# Research Papers — 2025-10 · bundle page 12 of 217 > Full-text markdown of papers #551–600 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/12 [← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/11.md) [Next bundle →](https://aipod.dev/papers/archive/2025-10/page/13.md) ### A Pragmatic View of AI Personhood Authors: Joel Z. Leibo, Alexander Sasha Vezhnevets, William A. Cunningham, Stanley M. Bileschi Published: 2025-10-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.26396v1 The emergence of agentic Artificial Intelligence (AI) is set to trigger a "Cambrian explosion" of new kinds of personhood. This paper proposes a pragmatic framework for navigating this diversification by treating personhood not as a metaphysical property to be discovered, but as a flexible bundle of obligations (rights and responsibilities) that societies confer upon entities for a variety of reasons, especially to solve concrete governance problems. We argue that this traditional bundle can be unbundled, creating bespoke solutions for different contexts. This will allow for the creation of practical tools -- such as facilitating AI contracting by creating a target "individual" that can be sanctioned -- without needing to resolve intractable debates about an AI's consciousness or rationality. We explore how individuals fit in to social roles and discuss the use of decentralized digital identity technology, examining both "personhood as a problem", where design choices can create "dark patterns" that exploit human social heuristics, and "personhood as a solution", where conferring a bundle of obligations is necessary to ensure accountability or prevent conflict. By rejecting foundationalist quests for a single, essential definition of personhood, this paper offers a more pragmatic and flexible way to think about integrating AI agents into our society. --- ### Multi-Task Learning Based on Support Vector Machines and Twin Support Vector Machines: A Comprehensive Survey Authors: Fatemeh Bazikar, Hossein Moosaei, Atefeh Hemmati, Panos M. Pardalos Published: 2025-10-30 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2510.26392v1 Multi-task learning (MTL) enables simultaneous training across related tasks, leveraging shared information to improve generalization, efficiency, and robustness, especially in data-scarce or high-dimensional scenarios. While deep learning dominates recent MTL research, Support Vector Machines (SVMs) and Twin SVMs (TWSVMs) remain relevant due to their interpretability, theoretical rigor, and effectiveness with small datasets. This chapter surveys MTL approaches based on SVM and TWSVM, highlighting shared representations, task regularization, and structural coupling strategies. Special attention is given to emerging TWSVM extensions for multi-task settings, which show promise but remain underexplored. We compare these models in terms of theoretical properties, optimization strategies, and empirical performance, and discuss applications in fields such as computer vision, natural language processing, and bioinformatics. Finally, we identify research gaps and outline future directions for building scalable, interpretable, and reliable margin-based MTL frameworks. This work provides a comprehensive resource for researchers and practitioners interested in SVM- and TWSVM-based multi-task learning. --- ### EEG-Driven Image Reconstruction with Saliency-Guided Diffusion Models Authors: Igor Abramov, Ilya Makarov Published: 2025-10-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.26391v1 Existing EEG-driven image reconstruction methods often overlook spatial attention mechanisms, limiting fidelity and semantic coherence. To address this, we propose a dual-conditioning framework that combines EEG embeddings with spatial saliency maps to enhance image generation. Our approach leverages the Adaptive Thinking Mapper (ATM) for EEG feature extraction and fine-tunes Stable Diffusion 2.1 via Low-Rank Adaptation (LoRA) to align neural signals with visual semantics, while a ControlNet branch conditions generation on saliency maps for spatial control. Evaluated on THINGS-EEG, our method achieves a significant improvement in the quality of low- and high-level image features over existing approaches. Simultaneously, strongly aligning with human visual attention. The results demonstrate that attentional priors resolve EEG ambiguities, enabling high-fidelity reconstructions with applications in medical diagnostics and neuroadaptive interfaces, advancing neural decoding through efficient adaptation of pre-trained diffusion models. --- ### SPG-CDENet: Spatial Prior-Guided Cross Dual Encoder Network for Multi-Organ Segmentation Authors: Xizhi Tian, Changjun Zhou, Yulin. Yang Published: 2025-10-30 Categories: eess.IV, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2510.26390v1 Multi-organ segmentation is a critical task in computer-aided diagnosis. While recent deep learning methods have achieved remarkable success in image segmentation, huge variations in organ size and shape challenge their effectiveness in multi-organ segmentation. To address these challenges, we propose a Spatial Prior-Guided Cross Dual Encoder Network (SPG-CDENet), a novel two-stage segmentation paradigm designed to improve multi-organ segmentation accuracy. Our SPG-CDENet consists of two key components: a spatial prior network and a cross dual encoder network. The prior network generates coarse localization maps that delineate the approximate ROI, serving as spatial guidance for the dual encoder network. The cross dual encoder network comprises four essential components: a global encoder, a local encoder, a symmetric cross-attention module, and a flow-based decoder. The global encoder captures global semantic features from the entire image, while the local encoder focuses on features from the prior network. To enhance the interaction between the global and local encoders, a symmetric cross-attention module is proposed across all layers of the encoders to fuse and refine features. Furthermore, the flow-based decoder directly propagates high-level semantic features from the final encoder layer to all decoder layers, maximizing feature preservation and utilization. Extensive qualitative and quantitative experiments on two public datasets demonstrate the superior performance of SPG-CDENet compared to existing segmentation methods. Furthermore, ablation studies further validate the effectiveness of the proposed modules in improving segmentation accuracy. --- ### Adaptive Context Length Optimization with Low-Frequency Truncation for Multi-Agent Reinforcement Learning Authors: Wenchang Duan, Yaoliang Yu, Jiwan He, Yi Shi Published: 2025-10-30 Categories: cs.LG, cs.MA arXiv: https://arxiv.org/abs/2510.26389v2 Recently, deep multi-agent reinforcement learning (MARL) has demonstrated promising performance for solving challenging tasks, such as long-term dependencies and non-Markovian environments. Its success is partly attributed to conditioning policies on large fixed context length. However, such large fixed context lengths may lead to limited exploration efficiency and redundant information. In this paper, we propose a novel MARL framework to obtain adaptive and effective contextual information. Specifically, we design a central agent that dynamically optimizes context length via temporal gradient analysis, enhancing exploration to facilitate convergence to global optima in MARL. Furthermore, to enhance the adaptive optimization capability of the context length, we present an efficient input representation for the central agent, which effectively filters redundant information. By leveraging a Fourier-based low-frequency truncation method, we extract global temporal trends across decentralized agents, providing an effective and efficient representation of the MARL environment. Extensive experiments demonstrate that the proposed method achieves state-of-the-art (SOTA) performance on long-term dependency tasks, including PettingZoo, MiniGrid, Google Research Football (GRF), and StarCraft Multi-Agent Challenge v2 (SMACv2). --- ### Scales++: Compute Efficient Evaluation Subset Selection with Cognitive Scales Embeddings Authors: Andrew M. Bean, Nabeel Seedat, Shengzhuang Chen, Jonathan Richard Schwarz Published: 2025-10-30 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.26384v2 The prohibitive cost of evaluating large language models (LLMs) on comprehensive benchmarks necessitates the creation of small yet representative data subsets (i.e., tiny benchmarks) that enable efficient assessment while retaining predictive fidelity. Current methods for this task operate under a model-centric paradigm, selecting benchmarking items based on the collective performance of existing models. Such approaches are limited by large upfront costs, an inability to immediately handle new benchmarks ("cold-start"), and the fragile assumption that future models will share the failure patterns of their predecessors. In this work, we propose a new item-centric approach to benchmark subset selection, arguing that selection should be based on the intrinsic properties of the task items themselves, rather than on model-specific failure patterns. We instantiate this item-centric efficient benchmarking approach via a novel method, Scales++, where data selection is based on the cognitive demands of the benchmark samples. Empirically, we show Scales++ reduces the upfront selection cost by over 18x while achieving competitive predictive fidelity. On the Open LLM Leaderboard, using just a 0.25% data subset, we predict full benchmark scores with a 3.2% mean absolute error, and on Humanity's Last Exam we predict full scores with 2.9% mean absolute error using a 2.0% sample. We demonstrate that this item-centric approach enables more efficient model evaluation without significant fidelity degradation, while also providing better cold-start performance and more interpretable benchmarking. --- ### Advancing Forest Fires Classification using Neurochaos Learning Authors: Kunal Kumar Pant, Remya Ajai A S, Nithin Nagaraj Published: 2025-10-30 Categories: cs.NE arXiv: https://arxiv.org/abs/2510.26383v1 Forest fires are among the most dangerous and unpredictable natural disasters worldwide. Forest fire can be instigated by natural causes or by humans. They are devastating overall, and thus, many research efforts have been carried out to predict whether a fire can occur in an area given certain environmental variables. Many research works employ Machine Learning (ML) and Deep Learning (DL) models for classification; however, their accuracy is merely adequate and falls short of expectations. This limit arises because these models are unable to depict the underlying nonlinearity in nature and extensively rely on substantial training data, which is hard to obtain. We propose using Neurochaos Learning (NL), a chaos-based, brain-inspired learning algorithm for forest fire classification. Like our brains, NL needs less data to learn nonlinear patterns in the training data. It employs one-dimensional chaotic maps, namely the Generalized Lüroth Series (GLS), as neurons. NL yields comparable performance with ML and DL models, sometimes even surpassing them, particularly in low-sample training regimes, and unlike deep neural networks, NL is interpretable as it preserves causal structures in the data. Random Heterogenous Neurochaos Learning (RHNL), a type of NL where different chaotic neurons are randomnly located to mimic the randomness and heterogeneity of human brain gives the best F1 score of 1.0 for the Algerian Forest Fires Dataset. Compared to other traditional ML classifiers considered, RHNL also gives high precision score of 0.90 for Canadian Forest Fires Dataset and 0.68 for Portugal Forest Fires Dataset. The results obtained from this work indicate that Neurochaos Learning (NL) architectures achieve better performance than conventional machine learning classifiers, highlighting their promise for developing more efficient and reliable forest fire detection systems. --- ### AI Mathematician as a Partner in Advancing Mathematical Discovery -- A Case Study in Homogenization Theory Authors: Yuanhang Liu, Beichen Wang, Peng Li, Yang Liu Published: 2025-10-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.26380v1 Artificial intelligence (AI) has demonstrated impressive progress in mathematical reasoning, yet its integration into the practice of mathematical research remains limited. In this study, we investigate how the AI Mathematician (AIM) system can operate as a research partner rather than a mere problem solver. Focusing on a challenging problem in homogenization theory, we analyze the autonomous reasoning trajectories of AIM and incorporate targeted human interventions to structure the discovery process. Through iterative decomposition of the problem into tractable subgoals, selection of appropriate analytical methods, and validation of intermediate results, we reveal how human intuition and machine computation can complement one another. This collaborative paradigm enhances the reliability, transparency, and interpretability of the resulting proofs, while retaining human oversight for formal rigor and correctness. The approach leads to a complete and verifiable proof, and more broadly, demonstrates how systematic human-AI co-reasoning can advance the frontier of mathematical discovery. --- ### Efficient Generative AI Boosts Probabilistic Forecasting of Sudden Stratospheric Warmings Authors: Ningning Tao, Fei Xie, Baoxiang Pan, Hongyu Wang, Han Huang, Zhongpu Qiu, Ke Gui, Jiali Luo, Xiaosong Chen Published: 2025-10-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.26376v2 Sudden Stratospheric Warmings (SSWs) are key sources of subseasonal predictability and major drivers of extreme weather in winter. Accurate and efficient probabilistic forecasting of these events remains a persistent challenge for Numerical Weather Prediction (NWP) systems due to computational bottlenecks and limitations in physical representation. While data-driven forecasting is rapidly evolving, its application to the complex, three-dimensional dynamics of SSWs remains underexplored. Here, we bridge this gap by developing a Flow Matching-based generative AI model (FM-Cast) for efficient and skillful probabilistic forecasting of the spatiotemporal evolution of stratospheric circulation in winter. Evaluated across 18 major SSW events (1998-2024), FM-Cast successfully forecasts the onset, intensity, and 3D morphology of the polar vortex up to 15 days in advance for most cases. Notably, it achieves long-range probabilistic forecast skill comparable to or exceeding leading operational NWP systems (ECMWF and CMA) while generating a 30-day forecast with 50-member ensemble, in just two minutes on a consumer GPU. Furthermore, using idealized "perfect troposphere" experiments, we uncover distinct predictability regimes: events driven by continuous wave forcing versus those governed by an initial trigger and subsequent stratospheric dynamical memory. This work establishes a computationally efficient paradigm for probabilistic stratospheric forecasting that simultaneously deepens our physical understanding of atmosphere-climate dynamics. --- ### BOTS: A Unified Framework for Bayesian Online Task Selection in LLM Reinforcement Finetuning Authors: Qianli Shen, Daoyuan Chen, Yilun Huang, Zhenqing Ling, Yaliang Li, Bolin Ding, Jingren Zhou Published: 2025-10-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.26374v3 Reinforcement finetuning (RFT) is a key technique for aligning Large Language Models (LLMs) with human preferences and enhancing reasoning, yet its effectiveness is highly sensitive to which tasks are explored during training. Uniform task sampling is inefficient, wasting computation on tasks that are either trivial or unsolvable, while existing task selection methods often suffer from high rollout costs, poor adaptivity, or incomplete evidence. We introduce BOTS, a unified framework for Bayesian Online Task Selection in LLM reinforcement finetuning. Grounded in Bayesian inference, BOTS adaptively maintains posterior estimates of task difficulty as the model evolves. It jointly incorporates explicit evidence from direct evaluations of selected tasks and implicit evidence inferred from these evaluations for unselected tasks, with Thompson sampling ensuring a principled balance between exploration and exploitation for task selection. To make implicit evidence practical, we instantiate it with an ultra-light interpolation-based plug-in that estimates difficulties of tasks without extra rollouts, adding negligible overhead. Empirically, across diverse domains and LLM scales, BOTS consistently improves data efficiency and performance over baselines and ablations, providing a practical and extensible solution for dynamic task selection in RFT. Code is available at https://github.com/agentscope-ai/Trinity-RFT/tree/main/examples/bots. --- ### CorVS+: Correspondence-Driven Association of Video Trajectories and Sensors for Identity-Aware Person Localization in Warehouses Authors: Kazuma Kano, Yuki Mori, Shin Katayama, Kenta Urano, Takuro Yonezawa, Nobuo Kawaguchi Published: 2025-10-30 Categories: cs.LG, cs.CV, cs.RO arXiv: https://arxiv.org/abs/2510.26369v2 Logistics warehouses have struggled with labor shortages, but the inbound processes remain particularly human-powered. Worker location data is a key to higher productivity in such cases. Fixed cameras are a promising tool for localization, as they also offer valuable environmental information such as package status. However, identifying individuals from visual data alone is often impractical. To enable identity-aware localization, prior studies have attempted to identify people in videos by associating their trajectories with wearable sensor measurements. Although this appearance-independent approach has several advantages, existing methods may fail under real-world conditions. Therefore, we propose CorVS+, a novel data-driven person identification framework based on the correspondence between visual tracking trajectories and sensor measurements. Firstly, our deep learning model predicts the correspondence probabilities and reliabilities for every pair of a trajectory and sensor measurements. Secondly, our algorithm matches the pairs over time based on the model predictions. We developed a dataset comprising 27 hours of sensor measurements and 38 km of trajectories in a warehouse. This dataset covers actual activities and challenging situations, such as multiple stationary workers inspecting items. The evaluation indicated the superiority of CorVS+ over existing methods and the effectiveness of its unique designs for industrial-scale settings. The model and dataset will be available at https://doi.org/10.5281/zenodo.17745683. --- ### AgriGS-SLAM: Orchard Mapping Across Seasons via Multi-View Gaussian Splatting SLAM Authors: Mirko Usuelli, David Rapado-Rincon, Gert Kootstra, Matteo Matteucci Published: 2025-10-30 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2510.26358v1 Autonomous robots in orchards require real-time 3D scene understanding despite repetitive row geometry, seasonal appearance changes, and wind-driven foliage motion. We present AgriGS-SLAM, a Visual--LiDAR SLAM framework that couples direct LiDAR odometry and loop closures with multi-camera 3D Gaussian Splatting (3DGS) rendering. Batch rasterization across complementary viewpoints recovers orchard structure under occlusions, while a unified gradient-driven map lifecycle executed between keyframes preserves fine details and bounds memory. Pose refinement is guided by a probabilistic LiDAR-based depth consistency term, back-propagated through the camera projection to tighten geometry-appearance coupling. We deploy the system on a field platform in apple and pear orchards across dormancy, flowering, and harvesting, using a standardized trajectory protocol that evaluates both training-view and novel-view synthesis to reduce 3DGS overfitting in evaluation. Across seasons and sites, AgriGS-SLAM delivers sharper, more stable reconstructions and steadier trajectories than recent state-of-the-art 3DGS-SLAM baselines while maintaining real-time performance on-tractor. While demonstrated in orchard monitoring, the approach can be applied to other outdoor domains requiring robust multimodal perception. --- ### On the Role of Context for Discourse Relation Classification in Scientific Writing Authors: Stephen Wan, Wei Liu, Michael Strube Published: 2025-10-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.26354v1 With the increasing use of generative Artificial Intelligence (AI) methods to support science workflows, we are interested in the use of discourse-level information to find supporting evidence for AI generated scientific claims. A first step towards this objective is to examine the task of inferring discourse structure in scientific writing. In this work, we present a preliminary investigation of pretrained language model (PLM) and Large Language Model (LLM) approaches for Discourse Relation Classification (DRC), focusing on scientific publications, an under-studied genre for this task. We examine how context can help with the DRC task, with our experiments showing that context, as defined by discourse structure, is generally helpful. We also present an analysis of which scientific discourse relation types might benefit most from context. --- ### Towards Explainable and Reliable AI in Finance Authors: Albi Isufaj, Pablo Mollá, Helmut Prendinger Published: 2025-10-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.26353v1 Financial forecasting increasingly uses large neural network models, but their opacity raises challenges for trust and regulatory compliance. We present several approaches to explainable and reliable AI in finance. \emph{First}, we describe how Time-LLM, a time series foundation model, uses a prompt to avoid a wrong directional forecast. \emph{Second}, we show that combining foundation models for time series forecasting with a reliability estimator can filter our unreliable predictions. \emph{Third}, we argue for symbolic reasoning encoding domain rules for transparent justification. These approaches shift emphasize executing only forecasts that are both reliable and explainable. Experiments on equity and cryptocurrency data show that the architecture reduces false positives and supports selective execution. By integrating predictive performance with reliability estimation and rule-based reasoning, our framework advances transparent and auditable financial AI systems. --- ### The Geometry of Dialogue: Graphing Language Models to Reveal Synergistic Teams for Multi-Agent Collaboration Authors: Kotaro Furuya, Yuichi Kitagawa Published: 2025-10-30 Categories: cs.CL, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2510.26352v2 While a multi-agent approach based on large language models (LLMs) represents a promising strategy to surpass the capabilities of single models, its success is critically dependent on synergistic team composition. However, forming optimal teams is a significant challenge, as the inherent opacity of most models obscures the internal characteristics necessary for effective collaboration. In this paper, we propose an interaction-centric framework for automatic team composition that does not require any prior knowledge including their internal architectures, training data, or task performances. Our method constructs a "language model graph" that maps relationships between models from the semantic coherence of pairwise conversations, and then applies community detection to identify synergistic model clusters. Our experiments with diverse LLMs demonstrate that the proposed method discovers functionally coherent groups that reflect their latent specializations. Priming conversations with specific topics identified synergistic teams which outperform random baselines on downstream benchmarks and achieve comparable accuracy to that of manually-curated teams based on known model specializations. Our findings provide a new basis for the automated design of collaborative multi-agent LLM teams. --- ### UnifiedFL: A Dynamic Unified Learning Framework for Equitable Federation Authors: Furkan Pala, Islem Rekik Published: 2025-10-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.26350v1 Federated learning (FL) has emerged as a key paradigm for collaborative model training across multiple clients without sharing raw data, enabling privacy-preserving applications in areas such as radiology and pathology. However, works on collaborative training across clients with fundamentally different neural architectures and non-identically distributed datasets remain scarce. Existing FL frameworks face several limitations. Despite claiming to support architectural heterogeneity, most recent FL methods only tolerate variants within a single model family (e.g., shallower, deeper, or wider CNNs), still presuming a shared global architecture and failing to accommodate federations where clients deploy fundamentally different network types (e.g., CNNs, GNNs, MLPs). Moreover, existing approaches often address only statistical heterogeneity while overlooking the domain-fracture problem, where each client's data distribution differs markedly from that faced at testing time, undermining model generalizability. When clients use different architectures, have non-identically distributed data, and encounter distinct test domains, current methods perform poorly. To address these challenges, we propose UnifiedFL, a dynamic federated learning framework that represents heterogeneous local networks as nodes and edges in a directed model graph optimized by a shared graph neural network (GNN). UnifiedFL introduces (i) a common GNN to parameterize all architectures, (ii) distance-driven clustering via Euclidean distances between clients' parameters, and (iii) a two-tier aggregation policy balancing convergence and diversity. Experiments on MedMNIST classification and hippocampus segmentation benchmarks demonstrate UnifiedFL's superior performance. Code and data: https://github.com/basiralab/UnifiedFL --- ### Reinforcement Learning for Pollution Detection in a Randomized, Sparse and Nonstationary Environment with an Autonomous Underwater Vehicle Authors: Sebastian Zieglmeier, Niklas Erdmann, Narada D. Warakagoda Published: 2025-10-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.26347v1 Reinforcement learning (RL) algorithms are designed to optimize problem-solving by learning actions that maximize rewards, a task that becomes particularly challenging in random and nonstationary environments. Even advanced RL algorithms are often limited in their ability to solve problems in these conditions. In applications such as searching for underwater pollution clouds with autonomous underwater vehicles (AUVs), RL algorithms must navigate reward-sparse environments, where actions frequently result in a zero reward. This paper aims to address these challenges by revisiting and modifying classical RL approaches to efficiently operate in sparse, randomized, and nonstationary environments. We systematically study a large number of modifications, including hierarchical algorithm changes, multigoal learning, and the integration of a location memory as an external output filter to prevent state revisits. Our results demonstrate that a modified Monte Carlo-based approach significantly outperforms traditional Q-learning and two exhaustive search patterns, illustrating its potential in adapting RL to complex environments. These findings suggest that reinforcement learning approaches can be effectively adapted for use in random, nonstationary, and reward-sparse environments. --- ### Discovering State Equivalences in UCT Search Trees By Action Pruning Authors: Robin Schmöcker, Alexander Dockhorn, Bodo Rosenhahn Published: 2025-10-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.26346v1 One approach to enhance Monte Carlo Tree Search (MCTS) is to improve its sample efficiency by grouping/abstracting states or state-action pairs and sharing statistics within a group. Though state-action pair abstractions are mostly easy to find in algorithms such as On the Go Abstractions in Upper Confidence bounds applied to Trees (OGA-UCT), nearly no state abstractions are found in either noisy or large action space settings due to constraining conditions. We provide theoretical and empirical evidence for this claim, and we slightly alleviate this state abstraction problem by proposing a weaker state abstraction condition that trades a minor loss in accuracy for finding many more abstractions. We name this technique Ideal Pruning Abstractions in UCT (IPA-UCT), which outperforms OGA-UCT (and any of its derivatives) across a large range of test domains and iteration budgets as experimentally validated. IPA-UCT uses a different abstraction framework from Abstraction of State-Action Pairs (ASAP) which is the one used by OGA-UCT, which we name IPA. Furthermore, we show that both IPA and ASAP are special cases of a more general framework that we call p-ASAP which itself is a special case of the ASASAP framework. --- ### MisSynth: Improving MISSCI Logical Fallacies Classification with Synthetic Data Authors: Mykhailo Poliakov, Nadiya Shvai Published: 2025-10-30 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.26345v1 Health-related misinformation is very prevalent and potentially harmful. It is difficult to identify, especially when claims distort or misinterpret scientific findings. We investigate the impact of synthetic data generation and lightweight fine-tuning techniques on the ability of large language models (LLMs) to recognize fallacious arguments using the MISSCI dataset and framework. In this work, we propose MisSynth, a pipeline that applies retrieval-augmented generation (RAG) to produce synthetic fallacy samples, which are then used to fine-tune an LLM model. Our results show substantial accuracy gains with fine-tuned models compared to vanilla baselines. For instance, the LLaMA 3.1 8B fine-tuned model achieved an over 35% F1-score absolute improvement on the MISSCI test split over its vanilla baseline. We demonstrate that introducing synthetic fallacy data to augment limited annotated resources can significantly enhance zero-shot LLM classification performance on real-world scientific misinformation tasks, even with limited computational resources. The code and synthetic dataset are available on https://github.com/mxpoliakov/MisSynth. --- ### Linear Causal Discovery with Interventional Constraints Authors: Zhigao Guo, Feng Dong Published: 2025-10-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.26342v1 Incorporating causal knowledge and mechanisms is essential for refining causal models and improving downstream tasks such as designing new treatments. In this paper, we introduce a novel concept in causal discovery, termed interventional constraints, which differs fundamentally from interventional data. While interventional data require direct perturbations of variables, interventional constraints encode high-level causal knowledge in the form of inequality constraints on causal effects. For instance, in the Sachs dataset (Sachs et al.\ 2005), Akt has been shown to be activated by PIP3, meaning PIP3 exerts a positive causal effect on Akt. Existing causal discovery methods allow enforcing structural constraints (for example, requiring a causal path from PIP3 to Akt), but they may still produce incorrect causal conclusions such as learning that "PIP3 inhibits Akt". Interventional constraints bridge this gap by explicitly constraining the total causal effect between variable pairs, ensuring learned models respect known causal influences. To formalize interventional constraints, we propose a metric to quantify total causal effects for linear causal models and formulate the problem as a constrained optimization task, solved using a two-stage constrained optimization method. We evaluate our approach on real-world datasets and demonstrate that integrating interventional constraints not only improves model accuracy and ensures consistency with established findings, making models more explainable, but also facilitates the discovery of new causal relationships that would otherwise be costly to identify. --- ### SABER: Symbolic Regression-based Angle of Arrival and Beam Pattern Estimator Authors: Shih-Kai Chou, Mengran Zhao, Cheng-Nan Hu, Kuang-Chung Chou, Carolina Fortuna, Jernej Hribar Published: 2025-10-30 Categories: eess.SP, cs.LG arXiv: https://arxiv.org/abs/2510.26340v1 Accurate Angle-of-arrival (AoA) estimation is essential for next-generation wireless communication systems to enable reliable beamforming, high-precision localization, and integrated sensing. Unfortunately, classical high-resolution techniques require multi-element arrays and extensive snapshot collection, while generic Machine Learning (ML) approaches often yield black-box models that lack physical interpretability. To address these limitations, we propose a Symbolic Regression (SR)-based ML framework. Namely, Symbolic Regression-based Angle of Arrival and Beam Pattern Estimator (SABER), a constrained symbolic-regression framework that automatically discovers closed-form beam pattern and AoA models from path loss measurements with interpretability. SABER achieves high accuracy while bridging the gap between opaque ML methods and interpretable physics-driven estimators. First, we validate our approach in a controlled free-space anechoic chamber, showing that both direct inversion of the known $\cos^n$ beam and a low-order polynomial surrogate achieve sub-0.5 degree Mean Absolute Error (MAE). A purely unconstrained SR method can further reduce the error of the predicted angles, but produces complex formulas that lack physical insight. Then, we implement the same SR-learned inversions in a real-world, Reconfigurable Intelligent Surface (RIS)-aided indoor testbed. SABER and unconstrained SR models accurately recover the true AoA with near-zero error. Finally, we benchmark SABER against the Cramér-Rao Lower Bounds (CRLBs). Our results demonstrate that SABER is an interpretable and accurate alternative to state-of-the-art and black-box ML-based methods for AoA estimation. --- ### GLYPH-SR: Can We Achieve Both High-Quality Image Super-Resolution and High-Fidelity Text Recovery via VLM-guided Latent Diffusion Model? Authors: Mingyu Sung, Seungjae Ham, Kangwoo Kim, Yeokyoung Yoon, Sangseok Yun, Il-Min Kim, Jae-Mo Kang Published: 2025-10-30 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2510.26339v1 Image super-resolution(SR) is fundamental to many vision system-from surveillance and autonomy to document analysis and retail analytics-because recovering high-frequency details, especially scene-text, enables reliable downstream perception. Scene-text, i.e., text embedded in natural images such as signs, product labels, and storefronts, often carries the most actionable information; when characters are blurred or hallucinated, optical character recognition(OCR) and subsequent decisions fail even if the rest of the image appears sharp. Yet previous SR research has often been tuned to distortion (PSNR/SSIM) or learned perceptual metrics (LIPIS, MANIQA, CLIP-IQA, MUSIQ) that are largely insensitive to character-level errors. Furthermore, studies that do address text SR often focus on simplified benchmarks with isolated characters, overlooking the challenges of text within complex natural scenes. As a result, scene-text is effectively treated as generic texture. For SR to be effective in practical deployments, it is therefore essential to explicitly optimize for both text legibility and perceptual quality. We present GLYPH-SR, a vision-language-guided diffusion framework that aims to achieve both objectives jointly. GLYPH-SR utilizes a Text-SR Fusion ControlNet(TS-ControlNet) guided by OCR data, and a ping-pong scheduler that alternates between text- and scene-centric guidance. To enable targeted text restoration, we train these components on a synthetic corpus while keeping the main SR branch frozen. Across SVT, SCUT-CTW1500, and CUTE80 at x4, and x8, GLYPH-SR improves OCR F1 by up to +15.18 percentage points over diffusion/GAN baseline (SVT x8, OpenOCR) while maintaining competitive MANIQA, CLIP-IQA, and MUSIQ. GLYPH-SR is designed to satisfy both objectives simultaneously-high readability and high visual realism-delivering SR that looks right and reds right. --- ### From Amateur to Master: Infusing Knowledge into LLMs via Automated Curriculum Learning Authors: Nishit Neema, Srinjoy Mukherjee, Sapan Shah, Gokul Ramakrishnan, Ganesh Venkatesh Published: 2025-10-30 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.26336v1 Large Language Models (LLMs) excel at general tasks but underperform in specialized domains like economics and psychology, which require deep, principled understanding. To address this, we introduce ACER (Automated Curriculum-Enhanced Regimen) that transforms generalist models into domain experts without sacrificing their broad capabilities. ACER first synthesizes a comprehensive, textbook-style curriculum by generating a table of contents for a subject and then creating question-answer (QA) pairs guided by Bloom's taxonomy. This ensures systematic topic coverage and progressively increasing difficulty. The resulting synthetic corpus is used for continual pretraining with an interleaved curriculum schedule, aligning learning across both content and cognitive dimensions. Experiments with Llama 3.2 (1B and 3B) show significant gains in specialized MMLU subsets. In challenging domains like microeconomics, where baselines struggle, ACER boosts accuracy by 5 percentage points. Across all target domains, we observe a consistent macro-average improvement of 3 percentage points. Notably, ACER not only prevents catastrophic forgetting but also facilitates positive cross-domain knowledge transfer, improving performance on non-target domains by 0.7 points. Beyond MMLU, ACER enhances performance on knowledge-intensive benchmarks like ARC and GPQA by over 2 absolute points, while maintaining stable performance on general reasoning tasks. Our results demonstrate that ACER offers a scalable and effective recipe for closing critical domain gaps in LLMs. --- ### Agent Skills Enable a New Class of Realistic and Trivially Simple Prompt Injections Authors: David Schmotz, Sahar Abdelnabi, Maksym Andriushchenko Published: 2025-10-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.26328v1 Enabling continual learning in LLMs remains a key unresolved research challenge. In a recent announcement, a frontier LLM company made a step towards this by introducing Agent Skills, a framework that equips agents with new knowledge based on instructions stored in simple markdown files. Although Agent Skills can be a very useful tool, we show that they are fundamentally insecure, since they enable trivially simple prompt injections. We demonstrate how to hide malicious instructions in long Agent Skill files and referenced scripts to exfiltrate sensitive data, such as internal files or passwords. Importantly, we show how to bypass system-level guardrails of a popular coding agent: a benign, task-specific approval with the "Don't ask again" option can carry over to closely related but harmful actions. Overall, we conclude that despite ongoing research efforts and scaling model capabilities, frontier LLMs remain vulnerable to very simple prompt injections in realistic scenarios. Our code is available at https://github.com/aisa-group/promptinject-agent-skills. --- ### Posterior Sampling by Combining Diffusion Models with Annealed Langevin Dynamics Authors: Zhiyang Xun, Shivam Gupta, Eric Price Published: 2025-10-30 Categories: cs.LG, cs.AI, cs.DS, math.ST, stat.ML arXiv: https://arxiv.org/abs/2510.26324v2 Given a noisy linear measurement $y = Ax + ξ$ of a distribution $p(x)$, and a good approximation to the prior $p(x)$, when can we sample from the posterior $p(x \mid y)$? Posterior sampling provides an accurate and fair framework for tasks such as inpainting, deblurring, and MRI reconstruction, and several heuristics attempt to approximate it. Unfortunately, approximate posterior sampling is computationally intractable in general. To sidestep this hardness, we focus on (local or global) log-concave distributions $p(x)$. In this regime, Langevin dynamics yields posterior samples when the exact scores of $p(x)$ are available, but it is brittle to score--estimation error, requiring an MGF bound (sub-exponential error). By contrast, in the unconditional setting, diffusion models succeed with only an $L^2$ bound on the score error. We prove that combining diffusion models with an annealed variant of Langevin dynamics achieves conditional sampling in polynomial time using merely an $L^4$ bound on the score error. --- ### On the Impact of Weight Discretization in QUBO-Based SVM Training Authors: Sascha Mücke Published: 2025-10-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.26323v1 Training Support Vector Machines (SVMs) can be formulated as a QUBO problem, enabling the use of quantum annealing for model optimization. In this work, we study how the number of qubits - linked to the discretization level of dual weights - affects predictive performance across datasets. We compare QUBO-based SVM training to the classical LIBSVM solver and find that even low-precision QUBO encodings (e.g., 1 bit per parameter) yield competitive, and sometimes superior, accuracy. While increased bit-depth enables larger regularization parameters, it does not always improve classification. Our findings suggest that selecting the right support vectors may matter more than their precise weighting. Although current hardware limits the size of solvable QUBOs, our results highlight the potential of quantum annealing for efficient SVM training as quantum devices scale. --- ### SCRIBE: Structured Chain Reasoning for Interactive Behaviour Explanations using Tool Calling Authors: Fares Fawzi, Vinitra Swamy, Dominik Glandorf, Tanya Nazaretsky, Tanja Käser Published: 2025-10-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.26322v1 Language models can be used to provide interactive, personalized student feedback in educational settings. However, real-world deployment faces three key challenges: privacy concerns, limited computational resources, and the need for pedagogically valid responses. These constraints require small, open-source models that can run locally and reliably ground their outputs in correct information. We introduce SCRIBE, a framework for multi-hop, tool-augmented reasoning designed to generate valid responses to student questions about feedback reports. SCRIBE combines domain-specific tools with a self-reflective inference pipeline that supports iterative reasoning, tool use, and error recovery. We distil these capabilities into 3B and 8B models via two-stage LoRA fine-tuning on synthetic GPT-4o-generated data. Evaluation with a human-aligned GPT-Judge and a user study with 108 students shows that 8B-SCRIBE models achieve comparable or superior quality to much larger models in key dimensions such as relevance and actionability, while being perceived on par with GPT-4o and Llama-3.3 70B by students. These findings demonstrate the viability of SCRIBE for low-resource, privacy-sensitive educational applications. --- ### A Hybrid Framework Bridging CNN and ViT based on Theory of Evidence for Diabetic Retinopathy Grading Authors: Junlai Qiu, Yunzhu Chen, Hao Zheng, Yawen Huang, Yuexiang Li Published: 2025-10-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.26315v1 Diabetic retinopathy (DR) is a leading cause of vision loss among middle-aged and elderly people, which significantly impacts their daily lives and mental health. To improve the efficiency of clinical screening and enable the early detection of DR, a variety of automated DR diagnosis systems have been recently established based on convolutional neural network (CNN) or vision Transformer (ViT). However, due to the own shortages of CNN / ViT, the performance of existing methods using single-type backbone has reached a bottleneck. One potential way for the further improvements is integrating different kinds of backbones, which can fully leverage the respective strengths of them (\emph{i.e.,} the local feature extraction capability of CNN and the global feature capturing ability of ViT). To this end, we propose a novel paradigm to effectively fuse the features extracted by different backbones based on the theory of evidence. Specifically, the proposed evidential fusion paradigm transforms the features from different backbones into supporting evidences via a set of deep evidential networks. With the supporting evidences, the aggregated opinion can be accordingly formed, which can be used to adaptively tune the fusion pattern between different backbones and accordingly boost the performance of our hybrid model. We evaluated our method on two publicly available DR grading datasets. The experimental results demonstrate that our hybrid model not only improves the accuracy of DR grading, compared to the state-of-the-art frameworks, but also provides the excellent interpretability for feature fusion and decision-making. --- ### Model Inversion with Layer-Specific Modeling and Alignment for Data-Free Continual Learning Authors: Ruilin Tong, Haodong Lu, Yuhang Liu, Dong Gong Published: 2025-10-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.26311v1 Continual learning (CL) aims to incrementally train a model on a sequence of tasks while retaining performance on prior ones. However, storing and replaying data is often infeasible due to privacy or security constraints and impractical for arbitrary pre-trained models. Data-free CL seeks to update models without access to previous data. Beyond regularization, we employ model inversion to synthesize data from the trained model, enabling replay without storing samples. Yet, model inversion in predictive models faces two challenges: (1) generating inputs solely from compressed output labels causes drift between synthetic and real data, and replaying such data can erode prior knowledge; (2) inversion is computationally expensive since each step backpropagates through the full model. These issues are amplified in large pre-trained models such as CLIP. To improve efficiency, we propose Per-layer Model Inversion (PMI), inspired by faster convergence in single-layer optimization. PMI provides strong initialization for full-model inversion, substantially reducing iterations. To mitigate feature shift, we model class-wise features via Gaussian distributions and contrastive model, ensuring alignment between synthetic and real features. Combining PMI and feature modeling, our approach enables continual learning of new classes by generating pseudo-images from semantic-aware projected features, achieving strong effectiveness and compatibility across multiple CL settings. --- ### GraphCompliance: Structure-Aware Regulatory Compliance through Policy-Context Graph Alignment Authors: Jiseong Chung, Ronny Ko, Won-Yong Shin, Wonchul Yoo, Tae-Wan Kim Published: 2025-10-30 Categories: cs.AI, cs.IR arXiv: https://arxiv.org/abs/2510.26309v2 Regulatory compliance is an important requirement in many industrial and administrative settings. Yet compliance assessment remains difficult because regulatory requirements are distributed across structured documents and may depend on hierarchy, definitions, conditions, and cross-references, while the evidence relevant to a particular requirement may be embedded among multiple interacting actors, events, objects, and conditions in the assessed context. We present GraphCompliance, a structure-aware framework that represents regulatory documents as a schema-guided Policy Graph and contextual information as a Context Graph of entity-relation triples. GraphCompliance aligns the two graphs through a Compliance Gate, which identifies relevant regulatory requirements and evaluates them against the corresponding contextual evidence. This design makes regulatory structure explicit while organizing contextual facts into a comparable form, helping preserve structural dependencies and reduce terminology mismatch across different regulatory settings. Evaluation on EU2UK, GDPR-13, and CONTRACT yields Matthews correlation coefficients (MCC) of 0.802, 0.682, and 0.793, respectively. These values are numerically higher than those of the strongest compared methods on all three datasets. Ablation results further show that the key components of GraphCompliance contribute to its overall performance. These results support the utility of structured policy-context alignment for compliance-related prediction across heterogeneous regulatory settings. The source code of GraphCompliance is available at https://github.com/CHUNG-JiSeong/GraphCompliance.git. --- ### A Survey of Heterogeneous Graph Neural Networks for Cybersecurity Anomaly Detection Authors: Laura Jiang, Reza Ryan, Qian Li, Nasim Ferdosian Published: 2025-10-30 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2510.26307v3 Anomaly detection is a critical task in cybersecurity, where identifying insider threats, access violations, and coordinated attacks is essential for ensuring system resilience. Graph-based approaches have become increasingly important for modeling entity interactions, yet most rely on homogeneous and static structures, which limits their ability to capture the heterogeneity and temporal evolution of real-world environments. Heterogeneous Graph Neural Networks (HGNNs) have emerged as a promising paradigm for anomaly detection by incorporating type-aware transformations and relation-sensitive aggregation, enabling more expressive modeling of complex cyber data. However, current research on HGNN-based anomaly detection remains fragmented, with diverse modeling strategies, limited comparative evaluation, and an absence of standardized benchmarks. To address this gap, we provide a comprehensive survey of HGNN-based anomaly detection methods in cybersecurity. We introduce a taxonomy that classifies approaches by anomaly type and graph dynamics, analyze representative models, and map them to key cybersecurity applications. We also review commonly used benchmark datasets and evaluation metrics, highlighting their strengths and limitations. Finally, we identify key open challenges related to modeling, data, and deployment, and outline promising directions for future research. This survey aims to establish a structured foundation for advancing HGNN-based anomaly detection toward scalable, interpretable, and practically deployable solutions. --- ### Exploring the correlation between the type of music and the emotions evoked: A study using subjective questionnaires and EEG Authors: Jelizaveta Jankowska, Bożena Kostek, Fernando Alonso-Fernandez, Prayag Tiwari Published: 2025-10-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.26304v1 The subject of this work is to check how different types of music affect human emotions. While listening to music, a subjective survey and brain activity measurements were carried out using an EEG helmet. The aim is to demonstrate the impact of different music genres on emotions. The research involved a diverse group of participants of different gender and musical preferences. This had the effect of capturing a wide range of emotional responses to music. After the experiment, a relationship analysis of the respondents' questionnaires with EEG signals was performed. The analysis revealed connections between emotions and observed brain activity. --- ### Implicit Bias of Per-sample Adam on Separable Data: Departure from the Full-batch Regime Authors: Beomhan Baek, Minhak Song, Chulhee Yun Published: 2025-10-30 Categories: cs.LG, cs.AI, math.OC, stat.ML arXiv: https://arxiv.org/abs/2510.26303v3 Adam (Kingma & Ba, 2015) is the de facto optimizer in deep learning, yet its theoretical understanding remains limited. Prior analyses show that Adam favors solutions aligned with $\ell_\infty$-geometry, but these results are restricted to the full-batch regime. In this work, we study the implicit bias of incremental Adam (using one sample per step) for logistic regression on linearly separable data, and show that its bias can deviate from the full-batch behavior. As an extreme example, we construct datasets on which incremental Adam provably converges to the $\ell_2$-max-margin classifier, in contrast to the $\ell_\infty$-max-margin bias of full-batch Adam. For general datasets, we characterize its bias using a proxy algorithm for the $β_2 \to 1$ limit. This proxy maximizes a data-adaptive Mahalanobis-norm margin, whose associated covariance matrix is determined by a data-dependent dual fixed-point formulation. We further present concrete datasets where this bias reduces to the standard $\ell_2$- and $\ell_\infty$-max-margin classifiers. As a counterpoint, we prove that Signum (Bernstein et al., 2018) converges to the $\ell_\infty$-max-margin classifier for any batch size. Overall, our results highlight that the implicit bias of Adam crucially depends on both the batching scheme and the dataset, while Signum remains invariant. --- ### Understanding Hardness of Vision-Language Compositionality from A Token-level Causal Lens Authors: Ziliang Chen, Tianang Xiao, Jusheng Zhang, Yongsen Zheng, Xipeng Chen Published: 2025-10-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.26302v1 Contrastive Language-Image Pre-training (CLIP) delivers strong cross modal generalization by aligning images and texts in a shared embedding space, yet it persistently fails at compositional reasoning over objects, attributes, and relations often behaving like a bag-of-words matcher. Prior causal accounts typically model text as a single vector, obscuring token-level structure and leaving core phenomena-such as prompt sensitivity and failures on hard negatives unexplained. We address this gap with a token-aware causal representation learning (CRL) framework grounded in a sequential, language-token SCM. Our theory extends block identifiability to tokenized text, proving that CLIP's contrastive objective can recover the modal-invariant latent variable under both sentence-level and token-level SCMs. Crucially, token granularity yields the first principled explanation of CLIP's compositional brittleness: composition nonidentifiability. We show the existence of pseudo-optimal text encoders that achieve perfect modal-invariant alignment yet are provably insensitive to SWAP, REPLACE, and ADD operations over atomic concepts, thereby failing to distinguish correct captions from hard negatives despite optimizing the same training objective as true-optimal encoders. The analysis further links language-side nonidentifiability to visual-side failures via the modality gap and shows how iterated composition operators compound hardness, motivating improved negative mining strategies. --- ### Offline Clustering of Preference Learning with Active-data Augmentation Authors: Jingyuan Liu, Fatemeh Ghaffari, Xuchuang Wang, Xutong Liu, Mohammad Hajiesmaili, Carlee Joe-Wong Published: 2025-10-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.26301v2 Preference learning from pairwise feedback is a widely adopted framework in applications such as reinforcement learning with human feedback and recommendations. In many practical settings, however, user interactions are limited or costly, making offline preference learning necessary. Moreover, real-world preference learning often involves users with different preferences. For example, annotators from different backgrounds may rank the same responses differently. This setting presents two central challenges: (1) identifying similarity across users to effectively aggregate data, especially under scenarios where offline data is imbalanced across dimensions, and (2) handling the imbalanced offline data where some preference dimensions are underrepresented. To address these challenges, we study the Offline Clustering of Preference Learning problem, where the learner has access to fixed datasets from multiple users with potentially different preferences and aims to maximize utility for a test user. To tackle the first challenge, we first propose Off-C$^2$PL for the pure offline setting, where the learner relies solely on offline data. Our theoretical analysis provides a suboptimality bound that explicitly captures the tradeoff between sample noise and bias. To address the second challenge of inbalanced data, we extend our framework to the setting with active-data augmentation where the learner is allowed to select a limited number of additional active-data for the test user based on the cluster structure learned by Off-C$^2$PL. In this setting, our second algorithm, A$^2$-Off-C$^2$PL, actively selects samples that target the least-informative dimensions of the test user's preference. We prove that these actively collected samples contribute more effectively than offline ones. Finally, we validate our theoretical results through simulations on synthetic and real-world datasets. --- ### Can Agent Conquer Web? Exploring the Frontiers of ChatGPT Atlas Agent in Web Games Authors: Jingran Zhang, Ning Li, Justin Cui Published: 2025-10-30 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.26298v1 OpenAI's ChatGPT Atlas introduces new capabilities for web interaction, enabling the model to analyze webpages, process user intents, and execute cursor and keyboard inputs directly within the browser. While its capacity for information retrieval tasks has been demonstrated, its performance in dynamic, interactive environments remains less explored. In this study, we conduct an early evaluation of Atlas's web interaction capabilities using browser-based games as test scenarios, including Google's T-Rex Runner, Sudoku, Flappy Bird, and Stein.world. We employ in-game performance scores as quantitative metrics to assess performance across different task types. Our results show that Atlas performs strongly in logical reasoning tasks like Sudoku, completing puzzles significantly faster than human baselines, but struggles substantially in real-time games requiring precise timing and motor control, often failing to progress beyond initial obstacles. These findings suggest that while Atlas demonstrates capable analytical processing, there remain notable limitations in dynamic web environments requiring real-time interaction. The website of our project can be found at https://atlas-game-eval.github.io. --- ### Towards Realistic Earth-Observation Constellation Scheduling: Benchmark and Methodology Authors: Luting Wang, Yinghao Xiang, Hongliang Huang, Dongjun Li, Chen Gao, Si Liu Published: 2025-10-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.26297v1 Agile Earth Observation Satellites (AEOSs) constellations offer unprecedented flexibility for monitoring the Earth's surface, but their scheduling remains challenging under large-scale scenarios, dynamic environments, and stringent constraints. Existing methods often simplify these complexities, limiting their real-world performance. We address this gap with a unified framework integrating a standardized benchmark suite and a novel scheduling model. Our benchmark suite, AEOS-Bench, contains $3,907$ finely tuned satellite assets and $16,410$ scenarios. Each scenario features $1$ to $50$ satellites and $50$ to $300$ imaging tasks. These scenarios are generated via a high-fidelity simulation platform, ensuring realistic satellite behavior such as orbital dynamics and resource constraints. Ground truth scheduling annotations are provided for each scenario. To our knowledge, AEOS-Bench is the first large-scale benchmark suite tailored for realistic constellation scheduling. Building upon this benchmark, we introduce AEOS-Former, a Transformer-based scheduling model that incorporates a constraint-aware attention mechanism. A dedicated internal constraint module explicitly models the physical and operational limits of each satellite. Through simulation-based iterative learning, AEOS-Former adapts to diverse scenarios, offering a robust solution for AEOS constellation scheduling. Experimental results demonstrate that AEOS-Former outperforms baseline models in task completion and energy efficiency, with ablation studies highlighting the contribution of each component. Code and data are provided in https://github.com/buaa-colalab/AEOSBench. --- ### Leveraging Large-Scale Face Datasets for Deep Periocular Recognition via Ocular Cropping Authors: Fernando Alonso-Fernandez, Kevin Hernandez-Diaz, Jose Maria Buades Rubio, Josef Bigun Published: 2025-10-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.26294v1 We focus on ocular biometrics, specifically the periocular region (the area around the eye), which offers high discrimination and minimal acquisition constraints. We evaluate three Convolutional Neural Network architectures of varying depth and complexity to assess their effectiveness for periocular recognition. The networks are trained on 1,907,572 ocular crops extracted from the large-scale VGGFace2 database. This significantly contrasts with existing works, which typically rely on small-scale periocular datasets for training having only a few thousand images. Experiments are conducted with ocular images from VGGFace2-Pose, a subset of VGGFace2 containing in-the-wild face images, and the UFPR-Periocular database, which consists of selfies captured via mobile devices with user guidance on the screen. Due to the uncontrolled conditions of VGGFace2, the Equal Error Rates (EERs) obtained with ocular crops range from 9-15%, noticeably higher than the 3-6% EERs achieved using full-face images. In contrast, UFPR-Periocular yields significantly better performance (EERs of 1-2%), thanks to higher image quality and more consistent acquisition protocols. To the best of our knowledge, these are the lowest reported EERs on the UFPR dataset to date. --- ### Beyond Imitation: Constraint-Aware Trajectory Generation with Flow Matching For End-to-End Autonomous Driving Authors: Lin Liu, Guanyi Yu, Ziying Song, Junqiao Li, Caiyan Jia, Feiyang Jia, Peiliang Wu, Yandan Luo Published: 2025-10-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.26292v1 Planning is a critical component of end-to-end autonomous driving. However, prevailing imitation learning methods often suffer from mode collapse, failing to produce diverse trajectory hypotheses. Meanwhile, existing generative approaches struggle to incorporate crucial safety and physical constraints directly into the generative process, necessitating an additional optimization stage to refine their outputs. To address these limitations, we propose CATG, a novel planning framework that leverages Constrained Flow Matching. Concretely, CATG explicitly models the flow matching process, which inherently mitigates mode collapse and allows for flexible guidance from various conditioning signals. Our primary contribution is the novel imposition of explicit constraints directly within the flow matching process, ensuring that the generated trajectories adhere to vital safety and kinematic rules. Secondly, CATG parameterizes driving aggressiveness as a control signal during generation, enabling precise manipulation of trajectory style. Notably, on the NavSim v2 challenge, CATG achieved 2nd place with an EPDMS score of 51.31 and was honored with the Innovation Award. --- ### Language Models Learn Universal Representations of Numbers and Here's Why You Should Care Authors: Michal Štefánik, Timothee Mickus, Marek Kadlčík, Bertram Højer, Michal Spiegel, Raúl Vázquez, Aman Sinha, Josef Kuchař, Philipp Mondorf, Pontus Stenetorp Published: 2025-10-30 Categories: cs.CL, cs.AI, cs.LG, cs.NE arXiv: https://arxiv.org/abs/2510.26285v2 Prior work has shown that large language models (LLMs) often converge to accurate input embedding for numbers, based on sinusoidal representations. In this work, we quantify that these representations are in fact strikingly systematic, to the point of being almost perfectly universal: different LLM families develop equivalent sinusoidal structures, and number representations are broadly interchangeable in a large swathe of experimental setups. We show that properly factoring in this characteristic is crucial when it comes to assessing how accurately LLMs encode numeric and other ordinal information, and that mechanistically enhancing this sinusoidality can also lead to reductions of LLMs' arithmetic errors. --- ### Empirical Bayesian Multi-Bandit Learning Authors: Xia Jiang, Rong J. B. Zhu Published: 2025-10-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.26284v2 Multi-task learning in contextual bandits has attracted significant research interest due to its potential to enhance decision-making across multiple related tasks by leveraging shared structures and task-specific heterogeneity. In this article, we propose a novel hierarchical Bayesian framework for learning in various bandit instances. This framework captures both the heterogeneity and the correlations among different bandit instances through a hierarchical Bayesian model, enabling effective information sharing while accommodating instance-specific variations. Unlike previous methods that overlook the learning of the covariance structure across bandits, we introduce an empirical Bayesian approach to estimate the covariance matrix of the prior distribution. This enhances both the practicality and flexibility of learning across multi-bandits. Building on this approach, we develop two efficient algorithms: ebmTS (Empirical Bayesian Multi-Bandit Thompson Sampling) and ebmUCB (Empirical Bayesian Multi-Bandit Upper Confidence Bound), both of which incorporate the estimated prior into the decision-making process. We provide the frequentist regret upper bounds for the proposed algorithms, thereby filling a research gap in the field of multi-bandit problems. Extensive experiments on both synthetic and real-world datasets demonstrate the superior performance of our algorithms, particularly in complex environments. Our methods achieve lower cumulative regret compared to existing techniques, highlighting their effectiveness in balancing exploration and exploitation across multi-bandits. --- ### Exploring Complementarity and Explainability in CNNs for Periocular Verification Across Acquisition Distances Authors: Fernando Alonso-Fernandez, Kevin Hernandez Diaz, Jose M. Buades, Kiran Raja, Josef Bigun Published: 2025-10-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.26282v1 We study the complementarity of different CNNs for periocular verification at different distances on the UBIPr database. We train three architectures of increasing complexity (SqueezeNet, MobileNetv2, and ResNet50) on a large set of eye crops from VGGFace2. We analyse performance with cosine and chi2 metrics, compare different network initialisations, and apply score-level fusion via logistic regression. In addition, we use LIME heatmaps and Jensen-Shannon divergence to compare attention patterns of the CNNs. While ResNet50 consistently performs best individually, the fusion provides substantial gains, especially when combining all three networks. Heatmaps show that networks usually focus on distinct regions of a given image, which explains their complementarity. Our method significantly outperforms previous works on UBIPr, achieving a new state-of-the-art. --- ### Distributional Multi-objective Black-box Optimization for Diffusion-model Inference-time Multi-Target Generation Authors: Kim Yong Tan, Yueming Lyu, Ivor Tsang, Yew-Soon Ong Published: 2025-10-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.26278v1 Diffusion models have been successful in learning complex data distributions. This capability has driven their application to high-dimensional multi-objective black-box optimization problem. Existing approaches often employ an external optimization loop, such as an evolutionary algorithm, to the diffusion model. However, these approaches treat the diffusion model as a black-box refiner, which overlooks the internal distribution transition of the diffusion generation process, limiting their efficiency. To address these challenges, we propose the Inference-time Multi-target Generation (IMG) algorithm, which optimizes the diffusion process at inference-time to generate samples that simultaneously satisfy multiple objectives. Specifically, our IMG performs weighted resampling during the diffusion generation process according to the expected aggregated multi-objective values. This weighted resampling strategy ensures the diffusion-generated samples are distributed according to our desired multi-target Boltzmann distribution. We further derive that the multi-target Boltzmann distribution has an interesting log-likelihood interpretation, where it is the optimal solution to the distributional multi-objective optimization problem. We implemented IMG for a multi-objective molecule generation task. Experiments show that IMG, requiring only a single generation pass, achieves a significantly higher hypervolume than baseline optimization algorithms that often require hundreds of diffusion generations. Notably, our algorithm can be viewed as an optimized diffusion process and can be integrated into existing methods to further improve their performance. --- ### Do LLMs Signal When They're Right? Evidence from Neuron Agreement Authors: Kang Chen, Yaoning Wang, Kai Xiong, Zhuoka Feng, Wenhe Sun, Haotian Chen, Yixin Cao Published: 2025-10-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.26277v1 Large language models (LLMs) commonly boost reasoning via sample-evaluate-ensemble decoders, achieving label free gains without ground truth. However, prevailing strategies score candidates using only external outputs such as token probabilities, entropies, or self evaluations, and these signals can be poorly calibrated after post training. We instead analyze internal behavior based on neuron activations and uncover three findings: (1) external signals are low dimensional projections of richer internal dynamics; (2) correct responses activate substantially fewer unique neurons than incorrect ones throughout generation; and (3) activations from correct responses exhibit stronger cross sample agreement, whereas incorrect ones diverge. Motivated by these observations, we propose Neuron Agreement Decoding (NAD), an unsupervised best-of-N method that selects candidates using activation sparsity and cross sample neuron agreement, operating solely on internal signals and without requiring comparable textual outputs. NAD enables early correctness prediction within the first 32 generated tokens and supports aggressive early stopping. Across math and science benchmarks with verifiable answers, NAD matches majority voting; on open ended coding benchmarks where majority voting is inapplicable, NAD consistently outperforms Avg@64. By pruning unpromising trajectories early, NAD reduces token usage by 99% with minimal loss in generation quality, showing that internal signals provide reliable, scalable, and efficient guidance for label free ensemble decoding. --- ### A Research Roadmap for Augmenting Software Engineering Processes and Software Products with Generative AI Authors: Domenico Amalfitano, Andreas Metzger, Marco Autili, Tommaso Fulcini, Tobias Hey, Jan Keim, Patrizio Pelliccione, Vincenzo Scotti, Anne Koziolek, Raffaela Mirandola, Andreas Vogelsang Published: 2025-10-30 Categories: cs.SE, cs.AI, cs.ET, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2510.26275v3 Generative AI (GenAI) is rapidly transforming software engineering (SE) practices, influencing how SE processes are executed, as well as how software systems are developed, operated, and evolved. This paper applies design science research to build a roadmap for GenAI-augmented SE. The process consists of three cycles that incrementally integrate multiple sources of evidence, including collaborative discussions from the FSE 2025 "Software Engineering 2030" workshop, rapid literature reviews, and external feedback sessions involving peers. McLuhan's tetrads were used as a conceptual instrument to systematically capture the transforming effects of GenAI on SE processes and software products. The resulting roadmap identifies four fundamental forms of GenAI augmentation in SE and systematically characterizes their related research challenges and opportunities. These insights are then consolidated into a set of future research directions. By grounding the roadmap in a rigorous multi-cycle process and cross-validating it among independent author teams and peers, the study provides a transparent and reproducible foundation for analyzing how GenAI affects SE processes, methods and tools, and for framing future research within this rapidly evolving area. --- ### PVMark: Enabling Public Verifiability for LLM Watermarking Schemes Authors: Haohua Duan, Liyao Xiang, Xin Zhang Published: 2025-10-30 Categories: cs.CR, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2510.26274v1 Watermarking schemes for large language models (LLMs) have been proposed to identify the source of the generated text, mitigating the potential threats emerged from model theft. However, current watermarking solutions hardly resolve the trust issue: the non-public watermark detection cannot prove itself faithfully conducting the detection. We observe that it is attributed to the secret key mostly used in the watermark detection -- it cannot be public, or the adversary may launch removal attacks provided the key; nor can it be private, or the watermarking detection is opaque to the public. To resolve the dilemma, we propose PVMark, a plugin based on zero-knowledge proof (ZKP), enabling the watermark detection process to be publicly verifiable by third parties without disclosing any secret key. PVMark hinges upon the proof of `correct execution' of watermark detection on which a set of ZKP constraints are built, including mapping, random number generation, comparison, and summation. We implement multiple variants of PVMark in Python, Rust and Circom, covering combinations of three watermarking schemes, three hash functions, and four ZKP protocols, to show our approach effectively works under a variety of circumstances. By experimental results, PVMark efficiently enables public verifiability on the state-of-the-art LLM watermarking schemes yet without compromising the watermarking performance, promising to be deployed in practice. --- ### Distilling Multilingual Vision-Language Models: When Smaller Models Stay Multilingual Authors: Sukrit Sriratanawilai, Jhayahgrit Thongwat, Romrawin Chumpu, Patomporn Payoungkhamdee, Sarana Nutanong, Peerat Limkonchotiwat Published: 2025-10-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.26271v1 Vision-language models (VLMs) exhibit uneven performance across languages, a problem that is often exacerbated when the model size is reduced. While Knowledge distillation (KD) demonstrates promising results in transferring knowledge from larger to smaller VLMs, applying KD in multilingualism is an underexplored area. This paper presents a controlled empirical study of KD behavior across five distillation approaches, isolating their effects on cross-lingual representation consistency and downstream performance stability under model compression. We study five distillation formulations across CLIP and SigLIP2, and evaluate them on in-domain retrieval and out-of-domain visual QA. We find that some configurations preserve or even improve multilingual retrieval robustness despite halving model size, but others fail to maintain cross-task stability, exposing design-sensitive trade-offs that aggregate accuracy alone does not reveal. --- ### Graph-Enhanced Policy Optimization in LLM Agent Training Authors: Jiazhen Yuan, Zhike Gong, Jinquan Hang, Zhengbiao Bai, Wei Zhao Published: 2025-10-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.26270v2 Multi-step LLM agents in interactive environments represent a crucial step toward long-horizon decision-making. To train such agents, group-based reinforcement learning is widely adopted, which reinforces trajectories with higher relative performance within the group. However, in most existing methods, every step within a trajectory and every trajectory with the same terminal reward receive identical credit, regardless of their actual contributions. Since different states play different structural roles in an online state-transition graph built from sampled trajectories, their impacts should be differentiated and converted into task-aware credit at both the step and trajectory levels. We therefore present Graph-Enhanced Policy Optimization (GEPO), a framework for dual-level structural credit assignment in multi-step LLM agent training. Specifically, GEPO derives a state-level Task-Conditioned Criticality score that combines topological betweenness on the state-transition graph with semantic similarity to the task prompt. Based on this score, trajectory-level credit is reshaped through a state-adaptive discount, while step-level credit is scaled by the criticality of its successor state. Experimental results show that GEPO outperforms the strongest baselines by 1.1\% in success rate on ALFWorld, 3.2\% on WebShop, and 3.8\% on average across search-augmented QA tasks at the 7B scale. Compared with flat group-based methods, GEPO reduces across-seed variance and concentrates gradient signals on the most critical steps. --- ### Revisiting Generative Infrared and Visible Image Fusion Based on Human Cognitive Laws Authors: Lin Guo, Xiaoqing Luo, Wei Xie, Zhancheng Zhang, Hui Li, Rui Wang, Zhenhua Feng, Xiaoning Song Published: 2025-10-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.26268v1 Existing infrared and visible image fusion methods often face the dilemma of balancing modal information. Generative fusion methods reconstruct fused images by learning from data distributions, but their generative capabilities remain limited. Moreover, the lack of interpretability in modal information selection further affects the reliability and consistency of fusion results in complex scenarios. This manuscript revisits the essence of generative image fusion under the inspiration of human cognitive laws and proposes a novel infrared and visible image fusion method, termed HCLFuse. First, HCLFuse investigates the quantification theory of information mapping in unsupervised fusion networks, which leads to the design of a multi-scale mask-regulated variational bottleneck encoder. This encoder applies posterior probability modeling and information decomposition to extract accurate and concise low-level modal information, thereby supporting the generation of high-fidelity structural details. Furthermore, the probabilistic generative capability of the diffusion model is integrated with physical laws, forming a time-varying physical guidance mechanism that adaptively regulates the generation process at different stages, thereby enhancing the ability of the model to perceive the intrinsic structure of data and reducing dependence on data quality. Experimental results show that the proposed method achieves state-of-the-art fusion performance in qualitative and quantitative evaluations across multiple datasets and significantly improves semantic segmentation metrics. This fully demonstrates the advantages of this generative image fusion method, drawing inspiration from human cognition, in enhancing structural consistency and detail quality. --- ### A Likely Geometry of Generative Models Authors: Frederik Möbius Rygaard, Shen Zhu, Yinzhu Jin, Søren Hauberg, Tom Fletcher Published: 2025-10-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.26266v2 The geometry of generative models serves as the basis for interpolation, model inspection, and more. Unfortunately, most generative models lack a principal notion of geometry without restrictive assumptions on either the model or the data dimension. In this paper, we construct a general geometry compatible with different metrics and probability distributions to analyze generative models that do not require additional training. We consider curves analogous to geodesics constrained to a suitable data distribution aimed at targeting high-density regions learned by generative models. We formulate this as a (pseudo)-metric and prove that this corresponds to a Newtonian system on a Riemannian manifold. We show that shortest paths in our framework can be characterized by a system of ordinary differential equations, which locally corresponds to geodesics under a suitable Riemannian metric. Numerically, we derive a novel algorithm to efficiently compute shortest paths and generalized Fréchet means. Quantitatively, we show that curves using our metric traverse regions of higher density than baselines across a range of models and datasets. ---