities in images may still hallucinate semantic relationships, generating incorrect dialogue attribution, character interactions, or emotional states. We introduce StoryMovie, a dataset of 1,757 stories aligned with movie scripts and subtitles through LCS matching. Our alignment pipeline synchronizes screenplay dialogue with subtitle timestamps, enabling dialogue attribution by linking character names from scripts to temporal positions from subtitles. Using this aligned content, we generate stories that maintain visual grounding tags while incorporating authentic character names, dialogue, and relationship dynamics. We fine-tune Qwen Storyteller3 on this dataset, building on prior work in visual grounding and entity re-identification. Evaluation using DeepSeek V3 as judge shows that Storyteller3 achieves an 89.9% win rate against base Qwen2.5-VL 7B on subtitle alignment. Compared to Storyteller, trained without script grounding, Storyteller3 achieves 48.5% versus 38.0%, confirming that semantic alignment progressively improves dialogue attribution beyond visual grounding alone. --- ### DocDjinn: Controllable Synthetic Document Generation with VLMs and Handwriting Diffusion Authors: Marcel Lamott, Saifullah Saifullah, Nauman Riaz, Yves-Noel Weweler, Tobias Alt-Veit, Ahmad Sarmad Ali, Muhammad Armaghan Shakir, Adrian Kalwa, Momina Moetesum, Andreas Dengel, Sheraz Ahmed, Faisal Shafait et al. Published: 2026-02-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.21824v1 Effective document intelligence models rely on large amounts of annotated training data. However, procuring sufficient and high-quality data poses significant challenges due to the labor-intensive and costly nature of data acquisition. Additionally, leveraging language models to annotate real documents raises concerns about data privacy. Synthetic document generation has emerged as a promising, privacy-preserving alternative. We propose DocDjinn, a novel framework for controllable synthetic document generation using Vision-Language Models (VLMs) that produces annotated documents from unlabeled seed samples. Our approach generates visually plausible and semantically consistent synthetic documents that follow the distribution of an existing source dataset through clustering-based seed selection with parametrized sampling. By enriching documents with realistic diffusion-based handwriting and contextual visual elements via semantic-visual decoupling, we generate diverse, high-quality annotated synthetic documents. We evaluate across eleven benchmarks spanning key information extraction, question answering, document classification, and document layout analysis. To our knowledge, this is the first work demonstrating that VLMs can generate faithful annotated document datasets at scale from unlabeled seeds that can effectively enrich or approximate real, manually annotated data for diverse document understanding tasks. We show that with only 100 real training samples, our framework achieves on average $87\%$ of the performance of the full real-world dataset. We publicly release our code and 140k+ synthetic document samples. --- ### Joint Shadow Generation and Relighting via Light-Geometry Interaction Maps Authors: Shan Wang, Peixia Li, Chenchen Xu, Ziang Cheng, Jiayu Yang, Hongdong Li, Pulak Purkait Published: 2026-02-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.21820v2 We propose Light-Geometry Interaction (LGI) maps, a novel representation that encodes light-aware occlusion from monocular depth. Unlike ray tracing, which requires full 3D reconstruction, LGI captures essential light-shadow interactions reliably and accurately, computed from off-the-shelf 2.5D depth map predictions. LGI explicitly ties illumination direction to geometry, providing a physics-inspired prior that constrains generative models. Without such prior, these models often produce floating shadows, inconsistent illumination, and implausible shadow geometry. Building on this representation, we propose a unified pipeline for joint shadow generation and relighting - unlike prior methods that treat them as disjoint tasks - capturing the intrinsic coupling of illumination and shadowing essential for modeling indirect effects. By embedding LGI into a bridge-matching generative backbone, we reduce ambiguity and enforce physically consistent light-shadow reasoning. To enable effective training, we curated the first large-scale benchmark dataset for joint shadow and relighting, covering reflections, transparency, and complex interreflections. Experiments show significant gains in realism and consistency across synthetic and real images. LGI thus bridges geometry-inspired rendering with generative modeling, enabling efficient, physically consistent shadow generation and relighting. --- ### SemVideo: Reconstructs What You Watch from Brain Activity via Hierarchical Semantic Guidance Authors: Minghan Yang, Lan Yang, Ke Li, Honggang Zhang, Kaiyue Pang, Yizhe Song Published: 2026-02-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.21819v3 Reconstructing dynamic visual experiences from brain activity provides a compelling avenue for exploring the neural mechanisms of human visual perception. While recent progress in fMRI-based image reconstruction has been notable, extending this success to video reconstruction remains a significant challenge. Current fMRI-to-video reconstruction approaches consistently encounter two major shortcomings: (i) inconsistent visual representations of salient objects across frames, leading to appearance mismatches; (ii) poor temporal coherence, resulting in motion misalignment or abrupt frame transitions. To address these limitations, we introduce SemVideo, a novel fMRI-to-video reconstruction framework guided by hierarchical semantic information. At the core of SemVideo is SemMiner, a hierarchical guidance module that constructs three levels of semantic cues from the original video stimulus: static anchor descriptions, motion-oriented narratives, and holistic summaries. Leveraging this semantic guidance, SemVideo comprises three key components: a Semantic Alignment Decoder that aligns fMRI signals with CLIP-style embeddings derived from SemMiner, a Motion Adaptation Decoder that reconstructs dynamic motion patterns using a novel tripartite attention fusion architecture, and a Conditional Video Render that leverages hierarchical semantic guidance for video reconstruction. Experiments conducted on the CC2017 and HCP datasets demonstrate that SemVideo achieves superior performance in both semantic alignment and temporal consistency, setting a new state-of-the-art in fMRI-to-video reconstruction. --- ### SemVideo: Reconstructs What You Watch from Brain Activity via Hierarchical Semantic Guidance Authors: Minghan Yang, Lan Yang, Ke Li, Honggang Zhang, Kaiyue Pang, Yizhe Song Published: 2026-02-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.21819v2 Reconstructing dynamic visual experiences from brain activity provides a compelling avenue for exploring the neural mechanisms of human visual perception. While recent progress in fMRI-based image reconstruction has been notable, extending this success to video reconstruction remains a significant challenge. Current fMRI-to-video reconstruction approaches consistently encounter two major shortcomings: (i) inconsistent visual representations of salient objects across frames, leading to appearance mismatches; (ii) poor temporal coherence, resulting in motion misalignment or abrupt frame transitions. To address these limitations, we introduce SemVideo, a novel fMRI-to-video reconstruction framework guided by hierarchical semantic information. At the core of SemVideo is SemMiner, a hierarchical guidance module that constructs three levels of semantic cues from the original video stimulus: static anchor descriptions, motion-oriented narratives, and holistic summaries. Leveraging this semantic guidance, SemVideo comprises three key components: a Semantic Alignment Decoder that aligns fMRI signals with CLIP-style embeddings derived from SemMiner, a Motion Adaptation Decoder that reconstructs dynamic motion patterns using a novel tripartite attention fusion architecture, and a Conditional Video Render that leverages hierarchical semantic guidance for video reconstruction. Experiments conducted on the CC2017 and HCP datasets demonstrate that SemVideo achieves superior performance in both semantic alignment and temporal consistency, setting a new state-of-the-art in fMRI-to-video reconstruction. --- ### SkyReels-V4: Multi-modal Video-Audio Generation, Inpainting and Editing model Authors: Guibin Chen, Dixuan Lin, Jiangping Yang, Youqiang Zhang, Zhengcong Fei, Debang Li, Sheng Chen, Chaofeng Ao, Nuo Pang, Yiming Wang, Yikun Dou, Zheng Chen et al. Published: 2026-02-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.21818v3 SkyReels V4 is a unified multi modal video foundation model for joint video audio generation, inpainting, and editing. The model adopts a dual stream Multimodal Diffusion Transformer (MMDiT) architecture, where one branch synthesizes video and the other generates temporally aligned audio, while sharing a powerful text encoder based on the Multimodal Large Language Models (MLLM). SkyReels V4 accepts rich multi modal instructions, including text, images, video clips, masks, and audio references. By combining the MLLMs multi modal instruction following capability with in context learning in the video branch MMDiT, the model can inject fine grained visual guidance under complex conditioning, while the audio branch MMDiT simultaneously leverages audio references to guide sound generation. On the video side, we adopt a channel concatenation formulation that unifies a wide range of inpainting style tasks, such as image to video, video extension, and video editing under a single interface, and naturally extends to vision referenced inpainting and editing via multi modal prompts. SkyReels V4 supports up to 1080p resolution, 32 FPS, and 15 second duration, enabling high fidelity, multi shot, cinema level video generation with synchronized audio. To make such high resolution, long-duration generation computationally feasible, we introduce an efficiency strategy: Joint generation of low resolution full sequences and high-resolution keyframes, followed by dedicated super-resolution and frame interpolation models. To our knowledge, SkyReels V4 is the first video foundation model that simultaneously supports multi-modal input, joint video audio generation, and a unified treatment of generation, inpainting, and editing, while maintaining strong efficiency and quality at cinematic resolutions and durations. --- ### Prompt Architecture Determines Reasoning Quality: A Variable Isolation Study on the Car Wash Problem Authors: Heejin Jo Published: 2026-02-25 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.21814v2 Large language models consistently fail the "car wash problem," a viral reasoning benchmark requiring implicit physical constraint inference. We present a variable isolation study (n=20 per condition, 6 conditions, 120 total trials) examining which prompt architecture layers in a production system enable correct reasoning. Using Claude 3.5 Sonnet with controlled hyperparameters (temperature 0.7, top_p 1.0), we find that the STAR (Situation-Task-Action-Result) reasoning framework alone raises accuracy from 0% to 85% (p=0.001, Fisher's exact test, odds ratio 13.22). Adding user profile context via vector database retrieval provides a further 10 percentage point gain, while RAG context contributes an additional 5 percentage points, achieving 100% accuracy in the full-stack condition. These results suggest that structured reasoning scaffolds -- specifically, forced goal articulation before inference -- matter substantially more than context injection for implicit constraint reasoning tasks. --- ### GeoMotion: Rethinking Motion Segmentation via Latent 4D Geometry Authors: Xiankang He, Peile Lin, Ying Cui, Dongyan Guo, Chunhua Shen, Xiaoqin Zhang Published: 2026-02-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.21810v1 Motion segmentation in dynamic scenes is highly challenging, as conventional methods heavily rely on estimating camera poses and point correspondences from inherently noisy motion cues. Existing statistical inference or iterative optimization techniques that struggle to mitigate the cumulative errors in multi-stage pipelines often lead to limited performance or high computational cost. In contrast, we propose a fully learning-based approach that directly infers moving objects from latent feature representations via attention mechanisms, thus enabling end-to-end feed-forward motion segmentation. Our key insight is to bypass explicit correspondence estimation and instead let the model learn to implicitly disentangle object and camera motion. Supported by recent advances in 4D scene geometry reconstruction (e.g., $π^3$), the proposed method leverages reliable camera poses and rich spatial-temporal priors, which ensure stable training and robust inference for the model. Extensive experiments demonstrate that by eliminating complex pre-processing and iterative refinement, our approach achieves state-of-the-art motion segmentation performance with high efficiency. The code is available at:https://github.com/zjutcvg/GeoMotion. --- ### An Evaluation of Context Length Extrapolation in Long Code via Positional Embeddings and Efficient Attention Authors: Madhusudan Ghosh, Rishabh Gupta Published: 2026-02-25 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2602.21800v1 The rapid advancement of large language models (LLMs) has led to a significant increase in automated tools in the software engineering, capable of performing various code-related tasks such as code generation, completion, and translation. Despite these advancements, its effectiveness is constrained by fixed context lengths, limiting its ability to generalize across long, domain-specific code sequences. To address this challenge, we investigate zero-shot, inference-only methods aimed at improving position encodings and optimizing attention mechanisms. Our goal is to provide a thorough analysis of current approaches that facilitate context length extrapolation in code, particularly in the context of long code completion tasks. --- ### Excitation: Momentum For Experts Authors: Sagi Shaier Published: 2026-02-25 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.21798v1 We propose Excitation, a novel optimization framework designed to accelerate learning in sparse architectures such as Mixture-of-Experts (MoEs). Unlike traditional optimizers that treat all parameters uniformly, Excitation dynamically modulates updates using batch-level expert utilization. It introduces a competitive update dynamic that amplifies updates to highly-utilized experts and can selectively suppress low-utilization ones, effectively sharpening routing specialization. Notably, we identify a phenomenon of "structural confusion" in deep MoEs, where standard optimizers fail to establish functional signal paths; Excitation acts as a specialization catalyst, "rescuing" these models and enabling stable training where baselines remain trapped. Excitation is optimizer-, domain-, and model-agnostic, requires minimal integration effort, and introduces neither additional per-parameter optimizer state nor learnable parameters, making it highly viable for memory-constrained settings. Across language and vision tasks, Excitation consistently improves convergence speed and final performance in MoE models, indicating that active update modulation is a key mechanism for effective conditional computation. --- ### Neural Learning of Fast Matrix Multiplication Algorithms: A StrassenNet Approach Authors: Paolo Andreini, Alessandra Bernardi, Monica Bianchini, Barbara Toniella Corradini, Sara Marziali, Giacomo Nunziati, Franco Scarselli Published: 2026-02-25 Categories: math.AG, cs.LG arXiv: https://arxiv.org/abs/2602.21797v1 Fast matrix multiplication can be described as searching for low-rank decompositions of the matrix--multiplication tensor. We design a neural architecture, \textsc{StrassenNet}, which reproduces the Strassen algorithm for $2\times 2$ multiplication. Across many independent runs the network always converges to a rank-$7$ tensor, thus numerically recovering Strassen's optimal algorithm. We then train the same architecture on $3\times 3$ multiplication with rank $r\in\{19,\dots,23\}$. Our experiments reveal a clear numerical threshold: models with $r=23$ attain significantly lower validation error than those with $r\le 22$, suggesting that $r=23$ could actually be the smallest effective rank of the matrix multiplication tensor $3\times 3$. We also sketch an extension of the method to border-rank decompositions via an $\varepsilon$--parametrisation and report preliminary results consistent with the known bounds for the border rank of the $3\times 3$ matrix--multiplication tensor. --- ### Efficient Scaling of LLM Training with Flexible Context Parallelism Authors: Yifan Niu, Han Xiao, Dongyi Liu, Wei Zhou, Jia Li Published: 2026-02-25 Categories: cs.DC, cs.LG arXiv: https://arxiv.org/abs/2602.21788v2 Scaling long-context capabilities is crucial for Large Language Models (LLMs). However, real-world data contain a large number of sequences with heterogeneous lengths. Existing training libraries for LLMs rely on static parallelism strategies, which suffer from severe load imbalance, redundant communication, and suboptimal hardware utilization under data heterogeneity. In this work, we propose Flexible Context Parallelism (FCP), an efficient parallelism strategy that adaptively reconfigures communication groups and context parallelism degrees during LLM training. We generalize more flexible non-power-of-two parallelism degrees and develop a polynomial-time algorithm to generate near-optimal parallelism strategies with only millisecond-level overhead per training batch. FCP is able to maintain high hardware efficiency even under extreme data heterogeneity. Experimental results demonstrate that FCP significantly outperforms Megatron-LM and DeepSpeed in both LLM and MLLM training, achieving up to 1.46x speedup in average throughput while maintaining near-linear scaling efficiency across large-scale clusters. For extremely unbalanced batches, FCP even achieves 2.24x speedup. --- ### D-COT: Disciplined Chain-of-Thought Learning for Efficient Reasoning in Small Language Models Authors: Shunsuke Ubukata Published: 2026-02-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.21786v1 Chain-of-Thought (CoT) distillation from Large Language Models (LLMs) often induces "overthinking" in Small Language Models (SLMs), leading to performance degradation and excessive token consumption. In this study, we propose Disciplined Chain-of-Thought (D-CoT), a novel framework that enforces a structured reasoning process using control tags -- such as <TEMP_LOW> for fact-checking and <TEMP_HIGH> for multi-perspective exploration -- as auxiliary scaffolding during training. By optimizing the CoT trajectory, D-CoT suppresses reasoning drift and simultaneously achieves token reduction and performance improvement. We demonstrate the efficacy of our approach on Qwen3-8B: with only 5,000 training samples, D-CoT significantly boosts accuracy on GPQA-diamond by 9.9% and MMLU-Pro (0-shot) by 9.1%, while drastically reducing computational costs. Furthermore, we confirm that the model internalizes this disciplined thought structure, maintaining high performance even without explicit control tags during inference. --- ### Therapist-Robot-Patient Physical Interaction is Worth a Thousand Words: Enabling Intuitive Therapist Guidance via Remote Haptic Control Authors: Beatrice Luciani, Alex van den Berg, Matti Lang, Alexandre L. Ratschat, Laura Marchal-Crespo Published: 2026-02-25 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2602.21783v1 Robotic systems can enhance the amount and repeatability of physically guided motor training. Yet their real-world adoption is limited, partly due to non-intuitive trainer/therapist-trainee/patient interactions. To address this gap, we present a haptic teleoperation system for trainers to remotely guide and monitor the movements of a trainee wearing an arm exoskeleton. The trainer can physically interact with the exoskeleton through a commercial handheld haptic device via virtual contact points at the exoskeleton's elbow and wrist, allowing intuitive guidance. Thirty-two participants tested the system in a trainer-trainee paradigm, comparing our haptic demonstration system with conventional visual demonstration in guiding trainees in executing arm poses. Quantitative analyses showed that haptic demonstration significantly reduced movement completion time and improved smoothness, while speech analysis using large language models for automated transcription and categorization of verbal commands revealed fewer verbal instructions. The haptic demonstration did not result in higher reported mental and physical effort by trainers compared to the visual demonstration, while trainers reported greater competence and trainees lower physical demand. These findings support the feasibility of our proposed interface for effective remote human-robot physical interaction. Future work should assess its usability and efficacy for clinical populations in restoring clinicians' sense of agency during robot-assisted therapy. --- ### XStreamVGGT: Extremely Memory-Efficient Streaming Vision Geometry Grounded Transformer with KV Cache Compression Authors: Zunhai Su, Weihao Ye, Hansen Feng, Keyu Fan, Jing Zhang, Dahai Yu, Zhengwu Liu, Ngai Wong Published: 2026-02-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.21780v1 Learning-based 3D visual geometry models have significantly advanced with the advent of large-scale transformers. Among these, StreamVGGT leverages frame-wise causal attention to deliver robust and efficient streaming 3D reconstruction. However, it suffers from unbounded growth in the Key-Value (KV) cache due to the massive influx of vision tokens from multi-image and long-video inputs, leading to increased memory consumption and inference latency as input frames accumulate. This ultimately limits its scalability for long-horizon applications. To address this gap, we propose XStreamVGGT, a tuning-free approach that seamlessly integrates pruning and quantization to systematically compress the KV cache, enabling extremely memory-efficient streaming inference. Specifically, redundant KVs generated from multi-frame inputs are initially pruned to conform to a fixed KV memory budget using an efficient token-importance identification mechanism that maintains full compatibility with high-performance attention kernels (e.g., FlashAttention). Additionally, leveraging the inherent distribution patterns of KV tensors, we apply dimension-adaptive KV quantization within the pruning pipeline to further minimize memory overhead while preserving numerical accuracy. Extensive evaluations show that XStreamVGGT achieves mostly negligible performance degradation while substantially reducing memory usage by 4.42$\times$ and accelerating inference by 5.48$\times$, enabling practical and scalable streaming 3D applications. The code is available at https://github.com/ywh187/XStreamVGGT/. --- ### Beyond Static Artifacts: A Forensic Benchmark for Video Deepfake Reasoning in Vision Language Models Authors: Zheyuan Gu, Qingsong Zhao, Yusong Wang, Zhaohong Huang, Xinqi Li, Cheng Yuan, Jiaowei Shao, Chi Zhang, Xuelong Li Published: 2026-02-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.21779v1 Current Vision-Language Models (VLMs) for deepfake detection excel at identifying spatial artifacts but overlook a critical dimension: temporal inconsistencies in video forgeries. Adapting VLMs to reason about these dynamic cues remains a distinct challenge. To bridge this gap, we propose Forensic Answer-Questioning (FAQ), a large-scale benchmark that formulates temporal deepfake analysis as a multiple-choice task. FAQ introduces a three-level hierarchy to progressively evaluate and equip VLMs with forensic capabilities: (1) Facial Perception, testing the ability to identify static visual artifacts; (2) Temporal Deepfake Grounding, requiring the localization of dynamic forgery artifacts across frames; and (3) Forensic Reasoning, challenging models to synthesize evidence for final authenticity verdicts. We evaluate a range of VLMs on FAQ and generate a corresponding instruction-tuning set, FAQ-IT. Extensive experiments show that models fine-tuned on FAQ-IT achieve advanced performance on both in-domain and cross-dataset detection benchmarks. Ablation studies further validate the impact of our key design choices, confirming that FAQ is the driving force behind the temporal reasoning capabilities of these VLMs. --- ### From Statics to Dynamics: Physics-Aware Image Editing with Latent Transition Priors Authors: Liangbing Zhao, Le Zhuo, Sayak Paul, Hongsheng Li, Mohamed Elhoseiny Published: 2026-02-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.21778v2 Instruction-based image editing has achieved remarkable success in semantic alignment, yet state-of-the-art models frequently fail to render physically plausible results when editing involves complex causal dynamics, such as refraction or material deformation. We attribute this limitation to the dominant paradigm that treats editing as a discrete mapping between image pairs, which provides only boundary conditions and leaves transition dynamics underspecified. To address this, we reformulate physics-aware editing as predictive physical state transitions and introduce PhysicTran38K, a large-scale video-based dataset comprising 38K transition trajectories across five physical domains, constructed via a two-stage filtering and constraint-aware annotation pipeline. Building on this supervision, we propose PhysicEdit, an end-to-end framework equipped with a textual-visual dual-thinking mechanism. It combines a frozen Qwen2.5-VL for physically grounded reasoning with learnable transition queries that provide timestep-adaptive visual guidance to a diffusion backbone. Experiments show that PhysicEdit improves over Qwen-Image-Edit by 5.9% in physical realism and 10.1% in knowledge-grounded editing, setting a new state-of-the-art for open-source methods, while remaining competitive with leading proprietary models. --- ### Easy to Learn, Yet Hard to Forget: Towards Robust Unlearning Under Bias Authors: JuneHyoung Kwon, MiHyeon Kim, Eunju Lee, Yoonji Lee, Seunghoon Lee, YoungBin Kim Published: 2026-02-25 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2602.21773v1 Machine unlearning, which enables a model to forget specific data, is crucial for ensuring data privacy and model reliability. However, its effectiveness can be severely undermined in real-world scenarios where models learn unintended biases from spurious correlations within the data. This paper investigates the unique challenges of unlearning from such biased models. We identify a novel phenomenon we term ``shortcut unlearning," where models exhibit an ``easy to learn, yet hard to forget" tendency. Specifically, models struggle to forget easily-learned, bias-aligned samples; instead of forgetting the class attribute, they unlearn the bias attribute, which can paradoxically improve accuracy on the class intended to be forgotten. To address this, we propose CUPID, a new unlearning framework inspired by the observation that samples with different biases exhibit distinct loss landscape sharpness. Our method first partitions the forget set into causal- and bias-approximated subsets based on sample sharpness, then disentangles model parameters into causal and bias pathways, and finally performs a targeted update by routing refined causal and bias gradients to their respective pathways. Extensive experiments on biased datasets including Waterbirds, BAR, and Biased NICO++ demonstrate that our method achieves state-of-the-art forgetting performance and effectively mitigates the shortcut unlearning problem. --- ### UniWhisper: Efficient Continual Multi-task Training for Robust Universal Audio Representation Authors: Yuxuan Chen, Peize He, Haoyuan Yu, Junzi Zhang Published: 2026-02-25 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2602.21772v2 A universal audio representation should capture fine-grained speech cues and high-level semantics for environmental sounds and music in a single encoder. Existing encoders often excel in one domain but degrade in others. We propose UniWhisper, an efficient continual multi-task training framework that casts heterogeneous audio tasks into a unified instruction and answer format. This enables standard next-token training without task-specific heads and losses. We train it on 38k hours of public audio and assess the encoder using shallow MLP probes and k-nearest neighbors (kNN) on 20 tasks spanning speech, environmental sound, and music. UniWhisper reaches normalized weighted averages of 0.81 with MLP probes and 0.61 with kNN, compared to 0.64 and 0.46 for Whisper, while retaining strong speech performance. --- ### RAMSeS: Robust and Adaptive Model Selection for Time-Series Anomaly Detection Algorithms Authors: Mohamed Abdelmaksoud, Sheng Ding, Andrey Morozov, Ziawasch Abedjan Published: 2026-02-25 Categories: cs.DB, cs.LG arXiv: https://arxiv.org/abs/2602.21766v1 Time-series data vary widely across domains, making a universal anomaly detector impractical. Methods that perform well on one dataset often fail to transfer because what counts as an anomaly is context dependent. The key challenge is to design a method that performs well in specific contexts while remaining adaptable across domains with varying data complexities. We present the Robust and Adaptive Model Selection for Time-Series Anomaly Detection RAMSeS framework. RAMSeS comprises two branches: (i) a stacking ensemble optimized with a genetic algorithm to leverage complementary detectors. (ii) An adaptive model-selection branch identifies the best single detector using techniques including Thompson sampling, robustness testing with generative adversarial networks, and Monte Carlo simulations. This dual strategy exploits the collective strength of multiple models and adapts to dataset-specific characteristics. We evaluate RAMSeS and show that it outperforms prior methods on F1. --- ### Generalisation of RLHF under Reward Shift and Clipped KL Regularisation Authors: Kenton Tang, Yuzhu Chen, Fengxiang He Published: 2026-02-25 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2602.21765v1 Alignment and adaptation in large language models heavily rely on reinforcement learning from human feedback (RLHF); yet, theoretical understanding of its generalisability remains premature, especially when the learned reward could shift, and the KL control is estimated and clipped. To address this issue, we develop generalisation theory for RLHF that explicitly accounts for (1) \emph{reward shift}: reward models are trained on preference data from earlier or mixed behaviour policies while RLHF optimises the current policy on its own rollouts; and (2) \emph{clipped KL regularisation}: the KL regulariser is estimated from sampled log-probability ratios and then clipped for stabilisation, resulting in an error to RLHF. We present generalisation bounds for RLHF, suggesting that the generalisation error stems from a sampling error from prompts and rollouts, a reward shift error, and a KL clipping error. We also discuss special cases of (1) initialising RLHF parameters with a uniform prior over a finite space, and (2) training RLHF by stochastic gradient descent, as an Ornstein-Uhlenbeck process. The theory yields practical implications in (1) optimal KL clipping threshold, and (2) budget allocation in prompts, rollouts, and preference data. --- ### Improving Implicit Discourse Relation Recognition with Natural Language Explanations from LLMs Authors: Heng Wang, Changxing Wu Published: 2026-02-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.21763v1 Implicit Discourse Relation Recognition (IDRR) remains a challenging task due to the requirement for deep semantic understanding in the absence of explicit discourse markers. A further limitation is that existing methods only predict relations without providing any supporting explanations. Recent advances in large language models (LLMs) have shown strong reasoning capabilities in both deep language understanding and natural language explanation generation. In this work, we propose a simple yet effective approach to distill the reasoning capabilities of LLMs into lightweight IDRR models to improve both performance and interpretability. Specifically, we first prompt an LLM to generate explanations for each training instance conditioned on its gold label. Then, we introduce a novel classification-generation framework that jointly performs relation prediction and explanation generation, and train it with the additional supervision of LLM-generated explanations. Our framework is plug-and-play, enabling easy integration with most existing IDRR models. Experimental results on PDTB demonstrate that our approach significantly improves IDRR performance, while human evaluation further confirms that the generated explanations enhance model interpretability. Furthermore, we validate the generality of our approach on sentiment classification and natural language inference --- ### SAPNet++: Evolving Point-Prompted Instance Segmentation with Semantic and Spatial Awareness Authors: Zhaoyang Wei, Xumeng Han, Xuehui Yu, Xue Yang, Guorong Li, Zhenjun Han, Jianbin Jiao Published: 2026-02-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.21762v1 Single-point annotation is increasingly prominent in visual tasks for labeling cost reduction. However, it challenges tasks requiring high precision, such as the point-prompted instance segmentation (PPIS) task, which aims to estimate precise masks using single-point prompts to train a segmentation network. Due to the constraints of point annotations, granularity ambiguity and boundary uncertainty arise the difficulty distinguishing between different levels of detail (eg. whole object vs. parts) and the challenge of precisely delineating object boundaries. Previous works have usually inherited the paradigm of mask generation along with proposal selection to achieve PPIS. However, proposal selection relies solely on category information, failing to resolve the ambiguity of different granularity. Furthermore, mask generators offer only finite discrete solutions that often deviate from actual masks, particularly at boundaries. To address these issues, we propose the Semantic-Aware Point-Prompted Instance Segmentation Network (SAPNet). It integrates Point Distance Guidance and Box Mining Strategy to tackle group and local issues caused by the point's granularity ambiguity. Additionally, we incorporate completeness scores within proposals to add spatial granularity awareness, enhancing multiple instance learning (MIL) in proposal selection termed S-MIL. The Multi-level Affinity Refinement conveys pixel and semantic clues, narrowing boundary uncertainty during mask refinement. These modules culminate in SAPNet++, mitigating point prompt's granularity ambiguity and boundary uncertainty and significantly improving segmentation performance. Extensive experiments on four challenging datasets validate the effectiveness of our methods, highlighting the potential to advance PPIS. --- ### Survey on Neural Routing Solvers Authors: Yunpeng Ba, Xi Lin, Changliang Zhou, Ruihao Zheng, Zhenkun Wang, Xinyan Liang, Zhichao Lu, Jianyong Sun, Yuhua Qian, Qingfu Zhang Published: 2026-02-25 Categories: math.OC, cs.AI, cs.LG, cs.NE arXiv: https://arxiv.org/abs/2602.21761v2 Neural routing solvers (NRSs) that leverage deep learning to tackle vehicle routing problems have demonstrated notable potential for practical applications. By learning implicit heuristic rules from data, NRSs replace the handcrafted counterparts in classic heuristic frameworks, thereby reducing reliance on costly manual design and trial-and-error adjustments. This survey makes two main contributions: (1) The heuristic nature of NRSs is highlighted, and existing NRSs are reviewed from the perspective of heuristics. A hierarchical taxonomy based on heuristic principles is further introduced. (2) A generalization-focused evaluation pipeline is proposed to address limitations of the conventional pipeline. Comparative benchmarking of representative NRSs across both pipelines uncovers a series of previously unreported gaps in current research. ---