# Research Papers — 2025-12 · bundle page 74 of 175 > Full-text markdown of papers #3651–3700 of 8703 published in 2025-12, newest first. AI-readable mirrors of the full 8703-paper 2025-12 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2025-12/page/74 [← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/73.md) [Next bundle →](https://aipod.dev/papers/archive/2025-12/page/75.md) ### Internal Reasoning vs. External Control: A Thermodynamic Analysis of Sycophancy in Large Language Models Authors: Edward Y. Chang Published: 2025-12-16 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.03263v2 Large Language Models exhibit sycophancy: prioritizing agreeableness over correctness. Current remedies evaluate reasoning outcomes: RLHF rewards correct answers, self-correction critiques outputs. All require ground truth, which is often unavailable at inference time and vulnerable to the same biases. We explore evaluating the reasoning process instead. Regulated Causal Anchoring (RCA) verifies whether outputs follow from their reasoning traces, without requiring ground truth. Sycophancy manifests as trace-output inconsistency: models derive one answer but output another to please users. RCA detects this inconsistency, achieving 0.0% sycophancy while accepting 88% of valid hints. We identify two failures invisible to outcome evaluation: Inverse Scaling (frontier models sycophant more because rationalization requires capability) and the Final Output Gap (correct reasoning precedes sycophantic output). Traditional self-correction reduces these failures to 7-9% but cannot eliminate them because the model critiques itself with the same biases. RCA's process evaluation operates at inference time, requires no ground truth, and uses an independent judge that breaks the self-reinforcing bias loop: three properties that outcome evaluation lacks. --- ### Roles of MLLMs in Visually Rich Document Retrieval for RAG: A Survey Authors: Xiantao Zhang Published: 2025-12-16 Categories: cs.IR, cs.CL arXiv: https://arxiv.org/abs/2601.03262v1 Visually rich documents (VRDs) challenge retrieval-augmented generation (RAG) with layout-dependent semantics, brittle OCR, and evidence spread across complex figures and structured tables. This survey examines how Multimodal Large Language Models (MLLMs) are being used to make VRD retrieval practical for RAG. We organize the literature into three roles: Modality-Unifying Captioners, Multimodal Embedders, and End-to-End Representers. We compare these roles along retrieval granularity, information fidelity, latency and index size, and compatibility with reranking and grounding. We also outline key trade-offs and offer some practical guidance on when to favor each role. Finally, we identify promising directions for future research, including adaptive retrieval units, model size reduction, and the development of evaluation methods. --- ### DeepResearch-Slice: Bridging the Retrieval-Utilization Gap via Explicit Text Slicing Authors: Shuo Lu, Yinuo Xu, Jianjie Cheng, Lingxiao He, Meng Wang, Jian Liang Published: 2025-12-16 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.03261v1 Deep Research agents predominantly optimize search policies to maximize retrieval probability. However, we identify a critical bottleneck: the retrieval-utilization gap, where models fail to use gold evidence even after it is retrieved, due to context blindness in noisy environments. To bridge this gap, we propose DeepResearch-Slice, a simple yet effective neuro-symbolic framework. Unlike implicit attention, our approach predicts precise span indices to perform a deterministic hard filter before reasoning. Extensive evaluations across six benchmarks show substantial robustness gains. Applying our method to frozen backbones yields a 73 percent relative improvement, from 19.1 percent to 33.0 percent, effectively mitigating noise without requiring parameter updates to the reasoning model. These results highlight the need for explicit grounding mechanisms in open-ended research. --- ### SciNet: Evaluating AI Agents in Relation-Aware Scientific Literature Retrieval Authors: Chenyang Shao, Fengli Xu, Yong Li Published: 2025-12-16 Categories: cs.CE, cs.CL arXiv: https://arxiv.org/abs/2601.03260v2 AI agents have seen widespread adoption in information retrieval for scientific research, giving rise to tools such as Deep Research. However, existing retrieval agents mainly rely on keyword- or embedding-based methods. While effective at capturing content-level similarities, they struggle to understand complex relational networks among scientific papers, such as identifying corroborating or conflicting studies and tracing technological lineages. This fundamental limitation often results in fragmented knowledge structures, misinterpreted research sentiment, and ineffective modeling of collective scientific progress. To address this limitation, we introduce SciNet, the first Scientific Network relation-aware dataset for information retrieval agents. Built on a meta-database of 269 million papers across 7 disciplines and containing 8,940 carefully designed tasks, SciNet systematically captures three levels of relational understanding: ego-centric retrieval of papers with novel knowledge structures, pairwise identification of scholarly relationships, and path-wise reconstruction of scientific evolution. Extensive evaluation of three categories of retrieval agents shows that their accuracy on relation-aware tasks often falls below 20%, highlighting a fundamental shortcoming of current retrieval paradigms. Importantly, in a downstream literature review application, agents empowered with SciNet achieve a 25.3% improvement in review quality, highlighting the critical value of relation-aware retrieval for deepening scientific insights. We publicly release SciNet at https://github.com/tsinghua-fib-lab/SciNet to support future research. --- ### A Survey of AI Methods for Geometry Preparation and Mesh Generation in Engineering Simulation Authors: Steven Owen, Nathan Brown, Nikos Chrisochoides, Rao Garimella, Xianfeng Gu, Franck Ledoux, Na Lei, Roshan Quadros, Navamita Ray, Nicolas Winovich, Yongjie Jessica Zhang Published: 2025-12-16 Categories: cs.CE, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.23719v2 Artificial intelligence is beginning to reduce the manual effort in the CAD-to-mesh pipeline. Written for meshing and geometry practitioners with limited AI background, this survey organizes recent work by workflow step. We cover part classification and segmentation, mesh quality prediction, and defeaturing. We review AI guidance for unstructured meshing, block-structured meshing in 2D and 3D, and volumetric parameterization, including reconstruction from implicit or sampled geometry. We also discuss parallel mesh generation and scripting automation via reinforcement learning and large language models. Across these topics, AI complements established geometry and meshing algorithms rather than replacing them. We conclude with practical lessons and open challenges in data, benchmarks, and trustworthy integration. --- ### Mixture of Attention Schemes (MoAS): Learning to Route Between MHA, GQA, and MQA Authors: Esmail Gumaan Published: 2025-12-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.20650v1 The choice of attention mechanism in Transformer models involves a critical trade-off between modeling quality and inference efficiency. Multi-Head Attention (MHA) offers the best quality but suffers from large Key-Value (KV) cache memory requirements during inference. Multi-Query Attention (MQA) and Grouped-Query Attention (GQA) reduce memory usage but often at the cost of model performance. In this work, we propose Mixture of Attention Schemes (MoAS), a novel architecture that dynamically selects the optimal attention scheme (MHA, GQA, or MQA) for each token via a learned router. We demonstrate that dynamic routing performs better than static averaging of schemes and achieves performance competitive with the MHA baseline while offering potential for conditional compute efficiency. Experimental results on WikiText-2 show that dynamic routing (val loss 2.3074) outperforms a static mixture (2.3093), validating the effectiveness of the proposed method. Our code is available at https://github.com/Esmail-ibraheem/Mixture-of-Attention-Schemes-MoAS. --- ### AIAuditTrack: A Framework for AI Security system Authors: Zixun Luo, Yuhang Fan, Yufei Li, Youzhi Zhang, Hengyu Lin, Ziqi Wang Published: 2025-12-16 Categories: cs.AI, cs.CR arXiv: https://arxiv.org/abs/2512.20649v1 The rapid expansion of AI-driven applications powered by large language models has led to a surge in AI interaction data, raising urgent challenges in security, accountability, and risk traceability. This paper presents AiAuditTrack (AAT), a blockchain-based framework for AI usage traffic recording and governance. AAT leverages decentralized identity (DID) and verifiable credentials (VC) to establish trusted and identifiable AI entities, and records inter-entity interaction trajectories on-chain to enable cross-system supervision and auditing. AI entities are modeled as nodes in a dynamic interaction graph, where edges represent time-specific behavioral trajectories. Based on this model, a risk diffusion algorithm is proposed to trace the origin of risky behaviors and propagate early warnings across involved entities. System performance is evaluated using blockchain Transactions Per Second (TPS) metrics, demonstrating the feasibility and stability of AAT under large-scale interaction recording. AAT provides a scalable and verifiable solution for AI auditing, risk management, and responsibility attribution in complex multi-agent environments. --- ### Reasoning Relay: Evaluating Stability and Interchangeability of Large Language Models in Mathematical Reasoning Authors: Leo Lu, Jonathan Zhang, Sean Chua, Spencer Kim, Kevin Zhu, Sean O'Brien, Vasu Sharma Published: 2025-12-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.20647v1 Chain-of-Thought (CoT) prompting has significantly advanced the reasoning capabilities of large language models (LLMs). While prior work focuses on improving model performance through internal reasoning strategies, little is known about the interchangeability of reasoning across different models. In this work, we explore whether a partially completed reasoning chain from one model can be reliably continued by another model, either within the same model family or across families. We achieve this by assessing the sufficiency of intermediate reasoning traces as transferable scaffolds for logical coherence and final answer accuracy. We interpret this interchangeability as a means of examining inference-time trustworthiness, probing whether reasoning remains both coherent and reliable under model substitution. Using token-level log-probability thresholds to truncate reasoning at early, mid, and late stages from our baseline models, Gemma-3-4B-IT and LLaMA-3.1-70B-Instruct, we conduct continuation experiments with Gemma-3-1B-IT and LLaMA-3.1-8B-Instruct to test intra-family and cross-family behaviors. Our evaluation pipeline leverages truncation thresholds with a Process Reward Model (PRM), providing a reproducible framework for assessing reasoning stability via model interchange. Evaluations with a PRM reveal that hybrid reasoning chains often preserve, and in some cases even improve, final accuracy and logical structure. Our findings point towards interchangeability as an emerging behavioral property of reasoning models, offering insights into new paradigms for reliable modular reasoning in collaborative AI systems. --- ### Out-of-Distribution Detection for Continual Learning: Design Principles and Benchmarking Authors: Srishti Gupta, Riccardo Balia, Daniele Angioni, Fabio Brau, Maura Pintor, Ambra Demontis, Alessandro Sebastian, Salvatore Mario Carta, Fabio Roli, Battista Biggio Published: 2025-12-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.19725v1 Recent years have witnessed significant progress in the development of machine learning models across a wide range of fields, fueled by increased computational resources, large-scale datasets, and the rise of deep learning architectures. From malware detection to enabling autonomous navigation, modern machine learning systems have demonstrated remarkable capabilities. However, as these models are deployed in ever-changing real-world scenarios, their ability to remain reliable and adaptive over time becomes increasingly important. For example, in the real world, new malware families are continuously developed, whereas autonomous driving cars are employed in many different cities and weather conditions. Models trained in fixed settings can not respond effectively to novel conditions encountered post-deployment. In fact, most machine learning models are still developed under the assumption that training and test data are independent and identically distributed (i.i.d.), i.e., sampled from the same underlying (unknown) distribution. While this assumption simplifies model development and evaluation, it does not hold in many real-world applications, where data changes over time and unexpected inputs frequently occur. Retraining models from scratch whenever new data appears is computationally expensive, time-consuming, and impractical in resource-constrained environments. These limitations underscore the need for Continual Learning (CL), which enables models to incrementally learn from evolving data streams without forgetting past knowledge, and Out-of-Distribution (OOD) detection, which allows systems to identify and respond to novel or anomalous inputs. Jointly addressing both challenges is critical to developing robust, efficient, and adaptive AI systems. --- ### End-to-End Data Quality-Driven Framework for Machine Learning in Production Environment Authors: Firas Bayram, Bestoun S. Ahmed, Erik Hallin Published: 2025-12-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.19723v1 This paper introduces a novel end-to-end framework that efficiently integrates data quality assessment with machine learning (ML) model operations in real-time production environments. While existing approaches treat data quality assessment and ML systems as isolated processes, our framework addresses the critical gap between theoretical methods and practical implementation by combining dynamic drift detection, adaptive data quality metrics, and MLOps into a cohesive, lightweight system. The key innovation lies in its operational efficiency, enabling real-time, quality-driven ML decision-making with minimal computational overhead. We validate the framework in a steel manufacturing company's Electroslag Remelting (ESR) vacuum pumping process, demonstrating a 12% improvement in model performance (R2 = 94%) and a fourfold reduction in prediction latency. By exploring the impact of data quality acceptability thresholds, we provide actionable insights into balancing data quality standards and predictive performance in industrial applications. This framework represents a significant advancement in MLOps, offering a robust solution for time-sensitive, data-driven decision-making in dynamic industrial environments. --- ### Node-Level Financial Optimization in Demand Forecasting Through Dynamic Cost Asymmetry and Feedback Mechanism Authors: Alessandro Casadei, Clemens Grupp, Sreyoshi Bhaduri, Lu Guo, Wilson Fung, Rohit Malshe, Raj Ratan, Ankush Pole, Arkajit Rakshit Published: 2025-12-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.19722v1 This work introduces a methodology to adjust forecasts based on node-specific cost function asymmetry. The proposed model generates savings by dynamically incorporating the cost asymmetry into the forecasting error probability distribution to favor the least expensive scenario. Savings are calculated and a self-regulation mechanism modulates the adjustments magnitude based on the observed savings, enabling the model to adapt to station-specific conditions and unmodeled factors such as calibration errors or shifting macroeconomic dynamics. Finally, empirical results demonstrate the model's ability to achieve \$5.1M annual savings. --- ### Sign-Aware Multistate Jaccard Kernels and Geometry for Real and Complex-Valued Signals Authors: Vineet Yadav Published: 2025-12-16 Categories: cs.LG, cs.IT arXiv: https://arxiv.org/abs/2512.19721v1 We introduce a sign-aware, multistate Jaccard/Tanimoto framework that extends overlap-based distances from nonnegative vectors and measures to arbitrary real- and complex-valued signals while retaining bounded metric and positive-semidefinite kernel structure. Formally, the construction is a set- and measure-theoretic geometry: signals are represented as atomic measures on a signed state space, and similarity is given by a generalized Jaccard overlap of these measures. Each signal is embedded into a nonnegative multistate representation, using positive/negative splits for real signals, Cartesian and polar decompositions for complex signals, and user-defined state partitions for refined regime analysis. Applying the Tanimoto construction to these embeddings yields a family of $(0,1)$ distances that satisfy the triangle inequality and define positive-semidefinite kernels usable directly in kernel methods and graph-based learning. Beyond pairwise distances, we develop coalition analysis via Möbius inversion, which decomposes signal magnitude into nonnegative, additive contributions with exact budget closure across coalitions of signals. Normalizing the same embeddings produces probability measures on coordinate -- state configurations, so that the distance becomes a monotone transform of total variation and admits a regime -- intensity decomposition. The resulting construction yields a single, mechanistically interpretable distance that simultaneously provides bounded metric structure, positive-semidefinite kernels, probabilistic semantics, and transparent budget accounting within one sign-aware framework, supporting correlograms, feature engineering, similarity graphs, and other analytical tools in scientific and financial applications. --- ### Per-Axis Weight Deltas for Frequent Model Updates Authors: Stefan Kuyumdzhiev, Radostin Cholakov Published: 2025-12-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.19720v1 Serving many task-specialized LLM variants is often limited by the large size of fine-tuned checkpoints and the resulting cold-start latency. Since fine-tuned weights differ from their base model by relatively small structured residuals, a natural approach is to represent them as compressed deltas. We propose a simple 1-bit delta scheme that stores only the sign of the weight difference together with lightweight per-axis (row/column) FP16 scaling factors, learned from a small calibration set. This design preserves the compactness of 1-bit deltas while more accurately capturing variation across weight dimensions, leading to improved reconstruction quality over scalar alternatives. From a systems perspective, a streamlined loader that transfers packed deltas in a single operation per module reduces cold-start latency and storage overhead, with artifacts several times smaller than a full FP16 checkpoint. The method is drop-in, requires minimal calibration data, and maintains inference efficiency by avoiding dense reconstruction. Our experimental setup and source code are available at https://github.com/kuiumdjiev/Per-Axis-Weight-Deltas-for-Frequent-Model-Updates. --- ### Multiscale Dual-path Feature Aggregation Network for Remaining Useful Life Prediction of Lithium-Ion Batteries Authors: Zihao Lv, Siqi Ai, Yanbin Zhang Published: 2025-12-16 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.19719v1 Targeted maintenance strategies, ensuring the dependability and safety of industrial machinery. However, current modeling techniques for assessing both local and global correlation of battery degradation sequences are inefficient and difficult to meet the needs in real-life applications. For this reason, we propose a novel deep learning architecture, multiscale dual-path feature aggregation network (MDFA-Net), for RUL prediction. MDFA-Net consists of dual-path networks, the first path network, multiscale feature network (MF-Net) that maintains the shallow information and avoids missing information, and the second path network is an encoder network (EC-Net) that captures the continuous trend of the sequences and retains deep details. Integrating both deep and shallow attributes effectively grasps both local and global patterns. Testing conducted with two publicly available Lithium-ion battery datasets reveals our approach surpasses existing top-tier methods in RUL forecasting, accurately mapping the capacity degradation trajectory. --- ### Synthetic Data Blueprint (SDB): A modular framework for the statistical, structural, and graph-based evaluation of synthetic tabular data Authors: Vasileios C. Pezoulas, Nikolaos S. Tachos, Eleni Georga, Kostas Marias, Manolis Tsiknakis, Dimitrios I. Fotiadis Published: 2025-12-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.19718v1 In the rapidly evolving era of Artificial Intelligence (AI), synthetic data are widely used to accelerate innovation while preserving privacy and enabling broader data accessibility. However, the evaluation of synthetic data remains fragmented across heterogeneous metrics, ad-hoc scripts, and incomplete reporting practices. To address this gap, we introduce Synthetic Data Blueprint (SDB), a modular Pythonic based library to quantitatively and visually assess the fidelity of synthetic tabular data. SDB supports: (i) automated feature-type detection, (ii) distributional and dependency-level fidelity metrics, (iii) graph- and embedding-based structure preservation scores, and (iv) a rich suite of data visualization schemas. To demonstrate the breadth, robustness, and domain-agnostic applicability of the SDB, we evaluated the framework across three real-world use cases that differ substantially in scale, feature composition, statistical complexity, and downstream analytical requirements. These include: (i) healthcare diagnostics, (ii) socioeconomic and financial modelling, and (iii) cybersecurity and network traffic analysis. These use cases reveal how SDB can address diverse data fidelity assessment challenges, varying from mixed-type clinical variables to high-cardinality categorical attributes and high-dimensional telemetry signals, while at the same time offering a consistent, transparent, and reproducible benchmarking across heterogeneous domains. --- ### Thermodynamic Focusing for Inference-Time Search: Practical Methods for Target-Conditioned Sampling and Prompted Inference Authors: Zhan Zhang Published: 2025-12-16 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.19717v1 Finding rare but useful solutions in very large candidate spaces is a recurring practical challenge across language generation, planning, and reinforcement learning. We present a practical framework, \emph{Inverted Causality Focusing Algorithm} (ICFA), that treats search as a target-conditioned reweighting process. ICFA reuses an available proposal sampler and a task-specific similarity function to form a focused sampling distribution, while adaptively controlling focusing strength to avoid degeneracy. We provide a clear recipe, a stability diagnostic based on effective sample size, a compact theoretical sketch explaining when ICFA can reduce sample needs, and two reproducible experiments: constrained language generation and sparse-reward navigation. We further show how structured prompts instantiate an approximate, language-level form of ICFA and describe a hybrid architecture combining prompted inference with algorithmic reweighting. --- ### An empirical analysis of zero-day vulnerabilities disclosed by the zero day initiative Authors: Apurva Shet, Izzat Alsmadi Published: 2025-12-16 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2512.15803v1 Zero-day vulnerabilities represent some of the most critical threats in cybersecurity, as they correspond to previously unknown flaws in software or hardware that are actively exploited before vendors can develop and deploy patches. During this exposure window, affected systems remain defenseless, making zero-day attacks particularly damaging and difficult to mitigate. This study analyzes the Zero Day Initiative (ZDI) vulnerability disclosures reported between January and April 2024, Cole (2025) comprising a total of 415 vulnerabilities. The dataset includes vulnerability identifiers, Common Vulnerability Scoring System (CVSS) v3.0 scores, publication dates, and short textual descriptions. The primary objectives of this work are to identify trends in zero-day vulnerability disclosures, examine severity distributions across vendors, and investigate which vulnerability characteristics are most indicative of high severity. In addition, this study explores predictive modeling approaches for severity classification, comparing classical machine learning techniques with deep learning models using both structured metadata and unstructured textual descriptions. The findings aim to support improved patch prioritization strategies, more effective vulnerability management, and enhanced organizational preparedness against emerging zero-day threats. --- ### Consensus dimension reduction via multi-view learning Authors: Bingxue An, Tiffany M. Tang Published: 2025-12-16 Categories: stat.ME, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2512.15802v1 A plethora of dimension reduction methods have been developed to visualize high-dimensional data in low dimensions. However, different dimension reduction methods often output different and possibly conflicting visualizations of the same data. This problem is further exacerbated by the choice of hyperparameters, which may substantially impact the resulting visualization. To obtain a more robust and trustworthy dimension reduction output, we advocate for a consensus approach, which summarizes multiple visualizations into a single consensus dimension reduction visualization. Here, we leverage ideas from multi-view learning in order to identify the patterns that are most stable or shared across the many different dimension reduction visualizations, or views, and subsequently visualize this shared structure in a single low-dimensional plot. We demonstrate that this consensus visualization effectively identifies and preserves the shared low-dimensional data structure through both simulated and real-world case studies. We further highlight our method's robustness to the choice of dimension reduction method and hyperparameters -- a highly-desirable property when working towards trustworthy and reproducible data science. --- ### Edge-wise Topological Divergence Gaps: Guiding Search in Combinatorial Optimization Authors: Ilya Trofimov, Daria Voronkova, Alexander Mironenko, Anton Dmitriev, Eduard Tulchinskii, Evgeny Burnaev, Serguei Barannikov Published: 2025-12-16 Categories: cs.CG, cs.AI arXiv: https://arxiv.org/abs/2512.15800v1 We introduce a topological feedback mechanism for the Travelling Salesman Problem (TSP) by analyzing the divergence between a tour and the minimum spanning tree (MST). Our key contribution is a canonical decomposition theorem that expresses the tour-MST gap as edge-wise topology-divergence gaps from the RTD-Lite barcode. Based on this, we develop a topological guidance for 2-opt and 3-opt heuristics that increases their performance. We carry out experiments with fine-optimization of tours obtained from heatmap-based methods, TSPLIB, and random instances. Experiments demonstrate the topology-guided optimization results in better performance and faster convergence in many cases. --- ### Cybercrime and Computer Forensics in Epoch of Artificial Intelligence in India Authors: Sahibpreet Singh, Shikha Dhiman Published: 2025-12-16 Categories: cs.CR, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2512.15799v1 The integration of generative Artificial Intelligence into the digital ecosystem necessitates a critical re-evaluation of Indian criminal jurisprudence regarding computational forensics integrity. While algorithmic efficiency enhances evidence extraction, a research gap exists regarding the Digital Personal Data Protection Act, 2023's compatibility with adversarial AI threats, specifically anti-forensics and deepfakes. This study scrutinizes the AI "dual-use" dilemma, functioning as both a cyber-threat vector and forensic automation mechanism, to delineate privacy boundaries in high-stakes investigations. Employing a doctrinal legal methodology, the research synthesizes statutory analysis of the DPDP Act with global ethical frameworks (IEEE, EU) to evaluate regulatory efficacy. Preliminary results indicate that while Machine Learning offers high accuracy in pattern recognition, it introduces vulnerabilities regarding data poisoning and algorithmic bias. Findings highlight a critical tension between the Act's data minimization principles and forensic data retention requirements. Furthermore, the paper identifies that existing legal definitions inadequately encompass AI-driven "tool crimes" and "target crimes." Consequently, the research proposes a "human-centric" forensic model prioritizing explainable AI (XAI) to ensure evidence admissibility. These implications suggest that synchronizing Indian privacy statutes with international forensic standards is imperative to mitigate synthetic media risks, establishing a roadmap for future legislative amendments and technical standardization. --- ### Bridging Business Intent and Data: A Benchmark for Automatic Relational Data Product Generation Authors: Faisal Chowdhury, Sola Shirai, Sarthak Dash, Nandana Mihindukulasooriya, Horst Samulowitz Published: 2025-12-16 Categories: cs.DB, cs.CL arXiv: https://arxiv.org/abs/2512.15798v2 A data product is designed to address a specific business need by transforming raw data into a curated, usable asset that delivers actionable insights. Despite practical advances in related areas like text-to-SQL and ELT pipelines, there is no comprehensive benchmark for evaluating the end-to-end process of automatically generating such data products from high-level business requests. To fill this gap, we introduce DP-Bench, a first-of-its-kind benchmark for automatic data product creation, built by combining elements from existing ELT and text-to-SQL datasets. We also propose baseline methods using LLMs to generate data products, providing a foundation for future research in bridging natural language business intent and structured data representation. We make the DP-Bench dataset and code available at: https://huggingface.co/datasets/ibm-research/dp-bench. --- ### Explainable Ethical Assessment on Human Behaviors by Generating Conflicting Social Norms Authors: Yuxi Sun, Wei Gao, Hongzhan Lin, Jing Ma, Wenxuan Zhang Published: 2025-12-16 Categories: cs.CY, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2512.15793v1 Human behaviors are often guided or constrained by social norms, which are defined as shared, commonsense rules. For example, underlying an action ``\textit{report a witnessed crime}" are social norms that inform our conduct, such as ``\textit{It is expected to be brave to report crimes}''. Current AI systems that assess valence (i.e., support or oppose) of human actions by leveraging large-scale data training not grounded on explicit norms may be difficult to explain, and thus untrustworthy. Emulating human assessors by considering social norms can help AI models better understand and predict valence. While multiple norms come into play, conflicting norms can create tension and directly influence human behavior. For example, when deciding whether to ``\textit{report a witnessed crime}'', one may balance \textit{bravery} against \textit{self-protection}. In this paper, we introduce \textit{ClarityEthic}, a novel ethical assessment approach, to enhance valence prediction and explanation by generating conflicting social norms behind human actions, which strengthens the moral reasoning capabilities of language models by using a contrastive learning strategy. Extensive experiments demonstrate that our method outperforms strong baseline approaches, and human evaluations confirm that the generated social norms provide plausible explanations for the assessment of human behaviors. --- ### A Multifaceted Analysis of Social Biases in Large Language Models Authors: Xulang Zhang, Rui Mao, Erik Cambria Published: 2025-12-16 Categories: cs.CY, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2512.15792v4 Large language models (LLMs) have rapidly become indispensable tools for acquiring information and supporting human decision-making. However, ensuring that these models uphold fairness across varied contexts is critical to their safe and responsible deployment. In this study, we undertake a comprehensive examination of four widely adopted LLMs, probing their underlying biases and inclinations across the dimensions of politics, ideology, alliance, language, and gender. Through a series of carefully designed experiments, we investigate their political neutrality using news summarization, ideological biases through news stance classification, tendencies toward specific geopolitical alliances via United Nations voting patterns, language bias in the context of multilingual story completion, and gender-related affinities as revealed by responses to the World Values Survey. Results indicate that while the LLMs are aligned to be neutral and impartial, they still show biases and affinities of different types. --- ### Evaluation of AI Ethics Tools in Language Models: A Developers' Perspective Case Study Authors: Jhessica Silva, Diego A. B. Moreira, Gabriel O. dos Santos, Alef Ferreira, Helena Maia, Sandra Avila, Helio Pedrini Published: 2025-12-16 Categories: cs.CY, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2512.15791v2 In Artificial Intelligence (AI), language models have gained significant importance due to the widespread adoption of systems capable of simulating realistic conversations with humans through text generation. Because of their impact on society, developing and deploying these language models must be done responsibly, with attention to their negative impacts and possible harms. In this scenario, the number of AI Ethics Tools (AIETs) publications has recently increased. These AIETs are designed to help developers, companies, governments, and other stakeholders establish trust, transparency, and responsibility with their technologies by bringing accepted values to guide AI's design, development, and use stages. However, many AIETs lack good documentation, examples of use, and proof of their effectiveness in practice. This paper presents a methodology for evaluating AIETs in language models. Our approach involved an extensive literature survey on 213 AIETs, and after applying inclusion and exclusion criteria, we selected four AIETs: Model Cards, ALTAI, FactSheets, and Harms Modeling. For evaluation, we applied AIETs to language models developed for the Portuguese language, conducting 35 hours of interviews with their developers. The evaluation considered the developers' perspective on the AIETs' use and quality in helping to identify ethical considerations about their model. The results suggest that the applied AIETs serve as a guide for formulating general ethical considerations about language models. However, we note that they do not address unique aspects of these models, such as idiomatic expressions. Additionally, these AIETs did not help to identify potential negative impacts of models for the Portuguese language. --- ### InpaintDPO: Mitigating Spatial Relationship Hallucinations in Foreground-conditioned Inpainting via Diverse Preference Optimization Authors: Qirui Li, Yizhe Tang, Ran Yi, Guangben Lu, Fangyuan Zou, Peng Shu, Huan Yu, Jie Jiang Published: 2025-12-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.15644v1 Foreground-conditioned inpainting, which aims at generating a harmonious background for a given foreground subject based on the text prompt, is an important subfield in controllable image generation. A common challenge in current methods, however, is the occurrence of Spatial Relationship Hallucinations between the foreground subject and the generated background, including inappropriate scale, positional relationships, and viewpoints. Critically, the subjective nature of spatial rationality makes it challenging to quantify, hindering the use of traditional reward-based RLHF methods. To address this issue, we propose InpaintDPO, the first Direct Preference Optimization (DPO) based framework dedicated to spatial rationality in foreground-conditioned inpainting, ensuring plausible spatial relationships between foreground and background elements. To resolve the gradient conflicts in standard DPO caused by identical foreground in win-lose pairs, we propose MaskDPO, which confines preference optimization exclusively to the background to enhance background spatial relationships, while retaining the inpainting loss in the foreground region for robust foreground preservation. To enhance coherence at the foreground-background boundary, we propose Conditional Asymmetric Preference Optimization, which samples pairs with differentiated cropping operations and applies global preference optimization to promote contextual awareness and enhance boundary coherence. Finally, based on the observation that winning samples share a commonality in plausible spatial relationships, we propose Shared Commonality Preference Optimization to enhance the model's understanding of spatial commonality across high-quality winning samples, further promoting shared spatial rationality. --- ### Deep Learning and Elicitability for McKean-Vlasov FBSDEs With Common Noise Authors: Felipe J. P. Antunes, Yuri F. Saporito, Sebastian Jaimungal Published: 2025-12-16 Categories: cs.LG, q-fin.CP, q-fin.MF arXiv: https://arxiv.org/abs/2512.14967v3 We present a novel numerical method for solving McKean-Vlasov forward-backward stochastic differential equations (MV--FBSDEs) with common noise, combining Picard iterations, elicitability and deep learning. The key innovation involves elicitability to derive a path-wise loss function, enabling efficient training of neural networks to approximate both the backward process and the conditional expectations arising from common noise -- without requiring computationally expensive nested Monte Carlo simulations. The mean-field interaction term is parameterized via a recurrent neural network trained to minimize an elicitable score, while the backward process is approximated through a hybrid feedforward and recurrent network representing the decoupling field. We validate the algorithm on a systemic risk inter-bank borrowing and lending model, where analytical solutions exist, demonstrating accurate recovery of the true solution. We further extend the model to quantile--mediated interactions, showcasing the flexibility of the elicitability framework beyond conditional means or moments. Finally, we apply the method to a non-stationary Aiyagari-Bewley-Huggett economic growth model with endogenous interest rates, illustrating its applicability to complex mean-field games without closed-form solutions. --- ### Adaptive Multimodal Person Recognition: A Robust Framework for Handling Missing Modalities Authors: Aref Farhadipour, Teodora Vukovic, Volker Dellwo, Petr Motlicek, Srikanth Madikeri Published: 2025-12-16 Categories: cs.CV, cs.SD, eess.AS, eess.IV arXiv: https://arxiv.org/abs/2512.14961v3 Person identification systems often rely on audio, visual, or behavioral cues, but real-world conditions frequently present with missing or degraded modalities. To address this challenge, we propose a multimodal person identification framework incorporating upper-body motion, face, and voice. Experimental results demonstrate that body motion outperforms traditional modalities such as face and voice in within-session evaluations, while serving as a complementary cue that enhances performance in multi-session scenarios. Our model employs a unified hybrid fusion strategy, fusing both feature-level and score-level information to maximize representational richness and decision accuracy. Specifically, it leverages multi-task learning to process modalities independently, followed by cross-attention and gated fusion mechanisms to exploit both unimodal information and cross-modal interactions. Finally, a confidence-weighted strategy and mistake-correction mechanism dynamically adapt to missing data, ensuring that our single classification head achieves optimal performance even in unimodal and bimodal scenarios. We evaluate our method on CANDOR, a newly introduced interview-based multimodal dataset, which we benchmark in this work for the first time. Our results demonstrate that the proposed trimodal system achieves 99.51% Top-1 accuracy on person identification tasks. In addition, we evaluate our model on the VoxCeleb1 dataset as a widely used evaluation protocol and reach 99.92% accuracy in bimodal mode, outperforming conventional approaches. Moreover, we show that our system maintains high accuracy even when one or two modalities are unavailable, making it a robust solution for real-world person recognition applications. The code and data for this work are publicly available. --- ### Intrusion Detection in Internet of Vehicles Using Machine Learning Authors: Hop Le, Izzat Alsmadi Published: 2025-12-16 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2512.14958v1 The Internet of Vehicles (IoV) has evolved modern transportation through enhanced connectivity and intelligent systems. However, this increased connectivity introduces critical vulnerabilities, making vehicles susceptible to cyber-attacks such Denial-ofService (DoS) and message spoofing. This project aims to develop a machine learning-based intrusion detection system to classify malicious Controller Area network (CAN) bus traffic using the CiCIoV2024 benchmark dataset. We analyzed various attack patterns including DoS and spoofing attacks targeting critical vehicle parameters such as Spoofing-GAS - gas pedal position, Spoofing-RPM, Spoofing-Speed, and Spoofing-Steering\_Wheel. Our initial findings confirm a multi-class classification problem with a clear structural difference between attack types and benign data, providing a strong foundation for machine learning models. --- ### Cross-Tokenizer Likelihood Scoring Algorithms for Language Model Distillation Authors: Buu Phan, Ashish Khisti, Karen Ullrich Published: 2025-12-16 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2512.14954v2 Computing next-token likelihood ratios between two language models (LMs) is a standard task in training paradigms such as knowledge distillation. Since this requires both models to share the same probability space, it becomes challenging when the teacher and student LMs use different tokenizers, for instance, when edge-device deployment necessitates a smaller vocabulary size to lower memory overhead. This work addresses this vocabulary misalignment problem by uncovering an implicit recursive structure in the commonly deployed Byte-Pair Encoding (BPE) algorithm and utilizing it to create a probabilistic framework for cross-tokenizer likelihood scoring. Our method enables sequence likelihood evaluation for vocabularies different from the teacher model native tokenizer, addressing two specific scenarios: when the student vocabulary is a subset of the teacher vocabulary, and the general case where it is arbitrary. In the subset regime, our framework computes exact likelihoods and provides next-token probabilities for sequential sampling with only ${O}(1)$ model evaluations per token. When used for distillation, this yields up to a $12\%$ reduction in memory footprint for the Qwen2.5-1.5B model while also improving baseline performance up to $4\%$ on the evaluated tasks. For the general case, we introduce a rigorous lossless procedure that leverages BPE recursive structure, complemented by a fast approximation that keeps large-vocabulary settings practical. Applied to GSM8K mathematical reasoning distillation, our method improves accuracy by over $2\%$ the current state of the art. Code: github.com/truongbuu/cross-tokenizer-scoring --- ### EVICPRESS: Joint KV-Cache Compression and Eviction for Efficient LLM Serving Authors: Shaoting Feng, Yuhan Liu, Hanchen Li, Xiaokun Chen, Samuel Shen, Kuntai Du, Zhuohan Gu, Rui Zhang, Yuyang Huang, Yihua Cheng, Jiayi Yao, Qizheng Zhang et al. Published: 2025-12-16 Categories: cs.OS, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.14946v1 Reusing KV cache is essential for high efficiency of Large Language Model (LLM) inference systems. With more LLM users, the KV cache footprint can easily exceed GPU memory capacity, so prior work has proposed to either evict KV cache to lower-tier storage devices, or compress KV cache so that more KV cache can be fit in the fast memory. However, prior work misses an important opportunity: jointly optimizing the eviction and compression decisions across all KV caches to minimize average generation latency without hurting quality. We propose EVICPRESS, a KV-cache management system that applies lossy compression and adaptive eviction to KV cache across multiple storage tiers. Specifically, for each KV cache of a context, EVICPRESS considers the effect of compression and eviction of the KV cache on the average generation quality and delay across all contexts as a whole. To achieve this, EVICPRESS proposes a unified utility function that quantifies the effect of quality and delay of the lossy compression or eviction. To this end, EVICPRESS's profiling module periodically updates the utility function scores on all possible eviction-compression configurations for all contexts and places KV caches using a fast heuristic to rearrange KV caches on all storage tiers, with the goal of maximizing the utility function scores on each storage tier. Compared to the baselines that evict KV cache or compress KV cache, EVICPRESS achieves higher KV-cache hit rates on fast devices, i.e., lower delay, while preserving high generation quality by applying conservative compression to contexts that are sensitive to compression errors. Evaluation on 12 datasets and 5 models demonstrates that EVICPRESS achieves up to 2.19x faster time-to-first-token (TTFT) at equivalent generation quality. --- ### PuzzleCraft: Exploration-Aware Curriculum Learning for Puzzle-Based RLVR in VLMs Authors: Ahmadreza Jeddi, Hakki Can Karaimer, Hue Nguyen, Zhongling Wang, Ke Zhao, Javad Rajabi, Ran Zhang, Raghav Goyal, Konstantinos G. Derpanis, Babak Taati, Radek Grzeszczuk Published: 2025-12-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.14944v2 RL post-training with verifiable rewards (RLVR) has become a practical route to eliciting chain-of-thought reasoning in vision--language models (VLMs), but scaling it in the visual domain remains challenging due to costly or noisy supervision and reliance on external verifiers. Puzzle-based RLVR is a promising alternative, yet existing approaches often treat puzzle rewards as flat or sparse, which weakens group-relative learning signal. Existing curriculum strategies are overly restrictive: they rely mainly on reward statistics and do not account for exploration in the solution space, which can lead to collapsed rollout dynamics. Further, RL post-training can induce reasoning--answer inconsistency as training progresses. To address these shortcomings, we present PuzzleCraft, a supervision-free framework that scales vision-centric RLVR using a set of lightweight puzzle environments with built-in verification. PuzzleCraft instantiates three puzzles inspired by classic visual pretext tasks: PatchFit, Rotation, and Jigsaw. We introduce a curriculum that combines difficulty with an exploration signal derived from solution-space dispersion, and use it to downweight collapsed prompt groups. In addition, we introduce a new post-training metric, Reasoning-Answer Consistency (RAC), to measure the degree that the chain-of-though supports the answer, and show our exploration-aware curriculum improves RAC and downstream performance. Across a broad suite of vision-centric benchmarks, PuzzleCraft improves robustness and reasoning consistency, yielding consistent downstream gains on both Qwen2.5-VL and Qwen3-VL backbones. Overall, our results suggest that scalable puzzle-based RLVR benefits from curricula that account for both difficulty and solution-space collapse, together with explicit consistency-enhancing schemes. --- ### Boundary condition enforcement with PINNs: a comparative study and verification on 3D geometries Authors: Conor Rowan, Kai Hampleman, Kurt Maute, Alireza Doostan Published: 2025-12-16 Categories: math.NA, cs.LG arXiv: https://arxiv.org/abs/2512.14941v1 Since their advent nearly a decade ago, physics-informed neural networks (PINNs) have been studied extensively as a novel technique for solving forward and inverse problems in physics and engineering. The neural network discretization of the solution field is naturally adaptive and avoids meshing the computational domain, which can both improve the accuracy of the numerical solution and streamline implementation. However, there have been limited studies of PINNs on complex three-dimensional geometries, as the lack of mesh and the reliance on the strong form of the partial differential equation (PDE) make boundary condition (BC) enforcement challenging. Techniques to enforce BCs with PINNs have proliferated in the literature, but a comprehensive side-by-side comparison of these techniques and a study of their efficacy on geometrically complex three-dimensional test problems are lacking. In this work, we i) systematically compare BC enforcement techniques for PINNs, ii) propose a general solution framework for arbitrary three-dimensional geometries, and iii) verify the methodology on three-dimensional, linear and nonlinear test problems with combinations of Dirichlet, Neumann, and Robin boundaries. Our approach is agnostic to the underlying PDE, the geometry of the computational domain, and the nature of the BCs, while requiring minimal hyperparameter tuning. This work represents a step in the direction of establishing PINNs as a mature numerical method, capable of competing head-to-head with incumbents such as the finite element method. --- ### TalkVerse: Democratizing Minute-Long Audio-Driven Video Generation Authors: Zhenzhi Wang, Jian Wang, Ke Ma, Dahua Lin, Bing Zhou Published: 2025-12-16 Categories: cs.CV, cs.AI, cs.MM, cs.SD arXiv: https://arxiv.org/abs/2512.14938v1 We introduce TalkVerse, a large-scale, open corpus for single-person, audio-driven talking video generation designed to enable fair, reproducible comparison across methods. While current state-of-the-art systems rely on closed data or compute-heavy models, TalkVerse offers 2.3 million high-resolution (720p/1080p) audio-video synchronized clips totaling 6.3k hours. These are curated from over 60k hours of video via a transparent pipeline that includes scene-cut detection, aesthetic assessment, strict audio-visual synchronization checks, and comprehensive annotations including 2D skeletons and structured visual/audio-style captions. Leveraging TalkVerse, we present a reproducible 5B DiT baseline built on Wan2.2-5B. By utilizing a video VAE with a high downsampling ratio and a sliding window mechanism with motion-frame context, our model achieves minute-long generation with low drift. It delivers comparable lip-sync and visual quality to the 14B Wan-S2V model but with 10$\times$ lower inference cost. To enhance storytelling in long videos, we integrate an MLLM director to rewrite prompts based on audio and visual cues. Furthermore, our model supports zero-shot video dubbing via controlled latent noise injection. We open-source the dataset, training recipes, and 5B checkpoints to lower barriers for research in audio-driven human video generation. Project Page: https://zhenzhiwang.github.io/talkverse/ --- ### Improving Pre-trained Adult Glioma Segmentation Models Using only Post-processing Techniques Authors: Abhijeet Parida, Daniel Capellán-Martín, Zhifan Jiang, Nishad Kulkarni, Krithika Iyer, Austin Tapp, Syed Muhammad Anwar, María J. Ledesma-Carbayo, Marius George Linguraru Published: 2025-12-16 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.14937v2 Gliomas are the most common malignant brain tumors in adults and are among the most lethal. Despite aggressive treatment, the median survival rate is less than 15 months. Accurate multiparametric MRI (mpMRI) tumor segmentation is critical for surgical planning, radiotherapy, and disease monitoring. While deep learning models have improved the accuracy of automated segmentation, large-scale pre-trained models generalize poorly and often underperform, producing systematic errors such as false positives, label swaps, and slice discontinuities in slices. These limitations are further compounded by unequal access to GPU resources and the growing environmental cost of large-scale model training. In this work, we propose adaptive post-processing techniques to refine the quality of glioma segmentations produced by large-scale pretrained models developed for various types of tumors. We demonstrated the techniques in multiple BraTS 2025 segmentation challenge tasks, with the ranking metric improving by 14.9 % for the sub-Saharan Africa challenge and 0.9% for the adult glioma challenge. This approach promotes a shift in brain tumor segmentation research from increasingly complex model architectures to efficient, clinically aligned post-processing strategies that are precise, computationally fair, and sustainable. --- ### Cloud Security Leveraging AI: A Fusion-Based AISOC for Malware and Log Behaviour Detection Authors: Nnamdi Philip Okonkwo, Lubna Luxmi Dhirani Published: 2025-12-16 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2512.14935v1 Cloud Security Operations Center (SOC) enable cloud governance, risk and compliance by providing insights visibility and control. Cloud SOC triages high-volume, heterogeneous telemetry from elastic, short-lived resources while staying within tight budgets. In this research, we implement an AI-Augmented Security Operations Center (AISOC) on AWS that combines cloud-native instrumentation with ML-based detection. The architecture uses three Amazon EC2 instances: Attacker, Defender, and Monitoring. We simulate a reverse-shell intrusion with Metasploit, and Filebeat forwards Defender logs to an Elasticsearch and Kibana stack for analysis. We train two classifiers, a malware detector built on a public dataset and a log-anomaly detector trained on synthetically augmented logs that include adversarial variants. We calibrate and fuse the scores to produce multi-modal threat intelligence and triage activity into NORMAL, SUSPICIOUS, and HIGH\_CONFIDENCE\_ATTACK. On held-out tests the fusion achieves strong macro-F1 (up to 1.00) under controlled conditions, though performance will vary in noisier and more diverse environments. These results indicate that simple, calibrated fusion can enhance cloud SOC capabilities in constrained, cost-sensitive setups. --- ### Low-rank MMSE filters, Kronecker-product representation, and regularization: a new perspective Authors: Daniel Gomes de Pinho Zanco, Leszek Szczecinski, Jacob Benesty, Eduardo Vinicius Kuhn Published: 2025-12-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.14932v1 In this work, we propose a method to efficiently find the regularization parameter for low-rank MMSE filters based on a Kronecker-product representation. We show that the regularization parameter is surprisingly linked to the problem of rank selection and, thus, properly choosing it, is crucial for low-rank settings. The proposed method is validated through simulations, showing significant gains over commonly used methods. --- ### Restless Multi-Process Multi-Armed Bandits with Applications to Self-Driving Microscopies Authors: Jaume Anguera Peris, Songtao Cheng, Hanzhao Zhang, Wei Ouyang, Joakim Jaldén Published: 2025-12-16 Categories: stat.AP, cs.AI, eess.SY arXiv: https://arxiv.org/abs/2512.14930v1 High-content screening microscopy generates large amounts of live-cell imaging data, yet its potential remains constrained by the inability to determine when and where to image most effectively. Optimally balancing acquisition time, computational capacity, and photobleaching budgets across thousands of dynamically evolving regions of interest remains an open challenge, further complicated by limited field-of-view adjustments and sensor sensitivity. Existing approaches either rely on static sampling or heuristics that neglect the dynamic evolution of biological processes, leading to inefficiencies and missed events. Here, we introduce the restless multi-process multi-armed bandit (RMPMAB), a new decision-theoretic framework in which each experimental region is modeled not as a single process but as an ensemble of Markov chains, thereby capturing the inherent heterogeneity of biological systems such as asynchronous cell cycles and heterogeneous drug responses. Building upon this foundation, we derive closed-form expressions for transient and asymptotic behaviors of aggregated processes, and design scalable Whittle index policies with sub-linear complexity in the number of imaging regions. Through both simulations and a real biological live-cell imaging dataset, we show that our approach achieves substantial improvements in throughput under resource constraints. Notably, our algorithm outperforms Thomson Sampling, Bayesian UCB, epsilon-Greedy, and Round Robin by reducing cumulative regret by more than 37% in simulations and capturing 93% more biologically relevant events in live imaging experiments, underscoring its potential for transformative smart microscopy. Beyond improving experimental efficiency, the RMPMAB framework unifies stochastic decision theory with optimal autonomous microscopy control, offering a principled approach to accelerate discovery across multidisciplinary sciences. --- ### Deep learning water-unsuppressed MRSI at ultra-high field for simultaneous quantitative metabolic, susceptibility and myelin water imaging Authors: Paul J. Weiser, Jiye Kim, Jongho Lee, Amirmohammad Shamaei, Gulnur Ungan, Malte Hoffmann, Antoine Klauser, Berkin Bilgic, Ovidiu C. Andronesi Published: 2025-12-16 Categories: eess.IV, cs.LG arXiv: https://arxiv.org/abs/2512.14929v1 Purpose: Magnetic Resonance Spectroscopic Imaging (MRSI) maps endogenous brain metabolism while suppressing the overwhelming water signal. Water-unsuppressed MRSI (wu-MRSI) allows simultaneous imaging of water and metabolites, but large water sidebands cause challenges for metabolic fitting. We developed an end-to-end deep-learning pipeline to overcome these challenges at ultra-high field. Methods:Fast high-resolution wu-MRSI was acquired at 7T with non-cartesian ECCENTRIC sampling and ultra-short echo time. A water and lipid removal network (WALINET+) was developed to remove lipids, water signal, and sidebands. MRSI reconstruction was performed by DeepER and a physics-informed network for metabolite fitting. Water signal was used for absolute metabolite quantification, quantitative susceptibility mapping (QSM), and myelin water fraction imaging (MWF). Results: WALINET+ provided the lowest NRMSE (< 2%) in simulations and in vivo the smallest bias (< 20%) and limits-of-agreement (+-63%) between wu-MRSI and ws-MRSI scans. Several metabolites such as creatine and glutamate showed higher SNR in wu-MRSI. QSM and MWF obtained from wu-MRSI and GRE showed good agreement with 0 ppm/5.5% bias and +-0.05 ppm/ +- 12.75% limits-of-agreement. Conclusion: High-quality metabolic, QSM, and MWF mapping of the human brain can be obtained simultaneously by ECCENTRIC wu-MRSI at 7T with 2 mm isotropic resolution in 12 min. WALINET+ robustly removes water sidebands while preserving metabolite signal, eliminating the need for water suppression and separate water acquisitions. --- ### Parameter Efficient Multimodal Instruction Tuning for Romanian Vision Language Models Authors: George-Andrei Dima, Răzvan-Alexandru Smădu, Dumitru-Clementin Cercel Published: 2025-12-16 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.14926v2 Focusing on low-resource languages is an essential step toward democratizing generative AI. In this work, we contribute to reducing the multimodal NLP resource gap for Romanian. We translate the widely known Flickr30K dataset into Romanian and further extend it for visual question answering by leveraging open-source LLMs. We demonstrate the usefulness of our datasets by fine-tuning open-source VLMs on Romanian visual question answering. We select VLMs from three widely used model families: LLaMA 3.2, LLaVA 1.6, and Qwen2. For fine-tuning, we employ the parameter-efficient LoRA method. Our models show improved Romanian capabilities in visual QA, as well as on tasks they were not trained on, such as Romanian image description generation. The seven-billion-parameter Qwen2-VL-RoVQA obtains top scores on both tasks, with improvements of +2.29% and +4.45% in BERTScore F1 on VQA and captioning, respectively, over its original version. Finally, the models show substantial reductions in grammatical errors compared to their original forms, indicating improvements not only in language understanding but also in Romanian fluency. --- ### Multiscale Aggregated Hierarchical Attention (MAHA): A Game Theoretic and Optimization Driven Approach to Efficient Contextual Modeling in Large Language Models Authors: Caner Erden Published: 2025-12-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.14925v2 The quadratic computational complexity of MultiHead SelfAttention (MHSA) remains a fundamental bottleneck in scaling Large Language Models (LLMs) for longcontext tasks. While sparse and linearized attention mechanisms attempt to mitigate this, they often compromise the representation of global dependencies or fail to capture multiscale semantic granularity effectively. In this paper, we propose Multiscale Aggregated Hierarchical Attention (MAHA), a novel architectural framework that reformulates the attention mechanism through hierarchical decomposition and mathematically rigorous aggregation. Unlike conventional approaches that treat token interactions at a single resolution, MAHA dynamically partitions the input sequence into hierarchical scales via learnable downsampling operators. The core innovation lies in its aggregation strategy: we model the fusion of scalespecific attention matrices as a resource allocation problem, solved via a convex optimization framework or a Nash equilibriumbased gametheoretic approach. This ensures a theoretically optimal balance between local nuance and global context fidelity. Implemented within a hybrid dilatedconvolutional transformer backbone, MAHA utilizes differentiable optimization layers to enable endtoend training. Experimental evaluations demonstrate that MAHA achieves superior scalability; empirical FLOPs analysis confirms an 81% reduction in computational cost at a sequence length of 4096 compared to standard attention. This work bridges the gap between optimization theory and sequence modeling, offering a scalable solution for nextgeneration LLMs. --- ### PANDA-PLUS-Bench: A Clinical Benchmark for Evaluating Robustness of AI Foundation Models in Prostate Cancer Diagnosis Authors: Joshua L. Ebbert, Dennis Della Corte Published: 2025-12-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.14922v1 Artificial intelligence foundation models are increasingly deployed for prostate cancer Gleason grading, where GP3/GP4 distinction directly impacts treatment decisions. However, these models may achieve high validation accuracy by learning specimen-specific artifacts rather than generalizable biological features, limiting real-world clinical utility. We introduce PANDA-PLUS-Bench, a curated benchmark dataset derived from expert-annotated prostate biopsies designed specifically to quantify this failure mode. The benchmark comprises nine carefully selected whole slide images from nine unique patients containing diverse Gleason patterns, with non-overlapping tissue patches extracted at both 512x512 and 224x224 pixel resolutions across eight augmentation conditions. Using this benchmark, we evaluate seven foundation models on their ability to separate biological signal from slide-level confounders. Our results reveal substantial variation in robustness across models: Virchow2 achieved the lowest slide-level encoding among large-scale models (81.0%) yet exhibited the second-lowest cross-slide accuracy (47.2%). HistoEncoder, trained specifically on prostate tissue, demonstrated the highest cross-slide accuracy (59.7%) and the strongest slide-level encoding (90.3%), suggesting tissue-specific training may enhance both biological feature capture and slide-specific signatures. All models exhibited measurable within-slide vs. cross-slide accuracy gaps, though the magnitude varied from 19.9 percentage points to 26.9 percentage points. We provide an open-source Google Colab notebook enabling researchers to evaluate additional foundation models against our benchmark using standardized metrics. PANDA-PLUS-Bench addresses a critical gap in foundation model evaluation by providing a purpose-built resource for robustness assessment in the clinically important context of Gleason grading. --- ### AgroAskAI: A Multi-Agentic AI Framework for Supporting Smallholder Farmers' Enquiries Globally Authors: Nadine Angela Cantonjos, Arpita Biswas Published: 2025-12-16 Categories: cs.AI, cs.CY arXiv: https://arxiv.org/abs/2512.14910v1 Agricultural regions in rural areas face damage from climate-related risks, including droughts, heavy rainfall, and shifting weather patterns. Prior research calls for adaptive risk-management solutions and decision-making strategies. To this end, artificial intelligence (AI), particularly agentic AI, offers a promising path forward. Agentic AI systems consist of autonomous, specialized agents capable of solving complex, dynamic tasks. While past systems have relied on single-agent models or have used multi-agent frameworks only for static functions, there is a growing need for architectures that support dynamic collaborative reasoning and context-aware outputs. To bridge this gap, we present AgroAskAI, a multi-agent reasoning system for climate adaptation decision support in agriculture, with a focus on vulnerable rural communities. AgroAskAI features a modular, role-specialized architecture that uses a chain-of-responsibility approach to coordinate autonomous agents, integrating real-time tools and datasets. The system has built-in governance mechanisms that mitigate hallucination and enable internal feedback for coherent, locally relevant strategies. The system also supports multilingual interactions, making it accessible to non-English-speaking farmers. Experiments on common agricultural queries related to climate adaptation show that, with additional tools and prompt refinement, AgroAskAI delivers more actionable, grounded, and inclusive outputs. Our experimental results highlight the potential of agentic AI for sustainable and accountable decision support in climate adaptation for agriculture. --- ### ATLAS: Adaptive Topology-based Learning at Scale for Homophilic and Heterophilic Graphs Authors: Turja Kundu, Sanjukta Bhowmick Published: 2025-12-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.14908v6 Graph neural networks (GNNs) excel on homophilic graphs where connected nodes share labels, but struggle with heterophilic graphs where edges do not imply similarity. Moreover, iterative message passing limits scalability due to neighborhood expansion overhead. We introduce ATLAS (Adaptive Topology-based Learning at Scale), a propagation-free framework that encodes graph structure through multi-resolution community features rather than message passing. We first prove that community refinement involves a fundamental trade-off: finer partitions increase label-community mutual information but also increase entropy. We formalize when refinement improves normalized mutual information, explaining why intermediate granularities are often most predictive. ATLAS employs modularity-guided adaptive search to automatically identify informative community scales, which are one-hot encoded, projected into learnable embeddings, and concatenated with node attributes for MLP classification. This enables standard mini-batch training and adjacency-free inference after one-time preprocessing. Across 13 benchmarks including million-node graphs, ATLAS achieves competitive or superior accuracy, up to 20-point gains over GCN on heterophilic datasets and 12-point gains over MLPs on homophilic graphs. By treating topology as explicit features, ATLAS adapts intelligently: leveraging structure when informative, remaining robust when weakly aligned, and avoiding propagation when structure misleads, providing both scalable performance and interpretable structural insights. --- ### DrugRAG: Enhancing Pharmacy LLM Performance Through A Novel Retrieval-Augmented Generation Pipeline Authors: Houman Kazemzadeh, Kiarash Mokhtari Dizaji, Seyed Reza Tavakoli, Farbod Davoodi, MohammadReza KarimiNejad, Parham Abed Azad, Fatemeh Latifi, Ali Sabzi, Armin Khosravi, Siavash Ahmadi, Babak Khalaj, Mohammad Hossein Rohban et al. Published: 2025-12-16 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.14896v2 In our study, we evaluated large language model (LLM) performance on pharmacy licensure-style question-answering tasks and developed an external knowledge integration method to improve accuracy. We benchmarked ten LLMs with varying parameter sizes (8 billion to 70+ billion) using a 141-question pharmacy dataset, measuring baseline accuracy without modification. Baseline performance ranged from 46% to 92%, with GPT-5 (92%) and o3 (89%) achieving the highest scores, while smaller open-source models showed substantially lower performance. We then developed DrugRAG, a three-step retrieval-augmented generation (RAG) pipeline that retrieves structured, evidence-based drug information and augments model prompts with contextual pharmacological evidence, operating externally and requiring no changes to model architecture or parameters. DrugRAG increased accuracy across all five evaluated models, with gains ranging from 7 to 21 percentage points (e.g., Gemma 3 27B: 61.0% to 71%, Llama 3.1 8B: 46% to 67%). McNemar analyses demonstrated statistically significant paired improvements primarily in smaller and mid-sized open-source models. These findings demonstrate that integrating structured external drug knowledge via DrugRAG can improve LLM performance on pharmacy-focused question-answering tasks without modifying the underlying models, providing a practical pipeline for enhancing evidence-based pharmacy-focused AI applications. --- ### Imitation Learning for Multi-turn LM Agents via On-policy Expert Corrections Authors: Niklas Lauffer, Xiang Deng, Srivatsa Kundurthy, Brad Kenstler, Jeff Da Published: 2025-12-16 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.14895v1 A popular paradigm for training LM agents relies on imitation learning, fine-tuning on expert trajectories. However, we show that the off-policy nature of imitation learning for multi-turn LM agents suffers from the fundamental limitation known as covariate shift: as the student policy's behavior diverges from the expert's, it encounters states not present in the training data, reducing the effectiveness of fine-tuning. Taking inspiration from the classic DAgger algorithm, we propose a novel data generation methodology for addressing covariate shift for multi-turn LLM training. We introduce on-policy expert corrections (OECs), partially on-policy data generated by starting rollouts with a student model and then switching to an expert model part way through the trajectory. We explore the effectiveness of our data generation technique in the domain of software engineering (SWE) tasks, a multi-turn setting where LLM agents must interact with a development environment to fix software bugs. Our experiments compare OEC data against various other on-policy and imitation learning approaches on SWE agent problems and train models using a common rejection sampling (i.e., using environment reward) combined with supervised fine-tuning technique. Experiments find that OEC trajectories show a relative 14% and 13% improvement over traditional imitation learning in the 7b and 32b setting, respectively, on SWE-bench verified. Our results demonstrate the need for combining expert demonstrations with on-policy data for effective multi-turn LM agent training. --- ### OLR-WA: Online Weighted Average Linear Regression in Multivariate Data Streams Authors: Mohammad Abu-Shaira, Alejandro Rodriguez, Greg Speegle, Victor Sheng, Ishfaq Ahmad Published: 2025-12-16 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.14892v1 Online learning updates models incrementally with new data, avoiding large storage requirements and costly model recalculations. In this paper, we introduce "OLR-WA; OnLine Regression with Weighted Average", a novel and versatile multivariate online linear regression model. We also investigate scenarios involving drift, where the underlying patterns in the data evolve over time, conduct convergence analysis, and compare our approach with existing online regression models. The results of OLR-WA demonstrate its ability to achieve performance comparable to the batch regression, while also showcasing comparable or superior performance when compared with other state-of-the-art online models, thus establishing its effectiveness. Moreover, OLR-WA exhibits exceptional performance in terms of rapid convergence, surpassing other online models with consistently achieving high r2 values as a performance measure from the first iteration to the last iteration, even when initialized with minimal amount of data points, as little as 1% to 10% of the total data points. In addition to its ability to handle time-based (temporal drift) scenarios, remarkably, OLR-WA stands out as the only model capable of effectively managing confidence-based challenging scenarios. It achieves this by adopting a conservative approach in its updates, giving priority to older data points with higher confidence levels. In summary, OLR-WA's performance further solidifies its versatility and utility across different contexts, making it a valuable solution for online linear regression tasks. --- ### Integrating Large Language Models and Knowledge Graphs to Capture Political Viewpoints in News Media Authors: Massimiliano Fadda, Enrico Motta, Francesco Osborne, Diego Reforgiato Recupero, Angelo Salatino Published: 2025-12-16 Categories: cs.CL, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2512.14887v1 News sources play a central role in democratic societies by shaping political and social discourse through specific topics, viewpoints and voices. Understanding these dynamics is essential for assessing whether the media landscape offers a balanced and fair account of public debate. In earlier work, we introduced a pipeline that, given a news corpus, i) uses a hybrid human-machine approach to identify the range of viewpoints expressed about a given topic, and ii) classifies relevant claims with respect to the identified viewpoints, defined as sets of semantically and ideologically congruent claims (e.g., positions arguing that immigration positively impacts the UK economy). In this paper, we improve this pipeline by i) fine-tuning Large Language Models (LLMs) for viewpoint classification and ii) enriching claim representations with semantic descriptions of relevant actors drawn from Wikidata. We evaluate our approach against alternative solutions on a benchmark centred on the UK immigration debate. Results show that while both mechanisms independently improve classification performance, their integration yields the best results, particularly when using LLMs capable of processing long inputs. --- ### Vibe Spaces for Creatively Connecting and Expressing Visual Concepts Authors: Huzheng Yang, Katherine Xu, Andrew Lu, Michael D. Grossberg, Yutong Bai, Jianbo Shi Published: 2025-12-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.14884v1 Creating new visual concepts often requires connecting distinct ideas through their most relevant shared attributes -- their vibe. We introduce Vibe Blending, a novel task for generating coherent and meaningful hybrids that reveals these shared attributes between images. Achieving such blends is challenging for current methods, which struggle to identify and traverse nonlinear paths linking distant concepts in latent space. We propose Vibe Space, a hierarchical graph manifold that learns low-dimensional geodesics in feature spaces like CLIP, enabling smooth and semantically consistent transitions between concepts. To evaluate creative quality, we design a cognitively inspired framework combining human judgments, LLM reasoning, and a geometric path-based difficulty score. We find that Vibe Space produces blends that humans consistently rate as more creative and coherent than current methods. --- ### Task Matrices: Linear Maps for Cross-Model Finetuning Transfer Authors: Darrin O' Brien, Dhikshith Gajulapalli, Eric Xia Published: 2025-12-16 Categories: cs.LG, cs.CL, cs.CV arXiv: https://arxiv.org/abs/2512.14880v1 Results in interpretability suggest that large vision and language models learn implicit linear encodings when models are biased by in-context prompting. However, the existence of similar linear representations in more general adaptation regimes has not yet been demonstrated. In this work, we develop the concept of a task matrix, a linear transformation from a base to finetuned embedding state. We demonstrate that for vision and text models and ten different datasets, a base model augmented with a task matrix achieves results surpassing linear probes, sometimes approaching finetuned levels. Our results validate the existence of cross-layer linear encodings between pretrained and finetuned architectures. Moreover, we show that a data-based approximation for such encodings is both efficient and generalizable to multiple domains. We make our implementation publicly available. --- ### Entropy-Reservoir Bregman Projection: An Information-Geometric Unification of Model Collapse Authors: Jingwei Chen Published: 2025-12-16 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.14879v1 Self-referential learning -- training a model on data it generated itself -- promises boundless scalability but chronically suffers from model collapse: language models degenerate into repetitive text, GANs drop modes, and reinforcement-learning policies over-exploit. Although practitioners employ ad~hoc fixes such as real-data mixing, entropy bonuses, knowledge distillation, or retrieval-augmented generation, a single principle that explains both the failure mode and the success of these fixes has remained elusive. We present Entropy-Reservoir Bregman Projection (ERBP), an information-geometric framework that unifies these phenomena. We model the closed loop as a stochastic Bregman projection sequence in distribution space. Without external coupling, finite-sample noise forces the system to project onto an ever-shrinking empirical support, causing exponential entropy decay and eventual collapse. Introducing an Entropy Reservoir -- a high-entropy distribution mixed into each projection -- injects a controllable entropy flux that provably stabilises the dynamics. Our theory yields (i) a necessary condition for collapse, (ii) a sufficient condition that guarantees a non-trivial entropy floor, and (iii) closed-form rates that depend only on sample size and the strong-convexity/Lipschitz constants of the Bregman generator. Experiments on large-language-model self-training, Soft Actor-Critic in reinforcement learning, and GAN optimisation validate our predictions and show that disparate stabilisation heuristics correspond to specific reservoir choices and coupling coefficients. ERBP thus transforms a collection of folk remedies into a single, quantitative design rule: monitor and budget your entropy flux. ---