# Research Papers — 2025-12 · bundle page 10 of 175

> Full-text markdown of papers #451–500 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/10
[← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/9.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-12/page/11.md)

### A Community-Aware Framework for Influence Maximization with Explicit Accounting for Inter-Community Influence

Authors: Eliot W. Robson, Abhishek K. Umrawal
Published: 2025-12-30
Categories: cs.SI, cs.AI, stat.ML
arXiv: https://arxiv.org/abs/2512.23973v2

Influence Maximization (IM) seeks to identify a small set of seed nodes in a social network to maximize expected information spread under a diffusion model. While community-based approaches improve scalability by exploiting modular structure, they typically assume independence between communities, overlooking inter-community influence$\unicode{x2014}$a limitation that reduces effectiveness in real-world networks. We introduce Community-IM++, a scalable framework that explicitly models cross-community diffusion through a principled heuristic based on community-based diffusion degree (CDD) and a progressive budgeting strategy. The algorithm partitions the network, computes CDD to prioritize bridging nodes, and allocates seeds adaptively across communities using lazy evaluation to minimize redundant computations. Experiments on large real-world social networks under different edge weight models show that Community-IM++ achieves near-greedy influence spread at up to 100 times lower runtime, while outperforming Community-IM and degree heuristics across budgets and structural conditions. These results demonstrate the practicality of Community-IM++ for large-scale applications such as viral marketing, misinformation control, and public health campaigns, where efficiency and cross-community reach are critical.

---

### CEC-Zero: Zero-Supervision Character Error Correction with Self-Generated Rewards

Authors: Zhiming Lin, Kai Zhao, Sophie Zhang, Peilai Yu, Canran Xiao
Published: 2025-12-30
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.23971v1

Large-scale Chinese spelling correction (CSC) remains critical for real-world text processing, yet existing LLMs and supervised methods lack robustness to novel errors and rely on costly annotations. We introduce CEC-Zero, a zero-supervision reinforcement learning framework that addresses this by enabling LLMs to correct their own mistakes. CEC-Zero synthesizes errorful inputs from clean text, computes cluster-consensus rewards via semantic similarity and candidate agreement, and optimizes the policy with PPO. It outperforms supervised baselines by 10--13 F$_1$ points and strong LLM fine-tunes by 5--8 points across 9 benchmarks, with theoretical guarantees of unbiased rewards and convergence. CEC-Zero establishes a label-free paradigm for robust, scalable CSC, unlocking LLM potential in noisy text pipelines.

---

### Efficient Context Scaling with LongCat ZigZag Attention

Authors: Chen Zhang, Yang Bai, Jiahuan Li, Anchun Gui, Keheng Wang, Feifan Liu, Guanyu Wu, Yuwei Jiang, Defei Bu, Li Wei, Haihang Jing, Hongyin Tang et al.
Published: 2025-12-30
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2512.23966v2

We introduce LongCat ZigZag Attention (LoZA), which is a sparse attention scheme designed to transform any existing full-attention models into sparse versions with rather limited compute budget. In long-context scenarios, LoZA can achieve significant speed-ups both for prefill-intensive (e.g., retrieval-augmented generation) and decode-intensive (e.g., tool-integrated reasoning) cases. Specifically, by applying LoZA to LongCat-Flash during mid-training, we serve LongCat-Flash-Exp as a long-context foundation model that can swiftly process up to 1 million tokens, enabling efficient long-term reasoning and long-horizon agentic capabilities.

---

### DUALFloodGNN: Physics-informed Graph Neural Network for Operational Flood Modeling

Authors: Carlo Malapad Acosta, Herath Mudiyanselage Viraj Vidura Herath, Jia Yu Lim, Abhishek Saha, Sanka Rasnayaka, Lucy Marshall
Published: 2025-12-30
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.23964v2

Flood models inform strategic disaster management by simulating the spatiotemporal hydrodynamics of flooding. While physics-based numerical flood models are accurate, their substantial computational cost limits their use in operational settings where rapid predictions are essential. Models designed with graph neural networks (GNNs) provide both speed and accuracy while having the ability to process unstructured spatial domains. Given its flexible input and architecture, GNNs can be leveraged alongside physics-informed techniques with ease, significantly improving interpretability and generalizability. We introduce a novel flood GNN architecture, DUALFloodGNN, which embeds physical constraints at both global and local scales through explicit loss terms. The model jointly predicts water volume at nodes and flow along edges through a shared message-passing framework. To improve performance for autoregressive inference, model training is conducted with a multi-step loss enhanced with dynamic curriculum learning. Compared with standard GNN architectures and state-of-the-art GNN flood models, DUALFloodGNN achieves substantial improvements in predicting multiple hydrologic variables (e.g., water volume, flow, and depth) while maintaining high computational efficiency. The model is open sourced at https://github.com/acostacos/dual_flood_gnn. The dataset is open sourced at https://hdl.handle.net/2123/35293 with the DOI 10.25910/9xav-0s86.

---

### An Comparative Analysis about KYC on a Recommendation System Toward Agentic Recommendation System

Authors: Junjie H. Xu
Published: 2025-12-30
Categories: cs.IR, cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2512.23961v1

This research presents a cutting-edge recommendation system utilizing agentic AI for KYC (Know Your Customer in the financial domain), and its evaluation across five distinct content verticals: Advertising (Ad), News, Gossip, Sharing (User-Generated Content), and Technology (Tech). The study compares the performance of four experimental groups, grouping by the intense usage of KYC, benchmarking them against the Normalized Discounted Cumulative Gain (nDCG) metric at truncation levels of $k=1$, $k=3$, and $k=5$. By synthesizing experimental data with theoretical frameworks and industry benchmarks from platforms such as Baidu and Xiaohongshu, this research provides insight by showing experimental results for engineering a large-scale agentic recommendation system.

---

### HGMEM: Hypergraph-based Working Memory to Improve Multi-step RAG for Long-Context Complex Relational Modeling

Authors: Chulun Zhou, Chunkang Zhang, Guoxin Yu, Fandong Meng, Jie Zhou, Wai Lam, Mo Yu
Published: 2025-12-30
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2512.23959v3

Multi-step retrieval-augmented generation (RAG) has become a widely adopted strategy for enhancing large language models (LLMs) on tasks that demand global comprehension and intensive reasoning. Although many RAG systems incorporate a working memory to consolidate information, existing designs primarily function as a passive storage for isolated facts. This static nature overlooks crucial high-order correlations among primitive facts, thereby limiting models' capacity for multi-step reasoning and resulting in fragmented reasoning and weak global sense-making within extended contexts. We introduce HGMem, a hypergraph-based working memory system, extending the concept of memory beyond simple storage into a dynamic, expressive structure for complex reasoning and global understanding. In our approach, memory is represented as a hypergraph where hyperedges correspond to distinct memory units, enabling the progressive formation of high-order interactions within memory. This mechanism connects facts and thoughts around the focal problem, evolving the memory into an integrated and situated knowledge structure that provides strong propositions for deeper reasoning. We evaluate HGMem on several challenging global sense-making benchmarks. Extensive experiments and in-depth analyses demonstrate that our method consistently improves multi-step RAG and substantially outperforms strong baseline systems across diverse datasets.

---

### Implicit geometric regularization in flow matching via density weighted Stein operators

Authors: Shinto Eguchi
Published: 2025-12-30
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2512.23956v2

Flow Matching (FM) has emerged as a powerful paradigm for continuous normalizing flows, yet standard FM implicitly performs an unweighted $L^2$ regression over the entire ambient space. In high dimensions, this leads to a fundamental inefficiency: the vast majority of the integration domain consists of low-density ``void'' regions where the target velocity fields are often chaotic or ill-defined. In this paper, we propose {$γ$-Flow Matching ($γ$-FM)}, a density-weighted variant that aligns the regression geometry with the underlying probability flow. While density weighting is desirable, naive implementations would require evaluating the intractable target density. We circumvent this by introducing a Dynamic Density-Weighting strategy that estimates the \emph{target} density directly from training particles. This approach allows us to dynamically downweight the regression loss in void regions without compromising the simulation-free nature of FM. Theoretically, we establish that $γ$-FM minimizes the transport cost on a statistical manifold endowed with the $γ$-Stein metric. Spectral analysis further suggests that this geometry induces an implicit Sobolev regularization, effectively damping high-frequency oscillations in void regions. Empirically, $γ$-FM significantly improves vector field smoothness and sampling efficiency on high-dimensional latent datasets, while demonstrating intrinsic robustness to outliers.

---

### T2VAttack: Adversarial Attack on Text-to-Video Diffusion Models

Authors: Changzhen Li, Yuecong Min, Jie Zhang, Zheng Yuan, Shiguang Shan, Xilin Chen
Published: 2025-12-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.23953v2

The rapid evolution of Text-to-Video (T2V) diffusion models has driven remarkable advancements in generating high-quality, temporally coherent videos from natural language descriptions. Despite these achievements, their vulnerability to adversarial attacks remains largely unexplored. In this paper, we introduce T2VAttack, a comprehensive study of adversarial attacks on T2V diffusion models from both semantic and temporal perspectives. Considering the inherently dynamic nature of video data, we propose two distinct attack objectives: a semantic objective to evaluate video-text alignment and a temporal objective to assess the temporal dynamics. To achieve an effective and efficient attack process, we propose two adversarial attack methods: (i) T2VAttack-S, which identifies semantically or temporally critical words in prompts and replaces them with synonyms via greedy search, and (ii) T2VAttack-I, which iteratively inserts optimized words with minimal perturbation to the prompt. By combining these objectives and strategies, we conduct a comprehensive evaluation on the adversarial robustness of several state-of-the-art T2V models, including ModelScope, CogVideoX, Open-Sora, and HunyuanVideo. Our experiments reveal that even minor prompt modifications, such as the substitution or insertion of a single word, can cause substantial degradation in semantic fidelity and temporal dynamics, highlighting critical vulnerabilities in current T2V diffusion models.

---

### U-Net-Like Spiking Neural Networks for Single Image Dehazing

Authors: Huibin Li, Haoran Liu, Mingzhe Liu, Yulong Xiao, Peng Li, Guibin Zan
Published: 2025-12-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.23950v1

Image dehazing is a critical challenge in computer vision, essential for enhancing image clarity in hazy conditions. Traditional methods often rely on atmospheric scattering models, while recent deep learning techniques, specifically Convolutional Neural Networks (CNNs) and Transformers, have improved performance by effectively analyzing image features. However, CNNs struggle with long-range dependencies, and Transformers demand significant computational resources. To address these limitations, we propose DehazeSNN, an innovative architecture that integrates a U-Net-like design with Spiking Neural Networks (SNNs). DehazeSNN captures multi-scale image features while efficiently managing local and long-range dependencies. The introduction of the Orthogonal Leaky-Integrate-and-Fire Block (OLIFBlock) enhances cross-channel communication, resulting in superior dehazing performance with reduced computational burden. Our extensive experiments show that DehazeSNN is highly competitive to state-of-the-art methods on benchmark datasets, delivering high-quality haze-free images with a smaller model size and less multiply-accumulate operations. The proposed dehazing method is publicly available at https://github.com/HaoranLiu507/DehazeSNN.

---

### DivQAT: Enhancing Robustness of Quantized Convolutional Neural Networks against Model Extraction Attacks

Authors: Kacem Khaled, Felipe Gohring de Magalhães, Gabriela Nicolescu
Published: 2025-12-30
Categories: cs.LG, cs.CR
arXiv: https://arxiv.org/abs/2512.23948v1

Convolutional Neural Networks (CNNs) and their quantized counterparts are vulnerable to extraction attacks, posing a significant threat of IP theft. Yet, the robustness of quantized models against these attacks is little studied compared to large models. Previous defenses propose to inject calculated noise into the prediction probabilities. However, these defenses are limited since they are not incorporated during the model design and are only added as an afterthought after training. Additionally, most defense techniques are computationally expensive and often have unrealistic assumptions about the victim model that are not feasible in edge device implementations and do not apply to quantized models. In this paper, we propose DivQAT, a novel algorithm to train quantized CNNs based on Quantization Aware Training (QAT) aiming to enhance their robustness against extraction attacks. To the best of our knowledge, our technique is the first to modify the quantization process to integrate a model extraction defense into the training process. Through empirical validation on benchmark vision datasets, we demonstrate the efficacy of our technique in defending against model extraction attacks without compromising model accuracy. Furthermore, combining our quantization technique with other defense mechanisms improves their effectiveness compared to traditional QAT.

---

### Improved Balanced Classification with Theoretically Grounded Loss Functions

Authors: Corinna Cortes, Mehryar Mohri, Yutao Zhong
Published: 2025-12-30
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2512.23947v1

The balanced loss is a widely adopted objective for multi-class classification under class imbalance. By assigning equal importance to all classes, regardless of their frequency, it promotes fairness and ensures that minority classes are not overlooked. However, directly minimizing the balanced classification loss is typically intractable, which makes the design of effective surrogate losses a central question. This paper introduces and studies two advanced surrogate loss families: Generalized Logit-Adjusted (GLA) loss functions and Generalized Class-Aware weighted (GCA) losses. GLA losses generalize Logit-Adjusted losses, which shift logits based on class priors, to the broader general cross-entropy loss family. GCA loss functions extend the standard class-weighted losses, which scale losses inversely by class frequency, by incorporating class-dependent confidence margins and extending them to the general cross-entropy family. We present a comprehensive theoretical analysis of consistency for both loss families. We show that GLA losses are Bayes-consistent, but only $H$-consistent for complete (i.e., unbounded) hypothesis sets. Moreover, their $H$-consistency bounds depend inversely on the minimum class probability, scaling at least as $1/\mathsf p_{\min}$. In contrast, GCA losses are $H$-consistent for any hypothesis set that is bounded or complete, with $H$-consistency bounds that scale more favorably as $1/\sqrt{\mathsf p_{\min}}$, offering significantly stronger theoretical guarantees in imbalanced settings. We report the results of experiments demonstrating that, empirically, both the GCA losses with calibrated class-dependent confidence margins and GLA losses can greatly outperform straightforward class-weighted losses as well as the LA losses. GLA generally performs slightly better in common benchmarks, whereas GCA exhibits a slight edge in highly imbalanced settings.

---

### Decoupling Constraints from Two Directions for Evolutionary Constrained Multi-objective Optimization

Authors: Ruiqing Sun, Dawei Feng, Xing Zhou, Lianghao Li, Sheng Qi, Bo Ding, Yijie Wang, Rui Wang, Huaimin Wang
Published: 2025-12-30
Categories: cs.NE
arXiv: https://arxiv.org/abs/2512.23945v2

Real-world constrained multi-objective optimization problems (CMOPs) commonly involve multiple constraints, and understanding and exploiting their coupling relationships is crucial for efficient optimization. Recent constraint-decoupling methods handle individual constraints separately, but they generally search only in the evolutionary direction to approximate single-constraint Pareto fronts (SCPFs). In this study, we show that part or all of the constrained Pareto front (CPF) may be unrelated to any SCPF and instead be shaped by the boundaries of infeasible regions. We refer to such a portion as the independent CPF (ICPF) and introduce the reverse CPF (RCPF) to characterize its associated informative infeasible boundaries. Based on these observations, we propose a bidirectional constraint-decoupling coevolutionary algorithm named DCF2D. DCF2D dynamically identifies the constraints obstructing the main population and activates constraint-specific auxiliary populations. These populations adaptively search in the evolutionary direction for the corresponding SCPFs or in the reverse evolutionary direction for the corresponding RCPFs. Its three-stage framework integrates unconstrained global exploration, event-driven bidirectional coevolution, and final convergence refinement. Experiments on 87 benchmark instances from seven test suites and 28 real-world engineering CMOPs demonstrate that DCF2D achieves the best overall performance among nine algorithms. Code available at: https://github.com/RuiqingS/DCF2D.

---

### Statistical Guarantees in the Search for Less Discriminatory Algorithms

Authors: Chris Hays, Ben Laufer, Solon Barocas, Manish Raghavan
Published: 2025-12-30
Categories: cs.CY, cs.LG, stat.ME
arXiv: https://arxiv.org/abs/2512.23943v2

U.S. discrimination law can impose liability on firms that fail to adopt a less discriminatory alternative (LDA): a decision policy that achieves the same business objectives while reducing disparate impact on legally protected groups. Recent scholarship argues that this doctrine has direct implications for algorithmic decision-making in high-stakes domains such as employment, lending, and housing, potentially obligating firms to search for "less discriminatory algorithms" (Black et al., 2024). Regulators have at times encouraged proactive LDA searches, reinforcing the expectation of a good-faith effort to identify equally performant models with lower disparate impact. Model multiplicity makes such searches plausible: retraining with different random seeds can yield models with comparable predictive performance but materially different disparate impacts. Yet firms cannot retrain indefinitely, raising a central question: when is the search sufficient to demonstrate good faith? We formalize LDA search under multiplicity as an optimal stopping problem in which a developer seeks to produce evidence that further search is unlikely to yield meaningful improvements. Our main contribution is an adaptive stopping algorithm that provides a high-probability upper bound on the best disparate-impact gains attainable through continued retraining, enabling developers to certify (e.g., to a court) that additional search is unlikely to help. We also show how stronger distributional assumptions over the model space can yield tighter bounds, and we validate the approach on real-world credit and housing datasets.

---

### Kinematic-Based Assessment of Surgical Actions in Microanastomosis

Authors: Yan Meng, Daniel Donoho, Marcelle Altshuler, Omar Arnaout
Published: 2025-12-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.23942v1

Proficiency in microanastomosis is a critical surgical skill in neurosurgery, where the ability to precisely manipulate fine instruments is crucial to successful outcomes. These procedures require sustained attention, coordinated hand movements, and highly refined motor skills, underscoring the need for objective and systematic methods to evaluate and enhance microsurgical training. Conventional assessment approaches typically rely on expert raters supervising the procedures or reviewing surgical videos, which is an inherently subjective process prone to inter-rater variability, inconsistency, and significant time investment. These limitations highlight the necessity for automated and scalable solutions. To address this challenge, we introduce a novel AI-driven framework for automated action segmentation and performance assessment in microanastomosis procedures, designed to operate efficiently on edge computing platforms. The proposed system comprises three main components: (1) an object tip tracking and localization module based on YOLO and DeepSORT; (2) an action segmentation module leveraging self-similarity matrix for action boundary detection and unsupervised clustering; and (3) a supervised classification module designed to evaluate surgical gesture proficiency. Experimental validation on a dataset of 58 expert-rated microanastomosis videos demonstrates the effectiveness of our approach, achieving a frame-level action segmentation accuracy of 92.4% and an overall skill classification accuracy of 85.5% in replicating expert evaluations. These findings demonstrate the potential of the proposed method to provide objective, real-time feedback in microsurgical education, thereby enabling more standardized, data-driven training protocols and advancing competency assessment in high-stakes surgical environments.

---

### Disentangling Learning from Judgment: Representation Learning for Open Response Analytics

Authors: Conrad Borchers, Manit Patel, Seiyon M. Lee, Anthony F. Botelho
Published: 2025-12-30
Categories: cs.CL, cs.CY
arXiv: https://arxiv.org/abs/2512.23941v2

Open-ended responses are central to learning, yet automated scoring often conflates what students wrote with how teachers grade. We present an analytics-first framework that separates content signals from rater tendencies, making judgments visible and auditable via analytics. Using de-identified ASSISTments mathematics responses, we model teacher histories as dynamic priors and represent text with sentence embeddings. We apply centroid normalization and response-problem embedding differences, and explicitly model teacher effects with priors to reduce problem- and teacher-related confounds. Temporally-validated linear models quantify the contributions of each signal, and model disagreements surface observations for qualitative inspection. Results show that teacher priors heavily influence grade predictions; the strongest results arise when priors are combined with content embeddings (AUC~0.815), while content-only models remain above chance but substantially weaker (AUC~0.626). Adjusting for rater effects sharpens the selection of features derived from content representations, retaining more informative embedding dimensions and revealing cases where semantic evidence supports understanding as opposed to surface-level differences in how students respond. The contribution presents a practical pipeline that transforms embeddings from mere features into learning analytics for reflection, enabling teachers and researchers to examine where grading practices align (or conflict) with evidence of student reasoning and learning.

---

### Learnable Query Aggregation with KV Routing for Cross-view Geo-localisation

Authors: Hualin Ye, Bingxi Liu, Jixiang Du, Yu Qin, Ziyi Chen, Hong Zhang
Published: 2025-12-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.23938v1

Cross-view geo-localisation (CVGL) aims to estimate the geographic location of a query image by matching it with images from a large-scale database. However, the significant view-point discrepancies present considerable challenges for effective feature aggregation and alignment. To address these challenges, we propose a novel CVGL system that incorporates three key improvements. Firstly, we leverage the DINOv2 backbone with a convolution adapter fine-tuning to enhance model adaptability to cross-view variations. Secondly, we propose a multi-scale channel reallocation module to strengthen the diversity and stability of spatial representations. Finally, we propose an improved aggregation module that integrates a Mixture-of-Experts (MoE) routing into the feature aggregation process. Specifically, the module dynamically selects expert subspaces for the keys and values in a cross-attention framework, enabling adaptive processing of heterogeneous input domains. Extensive experiments on the University-1652 and SUES-200 datasets demonstrate that our method achieves competitive performance with fewer trained parameters.

---

### MGML: A Plug-and-Play Meta-Guided Multi-Modal Learning Framework for Incomplete Multimodal Brain Tumor Segmentation

Authors: Yulong Zou, Bo Liu, Cun-Jing Zheng, Yuan-ming Geng, Siyue Li, Qiankun Zuo, Shuihua Wang, Yudong Zhang, Jin Hong
Published: 2025-12-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.23936v1

Leveraging multimodal information from Magnetic Resonance Imaging (MRI) plays a vital role in lesion segmentation, especially for brain tumors. However, in clinical practice, multimodal MRI data are often incomplete, making it challenging to fully utilize the available information. Therefore, maximizing the utilization of this incomplete multimodal information presents a crucial research challenge. We present a novel meta-guided multi-modal learning (MGML) framework that comprises two components: meta-parameterized adaptive modality fusion and consistency regularization module. The meta-parameterized adaptive modality fusion (Meta-AMF) enables the model to effectively integrate information from multiple modalities under varying input conditions. By generating adaptive soft-label supervision signals based on the available modalities, Meta-AMF explicitly promotes more coherent multimodal fusion. In addition, the consistency regularization module enhances segmentation performance and implicitly reinforces the robustness and generalization of the overall framework. Notably, our approach does not alter the original model architecture and can be conveniently integrated into the training pipeline for end-to-end model optimization. We conducted extensive experiments on the public BraTS2020 and BraTS2023 datasets. Compared to multiple state-of-the-art methods from previous years, our method achieved superior performance. On BraTS2020, for the average Dice scores across fifteen missing modality combinations, building upon the baseline, our method obtained scores of 87.55, 79.36, and 62.67 for the whole tumor (WT), the tumor core (TC), and the enhancing tumor (ET), respectively. We have made our source code publicly available at https://github.com/worldlikerr/MGML.

---

### A Proof-of-Concept for Explainable Disease Diagnosis Using Large Language Models and Answer Set Programming

Authors: Ioanna Gemou, Evangelos Lamprou
Published: 2025-12-30
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.23932v1

Accurate disease prediction is vital for timely intervention, effective treatment, and reducing medical complications. While symbolic AI has been applied in healthcare, its adoption remains limited due to the effort required for constructing high-quality knowledge bases. This work introduces McCoy, a framework that combines Large Language Models (LLMs) with Answer Set Programming (ASP) to overcome this barrier. McCoy orchestrates an LLM to translate medical literature into ASP code, combines it with patient data, and processes it using an ASP solver to arrive at the final diagnosis. This integration yields a robust, interpretable prediction framework that leverages the strengths of both paradigms. Preliminary results show McCoy has strong performance on small-scale disease diagnosis tasks.

---

### Assessing generative modeling approaches for free energy estimates in condensed matter

Authors: Maximilian Schebek, Jiajun He, Emil Hoffmann, Yuanqi Du, Frank Noé, Jutta Rogal
Published: 2025-12-30
Categories: cond-mat.stat-mech, cond-mat.mtrl-sci, cs.LG, physics.comp-ph
arXiv: https://arxiv.org/abs/2512.23930v2

The accurate estimation of free energy differences between two states is a long-standing challenge in molecular simulations. Traditional approaches generally rely on sampling multiple intermediate states to ensure sufficient overlap in phase space and are, consequently, computationally expensive. Boltzmann Generators and related generative-model-based methods have recently addressed this challenge by learning a direct probability density transform between two states. However, it remains unclear which approach provides the best trade-off between efficiency, accuracy, and scalability. In this work, we review and benchmark selected generative approaches for condensed-matter systems, including discrete and continuous normalizing flows for targeted free energy perturbation and FEAT (Free Energy Estimators with Adaptive Transport) combined with the escorted Jarzynski equality, using coarse-grained monatomic ice and Lennard-Jones solids as benchmark systems. All models yield highly accurate free energy estimates and, depending on the system, may require fewer energy evaluations than traditional methods. Continuous flows and FEAT are most efficient in energy evaluations, whereas discrete flows have substantially lower inference cost. By releasing all data together with our results, we enable future benchmarking of free energy estimation methods in condensed-phase systems.

---

### Soft Fitted Q-Iteration without Bellman Completeness: Occupancy Reweighting and Temperature Annealing

Authors: Lars van der Laan, Nathan Kallus
Published: 2025-12-30
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2512.23927v3

Fitted \(Q\)-iteration (FQI) is a standard regression-based method for optimal control in offline reinforcement learning, but its stability under function approximation often relies on Bellman completeness, which requires Bellman images of the fitted class to remain in the class. We study Kullback--Leibler (KL)-regularized, or soft, FQI relative to a fixed reference policy without this assumption. Our key insight is that soft control locally inherits the contraction of policy evaluation in a discounted-occupancy norm. At the soft-optimal fixed point, the linearization of the soft Bellman operator is exactly the Bellman operator for the soft-optimal policy, which contracts in its discounted-occupancy norm; projection in the same norm preserves this contraction. Standard soft FQI instead projects under the offline state-action distribution and need not preserve this property. Motivated by this observation, we propose \emph{occupancy-reweighted soft FQI}, which retains standard Bellman targets and least-squares updates while reweighting regressions by discounted-occupancy ratios induced by the current soft policy. Under \(Q\)-function realizability and local regularity, we establish local contraction and finite-sample convergence with estimated ratios, without Bellman completeness. We then use temperature annealing to convert the local result into global convergence from arbitrary initialization: sufficiently high temperature provides a globally contractive starting regime, while gradual cooling connects successive local contraction regions to any prescribed positive target temperature. Under an action-gap margin condition, switching at a fixed positive temperature to hard FQI with refreshed occupancy weights also yields population and finite-sample convergence to the unregularized optimum.

---

### Identification of fixations and saccades in eye-tracking data using adaptive threshold-based method

Authors: Charles Orioma, Josef Krivan, Rujeena Mathema, Pedro Lencastre, Pedro G. Lind, Alexander Szorkovszky, Shailendra Bhandari
Published: 2025-12-30
Categories: cs.NE, nlin.CD
arXiv: https://arxiv.org/abs/2512.23926v3

Properties of ocular fixations and saccades are highly stochastic during many experimental tasks, and their statistics are often used as proxies for various aspects of cognition. Although distinguishing saccades from fixations is not trivial, experimentalists generally use common ad-hoc thresholds in detection algorithms. This neglects inter-task and inter-individual variability in oculomotor dynamics, and potentially biases the resulting statistics. In this article, we introduce and evaluate an adaptive method based on a Markovian approximation of eye-gaze dynamics, using saccades and fixations as states such that the optimal threshold minimizes state transitions. Applying this to three common threshold-based algorithms (velocity, angular velocity, and dispersion), we evaluate the overall accuracy against a multi-threshold benchmark as well as robustness to noise. We find that a velocity threshold achieves the highest baseline accuracy (90-93\%) across both free-viewing and visual search tasks. However, velocity-based methods degrade rapidly under noise when thresholds remain fixed, with accuracy falling below 20% at high noise levels. Adaptive threshold optimization via K-ratio minimization substantially improves performance under noisy conditions for all algorithms. Adaptive dispersion thresholds demonstrate superior noise robustness, maintaining accuracy above 81% even at extreme noise levels (σ = 50 px), though a precision-recall trade-off emerges that favors fixation detection at the expense of saccade identification. In addition to demonstrating our parsimonious adaptive thresholding method, these findings provide practical guidance for selecting and tuning classification algorithms based on data quality and analytical priorities.

---

### Interactive Machine Learning: From Theory to Scale

Authors: Yinglun Zhu
Published: 2025-12-30
Categories: cs.LG, cs.AI, stat.ML
arXiv: https://arxiv.org/abs/2512.23924v1

Machine learning has achieved remarkable success across a wide range of applications, yet many of its most effective methods rely on access to large amounts of labeled data or extensive online interaction. In practice, acquiring high-quality labels and making decisions through trial-and-error can be expensive, time-consuming, or risky, particularly in large-scale or high-stakes settings. This dissertation studies interactive machine learning, in which the learner actively influences how information is collected or which actions are taken, using past observations to guide future interactions. We develop new algorithmic principles and establish fundamental limits for interactive learning along three dimensions: active learning with noisy data and rich model classes, sequential decision making with large action spaces, and model selection under partial feedback. Our results include the first computationally efficient active learning algorithms achieving exponential label savings without low-noise assumptions; the first efficient, general-purpose contextual bandit algorithms whose guarantees are independent of the size of the action space; and the first tight characterizations of the fundamental cost of model selection in sequential decision making. Overall, this dissertation advances the theoretical foundations of interactive learning by developing algorithms that are statistically optimal and computationally efficient, while also providing principled guidance for deploying interactive learning methods in large-scale, real-world settings.

---

### Learning to learn skill assessment for fetal ultrasound scanning

Authors: Yipei Wang, Qianye Yang, Lior Drukker, Aris T. Papageorghiou, Yipeng Hu, J. Alison Noble
Published: 2025-12-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.23920v1

Traditionally, ultrasound skill assessment has relied on expert supervision and feedback, a process known for its subjectivity and time-intensive nature. Previous works on quantitative and automated skill assessment have predominantly employed supervised learning methods, often limiting the analysis to predetermined or assumed factors considered influential in determining skill levels. In this work, we propose a novel bi-level optimisation framework that assesses fetal ultrasound skills by how well a task is performed on the acquired fetal ultrasound images, without using manually predefined skill ratings. The framework consists of a clinical task predictor and a skill predictor, which are optimised jointly by refining the two networks simultaneously. We validate the proposed method on real-world clinical ultrasound videos of scanning the fetal head. The results demonstrate the feasibility of predicting ultrasound skills by the proposed framework, which quantifies optimised task performance as a skill indicator.

---

### Tensor Computing Interface: An Application-Oriented, Lightweight Interface for Portable High-Performance Tensor Network Applications

Authors: Rong-Yang Sun, Tomonori Shirakawa, Hidehiko Kohshiro, D. N. Sheng, Seiji Yunoki
Published: 2025-12-30
Categories: quant-ph, cond-mat.str-el, cs.LG
arXiv: https://arxiv.org/abs/2512.23917v1

Tensor networks (TNs) are a central computational tool in quantum science and artificial intelligence. However, the lack of unified software interface across tensor-computing frameworks severely limits the portability of TN applications, coupling algorithmic development to specific hardware and software back ends. To address this challenge, we introduce the Tensor Computing Interface (TCI) -- an application-oriented, lightweight application programming interface designed to enable framework-independent, high-performance TN applications. TCI provides a well-defined type system that abstracts tensor objects together with a minimal yet expressive set of core functions covering essential tensor manipulations and tensor linear-algebra operations. Through numerical demonstrations on representative tensor-network applications, we show that codes written against TCI can be migrated seamlessly across heterogeneous hardware and software platforms while achieving performance comparable to native framework implementations. We further release an open-source implementation of TCI based on \textit{Cytnx}, demonstrating its practicality and ease of integration with existing tensor-computing frameworks.

---

### Constraint Breeds Generalization: Temporal Dynamics as an Inductive Bias

Authors: Xia Chen
Published: 2025-12-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.23916v2

Conventional deep learning prioritizes unconstrained optimization, yet biological systems operate under strict metabolic constraints. We propose that these physical constraints shape dynamics to function not as limitations, but as a temporal inductive bias that breeds generalization. Through a phase-space analysis of signal propagation, we reveal a fundamental asymmetry: expansive dynamics amplify noise, whereas proper dissipative dynamics compress phase space that aligns with the network's spectral bias, compelling the abstraction of invariant features. This condition can be imposed externally via input encoding, or intrinsically through the network's own temporal dynamics. Both pathways require architectures capable of temporal integration and proper constraints to decode induced invariants, whereas static architectures fail to capitalize on temporal structure. Through comprehensive evaluations across supervised classification, unsupervised reconstruction, and zero-shot reinforcement learning, we demonstrate that a critical "transition" regime maximizes generalization capability. These findings establish dynamical constraints as a distinct class of inductive bias, suggesting that robust AI development requires not only scaling and removing limitations, but computationally mastering the temporal characteristics that naturally promote generalization.

---

### A multimodal Transformer for InSAR-based ground deformation forecasting with cross-site generalization across Europe

Authors: Wendong Yao, Binhua Huang, Soumyabrata Dev
Published: 2025-12-30
Categories: eess.SP, cs.AI, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2512.23906v1

Near-real-time regional-scale monitoring of ground deformation is increasingly required to support urban planning, critical infrastructure management, and natural hazard mitigation. While Interferometric Synthetic Aperture Radar (InSAR) and continental-scale services such as the European Ground Motion Service (EGMS) provide dense observations of past motion, predicting the next observation remains challenging due to the superposition of long-term trends, seasonal cycles, and occasional abrupt discontinuities (e.g., co-seismic steps), together with strong spatial heterogeneity. In this study we propose a multimodal patch-based Transformer for single-step, fixed-interval next-epoch nowcasting of displacement maps from EGMS time series (resampled to a 64x64 grid over 100 km x 100 km tiles). The model ingests recent displacement snapshots together with (i) static kinematic indicators (mean velocity, acceleration, seasonal amplitude) computed in a leakage-safe manner from the training window only, and (ii) harmonic day-of-year encodings. On the eastern Ireland tile (E32N34), the STGCN is strongest in the displacement-only setting, whereas the multimodal Transformer clearly outperforms CNN-LSTM, CNN-LSTM+Attn, and multimodal STGCN when all models receive the same multimodal inputs, achieving RMSE = 0.90 mm and $R^2$ = 0.97 on the test set with the best threshold accuracies.

---

### Rethinking Dense Linear Transformations: Stagewise Pairwise Mixing (SPM) for Near-Linear Training in Neural Networks

Authors: Peter Farag
Published: 2025-12-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.23905v1

Dense linear layers are a dominant source of computational and parametric cost in modern machine learning models, despite their quadratic complexity and often being misaligned with the compositional structure of learned representations. We introduce Stagewise Pairwise Mixers (SPM), a structured linear operator that replaces dense matrices with a composition of sparse pairwise-mixing stages. An SPM layer implements a global linear transformation in $O(nL)$ time with $O(nL)$ parameters, where $L$ is typically constant or $log_2n$, and admits exact closed-form forward and backward computations. SPM is designed as a drop-in replacement for dense linear layers in feedforward networks, recurrent architectures, attention mechanisms, etc. We derive complete forward and backward expressions for two parameterizations: an orthogonal norm-preserving rotation-based variant and a fully general $2 \times 2$ mixing variant. Beyond computational savings, the stagewise structure of SPM induces an explicit compositional inductive bias that constrains model capacity and improves generalization when aligned with task structure. We present proof-of-concept experiments demonstrating substantial reductions in wall-clock cost and improved accuracy on structured learning problems, while retaining competitive performance on real-world benchmarks.

---

### An Agentic LLM Framework for Adverse Media Screening in AML Compliance

Authors: Pavel Chernakov, Sasan Jafarnejad, Raphaël Frank
Published: 2025-12-29
Categories: cs.AI, cs.CL, cs.IR
arXiv: https://arxiv.org/abs/2602.23373v1

Adverse media screening is a critical component of anti-money laundering (AML) and know-your-customer (KYC) compliance processes in financial institutions. Traditional approaches rely on keyword-based searches that generate high false-positive rates or require extensive manual review. We present an agentic system that leverages Large Language Models (LLMs) with Retrieval-Augmented Generation (RAG) to automate adverse media screening. Our system implements a multi-step approach where an LLM agent searches the web, retrieves and processes relevant documents, and computes an Adverse Media Index (AMI) score for each subject. We evaluate our approach using multiple LLM backends on a dataset comprising Politically Exposed Persons (PEPs), persons from regulatory watchlists, and sanctioned persons from OpenSanctions and clean names from academic sources, demonstrating the system's ability to distinguish between high-risk and low-risk individuals.

---

### Althea: The Fact-Checking--Metalearning Tradeoff in AI-Assisted Verification

Authors: Svetlana Churina, Kokil Jaidka, Anab Maulana Barik, Harshit Aneja, Cai Yang, Insyirah Binte Imam Mujtahid, Wynne Hsu, Mong Li Lee
Published: 2025-12-29
Categories: cs.HC, cs.CL
arXiv: https://arxiv.org/abs/2602.11161v3

Fact-checking systems must be scalable and epistemically trustworthy. We introduce Althea, a retrieval-augmented system for user-driven claim evaluation that matches standard pipelines on AVeriTeC while improving supported/refuted discrimination. A longitudinal survey experiment (N=961) treats a ten-day follow-up as a fading test: after modeling a verification procedure, we remove the system and ask whether users reproduce it unaided, testing metalearning rather than one-time accuracy. We compare two AI-assisted treatments, Exploratory (guided reasoning) and Summary (synthesized verdicts), against two baselines, unrelated news and Self-search. The treatments yield the strongest immediate accuracy and confidence gains but do not survive the fading test: on unseen claims they perform no better than news, while Self-search, with no procedure to fade, retains a large advantage. This reveals a factchecking-metalearning tradeoff: conditions that most improve immediate accuracy are least likely to produce metalearning, cautioning against treating AI-delivered verdicts as a source of durable literacy gains.

---

### BIRD: A Museum Open Dataset Combining Behavior Patterns and Identity Types to Better Model Visitors' Experience

Authors: Alexanne Worm, Florian Marchal, Sylvain Castagnos
Published: 2025-12-29
Categories: cs.HC, cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2602.11160v1

Lack of data is a recurring problem in Artificial Intelligence, as it is essential for training and validating models. This is particularly true in the field of cultural heritage, where the number of open datasets is relatively limited and where the data collected does not always allow for holistic modeling of visitors' experience due to the fact that data are ad hoc (i.e. restricted to the sole characteristics required for the evaluation of a specific model). To overcome this lack, we conducted a study between February and March 2019 aimed at obtaining comprehensive and detailed information about visitors, their visit experience and their feedback. We equipped 51 participants with eye-tracking glasses, leaving them free to explore the 3 floors of the museum for an average of 57 minutes, and to discover an exhibition of more than 400 artworks. On this basis, we built an open dataset combining contextual data (demographic data, preferences, visiting habits, motivations, social context. . . ), behavioral data (spatiotemporal trajectories, gaze data) and feedback (satisfaction, fatigue, liked artworks, verbatim. . . ). Our analysis made it possible to re-enact visitor identities combining the majority of characteristics found in the literature and to reproduce the Veron and Levasseur profiles. This dataset will ultimately make it possible to improve the quality of recommended paths in museums by personalizing the number of points of interest (POIs), the time spent at these different POIs, and the amount of information to be provided to each visitor based on their level of interest.

---

### Leveraging Adaptive Group Negotiation for Heterogeneous Multi-Robot Collaboration with Large Language Models

Authors: Siqi Song, Xuanbing Xie, Zonglin Li, Yuqiang Li, Shijie Wang, Biqing Qi
Published: 2025-12-29
Categories: cs.RO, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.06967v1

Multi-robot collaboration tasks often require heterogeneous robots to work together over long horizons under spatial constraints and environmental uncertainties. Although Large Language Models (LLMs) excel at reasoning and planning, their potential for coordinated control has not been fully explored. Inspired by human teamwork, we present CLiMRS (Cooperative Large-Language-Model-Driven Heterogeneous Multi-Robot System), an adaptive group negotiation framework among LLMs for multi-robot collaboration. This framework pairs each robot with an LLM agent and dynamically forms subgroups through a general proposal planner. Within each subgroup, a subgroup manager leads perception-driven multi-LLM discussions to get commands for actions. Feedback is provided by both robot execution outcomes and environment changes. This grouping-planning-execution-feedback loop enables efficient planning and robust execution. To evaluate these capabilities, we introduce CLiMBench, a heterogeneous multi-robot benchmark of challenging assembly tasks. Our experiments show that CLiMRS surpasses the best baseline, achieving over 40% higher efficiency on complex tasks without sacrificing success on simpler ones. Overall, our results demonstrate that leveraging human-inspired group formation and negotiation principles significantly enhances the efficiency of heterogeneous multi-robot collaboration. Our code is available here: https://github.com/song-siqi/CLiMRS.

---

### An Empirical Analysis of Fine-Tuning Large Language Models on Bioinformatics Literature: PRSGPT and BioStarsGPT

Authors: Muhammad Muneeb, David B. Ascher
Published: 2025-12-29
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.11573v1

Large language models (LLMs) often lack specialized knowledge for complex bioinformatics applications. We present a reproducible pipeline for fine-tuning LLMs on specialized bioinformatics data, demonstrated through two use cases: PRSGPT, focused on polygenic risk score (PRS) tools, and BioStarsGPT, trained on community forum discussions. The nine-step pipeline integrates diverse data sources, structured preprocessing, prompt-based question-answer (QA) generation (via Google Gemini), natural language inference (NLI) for quality control, semantic deduplication, clustering-based data splitting, and parameter-efficient fine-tuning using LoRA. We fine-tuned three LLMs (LLaMA-3.2-3B, Qwen2.5-7B, Gemma) and benchmarked them on over 14 lexical and semantic metrics. Qwen2.5-7B emerged as the best performer, with BLEU-4 and ROUGE-1 improvements of 82\% and 70\% for PRSGPT and 6\% and 18\% for BioStarsGPT, respectively. The open-source datasets produced include over 28,000 QA pairs for PRSGPT and 154,282 for BioStarsGPT. Human evaluation of PRSGPT yielded 61.9\% accuracy on the PRS tools comparison task, comparable to Google Gemini (61.4\%), but with richer methodological detail and accurate citations. BioStarsGPT demonstrated 59\% conceptual accuracy across 142 curated bioinformatics questions. Our pipeline enables scalable, domain-specific fine-tuning of LLMs. It enables privacy-preserving, locally deployable bioinformatics assistants, explores their practical applications, and addresses the challenges, limitations, and mitigation strategies associated with their development and use.

---

### Discrete Semantic States and Hamiltonian Dynamics in LLM Embedding Spaces

Authors: Timo Aukusti Laine
Published: 2025-12-29
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.11572v1

We investigate the structure of Large Language Model (LLM) embedding spaces using mathematical concepts, particularly linear algebra and the Hamiltonian formalism, drawing inspiration from analogies with quantum mechanical systems. Motivated by the observation that LLM embeddings exhibit distinct states, suggesting discrete semantic representations, we explore the application of these mathematical tools to analyze semantic relationships. We demonstrate that the L2 normalization constraint, a characteristic of many LLM architectures, results in a structured embedding space suitable for analysis using a Hamiltonian formalism. We derive relationships between cosine similarity and perturbations of embedding vectors, and explore direct and indirect semantic transitions. Furthermore, we explore a quantum-inspired perspective, deriving an analogue of zero-point energy and discussing potential connections to Koopman-von Neumann mechanics. While the interpretation warrants careful consideration, our results suggest that this approach offers a promising avenue for gaining deeper insights into LLMs and potentially informing new methods for mitigating hallucinations.

---

### Benchmarking Cross-Lingual Semantic Alignment in Multilingual Embeddings

Authors: Wen G. Gong
Published: 2025-12-29
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.09732v1

With hundreds of multilingual embedding models available, practitioners lack clear guidance on which provide genuine cross-lingual semantic alignment versus task performance through language-specific patterns. Task-driven benchmarks (MTEB) may mask fundamental alignment shortcomings. We introduce Semantic Affinity (SA), a bounded (between 0 and 1) metric measuring inter-lingual to intra-lingual spread ratio using cosine distance, combined with PHATE visualization in our Semanscope framework. Benchmarking 13 models across 4 datasets (52 experiments) reveals a three-tier structure: (1) Top BERT models (LaBSE SA = 0.70, USE SA = 0.68, S-BERT SA = 0.68) achieve strong alignment via translation-pair supervision; (2) LLM embeddings plateau at SA between 0.55 and 0.61 regardless of 0.6 B to 8 B scale; (3) MLM-only BERT models (mBERT, XLM-R, SA < 0.50) fail despite more than 100 language training. Training objective, not architecture or scale, determines alignment. Oracle Bone primitives (1200 BCE) expose semantic drift-models learn corpus patterns rather than cognitive primitives. This work provides semantic benchmarking to help practitioners select quality multilingual embeddings from hundreds of available models, showing cross-lingual alignment requires explicit translation supervision, not merely model scale or multilingual data.

---

### Geometric Patterns of Meaning: A PHATE Manifold Analysis of Multi-lingual Embeddings

Authors: Wen G Gong
Published: 2025-12-29
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.09731v1

We introduce a multi-level analysis framework for examining semantic geometry in multilingual embeddings, implemented through Semanscope (a visualization tool that applies PHATE manifold learning across four linguistic levels). Analysis of diverse datasets spanning sub-character components, alphabetic systems, semantic domains, and numerical concepts reveals systematic geometric patterns and critical limitations in current embedding models. At the sub-character level, purely structural elements (Chinese radicals) exhibit geometric collapse, highlighting model failures to distinguish semantic from structural components. At the character level, different writing systems show distinct geometric signatures. At the word level, content words form clustering-branching patterns across 20 semantic domains in English, Chinese, and German. Arabic numbers organize through spiral trajectories rather than clustering, violating standard distributional semantics assumptions. These findings establish PHATE manifold learning as an essential analytic tool not only for studying geometric structure of meaning in embedding space, but also for validating the effectiveness of embedding models in capturing semantic relationships.

---

### OptFormer: Optical Flow-Guided Attention and Phase Space Reconstruction for SST Forecasting

Authors: Yin Wang, Chunlin Gong, Zhuozhen Xu, Lehan Zhang, Xiang Wu
Published: 2025-12-29
Categories: cs.CV, physics.ao-ph
arXiv: https://arxiv.org/abs/2601.06078v1

Sea Surface Temperature (SST) prediction plays a vital role in climate modeling and disaster forecasting. However, it remains challenging due to its nonlinear spatiotemporal dynamics and extended prediction horizons. To address this, we propose OptFormer, a novel encoder-decoder model that integrates phase-space reconstruction with a motion-aware attention mechanism guided by optical flow. Unlike conventional attention, our approach leverages inter-frame motion cues to highlight relative changes in the spatial field, allowing the model to focus on dynamic regions and capture long-range temporal dependencies more effectively. Experiments on NOAA SST datasets across multiple spatial scales demonstrate that OptFormer achieves superior performance under a 1:1 training-to-prediction setting, significantly outperforming existing baselines in accuracy and robustness.

---

### One if by Land, Two if by Sea, Three if by Four Seas, and More to Come -- Values of Perception, Prediction, Communication, and Common Sense in Decision Making

Authors: Aolin Xu
Published: 2025-12-29
Categories: cs.IT, cs.AI, cs.LG, math.OC
arXiv: https://arxiv.org/abs/2601.06077v2

This work aims to rigorously define the values of perception, prediction, communication, and common sense in decision making. The defined quantities are decision-theoretic, but have information-theoretic analogues, e.g., they share some simple but key mathematical properties with Shannon entropy and mutual information, and can reduce to these quantities in particular settings. One interesting observation is that, the value of perception without prediction can be negative, while the value of perception together with prediction and the value of prediction alone are always nonnegative. The defined quantities suggest answers to practical questions arising in the design of autonomous decision-making systems. Example questions include: Do we need to observe and predict the behavior of a particular agent? How important is it? What is the best order to observe and predict the agents? The defined quantities may also provide insights to cognitive science and neural science, toward the understanding of how natural decision makers make use of information gained from different sources and operations.

---

### Jamming Detection in Cell-Free MIMO with Dynamic Graphs

Authors: Ali Hossary, Laura Crosara, Stefano Tomasin
Published: 2025-12-29
Categories: cs.IT, cs.AI
arXiv: https://arxiv.org/abs/2601.06075v1

Jamming attacks pose a critical threat to wireless networks, particularly in cell-free massive MIMO systems, where distributed access points and user equipment (UE) create complex, time-varying topologies. This paper proposes a novel jamming detection framework leveraging dynamic graphs and graph convolutional neural networks (GCN) to address this challenge. By modeling the network as a dynamic graph, we capture evolving communication links and detect jamming attacks as anomalies in the graph evolution. A GCN-Transformer-based model, trained with supervised learning, learns graph embeddings to identify malicious interference. Performance evaluation in simulated scenarios with moving UEs, varying jamming conditions and channel fadings, demonstrates the method's effectiveness, which is assessed through accuracy and F1 score metrics, achieving promising results for effective jamming detection.

---

### La norme technique comme catalyseur de transfert de connaissances : la francophonie a l'œuvre dans le domaine de l'{é}ducation

Authors: Mokhtar Ben Henda
Published: 2025-12-29
Categories: cs.CY, cs.CL
arXiv: https://arxiv.org/abs/2601.06069v1

Standards are adopted in a wide range of fields, both technical and industrial, as well as socio-economic, cultural and linguistic. They are presented explicitly as laws and regulations, technical and industrial standards or implicitly in the form of unwritten social standards. However, in a globalization marked by a very fine mosaic of socio-cultural identities, the question arises in relation to the construction of global, transparent and coherent systems in which considerable work of consensus is necessary to ensure all types of transfers and their local adaptations. The focus here is on the global education ecosystem which develops its own standards for the transfer of knowledge and socio-cultural values through learning, teaching and training. Subcommittee 36 of the International Organization for Standardization is one of the structures of this ecosystem in which the Francophonie participates to develop international standards for distance education on the basis of universal consensus.

---

### HyperTopo-Adapters: Geometry- and Topology-Aware Segmentation of Leaf Lesions on Frozen Encoders

Authors: Chimdi Walter Ndubuisi, Toni Kazic
Published: 2025-12-29
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.06067v1

Leaf-lesion segmentation is topology-sensitive: small merges, splits, or false holes can be biologically meaningful descriptors of biochemical pathways, yet they are weakly penalized by standard pixel-wise losses in Euclidean latents. I explore HyperTopo-Adapters, a lightweight, parameter-efficient head trained on top of a frozen vision encoder, which embeds features on a product manifold -- hyperbolic + Euclidean + spherical (H + E + S) -- to encourage hierarchical separation (H), local linear detail (E), and global closure (S). A topology prior complements Dice/BCE in two forms: (i) persistent-homology (PH) distance for evaluation and selection, and (ii) a differentiable surrogate that combines a soft Euler-characteristic match with total variation regularization for stable training. I introduce warm-ups for both the hyperbolic contrastive term and the topology prior, per-sample evaluation of structure-aware metrics (Boundary-F1, Betti errors, PD distance), and a min-PD within top-K Dice rule for checkpoint selection. On a Kaggle leaf-lesion dataset (N=2,940), early results show consistent gains in boundary and topology metrics (reducing Delta beta_1 hole error by 9%) while Dice/IoU remain competitive. The study is diagnostic by design: I report controlled ablations (curvature learning, latent dimensions, contrastive temperature, surrogate settings), and ongoing tests varying encoder strength (ResNet-50, DeepLabV3, DINOv2/v3), input resolution, PH weight, and partial unfreezing of late blocks. The contribution is an open, reproducible train/eval suite (available at https://github.com/ChimdiWalter/HyperTopo-Adapters) that isolates geometric/topological priors and surfaces failure modes to guide stronger, topology-preserving architectures.

---

### Evolving Cognitive Architectures

Authors: Alexander Serov
Published: 2025-12-29
Categories: q-bio.NC, cs.AI, cs.NE
arXiv: https://arxiv.org/abs/2601.05277v1

This article proposes a research and development direction that would lead to the creation of next-generation intelligent technical systems. A distinctive feature of these systems is their ability to undergo evolutionary change. Cognitive architectures are now one of the most promising ways to create Artificial General Intelligence systems. One of the main problems of modern cognitive architectures is an excessively schematic approach to modeling the processes of cognitive activity. It does not allow the creation of a universal architecture that would be capable of reproducing higher nervous functions without using a predetermined set of perception patterns. Our paper proposes an evolutionary approach to creating a cognitive architecture. The basis of this approach is the use of a functional core, which consistently generates the intellectual functions of an autonomous agent. We are considering a cognitive architecture that includes components, the interaction of which ensures the evolution of the agent. The discussion of the development of intelligence is carried out using the conceptual apparatus of semiotics. This allows us to consider the task of developing cognitive functions as a problem of establishing a connection between the Merkwelt and the Werkwelt through the creation of the Innenwelt. The problem of early postnatal ontogenesis is investigated on the basis of the theory of constructivism: we discuss the requirements for the functional core and its composition, as well as the mechanism that initiates the process of cognition.

---

### A Quantum Model for Constrained Markowitz Modern Portfolio Using Slack Variables to Process Mixed-Binary Optimization under QAOA

Authors: Pablo Thomassin, Guillaume Guerard, Sonia Djebali, Vincent Marc Lambert
Published: 2025-12-29
Categories: math.OC, cs.AI
arXiv: https://arxiv.org/abs/2601.03278v1

Effectively encoding inequality constraints is a primary obstacle in applying quantum algorithms to financial optimization. A quantum model for Markowitz portfolio optimization is presented that resolves this by embedding slack variables directly into the problem Hamiltonian. The method maps each slack variable to a dedicated ancilla qubit, transforming the problem into a Quadratic Unconstrained Binary Optimization (QUBO) formulation suitable for the Quantum Approximate Optimization Algorithm (QAOA). This process internalizes the constraints within the quantum state, altering the problem's energy landscape to facilitate optimization. The model is empirically validated through simulation, showing it consistently finds the optimal portfolio where a standard penalty-based QAOA fails. This work demonstrates that modifying the Hamiltonian architecture via a slack-ancilla scheme provides a robust and effective pathway for solving constrained optimization problems on quantum computers. A fundamental quantum limit on the simultaneous precision of portfolio risk and return is also posited.

---

### AI-Native Integrated Sensing and Communications for Self-Organizing Wireless Networks: Architectures, Learning Paradigms, and System-Level Design

Authors: S. Zhang, M. Feizarefi, A. F. Mirzaei
Published: 2025-12-29
Categories: cs.NI, cs.AI
arXiv: https://arxiv.org/abs/2601.02398v1

Integrated Sensing and Communications (ISAC) is emerging as a foundational paradigm for next-generation wireless networks, enabling communication infrastructures to simultaneously support data transmission and environment sensing. By tightly coupling radio sensing with communication functions, ISAC unlocks new capabilities for situational awareness, localization, tracking, and network adaptation. At the same time, the increasing scale, heterogeneity, and dynamics of future wireless systems demand self-organizing network intelligence capable of autonomously managing resources, topology, and services. Artificial intelligence (AI), particularly learning-driven and data-centric methods, has become a key enabler for realizing this vision. This survey provides a comprehensive and system-level review of AI-native ISAC-enabled self-organizing wireless networks. We develop a unified taxonomy that spans: (i) ISAC signal models and sensing modalities, (ii) network state abstraction and perception from sensing-aware radio data, (iii) learning-driven self-organization mechanisms for resource allocation, topology control, and mobility management, and (iv) cross-layer architectures integrating sensing, communication, and network intelligence. We further examine emerging learning paradigms, including deep reinforcement learning, graph-based learning, multi-agent coordination, and federated intelligence that enable autonomous adaptation under uncertainty, mobility, and partial observability. Practical considerations such as sensing-communication trade-offs, scalability, latency, reliability, and security are discussed alongside representative evaluation methodologies and performance metrics. Finally, we identify key open challenges and future research directions toward deployable, trustworthy, and scalable AI-native ISAC systems for 6G and beyond.

---

### Comment on: Your Brain on ChatGPT: Accumulation of Cognitive Debt When Using an AI Assistant for Essay Writing Tasks

Authors: Milos Stankovic, Ella Hirche, Sarah Kollatzsch, Julia Nadine Doetsch
Published: 2025-12-29
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.00856v1

Recently published work titled Your Brain on ChatGPT: Accumulation of Cognitive Debt When Using an AI Assistant for Essay Writing Task by Kosmyna et al. (2025) has sparked a vivid debate on the topic of artificial intelligence (AI) and human performance. We sincerely congratulate Kosmyna et al. for initiating such important research, collecting a valuable dataset, and establishing highly automated pipelines for Natural Language Processing (NLP) analyses and scoring. We aim to provide constructive comments that may improve the manuscript's readiness for peer-reviewed publication, as some results by Kosmyna et al. (2025) could be interpreted more conservatively. Our primary concerns focus on: (i) study design considerations, including the limited sample size; (ii) the reproducibility of the analyses; (iii) methodological issues related to the EEG analysis; (iv) inconsistencies in the reporting of results; and (v) limited transparency in several aspects of the study's procedures and findings.

---

### Physically-Constrained Autoencoder-Assisted Bayesian Optimization for Refinement of High-Dimensional Defect-Sensitive Single Crystalline Structure

Authors: Joseph Oche Agada, Andrew McAninch, Haley Day, Yasemin Tanyu, Ewan McCombs, Seyed M. Koohpayeh, Brian H. Toby, Yishu Wang, Arpan Biswas
Published: 2025-12-29
Categories: cond-mat.mtrl-sci, cs.LG
arXiv: https://arxiv.org/abs/2601.00855v1

Physical properties and functionalities of materials are dictated by global crystal structures as well as local defects. To establish a structure-property relationship, not only the crystallographic symmetry but also quantitative knowledge about defects are required. Here we present a hybrid Machine Learning framework that integrates a physically-constrained variational-autoencoder (pcVAE) with different Bayesian Optimization (BO) methods to systematically accelerate and improve crystal structure refinement with resolution of defects. We chose the pyrochlore structured Ho2Ti2O7 as a model system and employed the GSAS2 package for benchmarking crystallographic parameters from Rietveld refinement. However, the function space of these material systems is highly nonlinear, which limits optimizers like traditional Rietveld refinement, into trapping at local minima. Also, these naive methods don't provide an extensive learning about the overall function space, which is essential for large space, large time consuming explorations to identify various potential regions of interest. Thus, we present the approach of exploring the high Dimensional structure parameters of defect sensitive systems via pretrained pcVAE assisted BO and Sparse Axis Aligned BO. The pcVAE projects high-Dimensional diffraction data consisting of thousands of independently measured diffraction orders into a lowD latent space while enforcing scaling invariance and physical relevance. Then via BO methods, we aim to minimize the L2 norm based chisq errors in the real and latent spaces separately between experimental and simulated diffraction patterns, thereby steering the refinement towards potential optimum crystal structure parameters. We investigated and compared the results among different pcVAE assisted BO, non pcVAE assisted BO, and Rietveld refinement.

---

### Motion-Compensated Latent Semantic Canvases for Visual Situational Awareness on Edge

Authors: Igor Lodin, Sergii Filatov, Vira Filatova, Dmytro Filatov
Published: 2025-12-29
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.00854v1

We propose Motion-Compensated Latent Semantic Canvases (MCLSC) for visual situational awareness on resource-constrained edge devices. The core idea is to maintain persistent semantic metadata in two latent canvases - a slowly accumulating static layer and a rapidly updating dynamic layer - defined in a baseline coordinate frame stabilized from the video stream. Expensive panoptic segmentation (Mask2Former) runs asynchronously and is motion-gated: inference is triggered only when motion indicates new information, while stabilization/motion compensation preserves a consistent coordinate system for latent semantic memory. On prerecorded 480p clips, our prototype reduces segmentation calls by >30x and lowers mean end-to-end processing time by >20x compared to naive per-frame segmentation, while maintaining coherent static/dynamic semantic overlays.

---

### FedSCAM (Federated Sharpness-Aware Minimization with Clustered Aggregation and Modulation): Scam-resistant SAM for Robust Federated Optimization in Heterogeneous Environments

Authors: Sameer Rahil, Zain Abdullah Ahmad, Talha Asif
Published: 2025-12-29
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.00853v1

Federated Learning (FL) enables collaborative model training across decentralized edge devices while preserving data privacy. However, statistical heterogeneity among clients, often manifested as non-IID label distributions, poses significant challenges to convergence and generalization. While Sharpness-Aware Minimization (SAM) has been introduced to FL to seek flatter, more robust minima, existing approaches typically apply a uniform perturbation radius across all clients, ignoring client-specific heterogeneity. In this work, we propose \textbf{FedSCAM} (Federated Sharpness-Aware Minimization with Clustered Aggregation and Modulation), a novel algorithm that dynamically adjusts the SAM perturbation radius and aggregation weights based on client-specific heterogeneity scores. By calculating a heterogeneity metric for each client and modulating the perturbation radius inversely to this score, FedSCAM prevents clients with high variance from destabilizing the global model. Furthermore, we introduce a heterogeneity-aware weighted aggregation mechanism that prioritizes updates from clients that align with the global optimization direction. Extensive experiments on CIFAR-10 and Fashion-MNIST under various degrees of Dirichlet-based label skew demonstrate that FedSCAM achieves competitive performance among state-of-the-art baselines, including FedSAM, FedLESAM, etc. in terms of convergence speed and final test accuracy.

---

### Autonomous battery research: Principles of heuristic operando experimentation

Authors: Emily Lu, Gabriel Perez, Peter Baker, Daniel Irving, Santosh Kumar, Veronica Celorrio, Sylvia Britto, Thomas F. Headen, Miguel Gomez-Gonzalez, Connor Wright, Calum Green, Robert Scott Young et al.
Published: 2025-12-29
Categories: physics.ins-det, cond-mat.mtrl-sci, cs.LG
arXiv: https://arxiv.org/abs/2601.00851v1

Unravelling the complex processes governing battery degradation is critical to the energy transition, yet the efficacy of operando characterisation is severely constrained by a lack of Reliability, Representativeness, and Reproducibility (the 3Rs). Current methods rely on bespoke hardware and passive, pre-programmed methodologies that are ill-equipped to capture stochastic failure events. Here, using the Rutherford Appleton Laboratory's multi-modal toolkit as a case study, we expose the systemic inability of conventional experiments to capture transient phenomena like dendrite initiation. To address this, we propose Heuristic Operando experiments: a framework where an AI pilot leverages physics-based digital twins to actively steer the beamline to predict and deterministically capture these rare events. Distinct from uncertainty-driven active learning, this proactive search anticipates failure precursors, redefining experimental efficiency via an entropy-based metric that prioritises scientific insight per photon, neutron, or muon. By focusing measurements only on mechanistically decisive moments, this framework simultaneously mitigates beam damage and drastically reduces data redundancy. When integrated with FAIR data principles, this approach serves as a blueprint for the trusted autonomous battery laboratories of the future.

---

### EdgeJury: Cross-Reviewed Small-Model Ensembles for Truthful Question Answering on Serverless Edge Inference

Authors: Aayush Kumar
Published: 2025-12-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.00850v1

Hallucinations hinder reliable question answering, especially in resource-constrained deployments where frontier-scale models or retrieval pipelines may be impractical. We present EdgeJury, a lightweight ensemble framework that improves truthfulness and robustness using only small instruction-tuned language models (3B-8B) suitable for serverless edge inference. EdgeJury orchestrates four stages: (1) parallel role-specialized generation, (2) anonymized cross-review with structured critiques and rankings, (3) chairman synthesis that integrates the strongest content while addressing flagged issues, and (4) claim-level consistency labeling based on inter-model agreement. On TruthfulQA (MC1), EdgeJury achieves 76.2% accuracy (95% CI: 72.8-79.6%), a +21.4% relative improvement over a single 8B baseline (62.8%), and outperforms standard baselines including self-consistency and majority voting under transparent compute accounting (total tokens and platform cost reported). On a 200-question adversarial EdgeCases set, EdgeJury yields +48.2% relative gains (95% CI: 44.0-52.4%). Manual analysis on 100 incorrect answers shows an approximately 55% reduction in factual hallucination errors versus the single-model baseline. Deployed on Cloudflare Workers AI, EdgeJury achieves 8.4 s median end-to-end latency, demonstrating that coordinated small-model ensembles can improve truthfulness on misconception-heavy QA benchmarks without external retrieval or proprietary large-model APIs.

---

### Temporal Attack Pattern Detection in Multi-Agent AI Workflows: An Open Framework for Training Trace-Based Security Models

Authors: Ron F. Del Rosario
Published: 2025-12-29
Categories: cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2601.00848v1

We present an openly documented methodology for fine-tuning language models to detect temporal attack patterns in multi-agent AI workflows using OpenTelemetry trace analysis. We curate a dataset of 80,851 examples from 18 public cybersecurity sources and 35,026 synthetic OpenTelemetry traces. We apply iterative QLoRA fine-tuning on resource-constrained ARM64 hardware (NVIDIA DGX Spark) through three training iterations with strategic augmentation. Our custom benchmark accuracy improves from 42.86% to 74.29%, a statistically significant 31.4-point gain. Targeted examples addressing specific knowledge gaps outperform indiscriminate scaling. Key contributions include: (1) synthetic trace generation methodology for multi-agent coordination attacks and regulatory violations, (2) empirical evidence that training data composition fundamentally determines behavior, and (3) complete open release of datasets, training scripts, and evaluation benchmarks on HuggingFace. While practical deployment requires human oversight due to false positive rates, this work establishes the first reproducible framework enabling practitioners to build custom agentic security models adapted to their threat landscapes.

---