# Research Papers — 2025-10 · bundle page 11 of 217 > Full-text markdown of papers #501–550 of 10843 published in 2025-10, newest first. AI-readable mirrors of the full 10843-paper 2025-10 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2025-10/page/11 [← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/10.md) [Next bundle →](https://aipod.dev/papers/archive/2025-10/page/12.md) ### SA$^{2}$Net: Scale-Adaptive Structure-Affinity Transformation for Spine Segmentation from Ultrasound Volume Projection Imaging Authors: Hao Xie, Zixun Huang, Yushen Zuo, Yakun Ju, Frank H. F. Leung, N. F. Law, Kin-Man Lam, Yong-Ping Zheng, Sai Ho Ling Published: 2025-10-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.26568v1 Spine segmentation, based on ultrasound volume projection imaging (VPI), plays a vital role for intelligent scoliosis diagnosis in clinical applications. However, this task faces several significant challenges. Firstly, the global contextual knowledge of spines may not be well-learned if we neglect the high spatial correlation of different bone features. Secondly, the spine bones contain rich structural knowledge regarding their shapes and positions, which deserves to be encoded into the segmentation process. To address these challenges, we propose a novel scale-adaptive structure-aware network (SA$^{2}$Net) for effective spine segmentation. First, we propose a scale-adaptive complementary strategy to learn the cross-dimensional long-distance correlation features for spinal images. Second, motivated by the consistency between multi-head self-attention in Transformers and semantic level affinity, we propose structure-affinity transformation to transform semantic features with class-specific affinity and combine it with a Transformer decoder for structure-aware reasoning. In addition, we adopt a feature mixing loss aggregation method to enhance model training. This method improves the robustness and accuracy of the segmentation process. The experimental results demonstrate that our SA$^{2}$Net achieves superior segmentation performance compared to other state-of-the-art methods. Moreover, the adaptability of SA$^{2}$Net to various backbones enhances its potential as a promising tool for advanced scoliosis diagnosis using intelligent spinal image analysis. The code and experimental demo are available at https://github.com/taetiseo09/SA2Net. --- ### Multiclass Local Calibration with the Jensen-Shannon Distance Authors: Cesare Barbera, Lorenzo Perini, Giovanni De Toni, Andrea Passerini, Andrea Pugnana Published: 2025-10-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.26566v2 Developing trustworthy Machine Learning (ML) models requires their predicted probabilities to be well-calibrated, meaning they should reflect true-class frequencies. Among calibration notions in multiclass classification, strong calibration is the most stringent, as it requires all predicted probabilities to be simultaneously calibrated across all classes. However, existing approaches to multiclass calibration lack a notion of distance among inputs, which makes them vulnerable to proximity bias: predictions in sparse regions of the feature space are systematically miscalibrated. In this work, we address this main shortcoming by introducing a local perspective on multiclass calibration. First, we formally define multiclass local calibration and establish its relationship with strong calibration. Second, we theoretically analyze the pitfalls of existing evaluation metrics when applied to multiclass local calibration. Third, we propose a practical method to enhance local calibration in Neural Networks, which enforces alignment between predicted probabilities and local estimates of class frequencies using the Jensen-Shannon distance. Finally, we empirically validate our approach against existing multiclass calibration techniques. --- ### On Measuring Localization of Shortcuts in Deep Networks Authors: Nikita Tsoy, Nikola Konstantinov Published: 2025-10-30 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2510.26560v2 Shortcuts, spurious rules that perform well during training but fail to generalize, present a major challenge to the reliability of deep networks (Geirhos et al., 2020). However, the impact of shortcuts on feature representations remains understudied, obstructing the design of principled shortcut-mitigation methods. To overcome this limitation, we investigate the layer-wise localization of shortcuts in deep models. Our novel experiment design quantifies the layer-wise contribution to accuracy degradation caused by a shortcut-inducing skew by counterfactual training on clean and skewed datasets. We employ our design to study shortcuts on CIFAR-10, Waterbirds, and CelebA datasets across VGG, ResNet, DeiT, and ConvNeXt architectures. We find that shortcut learning is not localized in specific layers but distributed throughout the network. Different network parts play different roles in this process: shallow layers predominantly encode spurious features, while deeper layers predominantly forget core features that are predictive on clean data. We also analyze the differences in localization and describe its principal axes of variation. Finally, our analysis of layer-wise shortcut-mitigation strategies suggests the hardness of designing general methods, supporting dataset- and architecture-specific approaches instead. --- ### Boosted Trees on a Diet: Compact Models for Resource-Constrained Devices Authors: Nina Herrmann, Jan Stenkamp, Benjamin Karic, Stefan Oehmcke, Fabian Gieseke Published: 2025-10-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.26557v2 Deploying machine learning models on compute-constrained devices has become a key building block of modern IoT applications. In this work, we present a compression scheme for boosted decision trees, addressing the growing need for lightweight machine learning models. Specifically, we provide techniques for training compact boosted decision tree ensembles that exhibit a reduced memory footprint by rewarding, among other things, the reuse of features and thresholds during training. Our experimental evaluation shows that models achieved the same performance with a compression ratio of 4-16x compared to LightGBM models using an adapted training process and an alternative memory layout. Once deployed, the corresponding IoT devices can operate independently of constant communication or external energy supply, and, thus, autonomously, requiring only minimal computing power and energy. This capability opens the door to a wide range of IoT applications, including remote monitoring, edge analytics, and real-time decision making in isolated or power-limited environments. --- ### Adaptive Inverse Kinematics Framework for Learning Variable-Length Tool Manipulation in Robotics Authors: Prathamesh Kothavale, Sravani Boddepalli Published: 2025-10-30 Categories: cs.RO, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.26551v1 Conventional robots possess a limited understanding of their kinematics and are confined to preprogrammed tasks, hindering their ability to leverage tools efficiently. Driven by the essential components of tool usage - grasping the desired outcome, selecting the most suitable tool, determining optimal tool orientation, and executing precise manipulations - we introduce a pioneering framework. Our novel approach expands the capabilities of the robot's inverse kinematics solver, empowering it to acquire a sequential repertoire of actions using tools of varying lengths. By integrating a simulation-learned action trajectory with the tool, we showcase the practicality of transferring acquired skills from simulation to real-world scenarios through comprehensive experimentation. Remarkably, our extended inverse kinematics solver demonstrates an impressive error rate of less than 1 cm. Furthermore, our trained policy achieves a mean error of 8 cm in simulation. Noteworthy, our model achieves virtually indistinguishable performance when employing two distinct tools of different lengths. This research provides an indication of potential advances in the exploration of all four fundamental aspects of tool usage, enabling robots to master the intricate art of tool manipulation across diverse tasks. --- ### EdgeRunner 20B: Military Task Parity with GPT-5 while Running on the Edge Authors: Jack FitzGerald, Aristotelis Lazaridis, Dylan Bates, Aman Sharma, Jonnathan Castillo, Yousif Azami, Sean Bailey, Jeremy Cao, Peter Damianov, Kevin de Haan, Luke Kerbs, Vincent Lu et al. Published: 2025-10-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.26550v2 We present EdgeRunner 20B, a fine-tuned version of gpt-oss-20b optimized for military tasks. EdgeRunner 20B was trained on 1.6M high-quality records curated from military documentation and websites. We also present four new tests sets: (a) combat arms, (b) combat medic, (c) cyber operations, and (d) mil-bench-5k (general military knowledge). On these military test sets, EdgeRunner 20B matches or exceeds GPT-5 task performance with 95%+ statistical significance, except for the high reasoning setting on the combat medic test set and the low reasoning setting on the mil-bench-5k test set. Versus gpt-oss-20b, there is no statistically-significant regression on general-purpose benchmarks like ARC-C, GPQA Diamond, GSM8k, IFEval, MMLU Pro, or TruthfulQA, except for GSM8k in the low reasoning setting. We also present analyses on hyperparameter settings, cost, and throughput. These findings show that small, locally-hosted models are ideal solutions for data-sensitive operations such as in the military domain, allowing for deployment in air-gapped edge devices. --- ### The Structure of Relation Decoding Linear Operators in Large Language Models Authors: Miranda Anna Christ, Adrián Csiszárik, Gergely Becsó, Dániel Varga Published: 2025-10-30 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.26543v1 This paper investigates the structure of linear operators introduced in Hernandez et al. (2023) that decode specific relational facts in transformer language models. We extend their single-relation findings to a collection of relations and systematically chart their organization. We show that such collections of relation decoders can be highly compressed by simple order-3 tensor networks without significant loss in decoding accuracy. To explain this surprising redundancy, we develop a cross-evaluation protocol, in which we apply each linear decoder operator to the subjects of every other relation. Our results reveal that these linear maps do not encode distinct relations, but extract recurring, coarse-grained semantic properties (e.g., country of capital city and country of food are both in the country-of-X property). This property-centric structure clarifies both the operators' compressibility and highlights why they generalize only to new relations that are semantically close. Our findings thus interpret linear relational decoding in transformer language models as primarily property-based, rather than relation-specific. --- ### A Three-Stage Bayesian Transfer Learning Framework to Improve Predictions in Data-Scarce Domains Authors: Aidan Furlong, Robert Salko, Xingang Zhao, Xu Wu Published: 2025-10-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.26541v1 The use of ML in engineering has grown steadily to support a wide array of applications. Among these methods, deep neural networks have been widely adopted due to their performance and accessibility, but they require large, high-quality datasets. Experimental data are often sparse, noisy, or insufficient to build resilient data-driven models. Transfer learning, which leverages relevant data-abundant source domains to assist learning in data-scarce target domains, has shown efficacy. Parameter transfer, where pretrained weights are reused, is common but degrades under large domain shifts. Domain-adversarial neural networks (DANNs) help address this issue by learning domain-invariant representations, thereby improving transfer under greater domain shifts in a semi-supervised setting. However, DANNs can be unstable during training and lack a native means for uncertainty quantification. This study introduces a fully-supervised three-stage framework, the staged Bayesian domain-adversarial neural network (staged B-DANN), that combines parameter transfer and shared latent space adaptation. In Stage 1, a deterministic feature extractor is trained on the source domain. This feature extractor is then adversarially refined using a DANN in Stage 2. In Stage 3, a Bayesian neural network is built on the adapted feature extractor for fine-tuning on the target domain to handle conditional shifts and yield calibrated uncertainty estimates. This staged B-DANN approach was first validated on a synthetic benchmark, where it was shown to significantly outperform standard transfer techniques. It was then applied to the task of predicting critical heat flux in rectangular channels, leveraging data from tube experiments as the source domain. The results of this study show that the staged B-DANN method can improve predictive accuracy and generalization, potentially assisting other domains in nuclear engineering. --- ### Higher-Order Regularization Learning on Hypergraphs Authors: Adrien Weihs, Andrea L. Bertozzi, Matthew Thorpe Published: 2025-10-30 Categories: cs.LG, math.ST arXiv: https://arxiv.org/abs/2510.26533v2 Higher-Order Hypergraph Learning (HOHL) was recently introduced as a principled alternative to classical hypergraph regularization, enforcing higher-order smoothness via powers of multiscale Laplacians induced by the hypergraph structure. Prior work established the well- and ill-posedness of HOHL through an asymptotic consistency analysis in geometric settings. We extend this theoretical foundation by proving the consistency of a truncated version of HOHL and deriving explicit convergence rates when HOHL is used as a regularizer in fully supervised learning. We further demonstrate its strong empirical performance in active learning and in datasets lacking an underlying geometric structure, highlighting HOHL's versatility and robustness across diverse learning settings. --- ### Polybasic Speculative Decoding Through a Theoretical Perspective Authors: Ruilin Wang, Huixia Li, Yuexiao Ma, Xiawu Zheng, Fei Chao, Xuefeng Xiao, Rongrong Ji Published: 2025-10-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.26527v1 Inference latency stands as a critical bottleneck in the large-scale deployment of Large Language Models (LLMs). Speculative decoding methods have recently shown promise in accelerating inference without compromising the output distribution. However, existing work typically relies on a dualistic draft-verify framework and lacks rigorous theoretical grounding. In this paper, we introduce a novel \emph{polybasic} speculative decoding framework, underpinned by a comprehensive theoretical analysis. Specifically, we prove a fundamental theorem that characterizes the optimal inference time for multi-model speculative decoding systems, shedding light on how to extend beyond the dualistic approach to a more general polybasic paradigm. Through our theoretical investigation of multi-model token generation, we expose and optimize the interplay between model capabilities, acceptance lengths, and overall computational cost. Our framework supports both standalone implementation and integration with existing speculative techniques, leading to accelerated performance in practice. Experimental results across multiple model families demonstrate that our approach yields speedup ratios ranging from $3.31\times$ to $4.01\times$ for LLaMA2-Chat 7B, up to $3.87 \times$ for LLaMA3-8B, up to $4.43 \times$ for Vicuna-7B and up to $3.85 \times$ for Qwen2-7B -- all while preserving the original output distribution. We release our theoretical proofs and implementation code to facilitate further investigation into polybasic speculative decoding. --- ### Approximating Heavy-Tailed Distributions with a Mixture of Bernstein Phase-Type and Hyperexponential Models Authors: Abdelhakim Ziani, András Horváth, Paolo Ballarini Published: 2025-10-30 Categories: cs.PF, stat.AP, stat.ML arXiv: https://arxiv.org/abs/2510.26524v1 Heavy-tailed distributions, prevalent in a lot of real-world applications such as finance, telecommunications, queuing theory, and natural language processing, are challenging to model accurately owing to their slow tail decay. Bernstein phase-type (BPH) distributions, through their analytical tractability and good approximations in the non-tail region, can present a good solution, but they suffer from an inability to reproduce these heavy-tailed behaviors exactly, thus leading to inadequate performance in important tail areas. On the contrary, while highly adaptable to heavy-tailed distributions, hyperexponential (HE) models struggle in the body part of the distribution. Additionally, they are highly sensitive to initial parameter selection, significantly affecting their precision. To solve these issues, we propose a novel hybrid model of BPH and HE distributions, borrowing the most desirable features from each for enhanced approximation quality. Specifically, we leverage an optimization to set initial parameters for the HE component, significantly enhancing its robustness and reducing the possibility that the associated procedure results in an invalid HE model. Experimental validation demonstrates that the novel hybrid approach is more performant than individual application of BPH or HE models. More precisely, it can capture both the body and the tail of heavy-tailed distributions, with a considerable enhancement in matching parameters such as mean and coefficient of variation. Additional validation through experiments utilizing queuing theory proves the practical usefulness, accuracy, and precision of our hybrid approach. --- ### Hebrew Diacritics Restoration using Visual Representation Authors: Yair Elboher, Yuval Pinter Published: 2025-10-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.26521v3 Diacritics restoration in Hebrew is a fundamental task for ensuring accurate word pronunciation and disambiguating textual meaning. Despite the language's high degree of ambiguity when unvocalized, recent machine learning approaches have significantly advanced performance on this task. In this work, we present DiVRit, a novel system for Hebrew diacritization that frames the task as a zero-shot classification problem. Our approach operates at the word level, selecting the most appropriate diacritization pattern for each undiacritized word from a dynamically generated candidate set, conditioned on the surrounding textual context. A key innovation of DiVRit is its use of a Hebrew Visual Language Model to process diacritized candidates as images, allowing diacritic information to be embedded directly within their vector representations while the surrounding context remains tokenization-based. Through a comprehensive evaluation across various configurations, we demonstrate that the system effectively performs diacritization without relying on complex, explicit linguistic analysis. Notably, in an ``oracle'' setting where the correct diacritized form is guaranteed to be among the provided candidates, DiVRit achieves a high level of accuracy. Furthermore, strategic architectural enhancements and optimized training methodologies yield significant improvements in the system's overall generalization capabilities. These findings highlight the promising potential of visual representations for accurate and automated Hebrew diacritization. --- ### Think Outside the Policy: In-Context Steered Policy Optimization Authors: Hsiu-Yuan Huang, Chenming Tang, Weijie Liu, Clive Bai, Saiyong Yang, Yunfang Wu Published: 2025-10-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.26519v3 Existing Reinforcement Learning from Verifiable Rewards (RLVR) methods, such as Group Relative Policy Optimization (GRPO), have achieved remarkable progress in improving the reasoning capabilities of Large Reasoning Models (LRMs). However, they exhibit limited exploration due to reliance on on-policy rollouts which are confined to the current policy's distribution, resulting in narrow trajectory diversity. Recent approaches attempt to expand policy coverage by incorporating trajectories generated from stronger expert models, yet this reliance increases computational cost and such advanced models are often inaccessible. To address these issues, we propose In-Context Steered Policy Optimization (ICPO), a unified framework that leverages the inherent in-context learning capability of LRMs to provide expert guidance using existing datasets. ICPO introduces mixed-policy GRPO with implicit expert forcing, which expands exploration beyond the current policy distribution without requiring advanced LRM trajectories. To further stabilize optimization, ICPO integrates expert region reject sampling to filter unreliable off-policy trajectories and annealed expert-bonus reward shaping to balance early expert guidance with later autonomous improvement. Results demonstrate that ICPO consistently enhances RLVR performance and training stability on mathematical reasoning benchmarks, revealing a scalable and effective RLVR paradigm for LRMs. Our code is available at https://github.com/Celine-hxy/ICPO. --- ### Human-AI Complementarity: A Goal for Amplified Oversight Authors: Rishub Jain, Sophie Bridgers, Lili Janzer, Rory Greig, Tian Huey Teh, Vladimir Mikulik Published: 2025-10-30 Categories: cs.AI, cs.HC arXiv: https://arxiv.org/abs/2510.26518v2 Human feedback is critical for aligning AI systems to human values. As AI capabilities improve and AI is used to tackle more challenging tasks, verifying quality and safety becomes increasingly challenging. This paper explores how we can leverage AI to improve the quality of human oversight. We focus on an important safety problem that is already challenging for humans: fact-verification of AI outputs. We find that combining AI ratings and human ratings based on AI rater confidence is better than relying on either alone. Giving humans an AI fact-verification assistant further improves their accuracy, but the type of assistance matters. Displaying AI explanation, confidence, and labels leads to over-reliance, but just showing search results and evidence fosters more appropriate trust. These results have implications for Amplified Oversight -- the challenge of combining humans and AI to supervise AI systems even as they surpass human expert performance. --- ### Inside CORE-KG: Evaluating Structured Prompting and Coreference Resolution for Knowledge Graphs Authors: Dipak Meher, Carlotta Domeniconi Published: 2025-10-30 Categories: cs.CL, cs.AI, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2510.26512v2 Human smuggling networks are increasingly adaptive and difficult to analyze. Legal case documents offer critical insights but are often unstructured, lexically dense, and filled with ambiguous or shifting references, which pose significant challenges for automated knowledge graph (KG) construction. While recent LLM-based approaches improve over static templates, they still generate noisy, fragmented graphs with duplicate nodes due to the absence of guided extraction and coreference resolution. The recently proposed CORE-KG framework addresses these limitations by integrating a type-aware coreference module and domain-guided structured prompts, significantly reducing node duplication and legal noise. In this work, we present a systematic ablation study of CORE-KG to quantify the individual contributions of its two key components. Our results show that removing coreference resolution results in a 28.25% increase in node duplication and a 4.32% increase in noisy nodes, while removing structured prompts leads to a 4.29% increase in node duplication and a 73.33% increase in noisy nodes. These findings offer empirical insights for designing robust LLM-based pipelines for extracting structured representations from complex legal texts. --- ### LLMs as In-Context Meta-Learners for Model and Hyperparameter Selection Authors: Youssef Attia El Hili, Albert Thomas, Malik Tiomoko, Abdelhakim Benechehab, Corentin Léger, Corinne Ancourt, Balázs Kégl Published: 2025-10-30 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2510.26510v3 Model and hyperparameter selection are critical but challenging in machine learning, typically requiring expert intuition or expensive automated search. We investigate whether large language models (LLMs) can act as in-context meta-learners for this task. By converting each dataset into interpretable metadata, we prompt an LLM to recommend both model families and hyperparameters. We study two prompting strategies: (1) a zero-shot mode relying solely on pretrained knowledge, and (2) a meta-informed mode augmented with examples of models and their performance on past tasks. Across synthetic and real-world benchmarks, we show that LLMs can exploit dataset metadata to recommend competitive models and hyperparameters without search, and that improvements from meta-informed prompting demonstrate their capacity for in-context meta-learning. These results highlight a promising new role for LLMs as lightweight, general-purpose assistants for model selection and hyperparameter optimization. --- ### Analysis of the Robustness of an Edge Detector Based on Cellular Automata Optimized by Particle Swarm Authors: Vinícius Ferraria, Eurico Ruivo Published: 2025-10-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.26509v1 The edge detection task is essential in image processing aiming to extract relevant information from an image. One recurring problem in this task is the weaknesses found in some detectors, such as the difficulty in detecting loose edges and the lack of context to extract relevant information from specific problems. To address these weaknesses and adapt the detector to the properties of an image, an adaptable detector described by two-dimensional cellular automaton and optimized by meta-heuristic combined with transfer learning techniques was developed. This study aims to analyze the impact of expanding the search space of the optimization phase and the robustness of the adaptability of the detector in identifying edges of a set of natural images and specialized subsets extracted from the same image set. The results obtained prove that expanding the search space of the optimization phase was not effective for the chosen image set. The study also analyzed the adaptability of the model through a series of experiments and validation techniques and found that, regardless of the validation, the model was able to adapt to the input and the transfer learning techniques applied to the model showed no significant improvements. --- ### Enhancing ECG Classification Robustness with Lightweight Unsupervised Anomaly Detection Filters Authors: Mustafa Fuad Rifet Ibrahim, Maurice Meijer, Alexander Schlaefer, Peer Stelldinger Published: 2025-10-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.26501v2 Continuous electrocardiogram (ECG) monitoring via wearable devices is vital for early cardiovascular disease detection. However, deploying deep learning models on resource-constrained microcontrollers faces reliability challenges, particularly from Out-of-Distribution (OOD) pathologies and noise. Standard classifiers often yield high-confidence errors on such data. Existing OOD detection methods either neglect computational constraints or address noise and unseen classes separately. This paper investigates Unsupervised Anomaly Detection (UAD) as a lightweight, upstream filtering mechanism. We perform a Neural Architecture Search (NAS) on six UAD approaches, including Deep Support Vector Data Description (Deep SVDD), input reconstruction with (Variational-)Autoencoders (AE/VAE), Masked Anomaly Detection (MAD), Normalizing Flows (NFs) and Denoising Diffusion Probabilistic Models (DDPM) under strict hardware constraints ($\leq$512k parameters), suitable for microcontrollers. Evaluating on the PTB-XL and BUT QDB datasets, we demonstrate that a NAS-optimized Deep SVDD offers the superior Pareto efficiency between detection performance and model size. In a simulated deployment, this lightweight filter improves the accuracy of a diagnostic classifier by up to 21.0 percentage points, demonstrating that optimized UAD filters can safeguard ECG analysis on wearables. --- ### A Multi-agent Large Language Model Framework to Automatically Assess Performance of a Clinical AI Triage Tool Authors: Adam E. Flanders, Yifan Peng, Luciano Prevedello, Robyn Ball, Errol Colak, Prahlad Menon, George Shih, Hui-Ming Lin, Paras Lakhani Published: 2025-10-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.26498v1 Purpose: The purpose of this study was to determine if an ensemble of multiple LLM agents could be used collectively to provide a more reliable assessment of a pixel-based AI triage tool than a single LLM. Methods: 29,766 non-contrast CT head exams from fourteen hospitals were processed by a commercial intracranial hemorrhage (ICH) AI detection tool. Radiology reports were analyzed by an ensemble of eight open-source LLM models and a HIPAA compliant internal version of GPT-4o using a single multi-shot prompt that assessed for presence of ICH. 1,726 examples were manually reviewed. Performance characteristics of the eight open-source models and consensus were compared to GPT-4o. Three ideal consensus LLM ensembles were tested for rating the performance of the triage tool. Results: The cohort consisted of 29,766 head CTs exam-report pairs. The highest AUC performance was achieved with llama3.3:70b and GPT-4o (AUC= 0.78). The average precision was highest for Llama3.3:70b and GPT-4o (AP=0.75 & 0.76). Llama3.3:70b had the highest F1 score (0.81) and recall (0.85), greater precision (0.78), specificity (0.72), and MCC (0.57). Using MCC (95% CI) the ideal combination of LLMs were: Full-9 Ensemble 0.571 (0.552-0.591), Top-3 Ensemble 0.558 (0.537-0.579), Consensus 0.556 (0.539-0.574), and GPT4o 0.522 (0.500-0.543). No statistically significant differences were observed between Top-3, Full-9, and Consensus (p > 0.05). Conclusion: An ensemble of medium to large sized open-source LLMs provides a more consistent and reliable method to derive a ground truth retrospective evaluation of a clinical AI triage tool over a single LLM alone. --- ### Rethinking Text-to-SQL: Dynamic Multi-turn SQL Interaction for Real-world Database Exploration Authors: Linzhuang Sun, Tianyu Guo, Hao Liang, Yuying Li, Qifeng Cai, Jingxuan Wei, Bihui Yu, Wentao Zhang, Bin Cui Published: 2025-10-30 Categories: cs.DB, cs.CL arXiv: https://arxiv.org/abs/2510.26495v2 Recent advances in Text-to-SQL have achieved strong results in static, single-turn tasks, where models generate SQL queries from natural language questions. However, these systems fall short in real-world interactive scenarios, where user intents evolve and queries must be refined over multiple turns. In applications such as finance and business analytics, users iteratively adjust query constraints or dimensions based on intermediate results. To evaluate such dynamic capabilities, we introduce DySQL-Bench, a benchmark assessing model performance under evolving user interactions. Unlike previous manually curated datasets, DySQL-Bench is built through an automated two-stage pipeline of task synthesis and verification. Structured tree representations derived from raw database tables guide LLM-based task generation, followed by interaction-oriented filtering and expert validation. Human evaluation confirms 100% correctness of the synthesized data. We further propose a multi-turn evaluation framework simulating realistic interactions among an LLM-simulated user, the model under test, and an executable database. The model must adapt its reasoning and SQL generation as user intents change. DySQL-Bench covers 13 domains across BIRD and Spider 2 databases, totaling 1,072 tasks. Even GPT-4o attains only 58.34% overall accuracy and 23.81% on the Pass@5 metric, underscoring the benchmark's difficulty. All code and data are released at https://github.com/Aurora-slz/Real-World-SQL-Bench . --- ### Simulating and Experimenting with Social Media Mobilization Using LLM Agents Authors: Sadegh Shirani, Mohsen Bayati Published: 2025-10-30 Categories: cs.SI, cs.AI arXiv: https://arxiv.org/abs/2510.26494v1 Online social networks have transformed the ways in which political mobilization messages are disseminated, raising new questions about how peer influence operates at scale. Building on the landmark 61-million-person Facebook experiment \citep{bond201261}, we develop an agent-based simulation framework that integrates real U.S. Census demographic distributions, authentic Twitter network topology, and heterogeneous large language model (LLM) agents to examine the effect of mobilization messages on voter turnout. Each simulated agent is assigned demographic attributes, a personal political stance, and an LLM variant (\texttt{GPT-4.1}, \texttt{GPT-4.1-Mini}, or \texttt{GPT-4.1-Nano}) reflecting its political sophistication. Agents interact over realistic social network structures, receiving personalized feeds and dynamically updating their engagement behaviors and voting intentions. Experimental conditions replicate the informational and social mobilization treatments of the original Facebook study. Across scenarios, the simulator reproduces qualitative patterns observed in field experiments, including stronger mobilization effects under social message treatments and measurable peer spillovers. Our framework provides a controlled, reproducible environment for testing counterfactual designs and sensitivity analyses in political mobilization research, offering a bridge between high-validity field experiments and flexible computational modeling.\footnote{Code and data available at https://github.com/CausalMP/LLM-SocioPol} --- ### Context Engineering 2.0: The Context of Context Engineering Authors: Qishuo Hua, Lyumanshan Ye, Dayuan Fu, Yang Xiao, Xiaojie Cai, Yunze Wu, Jifan Lin, Junfei Wang, Pengfei Liu Published: 2025-10-30 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2510.26493v1 Karl Marx once wrote that ``the human essence is the ensemble of social relations'', suggesting that individuals are not isolated entities but are fundamentally shaped by their interactions with other entities, within which contexts play a constitutive and essential role. With the advent of computers and artificial intelligence, these contexts are no longer limited to purely human--human interactions: human--machine interactions are included as well. Then a central question emerges: How can machines better understand our situations and purposes? To address this challenge, researchers have recently introduced the concept of context engineering. Although it is often regarded as a recent innovation of the agent era, we argue that related practices can be traced back more than twenty years. Since the early 1990s, the field has evolved through distinct historical phases, each shaped by the intelligence level of machines: from early human--computer interaction frameworks built around primitive computers, to today's human--agent interaction paradigms driven by intelligent agents, and potentially to human--level or superhuman intelligence in the future. In this paper, we situate context engineering, provide a systematic definition, outline its historical and conceptual landscape, and examine key design considerations for practice. By addressing these questions, we aim to offer a conceptual foundation for context engineering and sketch its promising future. This paper is a stepping stone for a broader community effort toward systematic context engineering in AI systems. --- ### Wireless Sensor Networks as Parallel and Distributed Hardware Platform for Artificial Neural Networks Authors: Gursel Serpen Published: 2025-10-30 Categories: cs.NE, cs.AR, cs.DC arXiv: https://arxiv.org/abs/2510.26492v1 We are proposing fully parallel and maximally distributed hardware realization of a generic neuro-computing system. More specifically, the proposal relates to the wireless sensor networks technology to serve as a massively parallel and fully distributed hardware platform to implement and realize artificial neural network (ANN) algorithms. A parallel and distributed (PDP) hardware realization of ANNs makes it possible to have real time computation of large-scale (and complex) problems in a highly robust framework. We will demonstrate how a network of hundreds of thousands of processing nodes (or motes of a wireless sensor network), which have on-board processing and wireless communication features, can be used to implement fully parallel and massively distributed computation of artificial neural network algorithms for solution of truly large-scale problems in real time. The realization of artificial neural network algorithms in a massively parallel and fully distributed hardware has been the goal of neural network computing researchers. This is because a parallel and distributed computation of artificial neural network algorithms could not have been achieved against all the advancements in silicon- or optics-based computing. Accordingly, artificial neural networks could not be applied to very large-scale problems for real time computation of solutions. This hindered the development of neural algorithms for affordable and practical solutions of challenging problems since often special-purpose computing approaches in hardware, software or hybrid (non-neural) had to be developed for and fine-tuned to specific problems that are very large-scale and highly complex. Successful implementation is likely to revolutionize computing as we know it by making it possible to solve very large scale scientific, engineering or technical problems in real time. --- ### Data-Efficient RLVR via Off-Policy Influence Guidance Authors: Erle Zhu, Dazhi Jiang, Yuan Wang, Xujun Li, Jiale Cheng, Yuxian Gu, Yilin Niu, Aohan Zeng, Jie Tang, Minlie Huang, Hongning Wang Published: 2025-10-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.26491v2 Data selection is a critical aspect of Reinforcement Learning with Verifiable Rewards (RLVR) for enhancing the reasoning capabilities of large language models (LLMs). Current data selection methods are largely heuristic-based, lacking theoretical guarantees and generalizability. This work proposes a theoretically-grounded approach using influence functions to estimate the contribution of each data point to the learning objective. To overcome the prohibitive computational cost of policy rollouts required for online influence estimation, we introduce an off-policy influence estimation method that efficiently approximates data influence using pre-collected offline trajectories. Furthermore, to manage the high-dimensional gradients of LLMs, we employ sparse random projection to reduce dimensionality and improve storage and computation efficiency. Leveraging these techniques, we develop \textbf{C}urriculum \textbf{R}L with \textbf{O}ff-\textbf{P}olicy \text{I}nfluence guidance (\textbf{CROPI}), a multi-stage RL framework that iteratively selects the most influential data for the current policy. Experiments on models up to 7B parameters demonstrate that CROPI significantly accelerates training. On a 1.5B model, it achieves a 2.66x step-level acceleration while using only 10\% of the data per stage compared to full-dataset training. Our results highlight the substantial potential of influence-based data selection for efficient RLVR. --- ### Quantum Gated Recurrent GAN with Gaussian Uncertainty for Network Anomaly Detection Authors: Wajdi Hammami, Soumaya Cherkaoui, Jean-Frederic Laprade, Ola Ahmad, Shengrui Wang Published: 2025-10-30 Categories: cs.LG, cs.NI arXiv: https://arxiv.org/abs/2510.26487v1 Anomaly detection in time-series data is a critical challenge with significant implications for network security. Recent quantum machine learning approaches, such as quantum kernel methods and variational quantum circuits, have shown promise in capturing complex data distributions for anomaly detection but remain constrained by limited qubit counts. We introduce in this work a novel Quantum Gated Recurrent Unit (QGRU)-based Generative Adversarial Network (GAN) employing Successive Data Injection (SuDaI) and a multi-metric gating strategy for robust network anomaly detection. Our model uniquely utilizes a quantum-enhanced generator that outputs parameters (mean and log-variance) of a Gaussian distribution via reparameterization, combined with a Wasserstein critic to stabilize adversarial training. Anomalies are identified through a novel gating mechanism that initially flags potential anomalies based on Gaussian uncertainty estimates and subsequently verifies them using a composite of critic scores and reconstruction errors. Evaluated on benchmark datasets, our method achieves a high time-series aware F1 score (TaF1) of 89.43% demonstrating superior capability in detecting anomalies accurately and promptly as compared to existing classical and quantum models. Furthermore, the trained QGRU-WGAN was deployed on real IBM Quantum hardware, where it retained high anomaly detection performance, confirming its robustness and practical feasibility on current noisy intermediate-scale quantum (NISQ) devices. --- ### LINK-KG: LLM-Driven Coreference-Resolved Knowledge Graphs for Human Smuggling Networks Authors: Dipak Meher, Carlotta Domeniconi, Guadalupe Correa-Cabrera Published: 2025-10-30 Categories: cs.AI, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2510.26486v1 Human smuggling networks are complex and constantly evolving, making them difficult to analyze comprehensively. Legal case documents offer rich factual and procedural insights into these networks but are often long, unstructured, and filled with ambiguous or shifting references, posing significant challenges for automated knowledge graph (KG) construction. Existing methods either overlook coreference resolution or fail to scale beyond short text spans, leading to fragmented graphs and inconsistent entity linking. We propose LINK-KG, a modular framework that integrates a three-stage, LLM-guided coreference resolution pipeline with downstream KG extraction. At the core of our approach is a type-specific Prompt Cache, which consistently tracks and resolves references across document chunks, enabling clean and disambiguated narratives for structured knowledge graph construction from both short and long legal texts. LINK-KG reduces average node duplication by 45.21% and noisy nodes by 32.22% compared to baseline methods, resulting in cleaner and more coherent graph structures. These improvements establish LINK-KG as a strong foundation for analyzing complex criminal networks. --- ### Bayesian Network Fusion of Large Language Models for Sentiment Analysis Authors: Rasoul Amirzadeh, Dhananjay Thiruvady, Fatemeh Shiri Published: 2025-10-30 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.26484v1 Large language models (LLMs) continue to advance, with an increasing number of domain-specific variants tailored for specialised tasks. However, these models often lack transparency and explainability, can be costly to fine-tune, require substantial prompt engineering, yield inconsistent results across domains, and impose significant adverse environmental impact due to their high computational demands. To address these challenges, we propose the Bayesian network LLM fusion (BNLF) framework, which integrates predictions from three LLMs, including FinBERT, RoBERTa, and BERTweet, through a probabilistic mechanism for sentiment analysis. BNLF performs late fusion by modelling the sentiment predictions from multiple LLMs as probabilistic nodes within a Bayesian network. Evaluated across three human-annotated financial corpora with distinct linguistic and contextual characteristics, BNLF demonstrates consistent gains of about six percent in accuracy over the baseline LLMs, underscoring its robustness to dataset variability and the effectiveness of probabilistic fusion for interpretable sentiment classification. --- ### Who Has The Final Say? Conformity Dynamics in ChatGPT's Selections Authors: Clarissa Sabrina Arlinghaus, Tristan Kenneweg, Barbara Hammer, Günter W. Maier Published: 2025-10-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.26481v1 Large language models (LLMs) such as ChatGPT are increasingly integrated into high-stakes decision-making, yet little is known about their susceptibility to social influence. We conducted three preregistered conformity experiments with GPT-4o in a hiring context. In a baseline study, GPT consistently favored the same candidate (Profile C), reported moderate expertise (M = 3.01) and high certainty (M = 3.89), and rarely changed its choice. In Study 1 (GPT + 8), GPT faced unanimous opposition from eight simulated partners and almost always conformed (99.9%), reporting lower certainty and significantly elevated self-reported informational and normative conformity (p < .001). In Study 2 (GPT + 1), GPT interacted with a single partner and still conformed in 40.2% of disagreement trials, reporting less certainty and more normative conformity. Across studies, results demonstrate that GPT does not act as an independent observer but adapts to perceived social consensus. These findings highlight risks of treating LLMs as neutral decision aids and underline the need to elicit AI judgments prior to exposing them to human opinions. --- ### Statistical Inference for Matching Decisions via Matrix Completion under Dependent Missingness Authors: Congyuan Duan, Wanteng Ma, Dong Xia, Kan Xu Published: 2025-10-30 Categories: stat.ME, stat.ML arXiv: https://arxiv.org/abs/2510.26478v1 This paper studies decision-making and statistical inference for two-sided matching markets via matrix completion. In contrast to the independent sampling assumed in classical matrix completion literature, the observed entries, which arise from past matching data, are constrained by matching capacity. This matching-induced dependence poses new challenges for both estimation and inference in the matrix completion framework. We propose a non-convex algorithm based on Grassmannian gradient descent and establish near-optimal entrywise convergence rates for three canonical mechanisms, i.e., one-to-one matching, one-to-many matching with one-sided random arrival, and two-sided random arrival. To facilitate valid uncertainty quantification and hypothesis testing on matching decisions, we further develop a general debiasing and projection framework for arbitrary linear forms of the reward matrix, deriving asymptotic normality with finite-sample guarantees under matching-induced dependent sampling. Our empirical experiments demonstrate that the proposed approach provides accurate estimation, valid confidence intervals, and efficient evaluation of matching policies. --- ### ReSpec: Towards Optimizing Speculative Decoding in Reinforcement Learning Systems Authors: Qiaoling Chen, Zijun Liu, Peng Sun, Shenggui Li, Guoteng Wang, Ziming Liu, Yonggang Wen, Siyuan Feng, Tianwei Zhang Published: 2025-10-30 Categories: cs.LG, cs.DC arXiv: https://arxiv.org/abs/2510.26475v1 Adapting large language models (LLMs) via reinforcement learning (RL) is often bottlenecked by the generation stage, which can consume over 75\% of the training time. Speculative decoding (SD) accelerates autoregressive generation in serving systems, but its behavior under RL training remains largely unexplored. We identify three critical gaps that hinder the naive integration of SD into RL systems: diminishing speedups at large batch sizes, drafter staleness under continual actor updates, and drafter-induced policy degradation. To address these gaps, we present ReSpec, a system that adapts SD to RL through three complementary mechanisms: dynamically tuning SD configurations, evolving the drafter via knowledge distillation, and weighting updates by rollout rewards. On Qwen models (3B--14B), ReSpec achieves up to 4.5x speedup while preserving reward convergence and training stability, providing a practical solution for efficient RL-based LLM adaptation. --- ### Counteracting Matthew Effect in Self-Improvement of LVLMs through Head-Tail Re-balancing Authors: Xin Guo, Zhiheng Xi, Yiwen Ding, Yitao Zhai, Xiaowei Shi, Xunliang Cai, Tao Gui, Qi Zhang, Xuanjing Huang Published: 2025-10-30 Categories: cs.CV, cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2510.26474v1 Self-improvement has emerged as a mainstream paradigm for advancing the reasoning capabilities of large vision-language models (LVLMs), where models explore and learn from successful trajectories iteratively. However, we identify a critical issue during this process: the model excels at generating high-quality trajectories for simple queries (i.e., head data) but struggles with more complex ones (i.e., tail data). This leads to an imbalanced optimization that drives the model to prioritize simple reasoning skills, while hindering its ability to tackle more complex reasoning tasks. Over iterations, this imbalance becomes increasingly pronounced--a dynamic we term the "Matthew effect"--which ultimately hinders further model improvement and leads to performance bottlenecks. To counteract this challenge, we introduce four efficient strategies from two perspectives: distribution-reshaping and trajectory-resampling, to achieve head-tail re-balancing during the exploration-and-learning self-improvement process. Extensive experiments on Qwen2-VL-7B-Instruct and InternVL2.5-4B models across visual reasoning tasks demonstrate that our methods consistently improve visual reasoning capabilities, outperforming vanilla self-improvement by 3.86 points on average. --- ### Representation-Level Counterfactual Calibration for Debiased Zero-Shot Recognition Authors: Pei Peng, MingKun Xie, Hang Hao, Tong Jin, ShengJun Huang Published: 2025-10-30 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2510.26466v2 Object-context shortcuts remain a persistent challenge in vision-language models, undermining zero-shot reliability when test-time scenes differ from familiar training co-occurrences. We recast this issue as a causal inference problem and ask: Would the prediction remain if the object appeared in a different environment? To answer this at inference time, we estimate object and background expectations within CLIP's representation space, and synthesize counterfactual embeddings by recombining object features with diverse alternative contexts sampled from external datasets, batch neighbors, or text-derived descriptions. By estimating the Total Direct Effect and simulating intervention, we further subtract background-only activation, preserving beneficial object-context interactions while mitigating hallucinated scores. Without retraining or prompt design, our method substantially improves both worst-group and average accuracy on context-sensitive benchmarks, establishing a new zero-shot state of the art. Beyond performance, our framework provides a lightweight representation-level counterfactual approach, offering a practical causal avenue for debiased and reliable multimodal reasoning. --- ### Towards Fine-Grained Vision-Language Alignment for Few-Shot Anomaly Detection Authors: Yuanting Fan, Jun Liu, Xiaochen Chen, Bin-Bin Gao, Jian Li, Yong Liu, Jinlong Peng, Chengjie Wang Published: 2025-10-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.26464v1 Few-shot anomaly detection (FSAD) methods identify anomalous regions with few known normal samples. Most existing methods rely on the generalization ability of pre-trained vision-language models (VLMs) to recognize potentially anomalous regions through feature similarity between text descriptions and images. However, due to the lack of detailed textual descriptions, these methods can only pre-define image-level descriptions to match each visual patch token to identify potential anomalous regions, which leads to the semantic misalignment between image descriptions and patch-level visual anomalies, achieving sub-optimal localization performance. To address the above issues, we propose the Multi-Level Fine-Grained Semantic Caption (MFSC) to provide multi-level and fine-grained textual descriptions for existing anomaly detection datasets with automatic construction pipeline. Based on the MFSC, we propose a novel framework named FineGrainedAD to improve anomaly localization performance, which consists of two components: Multi-Level Learnable Prompt (MLLP) and Multi-Level Semantic Alignment (MLSA). MLLP introduces fine-grained semantics into multi-level learnable prompts through automatic replacement and concatenation mechanism, while MLSA designs region aggregation strategy and multi-level alignment training to facilitate learnable prompts better align with corresponding visual regions. Experiments demonstrate that the proposed FineGrainedAD achieves superior overall performance in few-shot settings on MVTec-AD and VisA datasets. --- ### Vectorized Context-Aware Embeddings for GAT-Based Collaborative Filtering Authors: Danial Ebrat, Sepideh Ahmadian, Luis Rueda Published: 2025-10-30 Categories: cs.IR, cs.LG arXiv: https://arxiv.org/abs/2510.26461v1 Recommender systems often struggle with data sparsity and cold-start scenarios, limiting their ability to provide accurate suggestions for new or infrequent users. This paper presents a Graph Attention Network (GAT) based Collaborative Filtering (CF) framework enhanced with Large Language Model (LLM) driven context aware embeddings. Specifically, we generate concise textual user profiles and unify item metadata (titles, genres, overviews) into rich textual embeddings, injecting these as initial node features in a bipartite user item graph. To further optimize ranking performance, we introduce a hybrid loss function that combines Bayesian Personalized Ranking (BPR) with a cosine similarity term and robust negative sampling, ensuring explicit negative feedback is distinguished from unobserved data. Experiments on the MovieLens 100k and 1M datasets show consistent improvements over state-of-the-art baselines in Precision, NDCG, and MAP while demonstrating robustness for users with limited interaction history. Ablation studies confirm the critical role of LLM-augmented embeddings and the cosine similarity term in capturing nuanced semantic relationships. Our approach effectively mitigates sparsity and cold-start limitations by integrating LLM-derived contextual understanding into graph-based architectures. Future directions include balancing recommendation accuracy with coverage and diversity, and introducing fairness-aware constraints and interpretability features to enhance system performance further. --- ### SecureReviewer: Enhancing Large Language Models for Secure Code Review through Secure-aware Fine-tuning Authors: Fang Liu, Simiao Liu, Yinghao Zhu, Xiaoli Lian, Li Zhang Published: 2025-10-30 Categories: cs.SE, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2510.26457v1 Identifying and addressing security issues during the early phase of the development lifecycle is critical for mitigating the long-term negative impacts on software systems. Code review serves as an effective practice that enables developers to check their teammates' code before integration into the codebase. To streamline the generation of review comments, various automated code review approaches have been proposed, where LLM-based methods have significantly advanced the capabilities of automated review generation. However, existing models primarily focus on general-purpose code review, their effectiveness in identifying and addressing security-related issues remains underexplored. Moreover, adapting existing code review approaches to target security issues faces substantial challenges, including data scarcity and inadequate evaluation metrics. To address these limitations, we propose SecureReviewer, a new approach designed for enhancing LLMs' ability to identify and resolve security-related issues during code review. Specifically, we first construct a dataset tailored for training and evaluating secure code review capabilities. Leveraging this dataset, we fine-tune LLMs to generate code review comments that can effectively identify security issues and provide fix suggestions with our proposed secure-aware fine-tuning strategy. To mitigate hallucination in LLMs and enhance the reliability of their outputs, we integrate the RAG technique, which grounds the generated comments in domain-specific security knowledge. Additionally, we introduce SecureBLEU, a new evaluation metric designed to assess the effectiveness of review comments in addressing security issues. Experimental results demonstrate that SecureReviewer outperforms state-of-the-art baselines in both security issue detection accuracy and the overall quality and practical utility of generated review comments. --- ### Robust Graph Condensation via Classification Complexity Mitigation Authors: Jiayi Luo, Qingyun Sun, Beining Yang, Haonan Yuan, Xingcheng Fu, Yanbiao Ma, Jianxin Li, Philip S. Yu Published: 2025-10-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.26451v2 Graph condensation (GC) has gained significant attention for its ability to synthesize smaller yet informative graphs. However, existing studies often overlook the robustness of GC in scenarios where the original graph is corrupted. In such cases, we observe that the performance of GC deteriorates significantly, while existing robust graph learning technologies offer only limited effectiveness. Through both empirical investigation and theoretical analysis, we reveal that GC is inherently an intrinsic-dimension-reducing process, synthesizing a condensed graph with lower classification complexity. Although this property is critical for effective GC performance, it remains highly vulnerable to adversarial perturbations. To tackle this vulnerability and improve GC robustness, we adopt the geometry perspective of graph data manifold and propose a novel Manifold-constrained Robust Graph Condensation framework named MRGC. Specifically, we introduce three graph data manifold learning modules that guide the condensed graph to lie within a smooth, low-dimensional manifold with minimal class ambiguity, thereby preserving the classification complexity reduction capability of GC and ensuring robust performance under universal adversarial attacks. Extensive experiments demonstrate the robustness of \ModelName\ across diverse attack scenarios. --- ### 1+1>2: A Synergistic Sparse and Low-Rank Compression Method for Large Language Models Authors: Zeliang Zong, Kai Zhang, Zheyang Li, Wenming Tan, Ye Ren, Yiyan Zhai, Jilin Hu Published: 2025-10-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.26446v1 Large Language Models (LLMs) have demonstrated remarkable proficiency in language comprehension and generation; however, their widespread adoption is constrained by substantial bandwidth and computational demands. While pruning and low-rank approximation have each demonstrated promising performance individually, their synergy for LLMs remains underexplored. We introduce \underline{S}ynergistic \underline{S}parse and \underline{L}ow-Rank \underline{C}ompression (SSLC) methods for LLMs, which leverages the strengths of both techniques: low-rank approximation compresses the model by retaining its essential structure with minimal information loss, whereas sparse optimization eliminates non-essential weights, preserving those crucial for generalization. Based on theoretical analysis, we first formulate the low-rank approximation and sparse optimization as a unified problem and solve it by iterative optimization algorithm. Experiments on LLaMA and Qwen2.5 models (7B-70B) show that SSLC, without any additional training steps, consistently surpasses standalone methods, achieving state-of-the-arts results. Notably, SSLC compresses Qwen2.5 by 50\% with no performance drop and achieves at least 1.63$\times$ speedup, offering a practical solution for efficient LLM deployment. --- ### Personalized Treatment Outcome Prediction from Scarce Data via Dual-Channel Knowledge Distillation and Adaptive Fusion Authors: Wenjie Chen, Li Zhuang, Ziying Luo, Yu Liu, Jiahao Wu, Shengcai Liu Published: 2025-10-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.26444v2 Personalized treatment outcome prediction based on trial data for small-sample and rare patient groups is a critical task in precision medicine. However, the high cost and scarcity of trial data limit the prediction performance. To address this issue, we propose a cross-fidelity knowledge distillation and adaptive fusion network (CFKD-AFN), which leverages abundant but low-fidelity simulation data to enhance the prediction on scarce but high-fidelity trial data. CFKD-AFN incorporates a dual-channel knowledge distillation module to extract complementary knowledge from the low-fidelity model, along with an attention-guided fusion module to adaptively integrate multi-source information. Experiments on chronic obstructive pulmonary disease show that CFKD-AFN reduces the mean squared error by 6.67% ~ 74.55% and the mean absolute percentage error by 1.43% ~ 51.54% compared to the evaluated competing methods and remains robust to varying high-fidelity dataset sizes. Furthermore, we extend the CFKD-AFN framework to an interpretable variant for exploratory analysis of feature-attribution patterns associated with treatment outcomes. --- ### PointSt3R: Point Tracking through 3D Grounded Correspondence Authors: Rhodri Guerrier, Adam W. Harley, Dima Damen Published: 2025-10-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.26443v1 Recent advances in foundational 3D reconstruction models, such as DUSt3R and MASt3R, have shown great potential in 2D and 3D correspondence in static scenes. In this paper, we propose to adapt them for the task of point tracking through 3D grounded correspondence. We first demonstrate that these models are competitive point trackers when focusing on static points, present in current point tracking benchmarks ($+33.5\%$ on EgoPoints vs. CoTracker2). We propose to combine the reconstruction loss with training for dynamic correspondence along with a visibility head, and fine-tuning MASt3R for point tracking using a relatively small amount of synthetic data. Importantly, we only train and evaluate on pairs of frames where one contains the query point, effectively removing any temporal context. Using a mix of dynamic and static point correspondences, we achieve competitive or superior point tracking results on four datasets (e.g. competitive on TAP-Vid-DAVIS 73.8 $δ_{avg}$ / 85.8\% occlusion acc. for PointSt3R compared to 75.7 / 88.3\% for CoTracker2; and significantly outperform CoTracker3 on EgoPoints 61.3 vs 54.2 and RGB-S 87.0 vs 82.8). We also present results on 3D point tracking along with several ablations on training datasets and percentage of dynamic correspondences. --- ### A-TPT: Angular Diversity Calibration Properties for Test-Time Prompt Tuning of Vision-Language Models Authors: Shihab Aaqil Ahamed, Udaya S. K. P. Miriya Thanthrige, Ranga Rodrigo, Muhammad Haris Khan Published: 2025-10-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.26441v2 Test-time prompt tuning (TPT) has emerged as a promising technique for adapting large vision-language models (VLMs) to unseen tasks without relying on labeled data. However, the lack of dispersion between textual features can hurt calibration performance, which raises concerns about VLMs' reliability, trustworthiness, and safety. Current TPT approaches primarily focus on improving prompt calibration by either maximizing average textual feature dispersion or enforcing orthogonality constraints to encourage angular separation. However, these methods may not always have optimal angular separation between class-wise textual features, which implies overlooking the critical role of angular diversity. To address this, we propose A-TPT, a novel TPT framework that introduces angular diversity to encourage uniformity in the distribution of normalized textual features induced by corresponding learnable prompts. This uniformity is achieved by maximizing the minimum pairwise angular distance between features on the unit hypersphere. We show that our approach consistently surpasses state-of-the-art TPT methods in reducing the aggregate average calibration error while maintaining comparable accuracy through extensive experiments with various backbones on different datasets. Notably, our approach exhibits superior zero-shot calibration performance on natural distribution shifts and generalizes well to medical datasets. We provide extensive analyses, including theoretical aspects, to establish the grounding of A-TPT. These results highlight the potency of promoting angular diversity to achieve well-dispersed textual features, significantly improving VLM calibration during test-time adaptation. Our code will be made publicly available. --- ### Co-Evolving Latent Action World Models Authors: Yucen Wang, Fengming Zhang, De-Chuan Zhan, Li Zhao, Kaixin Wang, Jiang Bian Published: 2025-10-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.26433v2 Adapting pretrained video generation models into controllable world models via latent actions is a promising step towards creating generalist world models. The dominant paradigm adopts a two-stage approach that trains latent action model (LAM) and the world model separately, resulting in redundant training and limiting their potential for co-adaptation. A conceptually simple and appealing idea is to directly replace the forward dynamic model in LAM with a powerful world model and training them jointly, but it is non-trivial and prone to representational collapse. In this work, we propose CoLA-World, which for the first time successfully realizes this synergistic paradigm, resolving the core challenge in joint learning through a critical warm-up phase that effectively aligns the representations of the from-scratch LAM with the pretrained world model. This unlocks a co-evolution cycle: the world model acts as a knowledgeable tutor, providing gradients to shape a high-quality LAM, while the LAM offers a more precise and adaptable control interface to the world model. Empirically, CoLA-World matches or outperforms prior two-stage methods in both video simulation quality and downstream visual planning, establishing a robust and efficient new paradigm for the field. --- ### Nexus: Execution-Grounded Multi-Agent Test Oracle Synthesis Authors: Dong Huang, Mingzhe Du, Jie M. Zhang, Zheng Lin, Meng Luo, Qianru Zhang, See-Kiong Ng Published: 2025-10-30 Categories: cs.SE, cs.CL arXiv: https://arxiv.org/abs/2510.26423v1 Test oracle generation in non-regression testing is a longstanding challenge in software engineering, where the goal is to produce oracles that can accurately determine whether a function under test (FUT) behaves as intended for a given input. In this paper, we introduce Nexus, a novel multi-agent framework to address this challenge. Nexus generates test oracles by leveraging a diverse set of specialized agents that synthesize test oracles through a structured process of deliberation, validation, and iterative self-refinement. During the deliberation phase, a panel of four specialist agents, each embodying a distinct testing philosophy, collaboratively critiques and refines an initial set of test oracles. Then, in the validation phase, Nexus generates a plausible candidate implementation of the FUT and executes the proposed oracles against it in a secure sandbox. For any oracle that fails this execution-based check, Nexus activates an automated selfrefinement loop, using the specific runtime error to debug and correct the oracle before re-validation. Our extensive evaluation on seven diverse benchmarks demonstrates that Nexus consistently and substantially outperforms state-of-theart baselines. For instance, Nexus improves the test-level oracle accuracy on the LiveCodeBench from 46.30% to 57.73% for GPT-4.1-Mini. The improved accuracy also significantly enhances downstream tasks: the bug detection rate of GPT4.1-Mini generated test oracles on HumanEval increases from 90.91% to 95.45% for Nexus compared to baselines, and the success rate of automated program repair improves from 35.23% to 69.32%. --- ### OmniEduBench: A Comprehensive Chinese Benchmark for Evaluating Large Language Models in Education Authors: Min Zhang, Hao Chen, Hao Chen, Wenqi Zhang, Didi Zhu, Xin Lin, Bo Jiang, Aimin Zhou, Fei Wu, Kun Kuang Published: 2025-10-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.26422v1 With the rapid development of large language models (LLMs), various LLM-based works have been widely applied in educational fields. However, most existing LLMs and their benchmarks focus primarily on the knowledge dimension, largely neglecting the evaluation of cultivation capabilities that are essential for real-world educational scenarios. Additionally, current benchmarks are often limited to a single subject or question type, lacking sufficient diversity. This issue is particularly prominent within the Chinese context. To address this gap, we introduce OmniEduBench, a comprehensive Chinese educational benchmark. OmniEduBench consists of 24.602K high-quality question-answer pairs. The data is meticulously divided into two core dimensions: the knowledge dimension and the cultivation dimension, which contain 18.121K and 6.481K entries, respectively. Each dimension is further subdivided into 6 fine-grained categories, covering a total of 61 different subjects (41 in the knowledge and 20 in the cultivation). Furthermore, the dataset features a rich variety of question formats, including 11 common exam question types, providing a solid foundation for comprehensively evaluating LLMs' capabilities in education. Extensive experiments on 11 mainstream open-source and closed-source LLMs reveal a clear performance gap. In the knowledge dimension, only Gemini-2.5 Pro surpassed 60\% accuracy, while in the cultivation dimension, the best-performing model, QWQ, still trailed human intelligence by nearly 30\%. These results highlight the substantial room for improvement and underscore the challenges of applying LLMs in education. --- ### SSCL-BW: Sample-Specific Clean-Label Backdoor Watermarking for Dataset Ownership Verification Authors: Yingjia Wang, Ting Qiao, Xing Liu, Chongzuo Li, Sixing Wu, Jianbin Li Published: 2025-10-30 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2510.26420v1 The rapid advancement of deep neural networks (DNNs) heavily relies on large-scale, high-quality datasets. However, unauthorized commercial use of these datasets severely violates the intellectual property rights of dataset owners. Existing backdoor-based dataset ownership verification methods suffer from inherent limitations: poison-label watermarks are easily detectable due to label inconsistencies, while clean-label watermarks face high technical complexity and failure on high-resolution images. Moreover, both approaches employ static watermark patterns that are vulnerable to detection and removal. To address these issues, this paper proposes a sample-specific clean-label backdoor watermarking (i.e., SSCL-BW). By training a U-Net-based watermarked sample generator, this method generates unique watermarks for each sample, fundamentally overcoming the vulnerability of static watermark patterns. The core innovation lies in designing a composite loss function with three components: target sample loss ensures watermark effectiveness, non-target sample loss guarantees trigger reliability, and perceptual similarity loss maintains visual imperceptibility. During ownership verification, black-box testing is employed to check whether suspicious models exhibit predefined backdoor behaviors. Extensive experiments on benchmark datasets demonstrate the effectiveness of the proposed method and its robustness against potential watermark removal attacks. --- ### Chain-of-Thought Hijacking Authors: Jianli Zhao, Tingchen Fu, Rylan Schaeffer, Mrinank Sharma, Fazl Barez Published: 2025-10-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.26418v4 Large Reasoning Models (LRMs) improve task performance through extended inference-time reasoning. Although previous studies suggest that longer reasoning should lead to more robust safety behavior, we find evidence to the contrary: over-extended reasoning can instead be exploited to systematically weaken refusal behavior. We propose Chain-of-Thought Hijacking, a simple yet effective black-box jailbreak attack that induces LRMs to engage in prolonged benign puzzle-solving reasoning, often lasting more than five minutes, before eliciting harmful compliance. Across HarmBench, CoT Hijacking achieves attack success rates of 99%, 94%, 100%, and 94% on Gemini 2.5 Pro, ChatGPT o4 Mini, Grok 3 Mini, and Claude 4 Sonnet, respectively. To understand why this attack succeeds, we conduct activation probing, attention-pattern analysis, and causal interventions on open-source reasoning models. Our results indicate that refusal behavior depends on a low-dimensional safety signal whose expression weakens as reasoning traces grow longer. In particular, extended benign reasoning shifts attention away from harmful intentions and attenuates refusal-related activations, producing what we call refusal dilution. These findings demonstrate that excessively prolonged reasoning can introduce a systematic jailbreak attack surface. We release our evaluation materials to support reproducibility and further research. --- ### LoCoT2V-Bench: Benchmarking Long-Form and Complex Text-to-Video Generation Authors: Xiangqing Zheng, Chengyue Wu, Kehai Chen, Min Zhang Published: 2025-10-30 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2510.26412v3 Recent advances in text-to-video generation have achieved impressive performance on short clips, yet evaluating long-form generation under complex textual inputs remains a significant challenge. In response to this challenge, we present LoCoT2V-Bench, a benchmark for long video generation (LVG) featuring multi-scene prompts with hierarchical metadata (e.g., character settings and camera behaviors), constructed from collected real-world videos. We further propose LoCoT2V-Eval, a multi-dimensional framework covering perceptual quality, text-video alignment, temporal quality, dynamic quality, and Human Expectation Realization Degree (HERD), with an emphasis on aspects such as fine-grained text-video alignment and temporal character consistency. Experiments on 17 representative LVG models reveal pronounced capability disparities across evaluation dimensions, with strong perceptual quality and background consistency but markedly weaker fine-grained text-video alignment and character consistency. These findings suggest that improving prompt faithfulness and identity preservation remains a key challenge for long-form video generation. Our code and data are released at https://github.com/XqZeppelinhead0702/LoCoT2V-Bench --- ### MedSAE: Dissecting MedCLIP Representations with Sparse Autoencoders Authors: Riccardo Renzulli, Colas Lepoutre, Enrico Cassano, Marco Grangetto Published: 2025-10-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.26411v2 Artificial intelligence in healthcare requires models that are accurate and interpretable. We advance mechanistic interpretability in medical vision by applying Medical Sparse Autoencoders (MedSAEs) to the latent space of MedCLIP, a vision-language model trained on chest radiographs and reports. To quantify interpretability, we propose an evaluation framework that combines correlation metrics, entropy analyses, and automated neuron naming via the MedGemma foundation model. Experiments on the CheXpert dataset show that MedSAE neurons achieve higher monosemanticity and interpretability than raw MedCLIP features. Our findings bridge high-performing medical AI and transparency, offering a scalable step toward clinically reliable representations. The source code supporting the findings of this study is available at https://github.com/EIDOSLAB/MedSAE. --- ### Human-in-the-loop Online Rejection Sampling for Robotic Manipulation Authors: Guanxing Lu, Rui Zhao, Haitao Lin, He Zhang, Yansong Tang Published: 2025-10-30 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2510.26406v1 Reinforcement learning (RL) is widely used to produce robust robotic manipulation policies, but fine-tuning vision-language-action (VLA) models with RL can be unstable due to inaccurate value estimates and sparse supervision at intermediate steps. In contrast, imitation learning (IL) is easy to train but often underperforms due to its offline nature. In this paper, we propose Hi-ORS, a simple yet effective post-training method that utilizes rejection sampling to achieve both training stability and high robustness. Hi-ORS stabilizes value estimation by filtering out negatively rewarded samples during online fine-tuning, and adopts a reward-weighted supervised training objective to provide dense intermediate-step supervision. For systematic study, we develop an asynchronous inference-training framework that supports flexible online human-in-the-loop corrections, which serve as explicit guidance for learning error-recovery behaviors. Across three real-world tasks and two embodiments, Hi-ORS fine-tunes a pi-base policy to master contact-rich manipulation in just 1.5 hours of real-world training, outperforming RL and IL baselines by a substantial margin in both effectiveness and efficiency. Notably, the fine-tuned policy exhibits strong test-time scalability by reliably executing complex error-recovery behaviors to achieve better performance. --- ### Autograder+: A Multi-Faceted AI Framework for Rich Pedagogical Feedback in Programming Education Authors: Vikrant Sahu, Gagan Raj Gupta, Raghav Borikar, Nitin Mane Published: 2025-10-30 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.26402v1 The rapid growth of programming education has outpaced traditional assessment tools, leaving faculty with limited means to provide meaningful, scalable feedback. Conventional autograders, while efficient, act as black-box systems that simply return pass/fail results, offering little insight into student thinking or learning needs. Autograder+ is designed to shift autograding from a purely summative process to a formative learning experience. It introduces two key capabilities: automated feedback generation using a fine-tuned Large Language Model, and visualization of student code submissions to uncover learning patterns. The model is fine-tuned on curated student code and expert feedback to ensure pedagogically aligned, context-aware guidance. In evaluation across 600 student submissions from multiple programming tasks, the system produced feedback with strong semantic alignment to instructor comments. For visualization, contrastively learned code embeddings trained on 1,000 annotated submissions enable grouping solutions into meaningful clusters based on functionality and approach. The system also supports prompt-pooling, allowing instructors to guide feedback style through selected prompt templates. By integrating AI-driven feedback, semantic clustering, and interactive visualization, Autograder+ reduces instructor workload while supporting targeted instruction and promoting stronger learning outcomes. --- ### Multi-Output Robust and Conjugate Gaussian Processes Authors: Joshua Rooijakkers, Leiv Rønneberg, François-Xavier Briol, Jeremias Knoblauch, Matias Altamirano Published: 2025-10-30 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2510.26401v1 Multi-output Gaussian process (MOGP) regression allows modelling dependencies among multiple correlated response variables. Similarly to standard Gaussian processes, MOGPs are sensitive to model misspecification and outliers, which can distort predictions within individual outputs. This situation can be further exacerbated by multiple anomalous response variables whose errors propagate due to correlations between outputs. To handle this situation, we extend and generalise the robust and conjugate Gaussian process (RCGP) framework introduced by Altamirano et al. (2024). This results in the multi-output RCGP (MO-RCGP): a provably robust MOGP that is conjugate, and jointly captures correlations across outputs. We thoroughly evaluate our approach through applications in finance and cancer research. ---