# Research Papers — 2025-11 · bundle page 10 of 197 > Full-text markdown of papers #451–500 of 9830 published in 2025-11, newest first. AI-readable mirrors of the full 9830-paper 2025-11 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2025-11/page/10 [← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/9.md) [Next bundle →](https://aipod.dev/papers/archive/2025-11/page/11.md) ### Context-Aware Detection and Victim-Centered Response Generation for Online Harassment in Private Messaging Authors: Pinxian Lu, Nimra Ishfaq, Emma Win, Morgan Rose, Sierra R Strickland, Candice L Biernesser, Jamie Zelazny, Munmun De Choudhury Published: 2025-11-28 Categories: cs.SI, cs.CL, cs.CY arXiv: https://arxiv.org/abs/2512.14700v2 Online harassment is a widespread social and public health concern, yet most computational approaches for detecting and addressing harassment focus on publicly visible social media content rather than private messaging environments. Private conversations present unique challenges because harmful interactions often unfold through context-dependent, multi-turn exchanges, while victims may lack timely support during moments of harassment. In this study, we investigate how large language models (LLMs) can support both the detection of and response to online harassment in private messaging. Using a dataset of 80,053 Instagram direct messages donated by 26 adolescents aged 12-18, including youth with suicide risk factors, we first construct a human-labeled dataset of online harassment in private conversations and develop a context-aware cascading LLM classification pipeline. The proposed pipeline outperforms baseline toxicity classifiers trained primarily on public social media data. We then develop a victim-centered response framework that produces context-sensitive and psychologically-grounded AI-generated responses to online harassment messages. Human evaluators perceived the AI-generated responses as significantly more helpful than the original participant responses (95% CI: 0.767--0.815, p < .001), particularly in terms of emotional support and de-escalation. Our findings highlight the potential of context-aware and victim-centered AI systems to provide just-in-time support during harassment in private messaging environments. --- ### Writing in Symbiosis: Mapping Human Creative Agency in the AI Era Authors: Vivan Doshi, Mengyuan Li Published: 2025-11-28 Categories: cs.CY, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2512.13697v2 The proliferation of Large Language Models (LLMs) raises a critical question about what it means to be human when we share an increasingly symbiotic relationship with persuasive and creative machines. This paper examines patterns of human-AI coevolution in creative writing, investigating how human craft and agency are adapting alongside machine capabilities. We challenge the prevailing notion of stylistic homogenization by examining diverse patterns in longitudinal writing data. Using a large-scale corpus spanning the pre- and post-LLM era, we observe patterns suggestive of a "Dual-Track Evolution": thematic convergence around AI-related topics, coupled with structured stylistic differentiation. Our analysis reveals three emergent adaptation patterns: authors showing increased similarity to AI style, those exhibiting decreased similarity, and those maintaining stylistic stability while engaging with AI-related themes. This Creative Archetype Map illuminates how authorship is coevolving with AI, contributing to discussions about human-AI collaboration, detection challenges, and the preservation of creative diversity. --- ### IoTEdu: Access Control, Detection, and Automatic Incident Response in Academic IoT Networks Authors: Joner Assolin, Diego Kreutz, Leandro Bertholdo Published: 2025-11-28 Categories: cs.CR, cs.AI, cs.NI, cs.SE arXiv: https://arxiv.org/abs/2512.09934v1 The growing presence of IoT devices in academic environments has increased operational complexity and exposed security weaknesses, especially in academic institutions without unified policies for registration, monitoring, and incident response involving IoT. This work presents IoTEdu, an integrated platform that combines access control, incident detection, and automatic blocking of IoT devices. The solution was evaluated in a controlled environment with simulated attacks, achieving an average time of 28.6 seconds between detection and blocking. The results show a reduction in manual intervention, standardization of responses, and unification of the processes of registration, monitoring, and incident response. --- ### Banach neural operator for Navier-Stokes equations Authors: Bo Zhang Published: 2025-11-28 Categories: cs.NE, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2512.09070v1 Classical neural networks are known for their ability to approximate mappings between finite-dimensional spaces, but they fall short in capturing complex operator dynamics across infinite-dimensional function spaces. Neural operators, in contrast, have emerged as powerful tools in scientific machine learning for learning such mappings. However, standard neural operators typically lack mechanisms for mixing or attending to input information across space and time. In this work, we introduce the Banach neural operator (BNO) -- a novel framework that integrates Koopman operator theory with deep neural networks to predict nonlinear, spatiotemporal dynamics from partial observations. The BNO approximates a nonlinear operator between Banach spaces by combining spectral linearization (via Koopman theory) with deep feature learning (via convolutional neural networks and nonlinear activations). This sequence-to-sequence model captures dominant dynamic modes and allows for mesh-independent prediction. Numerical experiments on the Navier-Stokes equations demonstrate the method's accuracy and generalization capabilities. In particular, BNO achieves robust zero-shot super-resolution in unsteady flow prediction and consistently outperforms conventional Koopman-based methods and deep learning models. --- ### ORCA: Open-ended Response Correctness Assessment for Audio Question Answering Authors: Šimon Sedláček, Sara Barahona, Bolaji Yusuf, Laura Herrera-Alarcón, Santosh Kesiraju, Cecilia Bolaños, Alicia Lozano-Diez, Sathvik Udupa, Fernando López, Allison Ferner, Ramani Duraiswami, Jan Černocký Published: 2025-11-28 Categories: cs.SD, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2512.09066v2 Reliable assessment of the abilities of large audio language models (LALMs) is essential to advancing the state of the art. As benchmarks rapidly evolve to incorporate complex reasoning and subjective tasks, they increasingly necessitate open-ended responses from LALMs. We present Open-ended Response Correctness Assessment (ORCA) -- a reliable and lightweight model-based approach for answer correctness and disagreement modeling. We employ a three-stage annotation pipeline combining human judgment, structured feedback, and human-AI correction, yielding 9,663 annotations across 3,699 question-answer pairs from 15 LALMs on three audio understanding and reasoning benchmarks (achieving a Krippendorff's alpha of 0.82). Our experiments employing curriculum learning show that ORCA models achieve a Spearman correlation of 0.91 with average human correctness ratings on seen benchmarks and generalize to unseen benchmarks with a score of 0.85, outperforming several LLM judge baselines including Gemini 2.5 Flash. Furthermore, we demonstrate that ORCA's predicted variance correlates strongly with human disagreement, allowing it to effectively identify problematic benchmark items. --- ### Multivariate time series prediction using clustered echo state network Authors: S. Hariharan, R. Suresh, V. K. Chandrasekar Published: 2025-11-28 Categories: nlin.CD, cs.LG arXiv: https://arxiv.org/abs/2512.08963v1 Many natural and physical processes can be understood by analyzing multiple system variables evolving, forming a multivariate time series. Predicting such time series is challenging due to the inherent noise and interdependencies among variables. Echo state networks (ESNs), a class of Reservoir Computing (RC) models, offer an efficient alternative to conventional recurrent neural networks by training only the output weights while keeping the reservoir dynamics fixed, reducing computational complexity. We propose a clustered ESNs (CESNs) that enhances the ability to model and predict multivariate time series by organizing the reservoir nodes into clusters, each corresponding to a distinct input variable. Input signals are directly mapped to their associated clusters, and intra-cluster connections remain dense while inter-cluster connections are sparse, mimicking the modular architecture of biological neural networks. This architecture improves information processing by limiting cross-variable interference and enhances computational efficiency through independent cluster-wise training via ridge regression. We further explore different reservoir topologies, including ring, Erdős-Rényi (ER), and scale-free (SF) networks, to evaluate their impact predictive performance. Our algorithm works well across diverse real-world datasets such as the stock market, solar wind, and chaotic Rössler system, demonstrating that CESNs consistently outperform conventional ESNs in terms of predictive accuracy and robustness to noise, particularly when using ER and SF topologies. These findings highlight the adaptability of CESNs for complex, multivariate time series forecasting. --- ### Resolving Conflicts in Lifelong Learning via Aligning Updates in Subspaces Authors: Yueer Zhou, Yichen Wu, Ying Wei Published: 2025-11-28 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2512.08960v1 Low-Rank Adaptation (LoRA) enables efficient Continual Learning but often suffers from catastrophic forgetting due to destructive interference between tasks. Our analysis reveals that this degradation is primarily driven by antagonistic directional updates where new task gradients directly oppose the historical weight trajectory. To address this, we propose PS-LoRA (Parameter Stability LoRA), a framework designed to resolve conflicts by aligning updates within the optimization subspace. Our approach employs a dual-regularization objective that penalizes conflicting directions and constrains magnitude deviations to ensure consistency with prior knowledge. Additionally, we implement a magnitude-based merging strategy to consolidate sequential adapters into a robust representation without retraining. Experiments on NLP and Vision benchmarks show that PS-LoRA outperforms state-of-the-art methods by preserving the stability of learned representations while efficiently adapting to new domains. --- ### EEG-Bench: A Benchmark for EEG Foundation Models in Clinical Applications Authors: Ard Kastrati, Josua Bürki, Jonas Lauer, Cheng Xuan, Raffaele Iaquinto, Roger Wattenhofer Published: 2025-11-28 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.08959v1 We introduce a unified benchmarking framework focused on evaluating EEG-based foundation models in clinical applications. The benchmark spans 11 well-defined diagnostic tasks across 14 publicly available EEG datasets, including epilepsy, schizophrenia, Parkinson's disease, OCD, and mild traumatic brain injury. It features minimal preprocessing, standardized evaluation protocols, and enables side-by-side comparisons of classical baselines and modern foundation models. Our results show that while foundation models achieve strong performance in certain settings, simpler models often remain competitive, particularly under clinical distribution shifts. To facilitate reproducibility and adoption, we release all prepared data and code in an accessible and extensible format. --- ### LUMOS: Large User MOdels for User Behavior Prediction Authors: Dhruv Nigam, Naman Agarwal, Krishna Murthy, Susmit Saha Published: 2025-11-28 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.08957v2 User behavior prediction at scale remains a critical challenge for online B2C platforms. Traditional approaches rely heavily on task-specific models and domain-specific feature engineering. This is time-consuming, computationally expensive, and requires domain expertise and therefore, not scalable. We present LUMOS (Large User MOdel Series), a transformer-based architecture that eliminates task-specific models and manual feature engineering by learning multiple tasks jointly using only raw user activity data. LUMOS introduces a novel cross-attention mechanism that conditions predictions on future known events (e.g., holidays, sales, etc.), enabling the model to predict complex behavior patterns like "how will upcoming holidays affect user engagement?" The architecture also employs multi-modal tokenization, combining user activities, event context, and static user demographic attributes into rich representations processed through specialized embedding pathways. Through extensive experiments on a production dataset spanning 1.7 trillion user activity tokens from 250 million users, we demonstrate that LUMOS achieves superior performance compared to traditional task-specific models. Across 5 tasks with established baselines, we achieve an average improvement of 0.025 in ROC-AUC for binary classification tasks and 4.6\% reduction in MAPE for regression tasks. Online A/B testing validates these improvements translate to measurable business impact with a 3.15\% increase in Daily Active Users. --- ### DW-KNN: A Transparent Local Classifier Integrating Distance Consistency and Neighbor Reliability Authors: Kumarjit Pathak, Karthik K, Sachin Madan, Jitin Kapila Published: 2025-11-28 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2512.08956v1 K-Nearest Neighbors (KNN) is one of the most used ML classifiers. However, if we observe closely, standard distance-weighted KNN and relative variants assume all 'k' neighbors are equally reliable. In heterogeneous feature space, this becomes a limitation that hinders reliability in predicting true levels of the observation. We propose DW-KNN (Double Weighted KNN), a transparent and robust variant that integrates exponential distance with neighbor validity. This enables instance-level interpretability, suppresses noisy or mislabeled samples, and reduces hyperparameter sensitivity. Comprehensive evaluation on 9 data-sets helps to demonstrate that DW-KNN achieves 0.8988 accuracy on average. It ranks 2nd among six methods and within 0.2% of the best-performing Ensemble KNN. It also exhibits the lowest cross-validation variance (0.0156), indicating reliable prediction stability. Statistical significance test confirmed ($p < 0.001$) improvement over compactness weighted KNN (+4.09\%) and Kernel weighted KNN (+1.13\%). The method provides a simple yet effective alternative to complex adaptive schemes, particularly valuable for high-stakes applications requiring explainable predictions. --- ### LLM4XCE: Large Language Models for Extremely Large-Scale Massive MIMO Channel Estimation Authors: Renbin Li, Shuangshuang Li, Peihao Dong Published: 2025-11-28 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.08955v1 Extremely large-scale massive multiple-input multiple-output (XL-MIMO) is a key enabler for sixth-generation (6G) networks, offering massive spatial degrees of freedom. Despite these advantages, the coexistence of near-field and far-field effects in hybrid-field channels presents significant challenges for accurate estimation, where traditional methods often struggle to generalize effectively. In recent years, large language models (LLMs) have achieved impressive performance on downstream tasks via fine-tuning, aligning with the semantic communication shift toward task-oriented understanding over bit-level accuracy. Motivated by this, we propose Large Language Models for XL-MIMO Channel Estimation (LLM4XCE), a novel channel estimation framework that leverages the semantic modeling capabilities of large language models to recover essential spatial-channel representations for downstream tasks. The model integrates a carefully designed embedding module with Parallel Feature-Spatial Attention, enabling deep fusion of pilot features and spatial structures to construct a semantically rich representation for LLM input. By fine-tuning only the top two Transformer layers, our method effectively captures latent dependencies in the pilot data while ensuring high training efficiency. Extensive simulations demonstrate that LLM4XCE significantly outperforms existing state-of-the-art methods under hybrid-field conditions, achieving superior estimation accuracy and generalization performance. --- ### An Electrocardiogram Multi-task Benchmark with Comprehensive Evaluations and Insightful Findings Authors: Yuhao Xu, Jiaying Lu, Sirui Ding, Defu Cao, Xiao Hu, Carl Yang Published: 2025-11-28 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.08954v1 In the process of patient diagnosis, non-invasive measurements are widely used due to their low risks and quick results. Electrocardiogram (ECG), as a non-invasive method to collect heart activities, is used to diagnose cardiac conditions. Analyzing the ECG typically requires domain expertise, which is a roadblock to applying artificial intelligence (AI) for healthcare. Through advances in self-supervised learning and foundation models, AI systems can now acquire and leverage domain knowledge without relying solely on human expertise. However, there is a lack of comprehensive analyses over the foundation models' performance on ECG. This study aims to answer the research question: "Are Foundation Models Useful for ECG Analysis?" To address it, we evaluate language/general time-series/ECG foundation models in comparison with time-series deep learning models. The experimental results show that general time-series/ECG foundation models achieve a top performance rate of 80%, indicating their effectiveness in ECG analysis. In-depth analyses and insights are provided along with comprehensive experimental results. This study highlights the limitations and potential of foundation models in advancing physiological waveform analysis. The data and code for this benchmark are publicly available at https://github.com/yuhaoxu99/ECGMultitasks-Benchmark. --- ### SimClinician: A Multimodal Simulation Testbed for Reliable Psychologist AI Collaboration in Mental Health Diagnosis Authors: Filippo Cenacchi, Longbing Cao, Deborah Richards Published: 2025-11-28 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2512.08953v1 AI based mental health diagnosis is often judged by benchmark accuracy, yet in practice its value depends on how psychologists respond whether they accept, adjust, or reject AI suggestions. Mental health makes this especially challenging: decisions are continuous and shaped by cues in tone, pauses, word choice, and nonverbal behaviors of patients. Current research rarely examines how AI diagnosis interface design influences these choices, leaving little basis for reliable testing before live studies. We present SimClinician, an interactive simulation platform, to transform patient data into psychologist AI collaborative diagnosis. Contributions include: (1) a dashboard integrating audio, text, and gaze-expression patterns; (2) an avatar module rendering de-identified dynamics for analysis; (3) a decision layer that maps AI outputs to multimodal evidence, letting psychologists review AI reasoning, and enter a diagnosis. Tested on the E-DAIC corpus (276 clinical interviews, expanded to 480,000 simulations), SimClinician shows that a confirmation step raises acceptance by 23%, keeping escalations below 9%, and maintaining smooth interaction flow. --- ### Learning When to Ask: Simulation-Trained Humanoids for Mental-Health Diagnosis Authors: Filippo Cenacchi, Deborah Richards, Longbing Cao Published: 2025-11-28 Categories: cs.LG, cs.AI, cs.HC, cs.RO arXiv: https://arxiv.org/abs/2512.08952v1 Testing humanoid robots with users is slow, causes wear, and limits iteration and diversity. Yet screening agents must master conversational timing, prosody, backchannels, and what to attend to in faces and speech for Depression and PTSD. Most simulators omit policy learning with nonverbal dynamics; many controllers chase task accuracy while underweighting trust, pacing, and rapport. We virtualise the humanoid as a conversational agent to train without hardware burden. Our agent-centred, simulation-first pipeline turns interview data into 276 Unreal Engine MetaHuman patients with synchronised speech, gaze/face, and head-torso poses, plus PHQ-8 and PCL-C flows. A perception-fusion-policy loop decides what and when to speak, when to backchannel, and how to avoid interruptions, under a safety shield. Training uses counterfactual replay (bounded nonverbal perturbations) and an uncertainty-aware turn manager that probes to reduce diagnostic ambiguity. Results are simulation-only; the humanoid is the transfer target. In comparing three controllers, a custom TD3 (Twin Delayed DDPG) outperformed PPO and CEM, achieving near-ceiling coverage with steadier pace at comparable rewards. Decision-quality analyses show negligible turn overlap, aligned cut timing, fewer clarification prompts, and shorter waits. Performance stays stable under modality dropout and a renderer swap, and rankings hold on a held-out patient split. Contributions: (1) an agent-centred simulator that turns interviews into 276 interactive patients with bounded nonverbal counterfactuals; (2) a safe learning loop that treats timing and rapport as first-class control variables; (3) a comparative study (TD3 vs PPO/CEM) with clear gains in completeness and social timing; and (4) ablations and robustness analyses explaining the gains and enabling clinician-supervised humanoid pilots. --- ### ByteStorm: a multi-step data-driven approach for Tropical Cyclones detection and tracking Authors: Davide Donno, Donatello Elia, Gabriele Accarino, Marco De Carlo, Enrico Scoccimarro, Silvio Gualdi Published: 2025-11-28 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.07885v2 Accurate tropical cyclones (TCs) tracking represents a critical challenge in the context of weather and climate science. Traditional tracking schemes mainly rely on subjective thresholds, which may introduce biases in their skills on the geographical region of application and are often computationally and data-intensive, due to the management of a large number of variables. We present \textit{ByteStorm}, an efficient data-driven framework for reconstructing TC tracks. It leverages deep learning networks to detect TC centers (via classification and localization), using only relative vorticity (850 mb) and mean sea-level pressure. Then, detected centers are linked into TC tracks through the BYTE algorithm. \textit{ByteStorm} is benchmarked with state-of-the-art deterministic trackers on the main global TC formation basins. The proposed framework achieves good tracking skills in terms of Probability of Detection and False Alarm Rate, accurately reproduces Seasonal and Inter-Annual Variability, and reconstructs reliable, smooth and coherent TC tracks. These results highlight the potential of integrating deep learning and computer vision to provide robust, computationally efficient and skillful data-driven alternatives to TC tracking. --- ### GSPN-2: Efficient Parallel Sequence Modeling Authors: Hongjun Wang, Yitong Jiang, Collin McCarthy, David Wehr, Hanrong Ye, Xinhao Li, Ka Chun Cheung, Wonmin Byeon, Jinwei Gu, Ke Chen, Kai Han, Hongxu Yin et al. Published: 2025-11-28 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2512.07884v1 Efficient vision transformer remains a bottleneck for high-resolution images and long-video related real-world applications. Generalized Spatial Propagation Network (GSPN) addresses this by replacing quadratic self-attention with a line-scan propagation scheme, bringing the cost close to linear in the number of rows or columns, while retaining accuracy. Despite this advancement, the existing GSPN implementation still suffers from (i) heavy overhead due to repeatedly launching GPU kernels, (ii) excessive data transfers from global GPU memory, and (iii) redundant computations caused by maintaining separate propagation weights for each channel. We introduce GSPN-2, a joint algorithm-system redesign. In particular, we eliminate thousands of micro-launches from the previous implementation into one single 2D kernel, explicitly pin one warp to each channel slice, and stage the previous column's activations in shared memory. On the model side, we introduce a compact channel propagation strategy that replaces per-channel matrices, trimming parameters, and align naturally with the affinity map used in transformer attention. Experiments demonstrate GSPN-2's effectiveness across image classification and text-to-image synthesis tasks, matching transformer-level accuracy with significantly lower computational cost. GSPN-2 establishes a new efficiency frontier for modeling global spatial context in vision applications through its unique combination of structured matrix transformations and GPU-optimized implementation. Project page: https://whj363636.github.io/GSPN2/ --- ### Poincaré Meets Bellman: Revisable Memory, Operational Quotients, and Evidence-Supported Learning in Changing Environments Authors: Xin Li Published: 2025-11-28 Categories: cs.LG, q-bio.NC arXiv: https://arxiv.org/abs/2512.05990v2 Memory consolidation determines both what a learner can do now and which changes remain implementable later. We develop a finite-model synthesis of operational state abstraction and optimal control under the stability-evidence-revision (SER) framework. ``Poincaré meets Bellman'' names two complementary roles: qualitative dynamics identifies reusable action-response structure, and dynamic programming prices acquisition, retention, reuse, merging, and forgetting. Recurrence enters separately through the timing and value of future demands. We distinguish active quotient merging from historical information erasure, characterize exact repair by zero-error functional coding and causal migration, and derive a Bellman recursion over the joint law of hidden state and complete deployed memory. A first-return model yields an explicit retention rule. Conditional results show how factor sharing avoids enumerating combinations and how independent informative observations improve identification, while leaving some zero-error evidence budgets unchanged. Finite enumerations verify the coding and retention calculations. The synthesis gives an exact benchmark for specified finite models, without claiming universal recurrence, bounded-memory open-ended learning, or tractable global planning. --- ### A self-driving lab for solution-processed electrochromic thin films Authors: Selma Dahms, Luca Torresi, Shahbaz Tareq Bandesha, Jan Hansmann, Holger Röhm, Alexander Colsmann, Marco Schott, Pascal Friederich Published: 2025-11-28 Categories: cs.LG, cond-mat.mtrl-sci arXiv: https://arxiv.org/abs/2512.05989v1 Solution-processed electrochromic materials offer high potential for energy-efficient smart windows and displays. Their performance varies with material choice and processing conditions. Electrochromic thin film electrodes require a smooth, defect-free coating for optimal contrast between bleached and colored states. The complexity of optimizing the spin-coated electrochromic thin layer poses challenges for rapid development. This study demonstrates the use of self-driving laboratories to accelerate the development of electrochromic coatings by coupling automation with machine learning. Our system combines automated data acquisition, image processing, spectral analysis, and Bayesian optimization to explore processing parameters efficiently. This approach not only increases throughput but also enables a pointed search for optimal processing parameters. The approach can be applied to various solution-processed materials, highlighting the potential of self-driving labs in enhancing materials discovery and process optimization. --- ### VG3T: Visual Geometry Grounded Gaussian Transformer Authors: Junho Kim, Seongwon Lee Published: 2025-11-28 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.05988v1 Generating a coherent 3D scene representation from multi-view images is a fundamental yet challenging task. Existing methods often struggle with multi-view fusion, leading to fragmented 3D representations and sub-optimal performance. To address this, we introduce VG3T, a novel multi-view feed-forward network that predicts a 3D semantic occupancy via a 3D Gaussian representation. Unlike prior methods that infer Gaussians from single-view images, our model directly predicts a set of semantically attributed Gaussians in a joint, multi-view fashion. This novel approach overcomes the fragmentation and inconsistency inherent in view-by-view processing, offering a unified paradigm to represent both geometry and semantics. We also introduce two key components, Grid-Based Sampling and Positional Refinement, to mitigate the distance-dependent density bias common in pixel-aligned Gaussian initialization methods. Our VG3T shows a notable 1.7%p improvement in mIoU while using 46% fewer primitives than the previous state-of-the-art on the nuScenes benchmark, highlighting its superior efficiency and performance. --- ### Adaptive Dataset Quantization: A New Direction for Dataset Pruning Authors: Chenyue Yu, Jianyu Yu Published: 2025-11-28 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.05987v1 This paper addresses the challenges of storage and communication costs for large-scale datasets in resource-constrained edge devices by proposing a novel dataset quantization approach to reduce intra-sample redundancy. Unlike traditional dataset pruning and distillation methods that focus on inter-sample redundancy, the proposed method compresses each image by reducing redundant or less informative content within samples while preserving essential features. It first applies linear symmetric quantization to obtain an initial quantization range and scale for each sample. Then, an adaptive quantization allocation algorithm is introduced to distribute different quantization ratios for samples with varying precision requirements, maintaining a constant total compression ratio. The main contributions include: (1) being the first to use limited bits to represent datasets for storage reduction; (2) introducing a dataset-level quantization algorithm with adaptive ratio allocation; and (3) validating the method's effectiveness through extensive experiments on CIFAR-10, CIFAR-100, and ImageNet-1K. Results show that the method maintains model training performance while achieving significant dataset compression, outperforming traditional quantization and dataset pruning baselines under the same compression ratios. --- ### Breaking Scale Anchoring: Frequency Representation Learning for Accurate High-Resolution Inference from Low-Resolution Training Authors: Wenshuo Wang, Fan Zhang Published: 2025-11-28 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.05132v2 Zero-Shot Super-Resolution Spatiotemporal Forecasting requires a deep learning model to be trained on low-resolution data and deployed for inference on high-resolution. Existing studies consider maintaining similar error across different resolutions as indicative of successful multi-resolution generalization. However, deep learning models serving as alternatives to numerical solvers should reduce error as resolution increases. The fundamental limitation is, the upper bound of physical law frequencies that low-resolution data can represent is constrained by its Nyquist frequency, making it difficult for models to process signals containing unseen frequency components during high-resolution inference. This results in errors being anchored at low resolution, incorrectly interpreted as successful generalization. We define this fundamental phenomenon as a new problem distinct from existing issues: Scale Anchoring. Therefore, we propose architecture-agnostic Frequency Representation Learning. It alleviates Scale Anchoring through resolution-aligned frequency representations and spectral consistency training: on grids with higher Nyquist frequencies, the frequency response in high-frequency bands of FRL-enhanced variants is more stable. This allows errors to decrease with resolution and significantly outperform baselines within our task and resolution range, while incurring only modest computational overhead. --- ### AREA3D: Active Reconstruction Agent with Unified Feed-Forward 3D Perception and Vision-Language Guidance Authors: Tianling Xu, Shengzhe Gan, Leslie Gu, Yuelei Li, Fangneng Zhan, Hanspeter Pfister Published: 2025-11-28 Categories: cs.CV, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2512.05131v2 Active 3D reconstruction enables an agent to autonomously select viewpoints to efficiently obtain accurate and complete scene geometry, rather than passively reconstructing scenes from pre-collected images. However, existing active reconstruction methods often rely on hand-crafted geometric heuristics, which can lead to redundant observations without substantially improving reconstruction quality. To address this limitation, we propose AREA3D, an active reconstruction agent that leverages feed-forward 3D reconstruction models and vision-language guidance. Our framework decouples view-uncertainty modeling from the underlying feed-forward reconstructor, enabling precise uncertainty estimation without expensive online optimization. In addition, an integrated vision-language model provides high-level semantic guidance, encouraging informative and diverse viewpoints beyond purely geometric cues. Extensive experiments on both scene-level and object-level benchmarks demonstrate that AREA3D achieves state-of-the-art reconstruction accuracy, particularly in the sparse-view regime. Code will be made available at: https://github.com/TianlingXu/AREA3D . --- ### Responsible LLM Deployment for High-Stake Decisions by Decentralized Technologies and Human-AI Interactions Authors: Swati Sachan, Theo Miller, Mai Phuong Nguyen Published: 2025-11-28 Categories: cs.CY, cs.AI, cs.HC, q-fin.CP arXiv: https://arxiv.org/abs/2512.04108v1 High-stakes decision domains are increasingly exploring the potential of Large Language Models (LLMs) for complex decision-making tasks. However, LLM deployment in real-world settings presents challenges in data security, evaluation of its capabilities outside controlled environments, and accountability attribution in the event of adversarial decisions. This paper proposes a framework for responsible deployment of LLM-based decision-support systems through active human involvement. It integrates interactive collaboration between human experts and developers through multiple iterations at the pre-deployment stage to assess the uncertain samples and judge the stability of the explanation provided by post-hoc XAI techniques. Local LLM deployment within organizations and decentralized technologies, such as Blockchain and IPFS, are proposed to create immutable records of LLM activities for automated auditing to enhance security and trace back accountability. It was tested on Bert-large-uncased, Mistral, and LLaMA 2 and 3 models to assess the capability to support responsible financial decisions on business lending. --- ### Rethinking AI Evaluation in Education: The TEACH-AI Framework and Benchmark for Generative AI Assistants Authors: Shi Ding, Brian Magerko Published: 2025-11-28 Categories: cs.CY, cs.AI, cs.HC, cs.LG arXiv: https://arxiv.org/abs/2512.04107v1 As generative artificial intelligence (AI) continues to transform education, most existing AI evaluations rely primarily on technical performance metrics such as accuracy or task efficiency while overlooking human identity, learner agency, contextual learning processes, and ethical considerations. In this paper, we present TEACH-AI (Trustworthy and Effective AI Classroom Heuristics), a domain-independent, pedagogically grounded, and stakeholder-aligned framework with measurable indicators and a practical toolkit for guiding the design, development, and evaluation of generative AI systems in educational contexts. Built on an extensive literature review and synthesis, the ten-component assessment framework and toolkit checklist provide a foundation for scalable, value-aligned AI evaluation in education. TEACH-AI rethinks "evaluation" through sociotechnical, educational, theoretical, and applied lenses, engaging designers, developers, researchers, and policymakers across AI and education. Our work invites the community to reconsider what constructs "effective" AI in education and to design model evaluation approaches that promote co-creation, inclusivity, and long-term human, social, and educational impact. --- ### Retrieval-Augmented Few-Shot Prompting Versus Fine-Tuning for Code Vulnerability Detection Authors: Fouad Trad, Ali Chehab Published: 2025-11-28 Categories: cs.SE, cs.AI, cs.CL, cs.CR arXiv: https://arxiv.org/abs/2512.04106v1 Few-shot prompting has emerged as a practical alternative to fine-tuning for leveraging the capabilities of large language models (LLMs) in specialized tasks. However, its effectiveness depends heavily on the selection and quality of in-context examples, particularly in complex domains. In this work, we examine retrieval-augmented prompting as a strategy to improve few-shot performance in code vulnerability detection, where the goal is to identify one or more security-relevant weaknesses present in a given code snippet from a predefined set of vulnerability categories. We perform a systematic evaluation using the Gemini-1.5-Flash model across three approaches: (1) standard few-shot prompting with randomly selected examples, (2) retrieval-augmented prompting using semantically similar examples, and (3) retrieval-based labeling, which assigns labels based on retrieved examples without model inference. Our results show that retrieval-augmented prompting consistently outperforms the other prompting strategies. At 20 shots, it achieves an F1 score of 74.05% and a partial match accuracy of 83.90%. We further compare this approach against zero-shot prompting and several fine-tuned models, including Gemini-1.5-Flash and smaller open-source models such as DistilBERT, DistilGPT2, and CodeBERT. Retrieval-augmented prompting outperforms both zero-shot (F1 score: 36.35%, partial match accuracy: 20.30%) and fine-tuned Gemini (F1 score: 59.31%, partial match accuracy: 53.10%), while avoiding the training time and cost associated with model fine-tuning. On the other hand, fine-tuning CodeBERT yields higher performance (F1 score: 91.22%, partial match accuracy: 91.30%) but requires additional training, maintenance effort, and resources. --- ### LegalWebAgent: Empowering Access to Justice via LLM-Based Web Agents Authors: Jinzhe Tan, Karim Benyekhlef Published: 2025-11-28 Categories: cs.CY, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2512.04105v1 Access to justice remains a global challenge, with many citizens still finding it difficult to seek help from the justice system when facing legal issues. Although the internet provides abundant legal information and services, navigating complex websites, understanding legal terminology, and filling out procedural forms continue to pose barriers to accessing justice. This paper introduces the LegalWebAgent framework that employs a web agent powered by multimodal large language models to bridge the gap in access to justice for ordinary citizens. The framework combines the natural language understanding capabilities of large language models with multimodal perception, enabling a complete process from user query to concrete action. It operates in three stages: the Ask Module understands user needs through natural language processing; the Browse Module autonomously navigates webpages, interacts with page elements (including forms and calendars), and extracts information from HTML structures and webpage screenshots; the Act Module synthesizes information for users or performs direct actions like form completion and schedule booking. To evaluate its effectiveness, we designed a benchmark test covering 15 real-world tasks, simulating typical legal service processes relevant to Québec civil law users, from problem identification to procedural operations. Evaluation results show LegalWebAgent achieved a peak success rate of 86.7%, with an average of 84.4% across all tested models, demonstrating high autonomy in complex real-world scenarios. --- ### Alleviating Choice Supportive Bias in LLM with Reasoning Dependency Generation Authors: Nan Zhuang, Wenshuo Wang, Lekai Qian, Yuxiao Wang, Boyu Cao, Qi Liu Published: 2025-11-28 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.03082v1 Recent studies have demonstrated that some Large Language Models exhibit choice-supportive bias (CSB) when performing evaluations, systematically favoring their chosen options and potentially compromising the objectivity of AI-assisted decision making. While existing debiasing approaches primarily target demographic and social biases, methods for addressing cognitive biases in LLMs remain largely unexplored. In this work, we present the first solution to address CSB through Reasoning Dependency Generation (RDG), a novel framework for generating unbiased reasoning data to mitigate choice-supportive bias through fine-tuning. RDG automatically constructs balanced reasoning QA pairs, explicitly (un)modeling the dependencies between choices, evidences, and justifications. Our approach is able to generate a large-scale dataset of QA pairs across domains, incorporating Contextual Dependency Data and Dependency Decouple Data. Experiments show that LLMs fine-tuned on RDG-generated data demonstrate a 81.5% improvement in memory-based experiments and 94.3% improvement in the evaluation-based experiment, while maintaining similar performance on standard BBQ benchmarks. This work pioneers an approach for addressing cognitive biases in LLMs and contributes to the development of more reliable AI-assisted decision support systems. --- ### Calibrating Geophysical Predictions under Constrained Probabilistic Distributions Authors: Zhewen Hou, Jiajin Sun, Subashree Venkatasubramanian, Peter Jin, Shuolin Li, Tian Zheng Published: 2025-11-28 Categories: physics.ao-ph, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2512.03081v2 Machine learning (ML) has shown significant promise in studying complex geophysical dynamical systems, including turbulence and climate processes. Such systems often display sensitive dependence on initial conditions, reflected in positive Lyapunov exponents, where even small perturbations in short-term forecasts can lead to large deviations in long-term outcomes. Thus, meaningful inference requires not only accurate short-term predictions, but also consistency with the system's long-term attractor that is captured by the marginal distribution of state variables. Existing approaches attempt to address this challenge by incorporating spatial and temporal dependence, but these strategies become impractical when data are extremely sparse. In this work, we show that prior knowledge of marginal distributions offers valuable complementary information to short-term observations, motivating a distribution-informed learning framework. We introduce a calibration algorithm based on normalization and the Kernelized Stein Discrepancy (KSD) to enhance ML predictions. The method here employs KSD within a reproducing kernel Hilbert space to calibrate model outputs, improving their fidelity to known physical distributions. This not only sharpens pointwise predictions but also enforces consistency with non-local statistical structures rooted in physical principles. Through synthetic experiments-spanning offline climatological CO2 fluxes and online quasi-geostrophic flow simulations-we demonstrate the robustness and broad utility of the proposed framework. --- ### AtomDisc: An Atom-level Tokenizer that Boosts Molecular LLMs and Reveals Structure--Property Associations Authors: Mingxu Zhang, Dazhong Shen, Ying Sun Published: 2025-11-28 Categories: physics.chem-ph, cs.AI, cs.CE arXiv: https://arxiv.org/abs/2512.03080v1 Advances in large language models (LLMs) are accelerating discovery in molecular science. However, adapting molecular information to the serialized, token-based processing of LLMs remains a key challenge. Compared to other representations, molecular graphs explicitly encode atomic connectivity and local topological environments, which are key determinants of atomic behavior and molecular properties. Despite recent efforts to tokenize overall molecular topology, there still lacks effective fine-grained tokenization of local atomic environments, which are critical for determining sophisticated chemical properties and reactivity. To address these issues, we introduce AtomDisc, a novel framework that quantizes atom-level local environments into structure-aware tokens embedded directly in LLM's token space. Our experiments show that AtomDisc, in a data-driven way, can distinguish chemically meaningful structural features that reveal structure-property associations. Equipping LLMs with AtomDisc tokens injects an interpretable inductive bias that delivers state-of-the-art performance on property prediction and molecular generation. Our methodology and findings can pave the way for constructing more powerful molecular LLMs aimed at mechanistic insight and complex chemical reasoning. --- ### Watermarks for Embeddings-as-a-Service Large Language Models Authors: Anudeex Shetty Published: 2025-11-28 Categories: cs.CL, cs.CR, cs.LG arXiv: https://arxiv.org/abs/2512.03079v1 Large Language Models (LLMs) have demonstrated exceptional capabilities in natural language understanding and generation. Based on these LLMs, businesses have started to provide Embeddings-as-a-Service (EaaS), offering feature extraction capabilities (in the form of text embeddings) that benefit downstream natural language processing tasks. However, prior research has demonstrated that EaaS is vulnerable to imitation attacks, where an attacker clones the service's model in a black-box manner without access to the model's internal workings. In response, watermarks have been added to the text embeddings to protect the intellectual property of EaaS providers by allowing them to check for model ownership. This thesis focuses on defending against imitation attacks by investigating EaaS watermarks. To achieve this goal, we unveil novel attacks and propose and validate new watermarking techniques. Firstly, we show that existing EaaS watermarks can be removed through paraphrasing the input text when attackers clone the model during imitation attacks. Our study illustrates that paraphrasing can effectively bypass current state-of-the-art EaaS watermarks across various attack setups (including different paraphrasing techniques and models) and datasets in most instances. This demonstrates a new vulnerability in recent EaaS watermarking techniques. Subsequently, as a countermeasure, we propose a novel watermarking technique, WET (Watermarking EaaS with Linear Transformation), which employs linear transformation of the embeddings. Watermark verification is conducted by applying a reverse transformation and comparing the similarity between recovered and original embeddings. We demonstrate its robustness against paraphrasing attacks with near-perfect verifiability. We conduct detailed ablation studies to assess the significance of each component and hyperparameter in WET. --- ### Risk-Entropic Flow Matching Authors: Vahid R. Ramezani, Benjamin Englard Published: 2025-11-28 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.03078v1 Tilted (entropic) risk, obtained by applying a log-exponential transform to a base loss, is a well established tool in statistics and machine learning for emphasizing rare or high loss events while retaining a tractable optimization problem. In this work, our aim is to interpret its structure for Flow Matching (FM). FM learns a velocity field that transports samples from a simple source distribution to data by integrating an ODE. In rectified FM, training pairs are obtained by linearly interpolating between a source sample and a data sample, and a neural velocity field is trained to predict the straight line displacement using a mean squared error loss. This squared loss collapses all velocity targets that reach the same space-time point into a single conditional mean, thereby ignoring higher order conditional information (variance, skewness, multi-modality) that encodes fine geometric structure about the data manifold and minority branches. We apply the standard risk-sensitive (log-exponential) transform to the conditional FM loss and show that the resulting tilted risk loss is a natural upper-bound on a meaningful conditional entropic FM objective defined at each space-time point. Furthermore, we show that a small order expansion of the gradient of this conditional entropic objective yields two interpretable first order corrections: covariance preconditioning of the FM residual, and a skew tail term that favors asymmetric or rare branches. On synthetic data designed to probe ambiguity and tails, the resulting risk-sensitive loss improves statistical metrics and recovers geometric structure more faithfully than standard rectified FM. --- ### From 'What-is' to 'What-if' in Human-Factor Analysis: A Post-Occupancy Evaluation Case Authors: Xia Chen, Ruiji Sun, Philipp Geyer, André Borrmann, Stefano Schiavon Published: 2025-11-28 Categories: stat.AP, cs.LG arXiv: https://arxiv.org/abs/2512.02060v1 Human-factor analysis typically employs correlation analysis and significance testing to identify relationships between variables. However, these descriptive ('what-is') methods, while effective for identifying associations, are often insufficient for answering causal ('what-if') questions. Their application in such contexts often overlooks confounding and colliding variables, potentially leading to bias and suboptimal or incorrect decisions. We advocate for explicitly distinguishing descriptive from interventional questions in human-factor analysis, and applying causal inference frameworks specifically to these problems to prevent methodological mismatches. This approach disentangles complex variable relationships and enables counterfactual reasoning. Using post-occupancy evaluation (POE) data from the Center for the Built Environment's (CBE) Occupant Survey as a demonstration case, we show how causal discovery reveals intervention hierarchies and directional relationships that traditional associational analysis misses. The systematic distinction between causally associated and independent variables, combined with intervention prioritization capabilities, offers broad applicability to complex human-centric systems, for example, in building science or ergonomics, where understanding intervention effects is critical for optimization and decision-making. --- ### Misalignment of LLM-Generated Personas with Human Perceptions in Low-Resource Settings Authors: Tabia Tanzin Prama, Christopher M. Danforth, Peter Sheridan Dodds Published: 2025-11-28 Categories: cs.CY, cs.CL arXiv: https://arxiv.org/abs/2512.02058v1 Recent advances enable Large Language Models (LLMs) to generate AI personas, yet their lack of deep contextual, cultural, and emotional understanding poses a significant limitation. This study quantitatively compared human responses with those of eight LLM-generated social personas (e.g., Male, Female, Muslim, Political Supporter) within a low-resource environment like Bangladesh, using culturally specific questions. Results show human responses significantly outperform all LLMs in answering questions, and across all matrices of persona perception, with particularly large gaps in empathy and credibility. Furthermore, LLM-generated content exhibited a systematic bias along the lines of the ``Pollyanna Principle'', scoring measurably higher in positive sentiment ($Φ_{avg} = 5.99$ for LLMs vs. $5.60$ for Humans). These findings suggest that LLM personas do not accurately reflect the authentic experience of real people in resource-scarce environments. It is essential to validate LLM personas against real-world human data to ensure their alignment and reliability before deploying them in social science research. --- ### Opening the Black Box: An Explainable, Few-shot AI4E Framework Informed by Physics and Expert Knowledge for Materials Engineering Authors: Haoxiang Zhang, Ruihao Yuan, Lihui Zhang, Yushi Luo, Qiang Zhang, Pan Ding, Xiaodong Ren, Weijie Xing, Niu Gao, Jishan Chen, Chubo Zhang Published: 2025-11-28 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.02057v1 The industrial adoption of Artificial Intelligence for Engineering (AI4E) faces two fundamental bottlenecks: scarce high-quality data and the lack of interpretability in black-box models-particularly critical in safety-sensitive sectors like aerospace. We present an explainable, few-shot AI4E framework that is systematically informed by physics and expert knowledge throughout its architecture. Starting from only 32 experimental samples in an aerial K439B superalloy castings repair welding case, we first augment physically plausible synthetic data through a three-stage protocol: differentiated noise injection calibrated to process variabilities, enforcement of hard physical constraints, and preservation of inter-parameter relationships. We then employ a nested optimization strategy for constitutive model discovery, where symbolic regression explores equation structures while differential evolution optimizes parameters, followed by intensive parameter refinement using hybrid global-local optimization. The resulting interpretable constitutive equation achieves 88% accuracy in predicting hot-cracking tendency. This equation not only provides quantitative predictions but also delivers explicit physical insight, revealing how thermal, geometric, and metallurgical mechanisms couple to drive cracking-thereby advancing engineers' cognitive understanding of the process. Furthermore, the constitutive equation serves as a multi-functional tool for process optimization and high-fidelity virtual data generation, enabling accuracy improvements in other data-driven models. Our approach provides a general blueprint for developing trustworthy AI systems that embed engineering domain knowledge directly into their architecture, enabling reliable adoption in high-stakes industrial applications where data is limited but physical understanding is available. --- ### SD-CGAN: Conditional Sinkhorn Divergence GAN for DDoS Anomaly Detection in IoT Networks Authors: Henry Onyeka, Emmanuel Samson, Liang Hong, Tariqul Islam, Imtiaz Ahmed, Kamrul Hasan Published: 2025-11-28 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2512.00251v1 The increasing complexity of IoT edge networks presents significant challenges for anomaly detection, particularly in identifying sophisticated Denial-of-Service (DoS) attacks and zero-day exploits under highly dynamic and imbalanced traffic conditions. This paper proposes SD-CGAN, a Conditional Generative Adversarial Network framework enhanced with Sinkhorn Divergence, tailored for robust anomaly detection in IoT edge environments. The framework incorporates CTGAN-based synthetic data augmentation to address class imbalance and leverages Sinkhorn Divergence as a geometry-aware loss function to improve training stability and reduce mode collapse. The model is evaluated on exploitative attack subsets from the CICDDoS2019 dataset and compared against baseline deep learning and GAN-based approaches. Results show that SD-CGAN achieves superior detection accuracy, precision, recall, and F1-score while maintaining computational efficiency suitable for deployment in edge-enabled IoT environments. --- ### A Hierarchical Hybrid AI Approach: Integrating Deep Reinforcement Learning and Scripted Agents in Combat Simulations Authors: Scotty Black, Christian Darken Published: 2025-11-28 Categories: cs.LG, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2512.00249v1 In the domain of combat simulations in support of wargaming, the development of intelligent agents has predominantly been characterized by rule-based, scripted methodologies with deep reinforcement learning (RL) approaches only recently being introduced. While scripted agents offer predictability and consistency in controlled environments, they fall short in dynamic, complex scenarios due to their inherent inflexibility. Conversely, RL agents excel in adaptability and learning, offering potential improvements in handling unforeseen situations, but suffer from significant challenges such as black-box decision-making processes and scalability issues in larger simulation environments. This paper introduces a novel hierarchical hybrid artificial intelligence (AI) approach that synergizes the reliability and predictability of scripted agents with the dynamic, adaptive learning capabilities of RL. By structuring the AI system hierarchically, the proposed approach aims to utilize scripted agents for routine, tactical-level decisions and RL agents for higher-level, strategic decision-making, thus addressing the limitations of each method while leveraging their individual strengths. This integration is shown to significantly improve overall performance, providing a robust, adaptable, and effective solution for developing and training intelligent agents in complex simulation environments. --- ### Optimizing Information Asset Investment Strategies in the Exploratory Phase of the Oil and Gas Industry: A Reinforcement Learning Approach Authors: Paulo Roberto de Melo Barros Junior, Monica Alexandra Vilar Ribeiro De Meireles, Jose Luis Lima de Jesus Silva Published: 2025-11-28 Categories: econ.TH, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2512.00243v1 Our work investigates the economic efficiency of the prevailing "ladder-step" investment strategy in oil and gas exploration, which advocates for the incremental acquisition of geological information throughout the project lifecycle. By employing a multi-agent Deep Reinforcement Learning (DRL) framework, we model an alternative strategy that prioritizes the early acquisition of high-quality information assets. We simulate the entire upstream value chain-comprising competitive bidding, exploration, and development phases-to evaluate the economic impact of this approach relative to traditional methods. Our results demonstrate that front-loading information investment significantly reduces the costs associated with redundant data acquisition and enhances the precision of reserve valuation. Specifically, we find that the alternative strategy outperforms traditional methods in highly competitive environments by mitigating the "winner's curse" through more accurate bidding. Furthermore, the economic benefits are most pronounced during the development phase, where superior data quality minimizes capital misallocation. These findings suggest that optimal investment timing is structurally dependent on market competition rather than solely on price volatility, offering a new paradigm for capital allocation in extractive industries. --- ### Polynomial Neural Sheaf Diffusion: A Spectral Filtering Approach on Cellular Sheaves Authors: Alessio Borgi, Fabrizio Silvestri, Pietro Liò Published: 2025-11-28 Categories: cs.LG, cs.AI, cs.ET, stat.ML arXiv: https://arxiv.org/abs/2512.00242v3 Sheaf Neural Networks equip graph structures with a cellular sheaf: a geometric structure which assigns local vector spaces (stalks) and a linear learnable restriction/transport maps to nodes and edges, yielding an edge-aware inductive bias that handles heterophily and limits oversmoothing. However, common Neural Sheaf Diffusion implementations rely on SVD-based sheaf normalization and dense per-edge restriction maps, which scale with stalk dimension, require frequent Laplacian rebuilds, and yield brittle gradients. To address these limitations, we introduce Polynomial Neural Sheaf Diffusion (PolyNSD), a new sheaf diffusion approach whose propagation operator is a degree-K polynomial in a normalised sheaf Laplacian, evaluated via a stable three-term recurrence on a spectrally rescaled operator. This provides an explicit K-hop receptive field in a single layer (independently of the stalk dimension), with a trainable spectral response obtained as a convex mixture of K+1 orthogonal polynomial basis responses. PolyNSD enforces stability via convex mixtures, spectral rescaling, and residual/gated paths, reaching new state-of-the-art results on both homophilic and heterophilic benchmarks, inverting the Neural Sheaf Diffusion trend by obtaining these results with just diagonal restriction maps, decoupling performance from large stalk dimension, while reducing runtime and memory requirements. --- ### Self-Supervised Dynamical System Representations for Physiological Time-Series Authors: Yenho Chen, Maxwell A. Xu, James M. Rehg, Christopher J. Rozell Published: 2025-11-28 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2512.00239v2 The effectiveness of self-supervised learning (SSL) for physiological time series depends on the ability of a pretraining objective to preserve information about the underlying physiological state while filtering out unrelated noise. However, existing strategies are limited due to reliance on heuristic principles or poorly constrained generative tasks. To address this limitation, we propose a pretraining framework that exploits the information structure of a dynamical systems generative model across multiple time-series. This framework reveals our key insight that class identity can be efficiently captured by extracting information about the generative variables related to the system parameters shared across similar time series samples, while noise unique to individual samples should be discarded. Building on this insight, we propose PULSE, a cross-reconstruction-based pretraining objective for physiological time series datasets that explicitly extracts system information while discarding non-transferrable sample-specific ones. We establish theory that provides sufficient conditions for the system information to be recovered, and empirically validate it using a synthetic dynamical systems experiment. Furthermore, we apply our method to diverse real-world datasets, demonstrating that PULSE learns representations that can broadly distinguish semantic classes, increase label efficiency, and improve transfer learning. --- ### OmniFusion: Simultaneous Multilingual Multimodal Translations via Modular Fusion Authors: Sai Koneru, Matthias Huck, Jan Niehues Published: 2025-11-28 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.00234v3 There has been significant progress in open-source text-only translation large language models (LLMs) with better language coverage and quality. However, these models can be only used in cascaded pipelines for speech translation (ST), performing automatic speech recognition first followed by translation. This introduces additional latency, which is particularly critical in simultaneous ST (SimulST), and prevents the model from exploiting multimodal context, such as images, which can aid disambiguation. Pretrained multimodal foundation models (MMFMs) already possess strong perception and reasoning capabilities across multiple modalities, but generally lack the multilingual coverage and specialized translation performance of dedicated translation LLMs. To build an effective multimodal translation system, we propose an end-to-end approach that fuses MMFMs with translation LLMs. We introduce a novel fusion strategy that connects hidden states from multiple layers of a pretrained MMFM to a translation LLM, enabling joint end-to-end training. The resulting model, OmniFusion, built on Omni 2.5-7B as the MMFM and SeedX PPO-7B as the translation LLM, can perform speech-to-text, speech-and-image-to-text, and text-and-image-to-text translation. Experiments demonstrate that OmniFusion effectively leverages both audio and visual inputs, achieves a 1-second latency reduction in SimulST compared to cascaded pipelines and also improves the overall translation quality\footnote{Code is available at https://github.com/saikoneru/OmniFusion}. --- ### CodeFlowLM: Incremental Just-In-Time Defect Prediction with Pretrained Language Models and Exploratory Insights into Defect Localization Authors: Monique Louise Monteiro, George G. Cabral, Adriano L. I. OLiveira Published: 2025-11-28 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2512.00231v1 This work introduces CodeFlowLM, an incremental learning framework for Just-In-Time Software Defect Prediction (JIT-SDP) that leverages pre-trained language models (PLMs). Unlike traditional online learners, CodeFlowLM employs continual fine-tuning to address concept drift, class imbalance, and verification latency without retraining from scratch. We evaluated encoder-only and encoder-decoder PLMs (notably CodeT5+ and UniXCoder) in JIT-SDP scenarios within and between projects, comparing them with the incremental baseline BORB. The results show that CodeFlowLM achieves up to 68% G-Mean gains, confirming its superior adaptability and robustness in evolving software environments. We further extend the analysis to Just-in-Time Defect Localization (JIT-DL), benchmarking Large Language Models (LLMs) such as GPT-5, Claude Sonnet 4.5, and Gemini 2.5 Pro against attention-based models. GPT-5 delivers comparable performance for Recall@20% and Effort@20% with higher stability, although attention-based methods retain an advantage in fine-grained ranking metrics (Top-k, IFA). A qualitative error analysis reveals that most false positives arise from (1) human-like conservative bias, (2) insufficient contextual information in diff-based prompts, and (3) potential dataset mislabeling in JIT-Defects4J. These findings highlight both the promise and the current limitations of LLM reasoning in defect localization. False negatives occur in smaller proportions. Overall, CodeFlowLM significantly advances the state of the art in incremental JIT-SDP, demonstrating superior adaptability and robustness in evolving software environments. Furthermore, our exploratory analysis of LLMs in JIT-DL not only benchmarks their performance against established attention-based models but also provides critical insights into the current limitations of prompt-based defect reasoning. --- ### TIE: A Training-Inversion-Exclusion Framework for Visually Interpretable and Uncertainty-Guided Out-of-Distribution Detection Authors: Pirzada Suhail, Rehna Afroz, Amit Sethi Published: 2025-11-28 Categories: cs.LG, cs.CV, eess.IV, stat.ML arXiv: https://arxiv.org/abs/2512.00229v1 Deep neural networks often struggle to recognize when an input lies outside their training experience, leading to unreliable and overconfident predictions. Building dependable machine learning systems therefore requires methods that can both estimate predictive \textit{uncertainty} and detect \textit{out-of-distribution (OOD)} samples in a unified manner. In this paper, we propose \textbf{TIE: a Training--Inversion--Exclusion} framework for visually interpretable and uncertainty-guided anomaly detection that jointly addresses these challenges through iterative refinement. TIE extends a standard $n$-class classifier to an $(n+1)$-class model by introducing a garbage class initialized with Gaussian noise to represent outlier inputs. Within each epoch, TIE performs a closed-loop process of \textit{training, inversion, and exclusion}, where highly uncertain inverted samples reconstructed from the just-trained classifier are excluded into the garbage class. Over successive iterations, the inverted samples transition from noisy artifacts into visually coherent class prototypes, providing transparent insight into how the model organizes its learned manifolds. During inference, TIE rejects OOD inputs by either directly mapping them to the garbage class or producing low-confidence, uncertain misclassifications within the in-distribution classes that are easily separable, all without relying on external OOD datasets. A comprehensive threshold-based evaluation using multiple OOD metrics and performance measures such as \textit{AUROC}, \textit{AUPR}, and \textit{FPR@95\%TPR} demonstrates that TIE offers a unified and interpretable framework for robust anomaly detection and calibrated uncertainty estimation (UE) achieving near-perfect OOD detection with \textbf{\(\!\approx\!\) 0 FPR@95\%TPR} when trained on MNIST or FashionMNIST and tested against diverse unseen datasets. --- ### DenseScan: Advancing 3D Scene Understanding with 2D Dense Annotation Authors: Zirui Wang, Tao Zhang Published: 2025-11-28 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.00226v1 3D understanding is a key capability for real-world AI assistance. High-quality data plays an important role in driving the development of the 3D understanding community. Current 3D scene understanding datasets often provide geometric and instance-level information, yet they lack the rich semantic annotations necessary for nuanced visual-language tasks.In this work, we introduce DenseScan, a novel dataset with detailed multi-level descriptions generated by an automated pipeline leveraging multi-view 2D images and multimodal large language models (MLLMs). Our approach enables dense captioning of scene elements, ensuring comprehensive object-level descriptions that capture context-sensitive details. Furthermore, we extend these annotations through scenario-based question generation, producing high-level queries that integrate object properties, spatial relationships, and scene context. By coupling geometric detail with semantic richness, DenseScan broadens the range of downstream tasks, from detailed visual-language navigation to interactive question answering. Experimental results demonstrate that our method significantly enhances object-level understanding and question-answering performance in 3D environments compared to traditional annotation pipelines. We release both the annotated dataset and our annotation pipeline to facilitate future research and applications in robotics, augmented reality, and beyond. Through DenseScan, we aim to catalyze new avenues in 3D scene understanding, allowing researchers and practitioners to tackle the complexities of real-world environments with richer, more contextually aware annotations. --- ### Statistical Inference under Adaptive Sampling with LinUCB Authors: Wei Fan, Kevin Tan, Yuting Wei Published: 2025-11-28 Categories: math.ST, cs.LG, stat.ME, stat.ML arXiv: https://arxiv.org/abs/2512.00222v1 Adaptively collected data has become ubiquitous within modern practice. However, even seemingly benign adaptive sampling schemes can introduce severe biases, rendering traditional statistical inference tools inapplicable. This can be mitigated by a property called stability, which states that if the rate at which an algorithm takes actions converges to a deterministic limit, one can expect that certain parameters are asymptotically normal. Building on a recent line of work for the multi-armed bandit setting, we show that the linear upper confidence bound (LinUCB) algorithm for linear bandits satisfies this property. In doing so, we painstakingly characterize the behavior of the eigenvalues and eigenvectors of the random design feature covariance matrix in the setting where the action set is the unit ball, showing that it decomposes into a rank-one direction that locks onto the true parameter and an almost-isotropic bulk that grows at a predictable $\sqrt{T}$ rate. This allows us to establish a central limit theorem for the LinUCB algorithm, establishing asymptotic normality for the limiting distribution of the estimation error where the convergence occurs at a $T^{-1/4}$ rate. The resulting Wald-type confidence sets and hypothesis tests do not depend on the feature covariance matrix and are asymptotically tighter than existing nonasymptotic confidence sets. Numerical simulations corroborate our findings. --- ### Minimal-Edit Instruction Tuning for Low-Resource Indic GEC Authors: Akhil Rajeev P Published: 2025-11-28 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.00219v1 Grammatical error correction for Indic languages faces limited supervision, diverse scripts, and rich morphology. We propose an augmentation-free setup that uses instruction-tuned large language models and conservative decoding. A 12B GEMMA 3 model is instruction-tuned in bnb 4-bit precision with parameter-efficient fine-tuning (PEFT) and Alpaca-style formatting. Decoding follows a deterministic, constraint-aware procedure with a lightweight normaliser that encourages minimal, meaning-preserving edits. We operationalise inference, subsequent to instruction fine-tuning (IFT), via a fixed, language-specific prompt directly synthesised from a deterministic error classifier's taxonomy, label distributions, and precedence ordering computed on the training corpus. Under the official untuned GLEU evaluation, the system scores 92.41 on Malayalam, sixth overall, and 81.44 on Hindi, third overall. These results indicate that classifier-informed prompt design, adapter-based instruction tuning, and deterministic decoding provide a reproducible and a computationally efficient alternative to augmentation-centred pipelines for Indic GEC. The approach also motivates future work on stronger morphosyntactic constraints and human-centred evaluation of conservative edits. --- ### Reasoning Under Pressure: How do Training Incentives Influence Chain-of-Thought Monitorability? Authors: Matt MacDermott, Qiyao Wei, Rada Djoneva, Francis Rhys Ward Published: 2025-11-28 Categories: cs.AI, cs.CR arXiv: https://arxiv.org/abs/2512.00218v2 AI systems that output their reasoning in natural language offer an opportunity for safety -- we can \emph{monitor} their chain of thought (CoT) for undesirable reasoning, such as the pursuit of harmful objectives. However, the extent to which CoT faithfully reflects the underlying reasoning process, and hence the extent to which it can be usefully monitored, may be influenced by certain aspects of training. We investigate how different \emph{training incentives}, applied to a reasoning model, affect its monitorability. We introduce a novel methodology for measuring monitorability according to whether a monitor can predict a key latent variable using the model's reasoning. When controlling for accuracy, we do not find evidence for consistent effects from commonly used incentives (length penalties and KL regularisation), but we find that adversarial optimisation (penalising monitor accuracy) degrades monitor performance, while direct optimisation for monitorability does not reliably lead to improvements. Our code is available at https://github.com/QiyaoWei/reasoning-under-pressure. --- ### Towards Corpus-Grounded Agentic LLMs for Multilingual Grammatical Analysis Authors: Matej Klemen, Tjaša Arčon, Luka Terčon, Marko Robnik-Šikonja, Kaja Dobrovoljc Published: 2025-11-28 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.00214v1 Empirical grammar research has become increasingly data-driven, but the systematic analysis of annotated corpora still requires substantial methodological and technical effort. We explore how agentic large language models (LLMs) can streamline this process by reasoning over annotated corpora and producing interpretable, data-grounded answers to linguistic questions. We introduce an agentic framework for corpus-grounded grammatical analysis that integrates concepts such as natural-language task interpretation, code generation, and data-driven reasoning. As a proof of concept, we apply it to Universal Dependencies (UD) corpora, testing it on multilingual grammatical tasks inspired by the World Atlas of Language Structures (WALS). The evaluation spans 13 word-order features and over 170 languages, assessing system performance across three complementary dimensions - dominant-order accuracy, order-coverage completeness, and distributional fidelity - which reflect how well the system generalizes, identifies, and quantifies word-order variations. The results demonstrate the feasibility of combining LLM reasoning with structured linguistic data, offering a first step toward interpretable, scalable automation of corpus-based grammatical inquiry. --- ### On the Prediction of Wi-Fi Performance through Deep Learning Authors: Gabriele Formis, Amanda Ericson, Stefan Forsstrom, Kyi Thar, Gianluca Cena, Stefano Scanzio Published: 2025-11-28 Categories: cs.NI, cs.AI arXiv: https://arxiv.org/abs/2512.00211v1 Ensuring reliable and predictable communications is one of the main goals in modern industrial systems that rely on Wi-Fi networks, especially in scenarios where continuity of operation and low latency are required. In these contexts, the ability to predict changes in wireless channel quality can enable adaptive strategies and significantly improve system robustness. This contribution focuses on the prediction of the Frame Delivery Ratio (FDR), a key metric that represents the percentage of successful transmissions, starting from time sequences of binary outcomes (success/failure) collected in a real scenario. The analysis focuses on two models of deep learning: a Convolutional Neural Network (CNN) and a Long Short-Term Memory network (LSTM), both selected for their ability to predict the outcome of time sequences. Models are compared in terms of prediction accuracy and computational complexity, with the aim of evaluating their applicability to systems with limited resources. Preliminary results show that both models are able to predict the evolution of the FDR with good accuracy, even from minimal information (a single binary sequence). In particular, CNN shows a significantly lower inference latency, with a marginal loss in accuracy compared to LSTM. --- ### ReactionMamba: Generating Short & Long Human Reaction Sequences Authors: Hajra Anwar Beg, Baptiste Chopin, Hao Tang, Mohamed Daoudi Published: 2025-11-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.00208v2 We present ReactionMamba, a novel framework for generating long 3D human reaction motions. Reaction-Mamba integrates a motion VAE for efficient motion encoding with Mamba-based state-space models to decode temporally consistent reactions. This design enables ReactionMamba to generate both short sequences of simple motions and long sequences of complex motions, such as dance and martial arts. We evaluate ReactionMamba on three datasets--NTU120-AS, Lindy Hop, and InterX--and demonstrate competitive performance in terms of realism, diversity, and long-sequence generation compared to previous methods, including InterFormer, ReMoS, and Ready-to-React, while achieving substantial improvements in inference speed. --- ### Constructing Efficient Fact-Storing MLPs for Transformers Authors: Owen Dugan, Roberto Garcia, Ronny Junkins, Jerry Liu, Dylan Zinsley, Sabri Eyuboglu, Atri Rudra, Chris Ré Published: 2025-11-28 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.00207v1 The success of large language models (LLMs) can be attributed in part to their ability to efficiently store factual knowledge as key-value mappings within their MLP parameters. Recent work has proposed explicit weight constructions to build such fact-storing MLPs, providing an improved understanding of LLM fact storage mechanisms. In this paper, we introduce an MLP construction framework that improves over previous constructions in three areas: it 1) works for all but a measure-zero set of feasible input-output pairs, 2) achieves asymptotically optimal parameter efficiency matching information-theoretic bounds for some embeddings, and 3) maintains usability within Transformers for factual recall. Through our improvements, we 1) discover a metric on value embeddings that characterizes facts-per-parameter scaling for both constructed and gradient-descent-trained MLPs, 2) identify a simple encoder-decoder mechanism that empirically matches gradient-descent MLP facts-per-parameter asymptotics across all the inputs and outputs we test, and 3) uncover a fundamental tradeoff between an MLP's fact-storage capacity and its usability within Transformers. Finally, we demonstrate a proof-of-concept application of fact-storing MLPs: modular fact editing on one-layer Transformers by \textit{replacing entire MLPs at once}. ---