# Research Papers — 2025-12 · bundle page 62 of 175

> Full-text markdown of papers #3051–3100 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/62
[← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/61.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-12/page/63.md)

### Make-It-Poseable: Feed-forward Latent Posing Model for 3D Characters

Authors: Zhiyang Guo, Ori Zhang, Jax Xiang, Alan Zhao, Zhenxun Yuan, Wengang Zhou, Houqiang Li
Published: 2025-12-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.16767v3

Posing 3D characters is a fundamental task in computer graphics. However, existing paradigms, ranging from traditional auto-rigging to recent pose-conditioned generative models, frequently struggle with inaccurate skinning weights, fixed mesh topologies, and poor pose conformance. These challenges have become particularly pronounced with the recent explosion of AI-generated 3D assets, which often exhibit flawed structures and fused geometry. To address these issues, we introduce \textbf{Make-It-Poseable}, a novel feed-forward framework that reformulates character posing as a skinning-free latent-space transformation problem. By decoupling shape deformation from the constraints of fixed mesh connectivity, our method directly operates on compact latent representations to reconstruct characters in target poses. To achieve this, our framework integrates a latent posing transformer for shape manipulation, a dense pose representation for fine-grained control, and an adaptive completion module optimized via a bipartite-matched latent loss to robustly handle topological changes. Extensive experiments demonstrate that our method significantly outperforms existing baselines in posing quality. Furthermore, our design shows promising generalization to diverse morphologies such as quadrupeds in our qualitative tests, and supports various 3D authoring applications such as part replacement and refinement.

---

### Make-It-Poseable: Feed-forward Latent Posing Model for 3D Humanoid Character Animation

Authors: Zhiyang Guo, Ori Zhang, Jax Xiang, Alan Zhao, Wengang Zhou, Houqiang Li
Published: 2025-12-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.16767v1

Posing 3D characters is a fundamental task in computer graphics and vision. However, existing methods like auto-rigging and pose-conditioned generation often struggle with challenges such as inaccurate skinning weight prediction, topological imperfections, and poor pose conformance, limiting their robustness and generalizability. To overcome these limitations, we introduce Make-It-Poseable, a novel feed-forward framework that reformulates character posing as a latent-space transformation problem. Instead of deforming mesh vertices as in traditional pipelines, our method reconstructs the character in new poses by directly manipulating its latent representation. At the core of our method is a latent posing transformer that manipulates shape tokens based on skeletal motion. This process is facilitated by a dense pose representation for precise control. To ensure high-fidelity geometry and accommodate topological changes, we also introduce a latent-space supervision strategy and an adaptive completion module. Our method demonstrates superior performance in posing quality. It also naturally extends to 3D editing applications like part replacement and refinement.

---

### Pattern recognition in complex systems via vector-field representations of spatio-temporal data

Authors: Ingrid Amaranta Membrillo Solis, Maria van Rossem, Tristan Madeleine, Tetiana Orlova, Nina Podoliak, Giampaolo D'Alessandro, Jacek Brodzki, Malgosia Kaczmarek
Published: 2025-12-18
Categories: cs.LG, cond-mat.soft, nlin.CD, nlin.PS
arXiv: https://arxiv.org/abs/2512.16763v1

A complex system comprises multiple interacting entities whose interdependencies form a unified whole, exhibiting emergent behaviours not present in individual components. Examples include the human brain, living cells, soft matter, Earth's climate, ecosystems, and the economy. These systems exhibit high-dimensional, non-linear dynamics, making their modelling, classification, and prediction particularly challenging. Advances in information technology have enabled data-driven approaches to studying such systems. However, the sheer volume and complexity of spatio-temporal data often hinder traditional methods like dimensionality reduction, phase-space reconstruction, and attractor characterisation. This paper introduces a geometric framework for analysing spatio-temporal data from complex systems, grounded in the theory of vector fields over discrete measure spaces. We propose a two-parameter family of metrics suitable for data analysis and machine learning applications. The framework supports time-dependent images, image gradients, and real- or vector-valued functions defined on graphs and simplicial complexes. We validate our approach using data from numerical simulations of biological and physical systems on flat and curved domains. Our results show that the proposed metrics, combined with multidimensional scaling, effectively address key analytical challenges. They enable dimensionality reduction, mode decomposition, phase-space reconstruction, and attractor characterisation. Our findings offer a robust pathway for understanding complex dynamical systems, especially in contexts where traditional modelling is impractical but abundant experimental data are available.

---

### NRGPT: An Energy-based Alternative for GPT

Authors: Nima Dehmamy, Benjamin Hoover, Bishwajit Saha, Leo Kozachkov, Jean-Jacques Slotine, Dmitry Krotov
Published: 2025-12-18
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.16762v3

Generative Pre-trained Transformer (GPT) architectures are the most popular design for language modeling. Energy-based modeling is a different paradigm that views inference as a dynamical process operating on an energy landscape. We propose a minimal modification of the GPT setting to unify it with the EBM framework. The inference step of our model, which we call eNeRgy-GPT (NRGPT), is conceptualized as an exploration of the tokens on the energy landscape. We prove, and verify empirically, that under certain circumstances this exploration becomes gradient descent, although they don't necessarily lead to the best performing models. We demonstrate that our model performs well for simple language (Shakespeare dataset), algebraic ListOPS tasks, and richer settings such as OpenWebText language modeling. We also observe that our models may be more resistant to overfitting, doing so only during very long training.

---

### NRGPT: An Energy-based Alternative for GPT

Authors: Nima Dehmamy, Benjamin Hoover, Bishwajit Saha, Leo Kozachkov, Jean-Jacques Slotine, Dmitry Krotov
Published: 2025-12-18
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.16762v1

Generative Pre-trained Transformer (GPT) architectures are the most popular design for language modeling. Energy-based modeling is a different paradigm that views inference as a dynamical process operating on an energy landscape. We propose a minimal modification of the GPT setting to unify it with the EBM framework. The inference step of our model, which we call eNeRgy-GPT (NRGPT), is conceptualized as an exploration of the tokens on the energy landscape. We prove, and verify empirically, that under certain circumstances this exploration becomes gradient descent, although they don't necessarily lead to the best performing models. We demonstrate that our model performs well for simple language (Shakespeare dataset), algebraic ListOPS tasks, and richer settings such as OpenWebText language modeling. We also observe that our models may be more resistant to overfitting, doing so only during very long training.

---

### CitySeeker: How Do VLMS Explore Embodied Urban Navigation With Implicit Human Needs?

Authors: Siqi Wang, Chao Liang, Yunfan Gao, Erxin Yu, Sen Li, Yushi Li, Jing Li, Haofen Wang
Published: 2025-12-18
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.16755v1

Vision-Language Models (VLMs) have made significant progress in explicit instruction-based navigation; however, their ability to interpret implicit human needs (e.g., "I am thirsty") in dynamic urban environments remains underexplored. This paper introduces CitySeeker, a novel benchmark designed to assess VLMs' spatial reasoning and decision-making capabilities for exploring embodied urban navigation to address implicit needs. CitySeeker includes 6,440 trajectories across 8 cities, capturing diverse visual characteristics and implicit needs in 7 goal-driven scenarios. Extensive experiments reveal that even top-performing models (e.g., Qwen2.5-VL-32B-Instruct) achieve only 21.1% task completion. We find key bottlenecks in error accumulation in long-horizon reasoning, inadequate spatial cognition, and deficient experiential recall. To further analyze them, we investigate a series of exploratory strategies-Backtracking Mechanisms, Enriching Spatial Cognition, and Memory-Based Retrieval (BCR), inspired by human cognitive mapping's emphasis on iterative observation-reasoning cycles and adaptive path optimization. Our analysis provides actionable insights for developing VLMs with robust spatial intelligence required for tackling "last-mile" navigation challenges.

---

### Plausibility as Failure: How LLMs and Humans Co-Construct Epistemic Error

Authors: Claudia Vale Oliveira, Nelson Zagalo, Filipe Silva, Anabela Brandao, Syeda Faryal Hussain Khurrum, Joaquim Santos
Published: 2025-12-18
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2512.16750v1

Large language models (LLMs) are increasingly used as epistemic partners in everyday reasoning, yet their errors remain predominantly analyzed through predictive metrics rather than through their interpretive effects on human judgment. This study examines how different forms of epistemic failure emerge, are masked, and are tolerated in human AI interaction, where failure is understood as a relational breakdown shaped by model-generated plausibility and human interpretive judgment. We conducted a three round, multi LLM evaluation using interdisciplinary tasks and progressively differentiated assessment frameworks to observe how evaluators interpret model responses across linguistic, epistemic, and credibility dimensions. Our findings show that LLM errors shift from predictive to hermeneutic forms, where linguistic fluency, structural coherence, and superficially plausible citations conceal deeper distortions of meaning. Evaluators frequently conflated criteria such as correctness, relevance, bias, groundedness, and consistency, indicating that human judgment collapses analytical distinctions into intuitive heuristics shaped by form and fluency. Across rounds, we observed a systematic verification burden and cognitive drift. As tasks became denser, evaluators increasingly relied on surface cues, allowing erroneous yet well formed answers to pass as credible. These results suggest that error is not solely a property of model behavior but a co-constructed outcome of generative plausibility and human interpretive shortcuts. Understanding AI epistemic failure therefore requires reframing evaluation as a relational interpretive process, where the boundary between system failure and human miscalibration becomes porous. The study provides implications for LLM assessment, digital literacy, and the design of trustworthy human AI communication.

---

### TreeNet: A Light Weight Model for Low Bitrate Image Compression

Authors: Mahadev Prasad Panda, Purnachandra Rao Makkena, Srivatsa Prativadibhayankaram, Siegfried Fößel, André Kaup
Published: 2025-12-18
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2512.16743v1

Reducing computational complexity remains a critical challenge for the widespread adoption of learning-based image compression techniques. In this work, we propose TreeNet, a novel low-complexity image compression model that leverages a binary tree-structured encoder-decoder architecture to achieve efficient representation and reconstruction. We employ attentional feature fusion mechanism to effectively integrate features from multiple branches. We evaluate TreeNet on three widely used benchmark datasets and compare its performance against competing methods including JPEG AI, a recent standard in learning-based image compression. At low bitrates, TreeNet achieves an average improvement of 4.83% in BD-rate over JPEG AI, while reducing model complexity by 87.82%. Furthermore, we conduct extensive ablation studies to investigate the influence of various latent representations within TreeNet, offering deeper insights into the factors contributing to reconstruction.

---

### Machine Learning Algorithms: Detection Official Hajj and Umrah Travel Agency Based on Text and Metadata Analysis

Authors: Wisnu Uriawan, Muhamad Veva Ramadhan, Firman Adi Nugraha, Hasbi Nur Wahid, M Dantha Arianvasya, Muhammad Zaki Alghifari
Published: 2025-12-18
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.16742v1

The rapid digitalization of Hajj and Umrah services in Indonesia has significantly facilitated pilgrims but has concurrently opened avenues for digital fraud through counterfeit mobile applications. These fraudulent applications not only inflict financial losses but also pose severe privacy risks by harvesting sensitive personal data. This research aims to address this critical issue by implementing and evaluating machine learning algorithms to verify application authenticity automatically. Using a comprehensive dataset comprising both official applications registered with the Ministry of Religious Affairs and unofficial applications circulating on app stores, we compare the performance of three robust classifiers: Support Vector Machine (SVM), Random Forest (RF), and Na"ive Bayes (NB). The study utilizes a hybrid feature extraction methodology that combines Textual Analysis (TF-IDF) of application descriptions with Metadata Analysis of sensitive access permissions. The experimental results indicate that the SVM algorithm achieves the highest performance with an accuracy of 92.3%, a precision of 91.5%, and an F1-score of 92.0%. Detailed feature analysis reveals that specific keywords related to legality and high-risk permissions (e.g., READ PHONE STATE) are the most significant discriminators. This system is proposed as a proactive, scalable solution to enhance digital trust in the religious tourism sector, potentially serving as a prototype for a national verification system.

---

### Task-Oriented Data Synthesis and Control-Rectify Sampling for Remote Sensing Semantic Segmentation

Authors: Yunkai Yang, Yudong Zhang, Kunquan Zhang, Jinxiao Zhang, Xinying Chen, Haohuan Fu, Runmin Dong
Published: 2025-12-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.16740v2

With the rapid progress of controllable generation, training data synthesis has become a promising way to expand labeled datasets and alleviate manual annotation in remote sensing (RS). However, the complexity of semantic mask control and the uncertainty of sampling quality often limit the utility of synthetic data in downstream semantic segmentation tasks. To address these challenges, we propose a task-oriented data synthesis framework (TODSynth), including a Multimodal Diffusion Transformer (MM-DiT) with unified triple attention and a plug-and-play sampling strategy guided by task feedback. Built upon the powerful DiT-based generative foundation model, we systematically evaluate different control schemes, showing that a text-image-mask joint attention scheme combined with full fine-tuning of the image and mask branches significantly enhances the effectiveness of RS semantic segmentation data synthesis, particularly in few-shot and complex-scene scenarios. Furthermore, we propose a control-rectify flow matching (CRFM) method, which dynamically adjusts sampling directions guided by semantic loss during the early high-plasticity stage, mitigating the instability of generated images and bridging the gap between synthetic data and downstream segmentation tasks. Extensive experiments demonstrate that our approach consistently outperforms state-of-the-art controllable generation methods, producing more stable and task-oriented synthetic data for RS semantic segmentation.

---

### Task-Oriented Data Synthesis and Control-Rectify Sampling for Remote Sensing Semantic Segmentation

Authors: Yunkai Yang, Yudong Zhang, Kunquan Zhang, Jinxiao Zhang, Xinying Chen, Haohuan Fu, Runmin Dong
Published: 2025-12-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.16740v1

With the rapid progress of controllable generation, training data synthesis has become a promising way to expand labeled datasets and alleviate manual annotation in remote sensing (RS). However, the complexity of semantic mask control and the uncertainty of sampling quality often limit the utility of synthetic data in downstream semantic segmentation tasks. To address these challenges, we propose a task-oriented data synthesis framework (TODSynth), including a Multimodal Diffusion Transformer (MM-DiT) with unified triple attention and a plug-and-play sampling strategy guided by task feedback. Built upon the powerful DiT-based generative foundation model, we systematically evaluate different control schemes, showing that a text-image-mask joint attention scheme combined with full fine-tuning of the image and mask branches significantly enhances the effectiveness of RS semantic segmentation data synthesis, particularly in few-shot and complex-scene scenarios. Furthermore, we propose a control-rectify flow matching (CRFM) method, which dynamically adjusts sampling directions guided by semantic loss during the early high-plasticity stage, mitigating the instability of generated images and bridging the gap between synthetic data and downstream segmentation tasks. Extensive experiments demonstrate that our approach consistently outperforms state-of-the-art controllable generation methods, producing more stable and task-oriented synthetic data for RS semantic segmentation.

---

### AI-Driven Prediction of Cancer Pain Episodes: A Hybrid Decision Support Approach

Authors: Yipeng Zhuang, Yifeng Guo, Yuewen Li, Yuheng Wu, Philip Leung-Ho Yu, Tingting Song, Zhiyong Wang, Kunzhong Zhou, Weifang Wang, Li Zhuang
Published: 2025-12-18
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.16739v2

Lung cancer patients frequently experience breakthrough pain episodes, with up to 91% requiring timely intervention. To enable proactive pain management, we propose a hybrid machine learning and large language model pipeline that predicts pain episodes within 48 and 72 hours of hospitalization using both structured and unstructured electronic health record data. A retrospective cohort of 266 inpatients was analyzed, with features including demographics, tumor stage, vital signs, and WHO-tiered analgesic use. The machine learning module captured temporal medication trends, while the large language model interpreted ambiguous dosing records and free-text clinical notes. Integrating these modalities improved sensitivity and interpretability. Our framework achieved an accuracy of 0.876 (48h) and 0.917 (72h), with improvements in sensitivity of 10.6% and 10.7%, respectively, attributable to large language model augmentation. This hybrid approach offers a clinically interpretable and scalable tool for early pain episode forecasting, with potential to enhance treatment precision and optimize resource allocation in oncology care.

---

### AI-Driven Prediction of Cancer Pain Episodes: A Hybrid Decision Support Approach

Authors: Yipeng Zhuang, Yifeng Guo, Yuewen Li, Yuheng Wu, Philip Leung-Ho Yu, Tingting Song, Zhiyong Wang, Kunzhong Zhou, Weifang Wang, Li Zhuang
Published: 2025-12-18
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.16739v1

Lung cancer patients frequently experience breakthrough pain episodes, with up to 91% requiring timely intervention. To enable proactive pain management, we propose a hybrid machine learning and large language model pipeline that predicts pain episodes within 48 and 72 hours of hospitalization using both structured and unstructured electronic health record data. A retrospective cohort of 266 inpatients was analyzed, with features including demographics, tumor stage, vital signs, and WHO-tiered analgesic use. The machine learning module captured temporal medication trends, while the large language model interpreted ambiguous dosing records and free-text clinical notes. Integrating these modalities improved sensitivity and interpretability. Our framework achieved an accuracy of 0.874 (48h) and 0.917 (72h), with an improvement in sensitivity of 8.6% and 10.4% due to the augmentation of large language model. This hybrid approach offers a clinically interpretable and scalable tool for early pain episode forecasting, with potential to enhance treatment precision and optimize resource allocation in oncology care.

---

### Autonomous Assessment of Generalizability of AI Agent Capabilities

Authors: Daniel Bramblett, Rushang Karia, Adrian Ciotinga, Pulkit Verma, YooJung Choi, Siddharth Srivastava
Published: 2025-12-18
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.16733v4

Safe deployment of black-box AI (BBAI) systems such as foundation model agents requires methods for evaluating their capabilities in novel settings. We define an agent's capability as its ability to achieve a short term objective and formalize the problem of learning models that predict whether, with what effects, and under what conditions, an agent can perform a capability. We introduce Monte Carlo Query Search (MCQS), an active query-synthesis method for learning symbolic stochastic capability models of BBAIs. MCQS models capabilities as conditional probability distributions over outcomes and formulates capability evaluation as an active learning problem over policies. We use Monte Carlo tree search to synthesize queries that maximally distinguish between extremal capability hypotheses: the lattice meet and join corresponding to the most pessimistic and optimistic models consistent with observed behavior. Executing these queries yields trajectories that prune inconsistent hypotheses. We prove soundness, completeness, and convergence properties under standard realizability and sampling assumptions. Experiments with multiple BBAI systems show that MCQS learns accurate capability models more efficiently than baseline query strategies, enabling systematic characterization of agent capability boundaries with fewer interactions.

---

### Discovering and Learning Probabilistic Models of Black-Box AI Capabilities

Authors: Daniel Bramblett, Rushang Karia, Adrian Ciotinga, Ruthvick Suresh, Pulkit Verma, YooJung Choi, Siddharth Srivastava
Published: 2025-12-18
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.16733v1

Black-box AI (BBAI) systems such as foundational models are increasingly being used for sequential decision making. To ensure that such systems are safe to operate and deploy, it is imperative to develop efficient methods that can provide a sound and interpretable representation of the BBAI's capabilities. This paper shows that PDDL-style representations can be used to efficiently learn and model an input BBAI's planning capabilities. It uses the Monte-Carlo tree search paradigm to systematically create test tasks, acquire data, and prune the hypothesis space of possible symbolic models. Learned models describe a BBAI's capabilities, the conditions under which they can be executed, and the possible outcomes of executing them along with their associated probabilities. Theoretical results show soundness, completeness and convergence of the learned models. Empirical results with multiple BBAI systems illustrate the scope, efficiency, and accuracy of the presented methods.

---

### OMG-Bench: A New Challenging Benchmark for Skeleton-based Online Micro Hand Gesture Recognition

Authors: Haochen Chang, Pengfei Ren, Buyuan Zhang, Da Li, Tianhao Han, Haoyang Zhang, Liang Xie, Hongbo Chen, Erwei Yin
Published: 2025-12-18
Categories: cs.CV, cs.HC
arXiv: https://arxiv.org/abs/2512.16727v2

Online micro gesture recognition from hand skeletons is critical for VR/AR interaction but faces challenges due to limited public datasets and task-specific algorithms. Micro gestures involve subtle motion patterns, which make constructing datasets with precise skeletons and frame-level annotations difficult. To this end, we develop a multi-view self-supervised pipeline to automatically generate skeleton data, complemented by heuristic rules and expert refinement for semi-automatic annotation. Based on this pipeline, we introduce OMG-Bench, the first large-scale public benchmark for skeleton-based online micro gesture recognition. It features 40 fine-grained gesture classes with 13,948 instances across 1,272 sequences, characterized by subtle motions, rapid dynamics, and continuous execution. To tackle these challenges, we propose Hierarchical Memory-Augmented Transformer (HMATr), an end-to-end framework that unifies gesture detection and classification by leveraging hierarchical memory banks which store frame-level details and window-level semantics to preserve historical context. In addition, it employs learnable position-aware queries initialized from the memory to implicitly encode gesture positions and semantics. Experiments show that HMATr outperforms state-of-the-art methods by 7.6% in detection rate, establishing a strong baseline for online micro gesture recognition. Project page: https://omg-bench.github.io/

---

### OMG-Bench: A New Challenging Benchmark for Skeleton-based Online Micro Hand Gesture Recognition

Authors: Haochen Chang, Pengfei Ren, Buyuan Zhang, Da Li, Tianhao Han, Haoyang Zhang, Liang Xie, Hongbo Chen, Erwei Yin
Published: 2025-12-18
Categories: cs.CV, cs.HC
arXiv: https://arxiv.org/abs/2512.16727v1

Online micro gesture recognition from hand skeletons is critical for VR/AR interaction but faces challenges due to limited public datasets and task-specific algorithms. Micro gestures involve subtle motion patterns, which make constructing datasets with precise skeletons and frame-level annotations difficult. To this end, we develop a multi-view self-supervised pipeline to automatically generate skeleton data, complemented by heuristic rules and expert refinement for semi-automatic annotation. Based on this pipeline, we introduce OMG-Bench, the first large-scale public benchmark for skeleton-based online micro gesture recognition. It features 40 fine-grained gesture classes with 13,948 instances across 1,272 sequences, characterized by subtle motions, rapid dynamics, and continuous execution. To tackle these challenges, we propose Hierarchical Memory-Augmented Transformer (HMATr), an end-to-end framework that unifies gesture detection and classification by leveraging hierarchical memory banks which store frame-level details and window-level semantics to preserve historical context. In addition, it employs learnable position-aware queries initialized from the memory to implicitly encode gesture positions and semantics. Experiments show that HMATr outperforms state-of-the-art methods by 7.6\% in detection rate, establishing a strong baseline for online micro gesture recognition. Project page: https://omg-bench.github.io/

---

### VERM: Leveraging Foundation Models to Create a Virtual Eye for Efficient 3D Robotic Manipulation

Authors: Yixiang Chen, Yan Huang, Keji He, Peiyan Li, Liang Wang
Published: 2025-12-18
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2512.16724v1

When performing 3D manipulation tasks, robots have to execute action planning based on perceptions from multiple fixed cameras. The multi-camera setup introduces substantial redundancy and irrelevant information, which increases computational costs and forces the model to spend extra training time extracting crucial task-relevant details. To filter out redundant information and accurately extract task-relevant features, we propose the VERM (Virtual Eye for Robotic Manipulation) method, leveraging the knowledge in foundation models to imagine a virtual task-adaptive view from the constructed 3D point cloud, which efficiently captures necessary information and mitigates occlusion. To facilitate 3D action planning and fine-grained manipulation, we further design a depth-aware module and a dynamic coarse-to-fine procedure. Extensive experimental results on both simulation benchmark RLBench and real-world evaluations demonstrate the effectiveness of our method, surpassing previous state-of-the-art methods while achieving 1.89x speedup in training time and 1.54x speedup in inference speed. More results can be found on our project website at https://verm-ral.github.io .

---

### KOSS: Kalman-Optimal Selective State Spaces for Long-Term Sequence Modeling

Authors: Lei Wang, Xin Tan, Mingwei Wang, Ying Zhang
Published: 2025-12-18
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.16723v1

Recent selective state space models (SSMs), such as Mamba and Mamba-2, have demonstrated strong performance in sequence modeling owing to input-dependent selection mechanisms. However, these mechanisms lack theoretical grounding and cannot support context-aware selection from latent state dynamics. To address these limitations, we propose KOSS, a Kalman-optimal Selective State Space model that formulates selection as latent state uncertainty minimization. Derived from estimation theory, KOSS adopts a continuous-time latent update driven by a Kalman gain that dynamically modulates information propagation based on content and context, enabling a closed-loop, context-aware selectivity mechanism. To ensure stable computation and near-linear scalability, KOSS employs global spectral differentiation for frequency-domain derivative estimation, along with a segment-wise scan for hardware-efficient processing. On a selective copying task with distractors, KOSS achieves over 79\% accuracy while baselines drop below 20\%, demonstrating robust context-aware selection. Furthermore, across nine long-term forecasting benchmarks, KOSS reduces MSE by 2.92--36.23\% and consistently outperforms state-of-the-art models in both accuracy and stability. To assess real-world applicability, a case study on secondary surveillance radar (SSR) tracking confirms KOSS's robustness under irregular intervals and noisy conditions and demonstrates its effectiveness in real-world applications. Finally, supplementary experiments verify Kalman gain convergence and the frequency response of spectral differentiation, providing theoretical support for the proposed closed-loop design.

---

### Polyharmonic Spline Packages: Composition, Efficient Procedures for Computation and Differentiation

Authors: Yuriy N. Bakhvalov
Published: 2025-12-18
Categories: cs.LG, math.NA
arXiv: https://arxiv.org/abs/2512.16718v1

In a previous paper it was shown that a machine learning regression problem can be solved within the framework of random function theory, with the optimal kernel analytically derived from symmetry and indifference principles and coinciding with a polyharmonic spline. However, a direct application of that solution is limited by O(N^3) computational cost and by a breakdown of the original theoretical assumptions when the input space has excessive dimensionality. This paper proposes a cascade architecture built from packages of polyharmonic splines that simultaneously addresses scalability and is theoretically justified for problems with unknown intrinsic low dimensionality. Efficient matrix procedures are presented for forward computation and end-to-end differentiation through the cascade.

---

### Phishing Detection System: An Ensemble Approach Using Character-Level CNN and Feature Engineering

Authors: Rudra Dubey, Arpit Mani Tripathi, Archit Srivastava, Sarvpal Singh
Published: 2025-12-18
Categories: cs.LG, cs.CR
arXiv: https://arxiv.org/abs/2512.16717v1

In actuality, phishing attacks remain one of the most prevalent cybersecurity risks in existence today, with malevolent actors constantly changing their strategies to successfully trick users. This paper presents an AI model for a phishing detection system that uses an ensemble approach to combine character-level Convolutional Neural Networks (CNN) and LightGBM with engineered features. Our system uses a character-level CNN to extract sequential features after extracting 36 lexical, structural, and domain-based features from the URLs. On a test dataset of 19,873 URLs, the ensemble model achieves an accuracy of 99.819 percent, precision of 100 percent, recall of 99.635 percent, and ROC-AUC of 99.947 percent. Through a FastAPI-based service with an intuitive user interface, the suggested system has been utilised to offer real-time detection. In contrast, the results demonstrate that the suggested solution performs better than individual models; LightGBM contributes 40 percent and character-CNN contributes 60 percent to the final prediction. The suggested method maintains extremely low false positive rates while doing a good job of identifying contemporary phishing techniques. Index Terms - Phishing detection, machine learning, deep learning, CNN, ensemble methods, cybersecurity, URL analysis

---

### Towards Reproducibility in Predictive Process Mining: SPICE -- A Deep Learning Library

Authors: Oliver Stritzel, Nick Hühnerbein, Simon Rauch, Itzel Zarate, Lukas Fleischmann, Moike Buck, Attila Lischka, Christian Frey
Published: 2025-12-18
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.16715v3

In recent years, Predictive Process Mining (PPM) techniques based on artificial neural networks have evolved as a method for monitoring the future behavior of unfolding business processes and predicting Key Performance Indicators (KPIs). However, many PPM approaches often lack reproducibility, transparency in decision making, usability for incorporating novel datasets and benchmarking, making comparisons among different implementations very difficult. In this paper, we propose SPICE, a Python framework that reimplements three popular, existing baseline deep-learning-based methods for PPM in PyTorch, while designing a common base framework with rigorous configurability to enable reproducible and robust comparison of past and future modelling approaches. We compare SPICE to original reported metrics and with fair metrics on 11 datasets.

---

### Towards Reproducibility in Predictive Process Mining: SPICE - A Deep Learning Library

Authors: Oliver Stritzel, Nick Hühnerbein, Simon Rauch, Itzel Zarate, Lukas Fleischmann, Moike Buck, Attila Lischka, Christian Frey
Published: 2025-12-18
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.16715v1

In recent years, Predictive Process Mining (PPM) techniques based on artificial neural networks have evolved as a method for monitoring the future behavior of unfolding business processes and predicting Key Performance Indicators (KPIs). However, many PPM approaches often lack reproducibility, transparency in decision making, usability for incorporating novel datasets and benchmarking, making comparisons among different implementations very difficult. In this paper, we propose SPICE, a Python framework that reimplements three popular, existing baseline deep-learning-based methods for PPM in PyTorch, while designing a common base framework with rigorous configurability to enable reproducible and robust comparison of past and future modelling approaches. We compare SPICE to original reported metrics and with fair metrics on 11 datasets.

---

### A multi-centre, multi-device benchmark dataset for landmark-based comprehensive fetal biometry

Authors: Chiara Di Vece, Zhehua Mao, Netanell Avisdris, Brian Dromey, Raffaele Napolitano, Dafna Ben Bashat, Francisco Vasconcelos, Danail Stoyanov, Leo Joskowicz, Sophia Bano
Published: 2025-12-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.16710v2

Accurate fetal growth assessment from ultrasound (US) relies on precise biometry measured by manually identifying anatomical landmarks in standard planes. Manual landmarking is time-consuming, operator-dependent, and sensitive to variability across scanners and sites, limiting the reproducibility of automated approaches. There is a need for multi-source annotated datasets to develop artificial intelligence-assisted fetal growth assessment methods. To address this bottleneck, we present an open, multi-centre, multi-device benchmark dataset of fetal US images with expert anatomical landmark annotations for clinically used fetal biometric measurements. These measurements include head bi-parietal and occipito-frontal diameters, abdominal transverse and antero-posterior diameters, and femoral length. The dataset comprises 4,513 de-identified US images from 1,904 subjects acquired at three clinical sites using seven different US devices. We provide standardised, subject-disjoint train/test splits, evaluation code, and baseline results to enable fair and reproducible comparison of methods. Using an automatic biometry model, we quantify domain shift and demonstrate that training and evaluation confined to a single centre substantially overestimate performance relative to multi-centre testing. To the best of our knowledge, this is the first publicly available multi-centre, multi-device, landmark-annotated dataset that covers all primary fetal biometry measures, providing a robust benchmark for domain adaptation and multi-centre generalisation in fetal biometry and enabling more reliable AI-assisted fetal growth assessment across centres. All data, annotations, training code, and evaluation pipelines are made publicly available.

---

### A multi-centre, multi-device benchmark dataset for landmark-based comprehensive fetal biometry

Authors: Chiara Di Vece, Zhehua Mao, Netanell Avisdris, Brian Dromey, Raffaele Napolitano, Dafna Ben Bashat, Francisco Vasconcelos, Danail Stoyanov, Leo Joskowicz, Sophia Bano
Published: 2025-12-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.16710v1

Accurate fetal growth assessment from ultrasound (US) relies on precise biometry measured by manually identifying anatomical landmarks in standard planes. Manual landmarking is time-consuming, operator-dependent, and sensitive to variability across scanners and sites, limiting the reproducibility of automated approaches. There is a need for multi-source annotated datasets to develop artificial intelligence-assisted fetal growth assessment methods. To address this bottleneck, we present an open, multi-centre, multi-device benchmark dataset of fetal US images with expert anatomical landmark annotations for clinically used fetal biometric measurements. These measurements include head bi-parietal and occipito-frontal diameters, abdominal transverse and antero-posterior diameters, and femoral length. The dataset contains 4,513 de-identified US images from 1,904 subjects acquired at three clinical sites using seven different US devices. We provide standardised, subject-disjoint train/test splits, evaluation code, and baseline results to enable fair and reproducible comparison of methods. Using an automatic biometry model, we quantify domain shift and demonstrate that training and evaluation confined to a single centre substantially overestimate performance relative to multi-centre testing. To the best of our knowledge, this is the first publicly available multi-centre, multi-device, landmark-annotated dataset that covers all primary fetal biometry measures, providing a robust benchmark for domain adaptation and multi-centre generalisation in fetal biometry and enabling more reliable AI-assisted fetal growth assessment across centres. All data, annotations, training code, and evaluation pipelines are made publicly available.

---

### Dual Computational Horizons: Incompleteness and Unpredictability in Intelligent Systems

Authors: Abhisek Ganguly
Published: 2025-12-18
Categories: cs.AI, cs.LO
arXiv: https://arxiv.org/abs/2512.16707v2

We formalize two independent computational limitations that constrain algorithmic intelligence: formal incompleteness and dynamical unpredictability. The former limits the deductive power of consistent reasoning systems while the latter bounds long-term prediction under finite precision. We show that these two extrema together impose structural bounds on an agent's ability to reason about its own predictive capabilities. In particular, an algorithmic agent cannot verify its own maximal prediction horizon universally. This perspective clarifies inherent trade-offs between reasoning, prediction, and self-analysis in intelligent systems. The construction presented here constitutes one representative instance of a broader logical class of such limitations.

---

### Dual Computational Horizons: Incompleteness and Unpredictability in Intelligent Systems

Authors: Abhisek Ganguly
Published: 2025-12-18
Categories: cs.AI, cs.LO
arXiv: https://arxiv.org/abs/2512.16707v1

We formalize two independent computational limitations that constrain algorithmic intelligence: formal incompleteness and dynamical unpredictability. The former limits the deductive power of consistent reasoning systems while the later bounds long-term prediction under finite precision. We show that these two extrema together impose structural bounds on an agent's ability to reason about its own predictive capabilities. In particular, an algorithmic agent cannot compute its own maximal prediction horizon generally. This perspective clarifies inherent trade-offs between reasoning, prediction, and self-analysis in intelligent systems.

---

### SDFoam: Signed-Distance Foam for explicit surface reconstruction

Authors: Antonella Rech, Nicola Conci, Nicola Garau
Published: 2025-12-18
Categories: cs.CV, cs.GR
arXiv: https://arxiv.org/abs/2512.16706v1

Neural radiance fields (NeRF) have driven impressive progress in view synthesis by using ray-traced volumetric rendering. Splatting-based methods such as 3D Gaussian Splatting (3DGS) provide faster rendering by rasterizing 3D primitives. RadiantFoam (RF) brought ray tracing back, achieving throughput comparable to Gaussian Splatting by organizing radiance with an explicit Voronoi Diagram (VD). Yet, all the mentioned methods still struggle with precise mesh reconstruction. We address this gap by jointly learning an explicit VD with an implicit Signed Distance Field (SDF). The scene is optimized via ray tracing and regularized by an Eikonal objective. The SDF introduces metric-consistent isosurfaces, which, in turn, bias near-surface Voronoi cell faces to align with the zero level set. The resulting model produces crisper, view-consistent surfaces with fewer floaters and improved topology, while preserving photometric quality and maintaining training speed on par with RadiantFoam. Across diverse scenes, our hybrid implicit-explicit formulation, which we name SDFoam, substantially improves mesh reconstruction accuracy (Chamfer distance) with comparable appearance (PSNR, SSIM), without sacrificing efficiency.

---

### Olaf: Bringing an Animated Character to Life in the Physical World

Authors: David Müller, Espen Knoop, Dario Mylonopoulos, Agon Serifi, Michael A. Hopkins, Ruben Grandia, Moritz Bächer
Published: 2025-12-18
Categories: cs.RO, cs.LG
arXiv: https://arxiv.org/abs/2512.16705v2

Animated characters often move in non-physical ways and have proportions that are far from a typical walking robot. This provides an ideal platform for innovation in both mechanical design and stylized motion control. In this paper, we bring Olaf to life in the physical world, relying on reinforcement learning guided by animation references for control. To create the illusion of Olaf's feet moving along his body, we hide two asymmetric legs under a soft foam skirt. To fit actuators inside the character, we use spherical and planar linkages in the arms, mouth, and eyes. Because the walk cycle results in harsh contact sounds, we introduce additional rewards that noticeably reduce impact noise. The large head, driven by small actuators in the character's slim neck, creates a risk of overheating, amplified by the costume. To keep actuators from overheating, we feed temperature values as additional inputs to policies, introducing new rewards to keep them within bounds. We validate the efficacy of our modeling in simulation and on hardware, demonstrating an unmatched level of believability for a costumed robotic character.

---

### Olaf: Bringing an Animated Character to Life in the Physical World

Authors: David Müller, Espen Knoop, Dario Mylonopoulos, Agon Serifi, Michael A. Hopkins, Ruben Grandia, Moritz Bächer
Published: 2025-12-18
Categories: cs.RO, cs.LG
arXiv: https://arxiv.org/abs/2512.16705v1

Animated characters often move in non-physical ways and have proportions that are far from a typical walking robot. This provides an ideal platform for innovation in both mechanical design and stylized motion control. In this paper, we bring Olaf to life in the physical world, relying on reinforcement learning guided by animation references for control. To create the illusion of Olaf's feet moving along his body, we hide two asymmetric legs under a soft foam skirt. To fit actuators inside the character, we use spherical and planar linkages in the arms, mouth, and eyes. Because the walk cycle results in harsh contact sounds, we introduce additional rewards that noticeably reduce impact noise. The large head, driven by small actuators in the character's slim neck, creates a risk of overheating, amplified by the costume. To keep actuators from overheating, we feed temperature values as additional inputs to policies, introducing new rewards to keep them within bounds. We validate the efficacy of our modeling in simulation and on hardware, demonstrating an unmatched level of believability for a costumed robotic character.

---

### How accurate are foundational machine learning interatomic potentials for heterogeneous catalysis?

Authors: Luuk H. E. Kempen, Raffaele Cheula, Mie Andersen
Published: 2025-12-18
Categories: cond-mat.mtrl-sci, cs.LG, physics.chem-ph
arXiv: https://arxiv.org/abs/2512.16702v1

Foundational machine learning interatomic potentials (MLIPs) are being developed at a rapid pace, promising closer and closer approximation to ab initio accuracy. This unlocks the possibility to simulate much larger length and time scales. However, benchmarks for these MLIPs are usually limited to ordered, crystalline and bulk materials. Hence, reported performance does not necessarily accurately reflect MLIP performance in real applications such as heterogeneous catalysis. Here, we systematically analyze zero-shot performance of 80 different MLIPs, evaluating tasks typical for heterogeneous catalysis across a range of different data sets, including adsorption and reaction on surfaces of alloyed metals, oxides, and metal-oxide interfacial systems. We demonstrate that current-generation foundational MLIPs can already perform at high accuracy for applications such as predicting vacancy formation energies of perovskite oxides or zero-point energies of supported nanoclusters. However, limitations also exist. We find that many MLIPs catastrophically fail when applied to magnetic materials, and structure relaxation in the MLIP generally increases the energy prediction error compared to single-point evaluation of a previously optimized structure. Comparing low-cost task-specific models to foundational MLIPs, we highlight some core differences between these model approaches and show that -- if considering only accuracy -- these models can compete with the current generation of best-performing MLIPs. Furthermore, we show that no single MLIP universally performs best, requiring users to investigate MLIP suitability for their desired application.

---

### Cyber Humanism in Education: Reclaiming Agency through AI and Learning Sciences

Authors: Giovanni Adorni
Published: 2025-12-18
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.16701v1

Generative Artificial Intelligence (GenAI) is rapidly reshaping how knowledge is produced and validated in education. Rather than adding another digital tool, large language models reconfigure reading, writing, and coding into hybrid human-AI workflows, raising concerns about epistemic automation, cognitive offloading, and the de-professiona\-lisation of teachers. This paper proposes \emph{Cyber Humanism in Education} as a framework for reclaiming human agency in this landscape. We conceptualise AI-enabled learning environments as socio-technical infrastructures co-authored by humans and machines, and position educators and learners as epistemic agents and \emph{algorithmic citizens} who have both the right and the responsibility to shape these infrastructures. We articulate three pillars for cyber-humanist design, \emph{reflexive competence}, \emph{algorithmic citizenship}, and \emph{dialogic design}, and relate them to major international digital and AI competence frameworks. We then present higher-education case studies that operationalise these ideas through \emph{prompt-based learning} and a new \emph{Conversational AI Educator} certification within the EPICT ecosystem. The findings show how such practices can strengthen epistemic agency while surfacing tensions around workload, equity, and governance, and outline implications for the future of AI-rich, human-centred education.

---

### CLARiTy: A Vision Transformer for Multi-Label Classification and Weakly-Supervised Localization of Chest X-ray Pathologies

Authors: John M. Statheros, Hairong Wang, Richard Klein
Published: 2025-12-18
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.16700v1

The interpretation of chest X-rays (CXRs) poses significant challenges, particularly in achieving accurate multi-label pathology classification and spatial localization. These tasks demand different levels of annotation granularity but are frequently constrained by the scarcity of region-level (dense) annotations. We introduce CLARiTy (Class Localizing and Attention Refining Image Transformer), a vision transformer-based model for joint multi-label classification and weakly-supervised localization of thoracic pathologies. CLARiTy employs multiple class-specific tokens to generate discriminative attention maps, and a SegmentCAM module for foreground segmentation and background suppression using explicit anatomical priors. Trained on image-level labels from the NIH ChestX-ray14 dataset, it leverages distillation from a ConvNeXtV2 teacher for efficiency. Evaluated on the official NIH split, the CLARiTy-S-16-512 (a configuration of CLARiTy), achieves competitive classification performance across 14 pathologies, and state-of-the-art weakly-supervised localization performance on 8 pathologies, outperforming prior methods by 50.7%. In particular, pronounced gains occur for small pathologies like nodules and masses. The lower-resolution variant of CLARiTy, CLARiTy-S-16-224, offers high efficiency while decisively surpassing baselines, thereby having the potential for use in low-resource settings. An ablation study confirms contributions of SegmentCAM, DINO pretraining, orthogonal class token loss, and attention pooling. CLARiTy advances beyond CNN-ViT hybrids by harnessing ViT self-attention for global context and class-specific localization, refined through convolutional background suppression for precise, noise-reduced heatmaps.

---

### Do Multi-Agents Solve Better Than Single? Evaluating Agentic Frameworks for Diagram-Grounded Geometry Problem Solving and Reasoning

Authors: Mahbub E Sobhani, Md. Faiyaz Abdullah Sayeedi, Mohammad Nehad Alam, Proma Hossain Progga, Swakkhar Shatabda
Published: 2025-12-18
Categories: cs.AI, cs.CG
arXiv: https://arxiv.org/abs/2512.16698v1

Diagram-grounded geometry problem solving is a critical benchmark for multimodal large language models (MLLMs), yet the benefits of multi-agent design over single-agent remain unclear. We systematically compare single-agent and multi-agent pipelines on four visual math benchmarks: Geometry3K, MathVerse, OlympiadBench, and We-Math. For open-source models, multi-agent consistently improves performance. For example, Qwen-2.5-VL (7B) gains +6.8 points and Qwen-2.5-VL (32B) gains +3.3 on Geometry3K, and both Qwen-2.5-VL variants see further gains on OlympiadBench and We-Math. In contrast, the closed-source Gemini-2.0-Flash generally performs better in single-agent mode on classic benchmarks, while multi-agent yields only modest improvements on the newer We-Math dataset. These findings show that multi-agent pipelines provide clear benefits for open-source models and can assist strong proprietary systems on newer, less familiar benchmarks, but agentic decomposition is not universally optimal. All code, data, and reasoning files are available at https://github.com/faiyazabdullah/Interpreter-Solver

---

### Unsupervised Thematic Clustering Of hadith Texts Using The Apriori Algorithm

Authors: Wisnu Uriawan, Achmad Ajie Priyajie, Angga Gustian, Fikri Nur Hidayat, Sendi Ahmad Rafiudin, Muhamad Fikri Zaelani
Published: 2025-12-18
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.16694v1

This research stems from the urgency to automate the thematic grouping of hadith in line with the growing digitalization of Islamic texts. Based on a literature review, the unsupervised learning approach with the Apriori algorithm has proven effective in identifying association patterns and semantic relations in unlabeled text data. The dataset used is the Indonesian Translation of the hadith of Bukhari, which first goes through preprocessing stages including case folding, punctuation cleaning, tokenization, stopword removal, and stemming. Next, an association rule mining analysis was conducted using the Apriori algorithm with support, confidence, and lift parameters. The results show the existence of meaningful association patterns such as the relationship between rakaat-prayer, verse-revelation, and hadith-story, which describe the themes of worship, revelation, and hadith narration. These findings demonstrate that the Apriori algorithm has the ability to automatically uncover latent semantic relationships, while contributing to the development of digital Islamic studies and technology-based learning systems.

---

### Detecting Localized Deepfakes: How Well Do Synthetic Image Detectors Handle Inpainting?

Authors: Serafino Pandolfini, Lorenzo Pellegrini, Matteo Ferrara, Davide Maltoni
Published: 2025-12-18
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.16688v1

The rapid progress of generative AI has enabled highly realistic image manipulations, including inpainting and region-level editing. These approaches preserve most of the original visual context and are increasingly exploited in cybersecurity-relevant threat scenarios. While numerous detectors have been proposed for identifying fully synthetic images, their ability to generalize to localized manipulations remains insufficiently characterized. This work presents a systematic evaluation of state-of-the-art detectors, originally trained for the deepfake detection on fully synthetic images, when applied to a distinct challenge: localized inpainting detection. The study leverages multiple datasets spanning diverse generators, mask sizes, and inpainting techniques. Our experiments show that models trained on a large set of generators exhibit partial transferability to inpainting-based edits and can reliably detect medium- and large-area manipulations or regeneration-style inpainting, outperforming many existing ad hoc detection approaches.

---

### Blog Data Showdown: Machine Learning vs Neuro-Symbolic Models for Gender Classification

Authors: Natnael Tilahun Sinshaw, Mengmei He, Tadesse K. Bahiru, Sudhir Kumar Mohapatra
Published: 2025-12-18
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.16687v2

Text classification problems, such as gender classification from a blog, have been a well-matured research area that has been well studied using machine learning algorithms. It has several application domains in market analysis, customer recommendation, and recommendation systems. This study presents a comparative analysis of the widely used machine learning algorithms, namely Support Vector Machines (SVM), Naive Bayes (NB), Logistic Regression (LR), AdaBoost, XGBoost, and an SVM variant (SVM_R) with neuro-symbolic AI (NeSy). The paper also explores the effect of text representations such as TF-IDF, the Universal Sentence Encoder (USE), and RoBERTa. Additionally, various feature extraction techniques, including Chi-Square, Mutual Information, and Principal Component Analysis, are explored. Building on these, we introduce a comparative analysis of the machine learning and deep learning approaches in comparison to the NeSy. The experimental results show that the use of the NeSy approach matched strong MLP results despite a limited dataset. Future work on this research will expand the knowledge base, the scope of embedding types, and the hyperparameter configuration to further study the effectiveness of the NeSy approach.

---

### Blog Data Showdown: Machine Learning vs Neuro-Symbolic Models for Gender Classification

Authors: Natnael Tilahun Sinshaw, Mengmei He, Tadesse K. Bahiru, Sudhir Kumar Mohapatra
Published: 2025-12-18
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.16687v1

Text classification problems, such as gender classification from a blog, have been a well-matured research area that has been well studied using machine learning algorithms. It has several application domains in market analysis, customer recommendation, and recommendation systems. This study presents a comparative analysis of the widely used machine learning algorithms, namely Support Vector Machines (SVM), Naive Bayes (NB), Logistic Regression (LR), AdaBoost, XGBoost, and an SVM variant (SVM_R) with neuro-symbolic AI (NeSy). The paper also explores the effect of text representations such as TF-IDF, the Universal Sentence Encoder (USE), and RoBERTa. Additionally, various feature extraction techniques, including Chi-Square, Mutual Information, and Principal Component Analysis, are explored. Building on these, we introduce a comparative analysis of the machine learning and deep learning approaches in comparison to the NeSy. The experimental results show that the use of the NeSy approach matched strong MLP results despite a limited dataset. Future work on this research will expand the knowledge base, the scope of embedding types, and the hyperparameter configuration to further study the effectiveness of the NeSy approach.

---

### Few-Shot Fingerprinting Subject Re-Identification in 3D-MRI and 2D-X-Ray

Authors: Gonçalo Gaspar Alves, Shekoufeh Gorgi Zadeh, Andreas Husch, Ben Bausch
Published: 2025-12-18
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2512.16685v1

Combining open-source datasets can introduce data leakage if the same subject appears in multiple sets, leading to inflated model performance. To address this, we explore subject fingerprinting, mapping all images of a subject to a distinct region in latent space, to enable subject re-identification via similarity matching. Using a ResNet-50 trained with triplet margin loss, we evaluate few-shot fingerprinting on 3D MRI and 2D X-ray data in both standard (20-way 1-shot) and challenging (1000-way 1-shot) scenarios. The model achieves high Mean- Recall-@-K scores: 99.10% (20-way 1-shot) and 90.06% (500-way 5-shot) on ChestXray-14; 99.20% (20-way 1-shot) and 98.86% (100-way 3-shot) on BraTS- 2021.

---

### DataFlow: An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI

Authors: Hao Liang, Xiaochen Ma, Zhou Liu, Zhen Hao Wong, Zhengyang Zhao, Zimo Meng, Runming He, Chengyu Shen, Qifeng Cai, Zhaoyang Han, Meiyi Qiang, Yalin Feng et al.
Published: 2025-12-18
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2512.16676v1

The rapidly growing demand for high-quality data in Large Language Models (LLMs) has intensified the need for scalable, reliable, and semantically rich data preparation pipelines. However, current practices remain dominated by ad-hoc scripts and loosely specified workflows, which lack principled abstractions, hinder reproducibility, and offer limited support for model-in-the-loop data generation. To address these challenges, we present DataFlow, a unified and extensible LLM-driven data preparation framework. DataFlow is designed with system-level abstractions that enable modular, reusable, and composable data transformations, and provides a PyTorch-style pipeline construction API for building debuggable and optimizable dataflows. The framework consists of nearly 200 reusable operators and six domain-general pipelines spanning text, mathematical reasoning, code, Text-to-SQL, agentic RAG, and large-scale knowledge extraction. To further improve usability, we introduce DataFlow-Agent, which automatically translates natural-language specifications into executable pipelines via operator synthesis, pipeline planning, and iterative verification. Across six representative use cases, DataFlow consistently improves downstream LLM performance. Our math, code, and text pipelines outperform curated human datasets and specialized synthetic baselines, achieving up to +3\% execution accuracy in Text-to-SQL over SynSQL, +7\% average improvements on code benchmarks, and 1--3 point gains on MATH, GSM8K, and AIME. Moreover, a unified 10K-sample dataset produced by DataFlow enables base models to surpass counterparts trained on 1M Infinity-Instruct data. These results demonstrate that DataFlow provides a practical and high-performance substrate for reliable, reproducible, and scalable LLM data preparation, and establishes a system-level foundation for future data-centric AI development.

---

### FrameDiffuser: G-Buffer-Conditioned Diffusion for Neural Forward Frame Rendering

Authors: Ole Beisswenger, Jan-Niklas Dihlmann, Hendrik P. A. Lensch
Published: 2025-12-18
Categories: cs.CV, cs.GR
arXiv: https://arxiv.org/abs/2512.16670v1

Neural rendering for interactive applications requires translating geometric and material properties (G-buffer) to photorealistic images with realistic lighting on a frame-by-frame basis. While recent diffusion-based approaches show promise for G-buffer-conditioned image synthesis, they face critical limitations: single-image models like RGBX generate frames independently without temporal consistency, while video models like DiffusionRenderer are too computationally expensive for most consumer gaming sets ups and require complete sequences upfront, making them unsuitable for interactive applications where future frames depend on user input. We introduce FrameDiffuser, an autoregressive neural rendering framework that generates temporally consistent, photorealistic frames by conditioning on G-buffer data and the models own previous output. After an initial frame, FrameDiffuser operates purely on incoming G-buffer data, comprising geometry, materials, and surface properties, while using its previously generated frame for temporal guidance, maintaining stable, temporal consistent generation over hundreds to thousands of frames. Our dual-conditioning architecture combines ControlNet for structural guidance with ControlLoRA for temporal coherence. A three-stage training strategy enables stable autoregressive generation. We specialize our model to individual environments, prioritizing consistency and inference speed over broad generalization, demonstrating that environment-specific training achieves superior photorealistic quality with accurate lighting, shadows, and reflections compared to generalized approaches.

---

### Microsoft Academic Graph Information Retrieval for Research Recommendation and Assistance

Authors: Shikshya Shiwakoti, Samuel Goldsmith, Ujjwal Pandit
Published: 2025-12-18
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2512.16661v2

In today's information-driven world, access to scientific publications has become increasingly easy. At the same time, filtering through the massive volume of available research has become more challenging than ever. Graph Neural Networks (GNNs) and graph attention mechanisms have shown strong effectiveness in searching large-scale information databases, particularly when combined with modern large language models. In this paper, we propose an Attention-Based Subgraph Retriever, a GNN-as-retriever model that applies attention-based pruning to extract a refined subgraph, which is then passed to a large language model for advanced knowledge reasoning.

---

### Microsoft Academic Graph Information Retrieval for Research Recommendation and Assistance

Authors: Jacob Reiss, Shikshya Shiwakoti, Samuel Goldsmith, Ujjwal Pandit
Published: 2025-12-18
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2512.16661v1

In today's information-driven world, access to scientific publications has become increasingly easy. At the same time, filtering through the massive volume of available research has become more challenging than ever. Graph Neural Networks (GNNs) and graph attention mechanisms have shown strong effectiveness in searching large-scale information databases, particularly when combined with modern large language models. In this paper, we propose an Attention-Based Subgraph Retriever, a GNN-as-retriever model that applies attention-based pruning to extract a refined subgraph, which is then passed to a large language model for advanced knowledge reasoning.

---

### Protecting Deep Neural Network Intellectual Property with Chaos-Based White-Box Watermarking

Authors: Sangeeth B, Serena Nicolazzo, Deepa K., Vinod P
Published: 2025-12-18
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2512.16658v2

The rapid proliferation of deep neural networks (DNNs) across several domains has led to increasing concerns regarding intellectual property (IP) protection and model misuse. Trained DNNs represent valuable assets, often developed through significant investments. However, the ease with which models can be copied, redistributed, or repurposed highlights the urgent need for effective mechanisms to assert and verify model ownership. In this work, we propose an efficient and resilient white-box watermarking framework that embeds ownership information into the internal parameters of a DNN using chaotic sequences. The watermark is generated using a logistic map, a well-known chaotic function, producing a sequence that is sensitive to its initialization parameters. This sequence is injected into the weights of a chosen intermediate layer without requiring structural modifications to the model or degradation in predictive performance. To validate ownership, we introduce a verification process based on a genetic algorithm that recovers the original chaotic parameters by optimizing the similarity between the extracted and regenerated sequences. The effectiveness of the proposed approach is demonstrated through extensive experiments on image classification tasks using MNIST and CIFAR-10 datasets. The results show that the embedded watermark remains detectable after fine-tuning, with negligible loss in model accuracy. In addition to numerical recovery of the watermark, we perform visual analyses using weight density plots and construct activation-based classifiers to distinguish between original, watermarked, and tampered models. Overall, the proposed method offers a flexible and scalable solution for embedding and verifying model ownership in white-box settings well-suited for real-world scenarios where IP protection is critical.

---

### Protecting Deep Neural Network Intellectual Property with Chaos-Based White-Box Watermarking

Authors: Sangeeth B, Serena Nicolazzo, Deepa K., Vinod P
Published: 2025-12-18
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2512.16658v1

The rapid proliferation of deep neural networks (DNNs) across several domains has led to increasing concerns regarding intellectual property (IP) protection and model misuse. Trained DNNs represent valuable assets, often developed through significant investments. However, the ease with which models can be copied, redistributed, or repurposed highlights the urgent need for effective mechanisms to assert and verify model ownership. In this work, we propose an efficient and resilient white-box watermarking framework that embeds ownership information into the internal parameters of a DNN using chaotic sequences. The watermark is generated using a logistic map, a well-known chaotic function, producing a sequence that is sensitive to its initialization parameters. This sequence is injected into the weights of a chosen intermediate layer without requiring structural modifications to the model or degradation in predictive performance. To validate ownership, we introduce a verification process based on a genetic algorithm that recovers the original chaotic parameters by optimizing the similarity between the extracted and regenerated sequences. The effectiveness of the proposed approach is demonstrated through extensive experiments on image classification tasks using MNIST and CIFAR-10 datasets. The results show that the embedded watermark remains detectable after fine-tuning, with negligible loss in model accuracy. In addition to numerical recovery of the watermark, we perform visual analyses using weight density plots and construct activation-based classifiers to distinguish between original, watermarked, and tampered models. Overall, the proposed method offers a flexible and scalable solution for embedding and verifying model ownership in white-box settings well-suited for real-world scenarios where IP protection is critical.

---

### Comprehensive AI Literacy: The Case for Centering Human Agency

Authors: Sri Yash Tadimalla, Justin Cary, Gordon Hull, Jordan Register, Daniel Maxwell, David Pugalee, Tina Heafner
Published: 2025-12-18
Categories: cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2512.16656v1

The rapid assimilation of Artificial Intelligence technologies into various facets of society has created a significant educational imperative that current frameworks are failing to effectively address. We are witnessing the rise of a dangerous literacy gap, where a focus on the functional, operational skills of using AI tools is eclipsing the development of critical and ethical reasoning about them. This position paper argues for a systemic shift toward comprehensive AI literacy that centers human agency - the empowered capacity for intentional, critical, and responsible choice. This principle applies to all stakeholders in the educational ecosystem: it is the student's agency to question, create with, or consciously decide not to use AI based on the task; it is the teacher's agency to design learning experiences that align with instructional values, rather than ceding pedagogical control to a tool. True literacy involves teaching about agency itself, framing technology not as an inevitability to be adopted, but as a choice to be made. This requires a deep commitment to critical thinking and a robust understanding of epistemology. Through the AI Literacy, Fluency, and Competency frameworks described in this paper, educators and students will become agents in their own human-centric approaches to AI, providing necessary pathways to clearly articulate the intentions informing decisions and attitudes toward AI and the impact of these decisions on academic work, career, and society.

---

### Prefix Probing: Lightweight Harmful Content Detection for Large Language Models

Authors: Jirui Yang, Hengqi Guo, Zhihui Lu, Yi Zhao, Yuansen Zhang, Shijing Hu, Qiang Duan, Yinggui Wang, Tao Wei
Published: 2025-12-18
Categories: cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2512.16650v1

Large language models often face a three-way trade-off among detection accuracy, inference latency, and deployment cost when used in real-world safety-sensitive applications. This paper introduces Prefix Probing, a black-box harmful content detection method that compares the conditional log-probabilities of "agreement/execution" versus "refusal/safety" opening prefixes and leverages prefix caching to reduce detection overhead to near first-token latency. During inference, the method requires only a single log-probability computation over the probe prefixes to produce a harmfulness score and apply a threshold, without invoking any additional models or multi-stage inference. To further enhance the discriminative power of the prefixes, we design an efficient prefix construction algorithm that automatically discovers highly informative prefixes, substantially improving detection performance. Extensive experiments demonstrate that Prefix Probing achieves detection effectiveness comparable to mainstream external safety models while incurring only minimal computational cost and requiring no extra model deployment, highlighting its strong practicality and efficiency.

---

### JustRL: Scaling a 1.5B LLM with a Simple RL Recipe

Authors: Bingxiang He, Zekai Qu, Zeyuan Liu, Yinghao Chen, Yuxin Zuo, Cheng Qian, Kaiyan Zhang, Weize Chen, Chaojun Xiao, Ganqu Cui, Ning Ding, Zhiyuan Liu
Published: 2025-12-18
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.16649v1

Recent advances in reinforcement learning for large language models have converged on increasing complexity: multi-stage training pipelines, dynamic hyperparameter schedules, and curriculum learning strategies. This raises a fundamental question: \textbf{Is this complexity necessary?} We present \textbf{JustRL}, a minimal approach using single-stage training with fixed hyperparameters that achieves state-of-the-art performance on two 1.5B reasoning models (54.9\% and 64.3\% average accuracy across nine mathematical benchmarks) while using 2$\times$ less compute than sophisticated approaches. The same hyperparameters transfer across both models without tuning, and training exhibits smooth, monotonic improvement over 4,000+ steps without the collapses or plateaus that typically motivate interventions. Critically, ablations reveal that adding ``standard tricks'' like explicit length penalties and robust verifiers may degrade performance by collapsing exploration. These results suggest that the field may be adding complexity to solve problems that disappear with a stable, scaled-up baseline. We release our models and code to establish a simple, validated baseline for the community.

---

### Exploiting Radio Frequency Fingerprints for Device Identification: Tackling Cross-receiver Challenges in the Source-data-free Scenario

Authors: Liu Yang, Qiang Li, Luxiong Wen, Jian Yang
Published: 2025-12-18
Categories: cs.LG, eess.SP
arXiv: https://arxiv.org/abs/2512.16648v1

With the rapid proliferation of edge computing, Radio Frequency Fingerprint Identification (RFFI) has become increasingly important for secure device authentication. However, practical deployment of deep learning-based RFFI models is hindered by a critical challenge: their performance often degrades significantly when applied across receivers with different hardware characteristics due to distribution shifts introduced by receiver variation. To address this, we investigate the source-data-free cross-receiver RFFI (SCRFFI) problem, where a model pretrained on labeled signals from a source receiver must adapt to unlabeled signals from a target receiver, without access to any source-domain data during adaptation. We first formulate a novel constrained pseudo-labeling-based SCRFFI adaptation framework, and provide a theoretical analysis of its generalization performance. Our analysis highlights a key insight: the target-domain performance is highly sensitive to the quality of the pseudo-labels generated during adaptation. Motivated by this, we propose Momentum Soft pseudo-label Source Hypothesis Transfer (MS-SHOT), a new method for SCRFFI that incorporates momentum-center-guided soft pseudo-labeling and enforces global structural constraints to encourage confident and diverse predictions. Notably, MS-SHOT effectively addresses scenarios involving label shift or unknown, non-uniform class distributions in the target domain -- a significant limitation of prior methods. Extensive experiments on real-world datasets demonstrate that MS-SHOT consistently outperforms existing approaches in both accuracy and robustness, offering a practical and scalable solution for source-data-free cross-receiver adaptation in RFFI.

---

### Implementing a Sharia Chatbot as a Consultation Medium for Questions About Islam

Authors: Wisnu Uriawan, Aria Octavian Hamza, Ade Ripaldi Nuralim, Adi Purnama, Ahmad Juaeni Yunus, Anissya Auliani Supriadi Putri
Published: 2025-12-18
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.16644v1

This research presents the implementation of a Sharia-compliant chatbot as an interactive medium for consulting Islamic questions, leveraging Reinforcement Learning (Q-Learning) integrated with Sentence-Transformers for semantic embedding to ensure contextual and accurate responses. Utilizing the CRISP-DM methodology, the system processes a curated Islam QA dataset of 25,000 question-answer pairs from authentic sources like the Qur'an, Hadith, and scholarly fatwas, formatted in JSON for flexibility and scalability. The chatbot prototype, developed with a Flask API backend and Flutter-based mobile frontend, achieves 87% semantic accuracy in functional testing across diverse topics including fiqh, aqidah, ibadah, and muamalah, demonstrating its potential to enhance religious literacy, digital da'wah, and access to verified Islamic knowledge in the Industry 4.0 era. While effective for closed-domain queries, limitations such as static learning and dataset dependency highlight opportunities for future enhancements like continuous adaptation and multi-turn conversation support, positioning this innovation as a bridge between traditional Islamic scholarship and modern AI-driven consultation.

---