# Research Papers — 2025-12 · bundle page 49 of 175 > Full-text markdown of papers #2401–2450 of 8703 published in 2025-12, newest first. AI-readable mirrors of the full 8703-paper 2025-12 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2025-12/page/49 [← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/48.md) [Next bundle →](https://aipod.dev/papers/archive/2025-12/page/50.md) ### Research on a hybrid LSTM-CNN-Attention model for text-based web content classification Authors: Mykola Kuz, Ihor Lazarovych, Mykola Kozlenko, Mykola Pikuliak, Andrii Kvasniuk Published: 2025-12-20 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2512.18475v2 This study presents a hybrid deep learning architecture that integrates LSTM, CNN, and an Attention mechanism to enhance the classification of web content based on text. Pretrained GloVe embeddings are used to represent words as dense vectors that preserve semantic similarity. The CNN layer extracts local n-gram patterns and lexical features, while the LSTM layer models long-range dependencies and sequential structure. The integrated Attention mechanism enables the model to focus selectively on the most informative parts of the input sequence. A 5-fold cross-validation setup was used to assess the robustness and generalizability of the proposed solution. Experimental results show that the hybrid LSTM-CNN-Attention model achieved outstanding performance, with an accuracy of 0.98, precision of 0.94, recall of 0.92, and F1-score of 0.93. These results surpass the performance of baseline models based solely on CNNs, LSTMs, or transformer-based classifiers such as BERT. The combination of neural network components enabled the model to effectively capture both fine-grained text structures and broader semantic context. Furthermore, the use of GloVe embeddings provided an efficient and effective representation of textual data, making the model suitable for integration into systems with real-time or near-real-time requirements. The proposed hybrid architecture demonstrates high effectiveness in text-based web content classification, particularly in tasks requiring both syntactic feature extraction and semantic interpretation. By combining presented mechanisms, the model addresses the limitations of individual architectures and achieves improved generalization. These findings support the broader use of hybrid deep learning approaches in NLP applications, especially where complex, unstructured textual data must be processed and classified with high reliability. --- ### APC-GNN++: An Adaptive Patient-Centric GNN with Context-Aware Attention and Mini-Graph Explainability for Diabetes Classification Authors: Khaled Berkani Published: 2025-12-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.18473v1 We propose APC-GNN++, an adaptive patient-centric Graph Neural Network for diabetes classification. Our model integrates context-aware edge attention, confidence-guided blending of node features and graph representations, and neighborhood consistency regularization to better capture clinically meaningful relationships between patients. To handle unseen patients, we introduce a mini-graph approach that leverages the nearest neighbors of the new patient, enabling real-time explainable predictions without retraining the global model. We evaluate APC-GNN++ on a real-world diabetes dataset collected from a regional hospital in Algeria and show that it outperforms traditional machine learning models (MLP, Random Forest, XGBoost) and a vanilla GCN, achieving higher test accuracy and macro F1- score. The analysis of node-level confidence scores further reveals how the model balances self-information and graph-based evidence across different patient groups, providing interpretable patient-centric insights. The system is also embedded in a Tkinter-based graphical user interface (GUI) for interactive use by healthcare professionals . --- ### The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning Authors: Xin Li Published: 2025-12-20 Categories: cs.LG, q-bio.NC arXiv: https://arxiv.org/abs/2512.18471v2 Continual learning systems face a fundamental geometric obstacle: as experience accumulates on a fixed-capacity manifold, covering numbers grow linearly with time, eventually forcing representational overlap and catastrophic interference. Prevailing approaches attack this problem by \emph{expansion} - projecting into higher-dimensional spaces via kernels, overparameterization, or replay. We argue the solution is the opposite: \emph{contraction}. We formalize abstraction as the \textbf{Urysohn Ladder}, a hierarchy of quotient maps that recursively collapse validated metric neighborhoods into compact tokens, converting unbounded ambient-space search into bounded navigation on a low-dimensional intrinsic scaffold. Geometrically, each collapsed token acts as a shortcut - a region of extreme metric contraction that bridges distant experiences, much like a wormhole in the representational manifold. We establish four results that collectively guarantee \emph{separability} (metric contraction renders nonlinearly entangled structure linearly separable at each quotient level, and this separability propagates faithfully through the entire hierarchy), \emph{bounded capacity} (covering numbers remain $O(1)$ per quotient level, independent of stream length), \emph{stability} (parity-partitioned flow/scaffold subspaces enable unbounded plasticity without catastrophic interference), and \emph{scalability} (inference cost scales with quotient distance, not ambient distance). We validate each claim empirically with pretrained models and real-world datasets. Moreover, we demonstrate the potential of Urysohn Ladder for scalable continual learning via scaffold amortization. --- ### SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarios Authors: Tue Le, Minh V. T. Thai, Dung Nguyen Manh, Huy Phan Nhat, Nghi D. Q. Bui Published: 2025-12-20 Categories: cs.SE, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2512.18470v6 Existing benchmarks for AI coding agents focus on isolated, single-issue tasks such as fixing a bug or adding a small feature. However, real-world software engineering is a long-horizon endeavor: developers interpret high-level requirements, coordinate changes across many files, and evolve codebases over multiple iterations while preserving functionality. We introduce SWE-EVO, a benchmark for this long-horizon software evolution challenge. Constructed from release notes of seven mature open-source Python projects, SWE-EVO comprises 48 tasks requiring multi-step modifications spanning an average of 21 files, validated against test suites averaging 874 tests per instance. Experiments reveal a striking capability gap: GPT-5.4 with OpenHands achieves only 25% on SWE-EVO versus 72.80% achieved by GPT-5.2 on SWE-Bench Verified, showing that current agents struggle with sustained, multi-file reasoning. We also propose Fix Rate, a metric capturing partial progress on these complex, long-horizon tasks. --- ### Self-organizing maps for water quality assessment in reservoirs and lakes: A systematic literature review Authors: Oraib Almegdadi, João Marcelino, Sarah Fakhreddine, João Manso, Nuno C. Marques Published: 2025-12-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.18466v1 Sustainable water quality underpins ecological balance and water security. Assessing and managing lakes and reservoirs is difficult due to data sparsity, heterogeneity, and nonlinear relationships among parameters. This review examines how Self-Organizing Map (SOM), an unsupervised AI technique, is applied to water quality assessment. It synthesizes research on parameter selection, spatial and temporal sampling strategies, and clustering approaches. Emphasis is placed on how SOM handles multidimensional data and uncovers hidden patterns to support effective water management. The growing availability of environmental data from in-situ sensors, remote sensing imagery, IoT technologies, and historical records has significantly expanded analytical opportunities in environmental monitoring. SOM has proven effective in analysing complex datasets, particularly when labelled data are limited or unavailable. It enables high-dimensional data visualization, facilitates the detection of hidden ecological patterns, and identifies critical correlations among diverse water quality indicators. This review highlights SOMs versatility in ecological assessments, trophic state classification, algal bloom monitoring, and catchment area impact evaluations. The findings offer comprehensive insights into existing methodologies, supporting future research and practical applications aimed at improving the monitoring and sustainable management of lake and reservoir ecosystems. --- ### Mitigating Spurious Correlations in NLI via LLM-Synthesized Counterfactuals and Dynamic Balanced Sampling Authors: Christopher Román Jaimes Published: 2025-12-20 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.18462v1 Natural Language Inference (NLI) models frequently rely on spurious correlations rather than semantic reasoning. Existing mitigation strategies often incur high annotation costs or trigger catastrophic forgetting during fine-tuning. We propose an automated, scalable pipeline to address these limitations. First, we introduce Log-Frequency LMI (LF-LMI) to accurately detect semantic artifacts. Second, we generate a high-quality synthetic contrast set via an LLM-synthesis pipeline with multi-judge verification. Finally, we introduce Dynamic Balanced Sampling, a training strategy that rotates the original data distribution to prevent forgetting. Our method improves consistency on a challenging benchmark from 63.5% to 81.0% while maintaining 88.4% in-domain accuracy, significantly outperforming naive fine-tuning. --- ### SoK: Understanding (New) Security Issues Across AI4Code Use Cases Authors: Qilong Wu, Taoran Li, Tianyang Zhou, Varun Chandrasekaran Published: 2025-12-20 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2512.18456v1 AI-for-Code (AI4Code) systems are reshaping software engineering, with tools like GitHub Copilot accelerating code generation, translation, and vulnerability detection. Alongside these advances, however, security risks remain pervasive: insecure outputs, biased benchmarks, and susceptibility to adversarial manipulation undermine their reliability. This SoK surveys the landscape of AI4Code security across three core applications, identifying recurring gaps: benchmark dominance by Python and toy problems, lack of standardized security datasets, data leakage in evaluation, and fragile adversarial robustness. A comparative study of six state-of-the-art models illustrates these challenges: insecure patterns persist in code generation, vulnerability detection is brittle to semantic-preserving attacks, fine-tuning often misaligns security objectives, and code translation yields uneven security benefits. From this analysis, we distill three forward paths: embedding secure-by-default practices in code generation, building robust and comprehensive detection benchmarks, and leveraging translation as a route to security-enhanced languages. We call for a shift toward security-first AI4Code, where vulnerability mitigation and robustness are embedded throughout the development life cycle. --- ### Plasticine: A Traceable Diffusion Model for Medical Image Translation Authors: Tianyang Zhang, Xinxing Cheng, Jun Cheng, Shaoming Zheng, He Zhao, Huazhu Fu, Alejandro F Frangi, Jiang Liu, Jinming Duan Published: 2025-12-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.18455v2 Domain gaps arising from variations in imaging devices and population distributions pose significant challenges for machine learning in medical image analysis. Existing image-to-image translation methods primarily aim to learn mappings between domains, often generating diverse synthetic data with variations in anatomical scale and shape, but they usually overlook spatial correspondence during the translation process. For clinical applications, traceability, defined as the ability to provide pixel-level correspondences between original and translated images, is equally important. This property enhances clinical interpretability but has been largely overlooked in previous approaches. To address this gap, we propose Plasticine, which is, to the best of our knowledge, the first end-to-end image-to-image translation framework explicitly designed with traceability as a core objective. Our method combines intensity translation and spatial transformation within a denoising diffusion framework. This design enables the generation of synthetic images with interpretable intensity transitions and spatially coherent deformations, supporting pixel-wise traceability throughout the translation process. --- ### Out-of-Distribution Detection in Molecular Complexes via Diffusion Models for Irregular Graphs Authors: David Graber, Victor Armegioiu, Rebecca Buller, Siddhartha Mishra Published: 2025-12-20 Categories: cs.LG, q-bio.QM arXiv: https://arxiv.org/abs/2512.18454v3 Predictive machine learning models generally excel on in-distribution data, but their performance degrades on out-of-distribution (OOD) inputs. Reliable deployment therefore requires robust OOD detection, yet this is particularly challenging for irregular 3D graphs that combine continuous geometry with categorical identities and are unordered by construction. Here, we present a probabilistic OOD detection framework for complex 3D graph data built on a diffusion model that learns a density of the training distribution in a fully unsupervised manner. A key ingredient we introduce is a unified continuous diffusion over both 3D coordinates and discrete features: categorical identities are embedded in a continuous space and trained with cross-entropy, while the corresponding diffusion score is obtained analytically via posterior-mean interpolation from predicted class probabilities. This yields a single self-consistent probability-flow ODE (PF-ODE) that produces per-sample log-likelihoods, providing a principled typicality score for distribution shift. We validate the approach on protein-ligand complexes and construct strict OOD datasets by withholding entire protein families from training. PF-ODE likelihoods identify held-out families as OOD and correlate strongly with prediction errors of an independent binding-affinity model (GEMS), enabling a priori reliability estimates on new complexes. Beyond scalar likelihoods, we show that multi-scale PF-ODE trajectory statistics - including path tortuosity, flow stiffness, and vector-field instability - provide complementary OOD information. Modeling the joint distribution of these trajectory features yields a practical, high-sensitivity detector that improves separation over likelihood-only baselines, offering a label-free OOD quantification workflow for geometric deep learning. --- ### NOVA: Discovering Well-Conditioned Winograd Transforms through Numerical Optimization of Vandermonde Arithmetic Authors: Jayant Lohia Published: 2025-12-20 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2512.18453v1 Winograd convolution is the standard algorithm for efficient inference, reducing arithmetic complexity by 2.25x for 3x3 kernels. However, it faces a critical barrier in the modern era of low precision computing: numerical instability. As tiles scale to maximize efficiency (e.g., F(6,3), F(8,3)), the condition numbers of standard integer based transforms explode, reaching kappa = 2 x 10^5 for F(8,3), rendering them unusable in FP16 or Int8. We introduce NOVA (Numerical Optimization of Vandermonde Arithmetic), a discovery framework that breaks the decades old convention of integer interpolation. Treating Winograd point selection as a continuous optimization problem, NOVA searches the manifold R^n-1 via Evolution Strategy, snaps candidates to simple rationals, and guarantees correctness via symbolic verification. This process uncovers a hidden landscape of stable, fractional configurations such as {+-5/6, +-7/6, +-3/5} that defy traditional vocabulary constraints. The impact is transformative: NOVA improves the conditioning of F(8,3) by 415x in 1D, which squares to a 172,484x improvement for 2D convolution. In real world FP16 ImageNet inference, where standard transforms collapse to random chance (e.g., 4.7 percent accuracy on VGG16), NOVA's points restore full accuracy (75 to 78 percent), recovering over 70 percentage points without retraining, calibration, or learned parameters. These discovered transforms act as drop in replacements, effectively unlocking the efficiency of large tile Winograd convolution for next generation hardware. --- ### Secret mixtures of experts inside your LLM Authors: Enric Boix-Adsera Published: 2025-12-20 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2512.18452v1 Despite being one of the earliest neural network layers, the Multilayer Perceptron (MLP) is arguably one of the least understood parts of the transformer architecture due to its dense computation and lack of easy visualization. This paper seeks to understand the MLP layers in dense LLM models by hypothesizing that these layers secretly approximately perform a sparse computation -- namely, that they can be well approximated by sparsely-activating Mixture of Experts (MoE) layers. Our hypothesis is based on a novel theoretical connection between MoE models and Sparse Autoencoder (SAE) structure in activation space. We empirically validate the hypothesis on pretrained LLMs, and demonstrate that the activation distribution matters -- these results do not hold for Gaussian data, but rather rely crucially on structure in the distribution of neural network activations. Our results shine light on a general principle at play in MLP layers inside LLMs, and give an explanation for the effectiveness of modern MoE-based transformers. Additionally, our experimental explorations suggest new directions for more efficient MoE architecture design based on low-rank routers. --- ### Agent-Based Output Drift Detection for Breast Cancer Response Prediction in a Multisite Clinical Decision Support System Authors: Xavier Rafael-Palou, Jose Munuera, Ana Jimenez-Pastor, Richard Osuala, Karim Lekadir, Oliver Diaz Published: 2025-12-20 Categories: cs.AI, cs.CV, cs.MA arXiv: https://arxiv.org/abs/2512.18450v1 Modern clinical decision support systems can concurrently serve multiple, independent medical imaging institutions, but their predictive performance may degrade across sites due to variations in patient populations, imaging hardware, and acquisition protocols. Continuous surveillance of predictive model outputs offers a safe and reliable approach for identifying such distributional shifts without ground truth labels. However, most existing methods rely on centralized monitoring of aggregated predictions, overlooking site-specific drift dynamics. We propose an agent-based framework for detecting drift and assessing its severity in multisite clinical AI systems. To evaluate its effectiveness, we simulate a multi-center environment for output-based drift detection, assigning each site a drift monitoring agent that performs batch-wise comparisons of model outputs against a reference distribution. We analyse several multi-center monitoring schemes, that differ in how the reference is obtained (site-specific, global, production-only and adaptive), alongside a centralized baseline. Results on real-world breast cancer imaging data using a pathological complete response prediction model shows that all multi-center schemes outperform centralized monitoring, with F1-score improvements up to 10.3% in drift detection. In the absence of site-specific references, the adaptive scheme performs best, with F1-scores of 74.3% for drift detection and 83.7% for drift severity classification. These findings suggest that adaptive, site-aware agent-based drift monitoring can enhance reliability of multisite clinical decision support systems. --- ### Object-Centric Framework for Video Moment Retrieval Authors: Zongyao Li, Yongkang Wong, Satoshi Yamazaki, Jianquan Liu, Mohan Kankanhalli Published: 2025-12-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.18448v1 Most existing video moment retrieval methods rely on temporal sequences of frame- or clip-level features that primarily encode global visual and semantic information. However, such representations often fail to capture fine-grained object semantics and appearance, which are crucial for localizing moments described by object-oriented queries involving specific entities and their interactions. In particular, temporal dynamics at the object level have been largely overlooked, limiting the effectiveness of existing approaches in scenarios requiring detailed object-level reasoning. To address this limitation, we propose a novel object-centric framework for moment retrieval. Our method first extracts query-relevant objects using a scene graph parser and then generates scene graphs from video frames to represent these objects and their relationships. Based on the scene graphs, we construct object-level feature sequences that encode rich visual and semantic information. These sequences are processed by a relational tracklet transformer, which models spatio-temporal correlations among objects over time. By explicitly capturing object-level state changes, our framework enables more accurate localization of moments aligned with object-oriented queries. We evaluated our method on three benchmarks: Charades-STA, QVHighlights, and TACoS. Experimental results demonstrate that our method outperforms existing state-of-the-art methods across all benchmarks. --- ### On the Universality of Transformer Architectures; How Much Attention Is Enough? Authors: Amirreza Abbasi, Mohsen Hooshmand Published: 2025-12-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.18445v1 Transformers are crucial across many AI fields, such as large language models, computer vision, and reinforcement learning. This prominence stems from the architecture's perceived universality and scalability compared to alternatives. This work examines the problem of universality in Transformers, reviews recent progress, including architectural refinements such as structural minimality and approximation rates, and surveys state-of-the-art advances that inform both theoretical and practical understanding. Our aim is to clarify what is currently known about Transformers expressiveness, separate robust guarantees from fragile ones, and identify key directions for future theoretical research. --- ### Snowveil: A Framework for Decentralised Preference Discovery Authors: Grammateia Kotsialou Published: 2025-12-20 Categories: cs.GT, cs.AI, cs.DC, cs.MA arXiv: https://arxiv.org/abs/2512.18444v2 Aggregating subjective preferences in social choice traditionally assumes a trusted central authority. In contrast, this paper formalises Decentralised Preference Discovery (DPD): the reliable identification of a social choice parameter (e.g. the canonical outcome of an aggregation rule applied to the global preference profile) under conditions of partial information, asynchronous interaction, censorship resistance, and no central coordinator. To address DPD, we propose Snowveil, a gossip-based framework where agents repeatedly sample random peer rankings and update local beliefs to converge on the canonical outcome. Using a potential function, submartingale theory, and concentration bounds, we prove the system reaches this stable state with tunable high probability, in finite expected time. This single-winner process can then be iterated to construct a set of winning candidates for multi-winner scenarios. Snowveil is agnostic to specific aggregation rules, requiring only that the rule satisfies axioms such as Positive Responsiveness, thus offering a formal basis for a wider class of DPD protocols. Demonstrating Snowveil's modularity, we introduce the Constrained Hybrid Borda (CHB), an aggregation rule designed to balance broad consensus with plurality support. We provide an axiomatic analysis of CHB and present empirical results via extensive simulation, validating Snowveil's O(n) scalability. Overall, this work provides a foundation for how a stable consensus emerges from subjective, expressive, and diverse preference profiles in large-scale decentralised systems. --- ### A Distributed Hierarchical Spatio-Temporal Edge-Enhanced Graph Neural Network for City-Scale Dynamic Logistics Routing Authors: Zihan Han, Lingran Meng, Jingwei Zhang Published: 2025-12-20 Categories: eess.SY, cs.AI arXiv: https://arxiv.org/abs/2512.18441v1 City-scale logistics routing has become increasingly challenging as metropolitan road networks grow to tens of millions of edges and traffic conditions evolve rapidly under high-volume mobility demands. Conventional centralized routing algorithms and monolithic graph neural network (GNN) models suffer from limited scalability, high latency, and poor real-time adaptability, which restricts their effectiveness in large urban logistics systems. To address these challenges, this paper proposes a Distributed Hierarchical Spatio-Temporal Edge-Enhanced Graph Neural Network (HSTE-GNN) for dynamic routing over ultra-large road networks. The framework partitions the city-scale graph into regional subgraphs processed in parallel across distributed computing nodes, enabling efficient learning of localized traffic dynamics. Within each region, an edge-enhanced spatio-temporal module jointly models node states, dynamic edge attributes, and short-term temporal dependencies. A hierarchical coordination layer further aggregates cross-region representations through an asynchronous parameter-server mechanism, ensuring global routing coherence under high-frequency traffic updates. This distributed hierarchical design balances local responsiveness with global consistency, significantly improving scalability and inference efficiency. Experiments on real-world large-scale traffic datasets from Beijing and New York demonstrate that HSTE-GNN outperforms strong spatio-temporal baselines such as ST-GRAPH, achieving 34.9% lower routing delay, 14.7% lower MAPE, and 11.8% lower RMSE, while improving global route consistency by 7.3%. These results confirm that the proposed framework provides a scalable, adaptive, and efficient solution for next-generation intelligent transportation systems and large-scale logistics platforms. --- ### An Agentic AI Framework for Training General Practitioner Student Skills Authors: Victor De Marez, Jens Van Nooten, Luna De Bruyne, Walter Daelemans Published: 2025-12-20 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.18440v1 Advancements in large language models offer strong potential for enhancing virtual simulated patients (VSPs) in medical education by providing scalable alternatives to resource-intensive traditional methods. However, current VSPs often struggle with medical accuracy, consistent roleplaying, scenario generation for VSP use, and educationally structured feedback. We introduce an agentic framework for training general practitioner student skills that unifies (i) configurable, evidence-based vignette generation, (ii) controlled persona-driven patient dialogue with optional retrieval grounding, and (iii) standards-based assessment and feedback for both communication and clinical reasoning. We instantiate the framework in an interactive spoken consultation setting and evaluate it with medical students ($\mathbf{N{=}14}$). Participants reported realistic and vignette-faithful dialogue, appropriate difficulty calibration, a stable personality signal, and highly useful example-rich feedback, alongside excellent overall usability. These results support agentic separation of scenario control, interaction control, and standards-based assessment as a practical pattern for building dependable and pedagogically valuable VSP training tools. --- ### MeniMV: A Multi-view Benchmark for Meniscus Injury Severity Grading Authors: Shurui Xu, Siqi Yang, Jiapin Ren, Zhong Cao, Hongwei Yang, Mengzhen Fan, Yuyu Sun, Shuyan Li Published: 2025-12-20 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.18437v1 Precise grading of meniscal horn tears is critical in knee injury diagnosis but remains underexplored in automated MRI analysis. Existing methods often rely on coarse study-level labels or binary classification, lacking localization and severity information. In this paper, we introduce MeniMV, a multi-view benchmark dataset specifically designed for horn-specific meniscus injury grading. MeniMV comprises 3,000 annotated knee MRI exams from 750 patients across three medical centers, providing 6,000 co-registered sagittal and coronal images. Each exam is meticulously annotated with four-tier (grade 0-3) severity labels for both anterior and posterior meniscal horns, verified by chief orthopedic physicians. Notably, MeniMV offers more than double the pathology-labeled data volume of prior datasets while uniquely capturing the dual-view diagnostic context essential in clinical practice. To demonstrate the utility of MeniMV, we benchmark multiple state-of-the-art CNN and Transformer-based models. Our extensive experiments establish strong baselines and highlight challenges in severity grading, providing a valuable foundation for future research in automated musculoskeletal imaging. --- ### VeruSAGE: A Study of Agent-Based Verification for Rust Systems Authors: Chenyuan Yang, Natalie Neamtu, Chris Hawblitzel, Jacob R. Lorch, Shan Lu Published: 2025-12-20 Categories: cs.OS, cs.AI, cs.FL, cs.SE arXiv: https://arxiv.org/abs/2512.18436v2 Large language models (LLMs) have shown impressive capability to understand and develop code. However, their capability to rigorously reason about and prove code correctness remains in question. This paper offers a comprehensive study of LLMs' capability to develop correctness proofs for system software written in Rust. We curate a new system-verification benchmark suite, VeruSAGE-Bench, which consists of 849 proof tasks extracted from eight open-source Verus-verified Rust systems. Furthermore, we design different agent systems to match the strengths and weaknesses of different LLMs (o4-mini, GPT-5, Sonnet 4, and Sonnet 4.5). Our study shows that different tools and agent settings are needed to stimulate the system-verification capability of different types of LLMs. The best LLM-agent combination in our study completes over 80% of system-verification tasks in VeruSAGE-Bench. It also completes over 90% of a set of system proof tasks not part of VeruSAGE-Bench because they had not yet been finished by human experts. This result shows the great potential for LLM-assisted development of verified system software. --- ### Federated Learning Based Decentralized Adaptive Intelligent Transmission Protocol for Privacy Preserving 6G Networks Authors: Ansar Ahmed Published: 2025-12-20 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2512.18432v1 The move to 6th Generation (6G) wireless networks creates new issues with privacy, scalability, and adaptability. The data-intensive nature of 6G is not handled well by older, centralized network models. A shift toward more secure and decentralized systems is therefore required. A new framework called the Federated Learning-based Decentralized Adaptive Intelligent Transmission Protocol (AITP) is proposed to meet these challenges. The AITP uses the distributed learning of Federated Learning (FL) within a decentralized system. Transmission parameters can be adjusted intelligently in real time. User privacy is maintained by keeping raw data on local edge devices. The protocol's performance was evaluated with mathematical modeling and detailed simulations. It was shown to be superior to traditional non-adaptive and centralized AI methods across several key metrics. These included latency, network throughput, energy efficiency, and robustness. The AITP is presented as a foundational technology for future 6G networks that supports a user-centric, privacy-first design. This study is a step forward for privacy-preserving research in 6G. --- ### E-RGB-D: Real-Time Event-Based Perception with Structured Light Authors: Seyed Ehsan Marjani Bajestani, Giovanni Beltrame Published: 2025-12-20 Categories: cs.CV, eess.IV arXiv: https://arxiv.org/abs/2512.18429v2 Event-based cameras (ECs) have emerged as bio-inspired sensors that report pixel brightness changes asynchronously, offering unmatched speed and efficiency in vision sensing. Despite their high dynamic range, temporal resolution, low power consumption, and computational simplicity, traditional monochrome ECs face limitations in detecting static or slowly moving objects and lack color information essential for certain applications. To address these challenges, we present a novel approach that integrates a Digital Light Processing (DLP) projector, forming Active Structured Light (ASL) for RGB-D sensing. By combining the benefits of ECs and projection-based techniques, our method enables the detection of color and the depth of each pixel separately. Dynamic projection adjustments optimize bandwidth, ensuring selective color data acquisition and yielding colorful point clouds without sacrificing spatial resolution. This integration, facilitated by a commercial TI LightCrafter 4500 projector and a monocular monochrome EC, not only enables frameless RGB-D sensing applications but also achieves remarkable performance milestones. With our approach, we achieved a color detection speed equivalent to 1400 fps and 4 kHz of pixel depth detection, significantly advancing the realm of computer vision across diverse fields from robotics to 3D reconstruction methods. Our code is publicly available: https://github.com/MISTLab/event_based_rgbd_ros --- ### MoE Pathfinder: Trajectory-driven Expert Pruning Authors: Xican Yang, Yuanhe Tian, Yan Song Published: 2025-12-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.18425v1 Mixture-of-experts (MoE) architectures used in large language models (LLMs) achieve state-of-the-art performance across diverse tasks yet face practical challenges such as deployment complexity and low activation efficiency. Expert pruning has thus emerged as a promising solution to reduce computational overhead and simplify the deployment of MoE models. However, existing expert pruning approaches conventionally rely on local importance metrics and often apply uniform layer-wise pruning, leveraging only partial evaluation signals and overlooking the heterogeneous contributions of experts across layers. To address these limitations, we propose an expert pruning approach based on the trajectory of activated experts across layers, which treats MoE as a weighted computation graph and casts expert selection as a global optimal path planning problem. Within this framework, we integrate complementary importance signals from reconstruction error, routing probabilities, and activation strength at the trajectory level, which naturally yields non-uniform expert retention across layers. Experiments show that our approach achieves superior pruning performance on nearly all tasks compared with most existing approaches. --- ### Few-Shot Learning of a Graph-Based Neural Network Model Without Backpropagation Authors: Mykyta Lapin, Kostiantyn Bokhan, Yurii Parzhyn Published: 2025-12-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.18412v1 We propose a structural-graph approach to classifying contour images in a few-shot regime without using backpropagation. The core idea is to make structure the carrier of explanations: an image is encoded as an attributed graph (critical points and lines represented as nodes with geometric attributes), and generalization is achieved via the formation of concept attractors (class-level concept graphs). Purpose. To design and experimentally validate an architecture in which class concepts are formed from a handful of examples (5 - 6 per class) through structural and parametric reductions, providing transparent decisions and eliminating backpropagation. Methods. Contour vectorization is followed by constructing a bipartite graph (Point/Line as nodes) with normalized geometric attributes such as coordinates, length, angle, and direction; reductions include the elimination of unstable substructures or noise and the alignment of paths between critical points. Concepts are formed by iterative composition of samples, and classification is performed by selecting the best graph-to-concept match (using approximated GED). Results. On an MNIST subset with 5 - 6 base examples per class (single epoch), we obtain a consistent accuracy of around 82% with full traceability of decisions: misclassifications can be explained by explicit structural similarities. An indicative comparison with SVM, MLP, CNN, as well as metric and meta-learning baselines, is provided. The structural-graph scheme with concept attractors enables few-shot learning without backpropagation and offers built-in explanations through the explicit graph structure. Limitations concern the computational cost of GED and the quality of skeletonization; promising directions include classification-algorithm optimization, work with static scenes, and associative recognition. --- ### AmPLe: Supporting Vision-Language Models via Adaptive-Debiased Ensemble Multi-Prompt Learning Authors: Fei Song, Yi Li, Jiangmeng Li, Rui Wang, Changwen Zheng, Fanjiang Xu, Hui Xiong Published: 2025-12-20 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.18411v1 Multi-prompt learning methods have emerged as an effective approach for facilitating the rapid adaptation of vision-language models to downstream tasks with limited resources. Existing multi-prompt learning methods primarily focus on utilizing various meticulously designed prompts within a single foundation vision-language model to achieve superior performance. However, the overlooked model-prompt matching bias hinders the development of multi-prompt learning, i.e., the same prompt can convey different semantics across distinct vision-language models, such as CLIP-ViT-B/16 and CLIP-ViT-B/32, resulting in inconsistent predictions of identical prompt. To mitigate the impact of this bias on downstream tasks, we explore an ensemble learning approach to sufficiently aggregate the benefits of diverse predictions. Additionally, we further disclose the presence of sample-prompt matching bias, which originates from the prompt-irrelevant semantics encapsulated in the input samples. Thus, directly utilizing all information from the input samples for generating weights of ensemble learning can lead to suboptimal performance. In response, we extract prompt-relevant semantics from input samples by leveraging the guidance of the information theory-based analysis, adaptively calculating debiased ensemble weights. Overall, we propose Adaptive-Debiased Ensemble MultiPrompt Learning, abbreviated as AmPLe, to mitigate the two types of bias simultaneously. Extensive experiments on three representative tasks, i.e., generalization to novel classes, new target datasets, and unseen domain shifts, show that AmPLe can widely outperform existing methods. Theoretical validation from a causal perspective further supports the effectiveness of AmPLe. --- ### Why Most Optimism Bandit Algorithms Have the Same Regret Analysis: A Simple Unifying Theorem Authors: Vikram Krishnamurthy Published: 2025-12-20 Categories: cs.LG, eess.SY, stat.ML arXiv: https://arxiv.org/abs/2512.18409v1 Several optimism-based stochastic bandit algorithms -- including UCB, UCB-V, linear UCB, and finite-arm GP-UCB -- achieve logarithmic regret using proofs that, despite superficial differences, follow essentially the same structure. This note isolates the minimal ingredients behind these analyses: a single high-probability concentration condition on the estimators, after which logarithmic regret follows from two short deterministic lemmas describing radius collapse and optimism-forced deviations. The framework yields unified, near-minimal proofs for these classical algorithms and extends naturally to many contemporary bandit variants. --- ### Through the PRISm: Importance-Aware Scene Graphs for Image Retrieval Authors: Dimitrios Georgoulopoulos, Nikolaos Chaidos, Angeliki Dimitriou, Giorgos Stamou Published: 2025-12-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.18407v1 Accurately retrieving images that are semantically similar remains a fundamental challenge in computer vision, as traditional methods often fail to capture the relational and contextual nuances of a scene. We introduce PRISm (Pruning-based Image Retrieval via Importance Prediction on Semantic Graphs), a multimodal framework that advances image-to-image retrieval through two novel components. First, the Importance Prediction Module identifies and retains the most critical objects and relational triplets within an image while pruning irrelevant elements. Second, the Edge-Aware Graph Neural Network explicitly encodes relational structure and integrates global visual features to produce semantically informed image embeddings. PRISm achieves image retrieval that closely aligns with human perception by explicitly modeling the semantic importance of objects and their interactions, capabilities largely absent in prior approaches. Its architecture effectively combines relational reasoning with visual representation, enabling semantically grounded retrieval. Extensive experiments on benchmark and real-world datasets demonstrate consistently superior top-ranked performance, while qualitative analyses show that PRISm accurately captures key objects and interactions, producing interpretable and semantically meaningful results. --- ### Automated Mosaic Tesserae Segmentation via Deep Learning Techniques Authors: Charilaos Kapelonis, Marios Antonakakis, Konstantinos Politof, Aristomenis Antoniadis, Michalis Zervakis Published: 2025-12-20 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2512.18406v1 Art is widely recognized as a reflection of civilization and mosaics represent an important part of cultural heritage. Mosaics are an ancient art form created by arranging small pieces, called tesserae, on a surface using adhesive. Due to their age and fragility, they are prone to damage, highlighting the need for digital preservation. This paper addresses the problem of digitizing mosaics by segmenting the tesserae to separate them from the background within the broader field of Image Segmentation in Computer Vision. We propose a method leveraging Segment Anything Model 2 (SAM 2) by Meta AI, a foundation model that outperforms most conventional segmentation models, to automatically segment mosaics. Due to the limited open datasets in the field, we also create an annotated dataset of mosaic images to fine-tune and evaluate the model. Quantitative evaluation on our testing dataset shows notable improvements compared to the baseline SAM 2 model, with Intersection over Union increasing from 89.00% to 91.02% and Recall from 92.12% to 95.89%. Additionally, on a benchmark proposed by a prior approach, our model achieves an F-measure 3% higher than previous methods and reduces the error in the absolute difference between predicted and actual tesserae from 0.20 to just 0.02. The notable performance of the fine-tuned SAM 2 model together with the newly annotated dataset can pave the way for real-time segmentation of mosaic images. --- ### AraToken: Optimizing Arabic Tokenization with Normalization Pipeline and Language Extension for Qwen3 Authors: Mark Kashirskiy, Artiom Lipinski, Ilya Makarov Published: 2025-12-20 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.18399v1 Tokenization is a critical preprocessing step for large language models (LLMs), directly impacting training efficiency and downstream performance. General-purpose tokenizers trained predominantly on English and Latin-script languages exhibit suboptimal performance on morphologically rich languages such as Arabic, resulting in inflated token sequences and reduced compression efficiency. In this work, we present AraToken, an Arabic-optimized tokenizer built on SentencePiece Unigram algorithm with a comprehensive normalization pipeline addressing Arabic-specific orthographic variations including Alif variants, diacritics, and Arabic-Indic numerals. We systematically compare BPE, WordPiece, and SentencePiece algorithms across multiple configurations, demonstrating that SentencePiece with normalization achieves 18% lower fertility (1.199 vs 1.35 tokens/word) compared to unnormalized baselines. Furthermore, we introduce the Language Extension Pipeline (LEP), a method for integrating the optimized tokenizer into Qwen3-0.6B through vocabulary extension with mean subtoken initialization and selective transformer layer unfreezing. Our experiments show that LEP reduces evaluation loss from 8.28 to 2.43 within 800 training steps on 100K Arabic samples. We release our tokenizer, training scripts, and model checkpoints to facilitate Arabic NLP research. --- ### The Challenger: When Do New Data Sources Justify Switching Machine Learning Models? Authors: Vassilis Digalakis, Christophe Pérignon, Sébastien Saurin, Flore Sentenac Published: 2025-12-20 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2512.18390v2 Organizations often have an incumbent predictive model in production when new data sources become available. Because historical training data lack the new features, a challenger model must be trained on a small but growing full-feature dataset. We study whether, and when, the organization should switch to the challenger. The decision is statistical and economic: the challenger's predictive performance improves as full-feature data accumulate, but repeated retraining is costly and delays benefits from deployment. We develop a framework linking learning-curve dynamics to model-switching economics. Under a standard power-law learning curve and finite data-collection horizon $T$, the optimal time to train and evaluate the challenger scales as $T^{1/(1+α)}$: learning-curve shape (through its learning speed $α$) is the primary theoretical determinant of when to stop experimenting; costs determine switching profitability. Even without knowing the learning curve, the operational problem is tractable: we show that any algorithm stopping on the $T^{2/3}$ scale and making reliable switch/discard decisions achieves $O(T^{2/3}\sqrt{\log T})$ regret relative to a full-foresight oracle. We propose a sequential evaluation algorithm that uses local learning-curve trends to anticipate improvement, and test it in a real-world credit-scoring study. Even with this local approximation, the algorithm theoretically and empirically achieves near-oracle performance. It is also more stable than greedy sequential evaluation algorithms, where noisy early estimates trigger premature discarding, or simple one-shot evaluation algorithms, which work only when their fixed evaluation time matches the (unknown in practice) theoretical timing scale. Our framework offers a step toward principled model governance when new data sources require costly collection, validation, and deployment. --- ### Neural Proofs for Sound Verification and Control of Complex Systems Authors: Alessandro Abate Published: 2025-12-20 Categories: eess.SY, cs.AI, cs.LG, cs.LO arXiv: https://arxiv.org/abs/2512.18389v1 This informal contribution presents an ongoing line of research that is pursuing a new approach to the construction of sound proofs for the formal verification and control of complex stochastic models of dynamical systems, of reactive programs and, more generally, of models of Cyber-Physical Systems. Neural proofs are made up of two key components: 1) proof rules encode requirements entailing the verification of general temporal specifications over the models of interest; and 2) certificates that discharge such rules, namely they are constructed from said proof rules with an inductive (that is, cyclic, repetitive) approach; this inductive approach involves: 2a) accessing samples from the model's dynamics and accordingly training neural networks, whilst 2b) generalising such networks via SAT-modulo-theory (SMT) queries that leverage the full knowledge of the models. In the context of sequential decision making problems over complex stochastic models, it is possible to additionally generate provably-correct policies/strategies/controllers, namely state-feedback functions that, in conjunction with neural certificates, formally attain the given specifications for the models of interest. --- ### Exploration vs. Fixation: Scaffolding Divergent and Convergent Thinking for Human-AI Co-Creation with Generative Models Authors: Chao Wen, Tung Phung, Pronita Mehrotra, Sumit Gulwani, Roger E. Beaty, Tomohiro Nagashima, Adish Singla Published: 2025-12-20 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2512.18388v2 Generative AI has democratized content creation, but popular chatbot-based interfaces often prioritize execution, generating fully rendered artifacts right away. This issue can lead to premature convergence and design fixation, where users are being anchored to initial outputs. Recent works have proposed new interfaces to address this issue by supporting exploration, though typically constrained to be semantically close to a user's initial task framing, potentially limiting the creativity of the outcomes. We examine an approach grounded in the Geneplore model of creative cognition and instantiate it in a human-AI co-creation system, HAICo, for creative image generation. HAICo explicitly structures the creative process into two switchable modes: DIVERGENT mode scaffolds the broad exploration of remote conceptual ideas; CONVERGENT mode supports a targeted refinement of selected ideas. Through a within-subjects study (N=24) on a poster image creation task, we demonstrate that HAICo outperforms ChatGPT across multiple dimensions of creativity and usability. Our results highlight the critical need to shift from pure execution-focused chatbots to scaffolded co-creation systems that actively guide exploration and foster the creative process. --- ### RecurGS: Interactive Scene Modeling via Discrete-State Recurrent Gaussian Fusion Authors: Wenhao Hu, Haonan Zhou, Zesheng Li, Liu Liu, Jiacheng Dong, Zhizhong Su, Gaoang Wang Published: 2025-12-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.18386v1 Recent advances in 3D scene representations have enabled high-fidelity novel view synthesis, yet adapting to discrete scene changes and constructing interactive 3D environments remain open challenges in vision and robotics. Existing approaches focus solely on updating a single scene without supporting novel-state synthesis. Others rely on diffusion-based object-background decoupling that works on one state at a time and cannot fuse information across multiple observations. To address these limitations, we introduce RecurGS, a recurrent fusion framework that incrementally integrates discrete Gaussian scene states into a single evolving representation capable of interaction. RecurGS detects object-level changes across consecutive states, aligns their geometric motion using semantic correspondence and Lie-algebra based SE(3) refinement, and performs recurrent updates that preserve historical structures through replay supervision. A voxelized, visibility-aware fusion module selectively incorporates newly observed regions while keeping stable areas fixed, mitigating catastrophic forgetting and enabling efficient long-horizon updates. RecurGS supports object-level manipulation, synthesizes novel scene states without requiring additional scans, and maintains photorealistic fidelity across evolving environments. Extensive experiments across synthetic and real-world datasets demonstrate that our framework delivers high-quality reconstructions with substantially improved update efficiency, providing a scalable step toward continuously interactive Gaussian worlds. --- ### AI Prior Art Search: Semantic Clusters and Evaluation Infrastructure Authors: Boris Genin, Alexander Gorbunov, Dmitry Zolkin, Igor Nekrasov Published: 2025-12-20 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2512.18384v2 The key to success in automating prior art search in patent research using artificial intelligence (AI) lies in developing large datasets for machine learning (ML) and ensuring their availability. This work is dedicated to providing a comprehensive solution to the problem of creating infrastructure for research in this field, including datasets and tools for calculating search quality criteria. The paper discusses the concept of semantic clusters of patent documents that determine the state of the art in a given subject, as proposed by the authors. A definition of such semantic clusters is also provided. Prior art search is presented as the task of identifying elements within a semantic cluster of patent documents in the subject area specified by the document under consideration. A generator of user-configurable datasets for ML, based on collections of U.S. and Russian patent documents, is described. The dataset generator creates a database of links to documents in semantic clusters. Then, based on user-defined parameters, it forms a dataset of semantic clusters in JSON format for ML. A collection of publicly available patent documents was created. The collection contains 14 million semantic clusters of US patent documents and 1 million clusters of Russian patent documents. To evaluate ML outcomes, it is proposed to calculate search quality scores that account for semantic clusters of the documents being searched. To automate the evaluation process, the paper describes a utility developed by the authors for assessing the quality of prior art document search. --- ### Towards Guided Descent: Optimization Algorithms for Training Neural Networks At Scale Authors: Ansh Nagwekar Published: 2025-12-20 Categories: cs.LG, math.OC, stat.ML arXiv: https://arxiv.org/abs/2512.18373v1 Neural network optimization remains one of the most consequential yet poorly understood challenges in modern AI research, where improvements in training algorithms can lead to enhanced feature learning in foundation models, order-of-magnitude reductions in training time, and improved interpretability into how networks learn. While stochastic gradient descent (SGD) and its variants have become the de facto standard for training deep networks, their success in these over-parameterized regimes often appears more empirical than principled. This thesis investigates this apparent paradox by tracing the evolution of optimization algorithms from classical first-order methods to modern higher-order techniques, revealing how principled algorithmic design can demystify the training process. Starting from first principles with SGD and adaptive gradient methods, the analysis progressively uncovers the limitations of these conventional approaches when confronted with anisotropy that is representative of real-world data. These breakdowns motivate the exploration of sophisticated alternatives rooted in curvature information: second-order approximation techniques, layer-wise preconditioning, adaptive learning rates, and more. Next, the interplay between these optimization algorithms and the broader neural network training toolkit, which includes prior and recent developments such as maximal update parametrization, learning rate schedules, and exponential moving averages, emerges as equally essential to empirical success. To bridge the gap between theoretical understanding and practical deployment, this paper offers practical prescriptions and implementation strategies for integrating these methods into modern deep learning workflows. --- ### PSI3D: Plug-and-Play 3D Stochastic Inference with Slice-wise Latent Diffusion Prior Authors: Wenhan Guo, Jinglun Yu, Yaning Wang, Jin U. Kang, Yu Sun Published: 2025-12-20 Categories: eess.IV, cs.LG arXiv: https://arxiv.org/abs/2512.18367v2 Diffusion models are highly expressive image priors for Bayesian inverse problems. However, most diffusion models cannot operate on large-scale, high-dimensional data due to high training and inference costs. In this work, we introduce a Plug-and-play algorithm for 3D stochastic inference with latent diffusion prior (PSI3D) to address massive ($1024\times 1024\times 128$) volumes. Specifically, we formulate a Markov chain Monte Carlo approach to reconstruct each two-dimensional (2D) slice by sampling from a 2D latent diffusion model. To enhance inter-slice consistency, we also incorporate total variation (TV) regularization stochastically along the concatenation axis. We evaluate our performance on optical coherence tomography (OCT) super-resolution. Our method significantly improves reconstruction quality for large-scale scientific imaging compared to traditional and learning-based baselines, while providing robust and credible reconstructions. --- ### Efficient Zero-Shot Inpainting with Decoupled Diffusion Guidance Authors: Badr Moufad, Navid Bagheri Shouraki, Alain Oliviero Durmus, Thomas Hirtz, Eric Moulines, Jimmy Olsson, Yazid Janati Published: 2025-12-20 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2512.18365v2 Diffusion models have emerged as powerful priors for image editing tasks such as inpainting and local modification, where the objective is to generate realistic content that remains consistent with observed regions. In particular, zero-shot approaches that leverage a pretrained diffusion model, without any retraining, have been shown to achieve highly effective reconstructions. However, state-of-the-art zero-shot methods typically rely on a sequence of surrogate likelihood functions, whose scores are used as proxies for the ideal score. This procedure however requires vector-Jacobian products through the denoiser at every reverse step, introducing significant memory and runtime overhead. To address this issue, we propose a new likelihood surrogate that yields simple and efficient to sample Gaussian posterior transitions, sidestepping the backpropagation through the denoiser network. Our extensive experiments show that our method achieves strong observation consistency compared with fine-tuned baselines and produces coherent, high-quality reconstructions, all while significantly reducing inference cost. Code is available at https://github.com/YazidJanati/ding. --- ### Enhancing 3D Semantic Scene Completion with a Refinement Module Authors: Dunxing Zhang, Jiachen Lu, Han Yang, Lei Bao, Bo Song Published: 2025-12-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.18363v2 We propose ESSC-RM, a plug-and-play Enhancing framework for Semantic Scene Completion with a Refinement Module, which can be seamlessly integrated into existing SSC models. ESSC-RM operates in two phases: a baseline SSC network first produces a coarse voxel prediction, which is subsequently refined by a 3D U-Net-based Prediction Noise-Aware Module (PNAM) and Voxel-level Local Geometry Module (VLGM) under multiscale supervision. Experiments on SemanticKITTI show that ESSC-RM consistently improves semantic prediction performance. When integrated into CGFormer and MonoScene, the mean IoU increases from 16.87% to 17.27% and from 11.08% to 11.51%, respectively. These results demonstrate that ESSC-RM serves as a general refinement framework applicable to a wide range of SSC models. --- ### SRS-Stories: Vocabulary-constrained multilingual story generation for language learning Authors: Wiktor Kamzela, Mateusz Lango, Ondrej Dusek Published: 2025-12-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.18362v1 In this paper, we use large language models to generate personalized stories for language learners, using only the vocabulary they know. The generated texts are specifically written to teach the user new vocabulary by simply reading stories where it appears in context, while at the same time seamlessly reviewing recently learned vocabulary. The generated stories are enjoyable to read and the vocabulary reviewing/learning is optimized by a Spaced Repetition System. The experiments are conducted in three languages: English, Chinese and Polish, evaluating three story generation methods and three strategies for enforcing lexical constraints. The results show that the generated stories are more grammatical, coherent, and provide better examples of word usage than texts generated by the standard constrained beam search approach --- ### LLM Agents Implement an NLG System from Scratch: Building Interpretable Rule-Based RDF-to-Text Generators Authors: Mateusz Lango, Ondřej Dušek Published: 2025-12-20 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.18360v1 We present a novel neurosymbolic framework for RDF-to-text generation, in which the model is "trained" through collaborative interactions among multiple LLM agents rather than traditional backpropagation. The LLM agents produce rule-based Python code for a generator for the given domain, based on RDF triples only, with no in-domain human reference texts. The resulting system is fully interpretable, requires no supervised training data, and generates text nearly instantaneously using only a single CPU. Our experiments on the WebNLG and OpenDialKG data show that outputs produced by our approach reduce hallucination, with only slight fluency penalties compared to finetuned or prompted language models --- ### DACE For Railway Acronym Disambiguation Authors: El Mokhtar Hribach, Oussama Mechhour, Mohammed Elmonstaser, Yassine El Boudouri, Othmane Kabal Published: 2025-12-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.18357v1 Acronym Disambiguation (AD) is a fundamental challenge in technical text processing, particularly in specialized sectors where high ambiguity complicates automated analysis. This paper addresses AD within the context of the TextMine'26 competition on French railway documentation. We present DACE (Dynamic Prompting, Retrieval Augmented Generation, Contextual Selection, and Ensemble Aggregation), a framework that enhances Large Language Models through adaptive in-context learning and external domain knowledge injection. By dynamically tailoring prompts to acronym ambiguity and aggregating ensemble predictions, DACE mitigates hallucination and effectively handles low-resource scenarios. Our approach secured the top rank in the competition with an F1 score of 0.9069. --- ### LLM-based Few-Shot Early Rumor Detection with Imitation Agent Authors: Fengzhu Zeng, Qian Shao, Ling Cheng, Wei Gao, Shih-Fen Cheng, Jing Ma, Cheng Niu Published: 2025-12-20 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.18352v2 Early Rumor Detection (EARD) aims to identify the earliest point at which a claim can be accurately classified based on a sequence of social media posts. This is especially challenging in data-scarce settings. While Large Language Models (LLMs) perform well in few-shot NLP tasks, they are not well-suited for time-series data and are computationally expensive for both training and inference. In this work, we propose a novel EARD framework that combines an autonomous agent and an LLM-based detection model, where the agent acts as a reliable decision-maker for \textit{early time point determination}, while the LLM serves as a powerful \textit{rumor detector}. This approach offers the first solution for few-shot EARD, necessitating only the training of a lightweight agent and allowing the LLM to remain training-free. Extensive experiments on four real-world datasets show our approach boosts performance across LLMs and surpasses existing EARD methods in accuracy and earliness. --- ### MCVI-SANet: A lightweight semi-supervised model for LAI and SPAD estimation of winter wheat under vegetation index saturation Authors: Zhiheng Zhang, Jiajun Yang, Hong Sun, Dong Wang, Honghua Jiang, Yaru Chen, Tangyuan Ning Published: 2025-12-20 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.18344v1 Vegetation index (VI) saturation during the dense canopy stage and limited ground-truth annotations of winter wheat constrain accurate estimation of LAI and SPAD. Existing VI-based and texture-driven machine learning methods exhibit limited feature expressiveness. In addition, deep learning baselines suffer from domain gaps and high data demands, which restrict their generalization. Therefore, this study proposes the Multi-Channel Vegetation Indices Saturation Aware Net (MCVI-SANet), a lightweight semi-supervised vision model. The model incorporates a newly designed Vegetation Index Saturation-Aware Block (VI-SABlock) for adaptive channel-spatial feature enhancement. It also integrates a VICReg-based semi-supervised strategy to further improve generalization. Datasets were partitioned using a vegetation height-informed strategy to maintain representativeness across growth stages. Experiments over 10 repeated runs demonstrate that MCVI-SANet achieves state-of-the-art accuracy. The model attains an average R2 of 0.8123 and RMSE of 0.4796 for LAI, and an average R2 of 0.6846 and RMSE of 2.4222 for SPAD. This performance surpasses the best-performing baselines, with improvements of 8.95% in average LAI R2 and 8.17% in average SPAD R2. Moreover, MCVI-SANet maintains high inference speed with only 0.10M parameters. Overall, the integration of semi-supervised learning with agronomic priors provides a promising approach for enhancing remote sensing-based precision agriculture. --- ### Large-scale benchmarking of multi-objective soft-computing metaheuristics for redundancy allocation in repairable k-out-of-n systems Authors: Mateusz Oszczypała, David Ibehej, Jakub Kudela Published: 2025-12-20 Categories: cs.NE arXiv: https://arxiv.org/abs/2512.18343v2 This paper presents a large-scale budget-aware benchmark of multi-objective soft-computing metaheuristics for a bi-objective redundancy allocation problem in repairable k-out-of-n systems. The problem combines cost minimization and steady-state availability maximization under weight constraints, with binary subsystem-level decisions determining both the number of redundant components and the redundancy strategy. Four strategies are considered: cold standby, warm standby, hot standby, and a mixed active-warm standby strategy. Subsystem availability is evaluated using continuous-time Markov chains, while the optimization task is treated as a constrained mixed-integer multi-objective problem. The study compares 65 metaheuristic algorithms from multiple algorithmic families under two initialization settings, with and without Scaled Binomial Initialization (SBI), across six case studies of increasing structural and dimensional complexity and four weight limits per case. Performance is assessed using hypervolume, budget-dependent convergence profiles, and non-parametric statistical comparisons. The results show that algorithm rankings are strongly budget-dependent, indicating that a single final-budget ranking can be misleading. SBI provides a substantial early advantage and can change the relative performance of competing methods, especially for larger instances. The best-performing algorithms vary across budget regimes: NNIA-SBI and CMOPSO-SBI are competitive under tight budgets, whereas NSGA-II+ARSBX-SBI performs robustly for medium and large budgets. From a system design perspective, Pareto-optimal solutions are dominated by hot standby and mixed redundancy strategies, while cold and warm standby rarely appear. The benchmark highlights the importance of initialization, computational budget, and problem complexity when selecting soft-computing optimizers for practical redundancy allocation. --- ### Towards Efficient Agents: A Co-Design of Inference Architecture and System Authors: Weizhe Lin, Hui-Ling Zhen, Shuai Yang, Xian Wang, Renxi Liu, Hanting Chen, Wangze Zhang, Chuansai Zhou, Yiming Li, Chen Chen, Xing Li, Zhiyuan Yang et al. Published: 2025-12-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.18337v2 The rapid development of large language model (LLM)-based agents has unlocked new possibilities for autonomous multi-turn reasoning and tool-augmented decision-making. However, their real-world deployment is hindered by severe inefficiencies that arise not from isolated model inference, but from the systemic latency accumulated across reasoning loops, context growth, and heterogeneous tool interactions. This paper presents AgentInfer, a unified framework for end-to-end agent acceleration that bridges inference optimization and architectural design. We decompose the problem into four synergistic components: AgentCollab, a hierarchical dual-model reasoning framework that balances large- and small-model usage through dynamic role assignment; AgentSched, a cache-aware hybrid scheduler that minimizes latency under heterogeneous request patterns; AgentSAM, a suffix-automaton-based speculative decoding method that reuses multi-session semantic memory to achieve low-overhead inference acceleration; and AgentCompress, a semantic compression mechanism that asynchronously distills and reorganizes agent memory without disrupting ongoing reasoning. Together, these modules form a Self-Evolution Engine capable of sustaining efficiency and cognitive stability throughout long-horizon reasoning tasks. Experiments on the BrowseComp-zh and DeepDiver benchmarks demonstrate that through the synergistic collaboration of these methods, AgentInfer reduces ineffective token consumption by over 50%, achieving an overall 1.8-2.5 times speedup with preserved accuracy. These results underscore that optimizing for agentic task completion-rather than merely per-token throughput-is the key to building scalable, efficient, and self-improving intelligent systems. --- ### Dynamic Entropy Tuning in Reinforcement Learning Low-Level Quadcopter Control: Stochasticity vs Determinism Authors: Youssef Mahran, Zeyad Gamal, Ayman El-Badawy Published: 2025-12-20 Categories: cs.RO, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.18336v2 This paper explores the impact of dynamic entropy tuning in Reinforcement Learning (RL) algorithms that train a stochastic policy. Its performance is compared against algorithms that train a deterministic one. Stochastic policies optimize a probability distribution over actions to maximize rewards, while deterministic policies select a single deterministic action per state. The effect of training a stochastic policy with both static entropy and dynamic entropy and then executing deterministic actions to control the quadcopter is explored. It is then compared against training a deterministic policy and executing deterministic actions. For the purpose of this research, the Soft Actor-Critic (SAC) algorithm was chosen for the stochastic algorithm while the Twin Delayed Deep Deterministic Policy Gradient (TD3) was chosen for the deterministic algorithm. The training and simulation results show the positive effect the dynamic entropy tuning has on controlling the quadcopter by preventing catastrophic forgetting and improving exploration efficiency. --- ### Reinforcement Learning Position Control of a Quadrotor Using Soft Actor-Critic (SAC) Authors: Youssef Mahran, Zeyad Gamal, Ayman El-Badawy Published: 2025-12-20 Categories: cs.RO, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.18333v2 This paper proposes a new Reinforcement Learning (RL) based control architecture for quadrotors. With the literature focusing on controlling the four rotors' RPMs directly, this paper aims to control the quadrotor's thrust vector. The RL agent computes the percentage of overall thrust along the quadrotor's z-axis along with the desired Roll ($φ$) and Pitch ($θ$) angles. The agent then sends the calculated control signals along with the current quadrotor's Yaw angle ($ψ$) to an attitude PID controller. The PID controller then maps the control signals to motor RPMs. The Soft Actor-Critic algorithm, a model-free off-policy stochastic RL algorithm, was used to train the RL agents. Training results show the faster training time of the proposed thrust vector controller in comparison to the conventional RPM controllers. Simulation results show smoother and more accurate path-following for the proposed thrust vector controller. --- ### A two-stream network with global-local feature fusion for bone age assessment Authors: Qiong Lou, Han Yang, Fang Lu Published: 2025-12-20 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2512.18331v1 Bone Age Assessment (BAA) is a widely used clinical technique that can accurately reflect an individual's growth and development level, as well as maturity. In recent years, although deep learning has advanced the field of bone age assessment, existing methods face challenges in efficiently balancing global features and local skeletal details. This study aims to develop an automated bone age assessment system based on a two-stream deep learning architecture to achieve higher accuracy in bone age assessment. We propose the BoNet+ model incorporating global and local feature extraction channels. A Transformer module is introduced into the global feature extraction channel to enhance the ability in extracting global features through multi-head self-attention mechanism. A RFAConv module is incorporated into the local feature extraction channel to generate adaptive attention maps within multiscale receptive fields, enhancing local feature extraction capabilities. Global and local features are concatenated along the channel dimension and optimized by an Inception-V3 network. The proposed method has been validated on the Radiological Society of North America (RSNA) and Radiological Hand Pose Estimation (RHPE) test datasets, achieving mean absolute errors (MAEs) of 3.81 and 5.65 months, respectively. These results are comparable to the state-of-the-art. The BoNet+ model reduces the clinical workload and achieves automatic, high-precision, and more objective bone age assessment. --- ### LIR$^3$AG: A Lightweight Rerank Reasoning Strategy Framework for Retrieval-Augmented Generation Authors: Guo Chen, Junjie Huang, Huaijin Xie, Fei Sun, Tao Jia Published: 2025-12-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.18329v2 Retrieval-Augmented Generation (RAG) effectively enhances Large Language Models (LLMs) by incorporating retrieved external knowledge into the generation process. Reasoning models improve LLM performance in multi-hop QA tasks, which require integrating and reasoning over multiple pieces of evidence across different documents to answer a complex question. However, they often introduce substantial computational costs, including increased token consumption and inference latency. To better understand and mitigate this trade-off, we conduct a comprehensive study of reasoning strategies for reasoning models in RAG multi-hop QA tasks. Our findings reveal that reasoning models adopt structured strategies to integrate retrieved and internal knowledge, primarily following two modes: Context-Grounded Reasoning, which relies directly on retrieved content, and Knowledge-Reconciled Reasoning, which resolves conflicts or gaps using internal knowledge. To this end, we propose a novel Lightweight Rerank Reasoning Strategy Framework for RAG (LiR$^3$AG) to enable non-reasoning models to transfer reasoning strategies by restructuring retrieved evidence into coherent reasoning chains. LiR$^3$AG significantly reduce the average 98% output tokens overhead and 58.6% inferencing time while improving 8B non-reasoning model's F1 performance ranging from 6.2% to 22.5% to surpass the performance of 32B reasoning model in RAG, offering a practical and efficient path forward for RAG systems. --- ### CTTA-T: Continual Test-Time Adaptation for Text Understanding via Teacher-Student with a Domain-aware and Generalized Teacher Authors: Tianlun Liu, Zhiliang Tian, Zhen Huang, Xingzhi Zhou, Wanlong Yu, Tianle Liu, Feng Liu, Dongsheng Li Published: 2025-12-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.18321v2 Text understanding often suffers from domain shifts. To handle testing domains, domain adaptation (DA) is trained to adapt to a fixed and observed testing domain; a more challenging paradigm, test-time adaptation (TTA), cannot access the testing domain during training and online adapts to the testing samples during testing, where the samples are from a fixed domain. We aim to explore a more practical and underexplored scenario, continual test-time adaptation (CTTA) for text understanding, which involves a sequence of testing (unobserved) domains in testing. Current CTTA methods struggle in reducing error accumulation over domains and enhancing generalization to handle unobserved domains: 1) Noise-filtering reduces accumulated errors but discards useful information, and 2) accumulating historical domains enhances generalization, but it is hard to achieve adaptive accumulation. In this paper, we propose a CTTA-T (continual test-time adaptation for text understanding) framework adaptable to evolving target domains: it adopts a teacher-student framework, where the teacher is domain-aware and generalized for evolving domains. To improve teacher predictions, we propose a refine-then-filter based on dropout-driven consistency, which calibrates predictions and removes unreliable guidance. For the adaptation-generalization trade-off, we construct a domain-aware teacher by dynamically accumulating cross-domain semantics via incremental PCA, which continuously tracks domain shifts. Experiments show CTTA-T excels baselines. --- ### Asynchronous Pipeline Parallelism for Real-Time Multilingual Lip Synchronization in Video Communication Systems Authors: Eren Caglar, Amirkia Rafiei Oskooei, Mehmet Kutanoglu, Mustafa Keles, Mehmet S. Aktas Published: 2025-12-20 Categories: cs.MM, cs.AI, cs.CV, cs.DC, cs.NI arXiv: https://arxiv.org/abs/2512.18318v1 This paper introduces a parallel and asynchronous Transformer framework designed for efficient and accurate multilingual lip synchronization in real-time video conferencing systems. The proposed architecture integrates translation, speech processing, and lip-synchronization modules within a pipeline-parallel design that enables concurrent module execution through message-queue-based decoupling, reducing end-to-end latency by up to 3.1 times compared to sequential approaches. To enhance computational efficiency and throughput, the inference workflow of each module is optimized through low-level graph compilation, mixed-precision quantization, and hardware-accelerated kernel fusion. These optimizations provide substantial gains in efficiency while preserving model accuracy and visual quality. In addition, a context-adaptive silence-detection component segments the input speech stream at semantically coherent boundaries, improving translation consistency and temporal alignment across languages. Experimental results demonstrate that the proposed parallel architecture outperforms conventional sequential pipelines in processing speed, synchronization stability, and resource utilization. The modular, message-oriented design makes this work applicable to resource-constrained IoT communication scenarios including telemedicine, multilingual kiosks, and remote assistance systems. Overall, this work advances the development of low-latency, resource-efficient multimodal communication frameworks for next-generation AIoT systems. ---