# Research Papers — 2025-12 · bundle page 41 of 175

> Full-text markdown of papers #2001–2050 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/41
[← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/40.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-12/page/42.md)

### MauBERT: Universal Phonetic Inductive Biases for Few-Shot Acoustic Units Discovery

Authors: Angelo Ortiz Tandazo, Manel Khentout, Youssef Benchekroun, Thomas Hueber, Emmanuel Dupoux
Published: 2025-12-22
Categories: cs.CL, eess.AS
arXiv: https://arxiv.org/abs/2512.19612v3

This paper introduces MauBERT, a multilingual extension of HuBERT that leverages articulatory features for robust cross-lingual phonetic representation learning. We continue HuBERT pre-training with supervision based on a phonetic-to-articulatory feature mapping in 55 languages. Our models learn from multilingual data to predict articulatory features or phones, resulting in language-independent representations that capture multilingual phonetic properties. Through comprehensive ABX discriminability testing, we show MauBERT models produce more context-invariant representations than state-of-the-art multilingual self-supervised learning models. Additionally, the models effectively adapt to unseen languages and casual speech with minimal self-supervised fine-tuning (10 hours of speech). This establishes an effective approach for instilling linguistic inductive biases in self-supervised speech models.

---

### MapTrace: Scalable Data Generation for Route Tracing on Maps

Authors: Artemis Panagopoulou, Aveek Purohit, Achin Kulshrestha, Soroosh Yazdani, Mohit Goyal
Published: 2025-12-22
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2512.19609v1

While Multimodal Large Language Models have achieved human-like performance on many visual and textual reasoning tasks, their proficiency in fine-grained spatial understanding, such as route tracing on maps remains limited. Unlike humans, who can quickly learn to parse and navigate maps, current models often fail to respect fundamental path constraints, in part due to the prohibitive cost and difficulty of collecting large-scale, pixel-accurate path annotations. To address this, we introduce a scalable synthetic data generation pipeline that leverages synthetic map images and pixel-level parsing to automatically produce precise annotations for this challenging task. Using this pipeline, we construct a fine-tuning dataset of 23k path samples across 4k maps, enabling models to acquire more human-like spatial capabilities. Using this dataset, we fine-tune both open-source and proprietary MLLMs. Results on MapBench show that finetuning substantially improves robustness, raising success rates by up to 6.4 points, while also reducing path-tracing error (NDTW). These gains highlight that fine-grained spatial reasoning, absent in pretrained models, can be explicitly taught with synthetic supervision.

---

### KerJEPA: Kernel Discrepancies for Euclidean Self-Supervised Learning

Authors: Eric Zimmermann, Harley Wiltzer, Justin Szeto, David Alvarez-Melis, Lester Mackey
Published: 2025-12-22
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2512.19605v2

Breakthroughs in self-supervised Joint-Embedding Predictive Architectures (JEPAs) have established that regularizing Euclidean representations toward isotropic Gaussian priors yields provable gains in training stability and downstream generalization. We introduce a new, flexible family of Euclidean joint embedding self-supervised learning algorithms with kernel-based regularizers. One instance of this family corresponds to the SIGReg Epps-Pulley regularizer which approximates a sliced Maximum Mean Discrepancy (MMD) with a Gaussian prior and Gaussian kernel. By expanding the class of viable kernels and priors and computing the closed-form high-dimensional limit of sliced discrepancies, we develop alternative methods with improved training stability and design flexibility and leverage those techniques to train strong vision learners at scale.

---

### No Data? No Problem: Robust Vision-Tabular Learning with Missing Values

Authors: Marta Hasny, Laura Daza, Keno Bressem, Maxime Di Folco, Julia Schnabel
Published: 2025-12-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.19602v2

Large-scale medical biobanks provide imaging data complemented by extensive tabular information, such as clinical measurements or demographics. However, this abundance of tabular attributes does not reflect real-world datasets, where only a subset of attributes may be available. This discrepancy calls for methods that remain robust to missing values at inference. To address this challenge, we propose RoVTL (Robust Vision-Tabular Learning), a framework designed to handle any level of tabular data availability, from 0% to 100%. RoVTL comprises two key stages: contrastive pretraining, where we introduce tabular attribute missingness as data augmentation to promote robustness, and downstream task tuning, where tabular missingness is complemented by a novel Tabular More vs. Fewer loss that ranks performance based on the amount of available tabular data. Combined with gated-cross attention fusion module, our tuning approach enables consistent performance across all tabular data completeness scenarios. We evaluate RoVTL on cardiac MRI scans from the UK Biobank, demonstrating superior robustness to missing tabular data compared to prior methods. Furthermore, RoVTL successfully generalizes to an external cardiac MRI dataset for multimodal disease classification, and extends to the natural images domain, achieving robust performance on a car advertisements dataset. The model weights and code are available at https://github.com/marteczkah/RoVTL.

---

### Increasing the Thinking Budget is Not All You Need

Authors: Ignacio Iacobacci, Zhaozhi Qian, Faroq AL-Tam, Muhammad AL-Qurishi, Riad Souissi
Published: 2025-12-22
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.19585v1

Recently, a new wave of thinking-capable Large Language Models has emerged, demonstrating exceptional capabilities across a wide range of reasoning benchmarks. Early studies have begun to explore how the amount of compute in terms of the length of the reasoning process, the so-called thinking budget, impacts model performance. In this work, we propose a systematic investigation of the thinking budget as a key parameter, examining its interaction with various configurations such as self-consistency, reflection, and others. Our goal is to provide an informative, balanced comparison framework that considers both performance outcomes and computational cost. Among our findings, we discovered that simply increasing the thinking budget is not the most effective use of compute. More accurate responses can instead be achieved through alternative configurations, such as self-consistency and self-reflection.

---

### Patlak Parametric Image Estimation from Dynamic PET Using Diffusion Model Prior

Authors: Ziqian Huang, Boxiao Yu, Siqi Li, Savas Ozdemir, Sangjin Bae, Jae Sung Lee, Guobao Wang, Kuang Gong
Published: 2025-12-22
Categories: eess.IV, cs.CV, physics.med-ph
arXiv: https://arxiv.org/abs/2512.19584v1

Dynamic PET enables the quantitative estimation of physiology-related parameters and is widely utilized in research and increasingly adopted in clinical settings. Parametric imaging in dynamic PET requires kinetic modeling to estimate voxel-wise physiological parameters based on specific kinetic models. However, parametric images estimated through kinetic model fitting often suffer from low image quality due to the inherently ill-posed nature of the fitting process and the limited counts resulting from non-continuous data acquisition across multiple bed positions in whole-body PET. In this work, we proposed a diffusion model-based kinetic modeling framework for parametric image estimation, using the Patlak model as an example. The score function of the diffusion model was pre-trained on static total-body PET images and served as a prior for both Patlak slope and intercept images by leveraging their patch-wise similarity. During inference, the kinetic model was incorporated as a data-consistency constraint to guide the parametric image estimation. The proposed framework was evaluated on total-body dynamic PET datasets with different dose levels, demonstrating the feasibility and promising performance of the proposed framework in improving parametric image quality.

---

### Deep Learning for Primordial $B$-mode Extraction

Authors: Eric Guzman, Joel Meyers
Published: 2025-12-22
Categories: astro-ph.CO, cs.CV, stat.ML
arXiv: https://arxiv.org/abs/2512.19577v1

The search for primordial gravitational waves is a central goal of cosmic microwave background (CMB) surveys. Isolating the characteristic $B$-mode polarization signal sourced by primordial gravitational waves is challenging for several reasons: the amplitude of the signal is inherently small; astrophysical foregrounds produce $B$-mode polarization contaminating the signal; and secondary $B$-mode polarization fluctuations are produced via the conversion of $E$ modes. Current and future low-noise, multi-frequency observations enable sufficient precision to address the first two of these challenges such that secondary $B$ modes will become the bottleneck for improved constraints on the amplitude of primordial gravitational waves. The dominant source of secondary $B$-mode polarization is gravitational lensing by large scale structure. Various strategies have been developed to estimate the lensing deflection and to reverse its effects the CMB, thus reducing confusion from lensing $B$ modes in the search for primordial gravitational waves. However, a few complications remain. First, there may be additional sources of secondary $B$-mode polarization, for example from patchy reionization or from cosmic polarization rotation. Second, the statistics of delensed CMB maps can become complicated and non-Gaussian, especially when advanced lensing reconstruction techniques are applied. We previously demonstrated how a deep learning network, ResUNet-CMB, can provide nearly optimal simultaneous estimates of multiple sources of secondary $B$-mode polarization. In this paper, we show how deep learning can be applied to estimate and remove multiple sources of secondary $B$-mode polarization, and we further show how this technique can be used in a likelihood analysis to produce nearly optimal, unbiased estimates of the amplitude of primordial gravitational waves.

---

### LeLaR: The First In-Orbit Demonstration of an AI-Based Satellite Attitude Controller

Authors: Kirill Djebko, Tom Baumann, Erik Dilger, Frank Puppe, Sergio Montenegro
Published: 2025-12-22
Categories: cs.RO, cs.AI, cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2512.19576v5

Attitude control is essential for many satellite missions. Classical controllers, however, are time-consuming to design and sensitive to model uncertainties and variations in operational boundary conditions. Deep Reinforcement Learning (DRL) offers a promising alternative by learning adaptive control strategies through autonomous interaction with a simulation environment. Overcoming the Sim2Real gap, which involves deploying an agent trained in simulation onto the real physical satellite, remains a significant challenge. In this work, we present the first successful in-orbit demonstration of an AI-based attitude controller for inertial pointing maneuvers. The controller was trained entirely in simulation and deployed to the InnoCube 3U nanosatellite, which was developed by the Julius-Maximilians-Universität Würzburg in cooperation with the Technische Universität Berlin, and launched in January 2025. We present the AI agent design, the methodology of the training procedure, the discrepancies between the simulation and the observed behavior of the real satellite, and a comparison of the AI-based attitude controller with the classical PD controller of InnoCube. Steady-state metrics confirm the robust performance of the AI-based controller during repeated in-orbit maneuvers.

---

### The Epistemological Consequences of Large Language Models: Rethinking collective intelligence and institutional knowledge

Authors: Angjelin Hila
Published: 2025-12-22
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2512.19570v2

We examine epistemological threats posed by human and LLM interaction. We develop collective epistemology as a theory of epistemic warrant distributed across human collectives, using bounded rationality and dual process theory as background. We distinguish internalist justification, defined as reflective understanding of why a proposition is true, from externalist justification, defined as reliable transmission of truths. Both are necessary for collective rationality, but only internalist justification produces reflective knowledge. We specify reflective knowledge as follows: agents understand the evaluative basis of a claim, when that basis is unavailable agents consistently assess the reliability of truth sources, and agents have a duty to apply these standards within their domains of competence. We argue that LLMs approximate externalist reliabilism because they can reliably transmit information whose justificatory basis is established elsewhere, but they do not themselves possess reflective justification. Widespread outsourcing of reflective work to reliable LLM outputs can weaken reflective standards of justification, disincentivize comprehension, and reduce agents' capacity to meet professional and civic epistemic duties. To mitigate these risks, we propose a three tier norm program that includes an epistemic interaction model for individual use, institutional and organizational frameworks that seed and enforce norms for epistemically optimal outcomes, and deontic constraints at organizational and or legislative levels that instantiate discursive norms and curb epistemic vices.

---

### Owning the Intelligence: Global AI Patents Landscape and Europe's Quest for Technological Sovereignty

Authors: Lapo Santarlasci, Armando Rungi, Loredana Fattorini, Nestor Maslej
Published: 2025-12-22
Categories: econ.GN, cs.AI
arXiv: https://arxiv.org/abs/2512.19569v1

Artificial intelligence has become a key arena of global technological competition and a central concern for Europe's quest for technological sovereignty. This paper analyzes global AI patenting from 2010 to 2023 to assess Europe's position in an increasingly bipolar innovation landscape dominated by the United States and China. Using linked patent, firm, ownership, and citation data, we examine the geography, specialization, and international diffusion of AI innovation. We find a highly concentrated patent landscape: China leads in patent volumes, while the United States dominates in citation impact and technological influence. Europe accounts for a limited share of AI patents but exhibits signals of relatively high patent quality. Technological proximity reveals global convergence toward U.S. innovation trajectories, with Europe remaining fragmented rather than forming an autonomous pole. Gravity-model estimates show that cross-border AI knowledge flows are driven primarily by technological capability and specialization, while geographic and institutional factors play a secondary role. EU membership does not significantly enhance intra-European knowledge diffusion, suggesting that technological capacity, rather than political integration, underpins participation in global AI innovation networks.

---

### Results of the 2024 CommonRoad Motion Planning Competition for Autonomous Vehicles

Authors: Yanliang Huang, Xia Yan, Peiran Yin, Zhenduo Zhang, Zeyan Shao, Youran Wang, Haoliang Huang, Matthias Althoff
Published: 2025-12-22
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2512.19564v1

Over the past decade, a wide range of motion planning approaches for autonomous vehicles has been developed to handle increasingly complex traffic scenarios. However, these approaches are rarely compared on standardized benchmarks, limiting the assessment of relative strengths and weaknesses. To address this gap, we present the setup and results of the 4th CommonRoad Motion Planning Competition held in 2024, conducted using the CommonRoad benchmark suite. This annual competition provides an open-source and reproducible framework for benchmarking motion planning algorithms. The benchmark scenarios span highway and urban environments with diverse traffic participants, including passenger cars, buses, and bicycles. Planner performance is evaluated along four dimensions: efficiency, safety, comfort, and compliance with selected traffic rules. This report introduces the competition format and provides a comparison of representative high-performing planners from the 2023 and 2024 editions.

---

### REALM: A Real-to-Sim Validated Benchmark for Generalization in Robotic Manipulation

Authors: Martin Sedlacek, Pavlo Yefanov, Georgy Ponimatkin, Jai Bardhan, Simon Pilc, Mederic Fourmy, Evangelos Kazakos, Cees G. M. Snoek, Josef Sivic, Vladimir Petrik
Published: 2025-12-22
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2512.19562v1

Vision-Language-Action (VLA) models empower robots to understand and execute tasks described by natural language instructions. However, a key challenge lies in their ability to generalize beyond the specific environments and conditions they were trained on, which is presently difficult and expensive to evaluate in the real-world. To address this gap, we present REALM, a new simulation environment and benchmark designed to evaluate the generalization capabilities of VLA models, with a specific emphasis on establishing a strong correlation between simulated and real-world performance through high-fidelity visuals and aligned robot control. Our environment offers a suite of 15 perturbation factors, 7 manipulation skills, and more than 3,500 objects. Finally, we establish two task sets that form our benchmark and evaluate the π_{0}, π_{0}-FAST, and GR00T N1.5 VLA models, showing that generalization and robustness remain an open challenge. More broadly, we also show that simulation gives us a valuable proxy for the real-world and allows us to systematically probe for and quantify the weaknesses and failure modes of VLAs. Project page: https://martin-sedlacek.com/realm

---

### BabyFlow: 3D modeling of realistic and expressive infant faces

Authors: Antonia Alomar, Mireia Masias, Marius George Linguraru, Federico M. Sukno, Gemma Piella
Published: 2025-12-22
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2512.19560v1

Early detection of developmental disorders can be aided by analyzing infant craniofacial morphology, but modeling infant faces is challenging due to limited data and frequent spontaneous expressions. We introduce BabyFlow, a generative AI model that disentangles facial identity and expression, enabling independent control over both. Using normalizing flows, BabyFlow learns flexible, probabilistic representations that capture the complex, non-linear variability of expressive infant faces without restrictive linear assumptions. To address scarce and uncontrolled expressive data, we perform cross-age expression transfer, adapting expressions from adult 3D scans to enrich infant datasets with realistic and systematic expressive variants. As a result, BabyFlow improves 3D reconstruction accuracy, particularly in highly expressive regions such as the mouth, eyes, and nose, and supports synthesis and modification of infant expressions while preserving identity. Additionally, by integrating with diffusion models, BabyFlow generates high-fidelity 2D infant images with consistent 3D geometry, providing powerful tools for data augmentation and early facial analysis.

---

### Augmenting Intelligence: A Hybrid Framework for Scalable and Stable Explanations

Authors: Lawrence Krukrubo, Julius Odede, Olawande Olusegun
Published: 2025-12-22
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.19557v1

Current approaches to Explainable AI (XAI) face a "Scalability-Stability Dilemma." Post-hoc methods (e.g., LIME, SHAP) may scale easily but suffer from instability, while supervised explanation frameworks (e.g., TED) offer stability but require prohibitive human effort to label every training instance. This paper proposes a Hybrid LRR-TED framework that addresses this dilemma through a novel "Asymmetry of Discovery." When applied to customer churn prediction, we demonstrate that automated rule learners (GLRM) excel at identifying broad "Safety Nets" (retention patterns) but struggle to capture specific "Risk Traps" (churn triggers)-a phenomenon we term the Anna Karenina Principle of Churn. By initialising the explanation matrix with automated safety rules and augmenting it with a Pareto-optimal set of just four human-defined risk rules, our approach achieves 94.00% predictive accuracy. This configuration outperforms the full 8-rule manual expert baseline while reducing human annotation effort by 50%, proposing a shift in the paradigm for Human-in-the-Loop AI: moving experts from the role of "Rule Writers" to "Exception Handlers."

---

### CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal Reasoning

Authors: Yongxin Wang, Zhicheng Yang, Meng Cao, Mingfei Han, Haokun Lin, Yingying Zhu, Xiaojun Chang, Xiaodan Liang
Published: 2025-12-22
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.19554v4

Group-relative reinforcement learning with verifiable rewards (RLVR) often wastes the most informative data it already has the failures. When all rollouts are wrong, gradients stall; when one happens to be correct, the update usually ignores why the others are close-but-wrong, and credit can be misassigned to spurious chains. We present CARE (Contrastive Anchored REflection), a failure-centric post-training framework for multimodal reasoning that turns errors into supervision. CARE combines: (i) an anchored-contrastive objective that forms a compact subgroup around the best rollout and a set of semantically proximate hard negatives, performs within-subgroup z-score normalization with negative-only scaling, and includes an all-negative rescue to prevent zero-signal batches; and (ii) Reflection-Guided Resampling (RGR), a one-shot structured self-repair that rewrites a representative failure and re-scores it with the same verifier, converting near-misses into usable positives without any test-time reflection. CARE improves accuracy and training smoothness while explicitly increasing the share of learning signal that comes from failures. On Qwen2.5-VL-7B, CARE lifts macro-averaged accuracy by 4.6 points over GRPO across six verifiable visual-reasoning benchmarks; with Qwen3-VL-8B it reaches competitive or state-of-the-art results on MathVista and MMMU-Pro under an identical evaluation protocol.

---

### Towards Closed-Loop Embodied Empathy Evolution: Probing LLM-Centric Lifelong Empathic Motion Generation in Unseen Scenarios

Authors: Jiawen Wang, Jingjing Wang Tianyang Chen, Min Zhang, Guodong Zhou
Published: 2025-12-22
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.19551v1

In the literature, existing human-centric emotional motion generation methods primarily focus on boosting performance within a single scale-fixed dataset, largely neglecting the flexible and scale-increasing motion scenarios (e.g., sports, dance), whereas effectively learning these newly emerging scenarios can significantly enhance the model's real-world generalization ability. Inspired by this, this paper proposes a new LLM-Centric Lifelong Empathic Motion Generation (L^2-EMG) task, which aims to equip LLMs with the capability to continually acquire emotional motion generation knowledge across different unseen scenarios, potentially contributing to building a closed-loop and self-evolving embodied agent equipped with both empathy and intelligence. Further, this paper poses two key challenges in the L^2-EMG task, i.e., the emotion decoupling challenge and the scenario adapting challenge. To this end, this paper proposes an Emotion-Transferable and Scenario-Adapted Mixture of Experts (ES-MoE) approach which designs a causal-guided emotion decoupling block and a scenario-adapted expert constructing block to address the two challenges, respectively. Especially, this paper constructs multiple L^2-EMG datasets to validate the effectiveness of the ES-MoE approach. Extensive evaluations show that ES-MoE outperforms advanced baselines.

---

### DFORD: Directional Feedback based Online Ordinal Regression Learning

Authors: Naresh Manwani, M Elamparithy, Tanish Taneja
Published: 2025-12-22
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.19550v1

In this paper, we introduce directional feedback in the ordinal regression setting, in which the learner receives feedback on whether the predicted label is on the left or the right side of the actual label. This is a weak supervision setting for ordinal regression compared to the full information setting, where the learner can access the labels. We propose an online algorithm for ordinal regression using directional feedback. The proposed algorithm uses an exploration-exploitation scheme to learn from directional feedback efficiently. Furthermore, we introduce its kernel-based variant to learn non-linear ordinal regression models in an online setting. We use a truncation trick to make the kernel implementation more memory efficient. The proposed algorithm maintains the ordering of the thresholds in the expected sense. Moreover, it achieves the expected regret of $\mathcal{O}(\log T)$. We compare our approach with a full information and a weakly supervised algorithm for ordinal regression on synthetic and real-world datasets. The proposed approach, which learns using directional feedback, performs comparably (sometimes better) to its full information counterpart.

---

### ActAvatar: Temporally-Aware Precise Action Control for Talking Avatars

Authors: Ziqiao Peng, Yi Chen, Yifeng Ma, Guozhen Zhang, Zhiyao Sun, Zixiang Zhou, Youliang Zhang, Zhengguang Zhou, Zhaoxin Fan, Hongyan Liu, Yuan Zhou, Qinglin Lu et al.
Published: 2025-12-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.19546v2

Despite significant advances in talking avatar generation, existing methods face critical challenges: insufficient text-following capability for diverse actions, lack of temporal alignment between actions and audio content, and dependency on additional control signals such as pose skeletons. We present ActAvatar, a framework that achieves phase-level precision in action control through textual guidance by capturing both action semantics and temporal context. Our approach introduces three core innovations: (1) Phase-Aware Cross-Attention (PACA), which decomposes prompts into a global base block and temporally-anchored phase blocks, enabling the model to concentrate on phase-relevant tokens for precise temporal-semantic alignment; (2) Progressive Audio-Visual Alignment, which aligns modality influence with the hierarchical feature learning process-early layers prioritize text for establishing action structure while deeper layers emphasize audio for refining lip movements, preventing modality interference; (3) A two-stage training strategy that first establishes robust audio-visual correspondence on diverse data, then injects action control through fine-tuning on structured annotations, maintaining both audio-visual alignment and the model's text-following capabilities. Extensive experiments demonstrate that ActAvatar significantly outperforms state-of-the-art methods in both action control and visual quality.

---

### Algerian Dialect

Authors: Zakaria Benmounah, Abdennour Boulesnane
Published: 2025-12-22
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.19543v1

We present Algerian Dialect, a large-scale sentiment-annotated dataset consisting of 45,000 YouTube comments written in Algerian Arabic dialect. The comments were collected from more than 30 Algerian press and media channels using the YouTube Data API. Each comment is manually annotated into one of five sentiment categories: very negative, negative, neutral, positive, and very positive. In addition to sentiment labels, the dataset includes rich metadata such as collection timestamps, like counts, video URLs, and annotation dates. This dataset addresses the scarcity of publicly available resources for Algerian dialect and aims to support research in sentiment analysis, dialectal Arabic NLP, and social media analytics. The dataset is publicly available on Mendeley Data under a CC BY 4.0 license at https://doi.org/10.17632/zzwg3nnhsz.2.

---

### Active Convolved Illumination with Deep Transfer Learning for Complex Beam Transmission through Atmospheric Turbulence

Authors: Adrian A. Moazzam, Anindya Ghoshroy, Breeanne Heusdens, Durdu O. Guney, Roohollah Askari
Published: 2025-12-22
Categories: physics.optics, cs.LG
arXiv: https://arxiv.org/abs/2512.19540v1

Atmospheric turbulence imposes a fundamental limitation across a broad range of applications, including optical imaging, remote sensing, and free-space optical communication. Recent advances in adaptive optics, wavefront shaping, and machine learning, driven by synergistic progress in fundamental theories, optoelectronic hardware, and computational algorithms, have demonstrated substantial potential in mitigating turbulence-induced distortions. Recently, active convolved illumination (ACI) was proposed as a versatile and physics-driven technique for transmitting structured light beams with minimal distortion through highly challenging turbulent regimes. While distinct in its formulation, ACI shares conceptual similarities with other physics-driven distortion correction approaches and stands to benefit from complementary integration with data-driven deep learning (DL) models. Inspired by recent work coupling deep learning with traditional turbulence mitigation strategies, the present work investigates the feasibility of integrating ACI with neural network-based methods. We outline a conceptual framework for coupling ACI with data-driven models and identify conditions under which learned representations can meaningfully support ACI's correlation-injection mechanism. As a representative example, we employ a convolutional neural network (CNN) together with a transfer-learning approach to examine how a learned model may operate in tandem with ACI. This exploratory study demonstrates feasible implementation pathways and establishes an early foundation for assessing the potential of future ACI-DL hybrid architectures, representing a step toward evaluating broader synergistic interactions between ACI and modern DL models.

---

### StoryMem: Multi-shot Long Video Storytelling with Memory

Authors: Kaiwen Zhang, Liming Jiang, Angtian Wang, Jacob Zhiyuan Fang, Tiancheng Zhi, Qing Yan, Hao Kang, Xin Lu, Xingang Pan
Published: 2025-12-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.19539v1

Visual storytelling requires generating multi-shot videos with cinematic quality and long-range consistency. Inspired by human memory, we propose StoryMem, a paradigm that reformulates long-form video storytelling as iterative shot synthesis conditioned on explicit visual memory, transforming pre-trained single-shot video diffusion models into multi-shot storytellers. This is achieved by a novel Memory-to-Video (M2V) design, which maintains a compact and dynamically updated memory bank of keyframes from historical generated shots. The stored memory is then injected into single-shot video diffusion models via latent concatenation and negative RoPE shifts with only LoRA fine-tuning. A semantic keyframe selection strategy, together with aesthetic preference filtering, further ensures informative and stable memory throughout generation. Moreover, the proposed framework naturally accommodates smooth shot transitions and customized story generation applications. To facilitate evaluation, we introduce ST-Bench, a diverse benchmark for multi-shot video storytelling. Extensive experiments demonstrate that StoryMem achieves superior cross-shot consistency over previous methods while preserving high aesthetic quality and prompt adherence, marking a significant step toward coherent minute-long video storytelling.

---

### Event Extraction in Large Language Model

Authors: Bobo Li, Xudong Han, Jiang Liu, Yuzhe Ding, Liqiang Jing, Zhaoqi Zhang, Jinheng Li, Xinya Du, Fei Li, Meishan Zhang, Min Zhang, Aixin Sun et al.
Published: 2025-12-22
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.19537v1

Large language models (LLMs) and multimodal LLMs are changing event extraction (EE): prompting and generation can often produce structured outputs in zero shot or few shot settings. Yet LLM based pipelines face deployment gaps, including hallucinations under weak constraints, fragile temporal and causal linking over long contexts and across documents, and limited long horizon knowledge management within a bounded context window. We argue that EE should be viewed as a system component that provides a cognitive scaffold for LLM centered solutions. Event schemas and slot constraints create interfaces for grounding and verification; event centric structures act as controlled intermediate representations for stepwise reasoning; event links support relation aware retrieval with graph based RAG; and event stores offer updatable episodic and agent memory beyond the context window. This survey covers EE in text and multimodal settings, organizing tasks and taxonomy, tracing method evolution from rule based and neural models to instruction driven and generative frameworks, and summarizing formulations, decoding strategies, architectures, representations, datasets, and evaluation. We also review cross lingual, low resource, and domain specific settings, and highlight open challenges and future directions for reliable event centric systems. Finally, we outline open challenges and future directions that are central to the LLM era, aiming to evolve EE from static extraction into a structurally reliable, agent ready perception and memory layer for open world systems.

---

### CASA: Cross-Attention over Self-Attention for Efficient Vision-Language Fusion

Authors: Moritz Böhle, Amélie Royer, Juliette Marrie, Edouard Grave, Patrick Pérez
Published: 2025-12-22
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2512.19535v2

Vision-language models (VLMs) are commonly trained by directly inserting image tokens from a pretrained vision encoder into the text stream of a language model. This allows text and image information to fully attend to one another within the model, but becomes rapidly costly for long multi-image conversations or streaming video applications, both in terms of memory and compute. VLMs leveraging cross-attention (CA) are an efficient alternative to token insertion as image tokens are not added to the KV cache. Despite being introduced early on, multimodal CA models are scarce in the current VLM literature and often underperform their token insertion counterparts. In this work, we reinvestigate the effectiveness of cross-attention for vision-language modeling: (i) We analyze the core differences between the cross-attention and self-attention mechanisms, (ii) we train cross-attention VLMs both from a text-only LLM and by adapting a pretrained insertion-based VLM, showing that simple cross-attention is far more competitive with token insertion than previously reported, and (iii) we demonstrate the practical advantages of cross-attention on real-time video captioning, where it naturally maintains low latency and near-constant memory cost. For samples and code, please see our project page at https://kyutai.org/casa .

---

### SlicerOrbitSurgerySim: An Open-Source Platform for Virtual Registration and Quantitative Comparison of Preformed Orbital Plates

Authors: Chi Zhang, Braedon Gunn, Andrew M. Read-Fuller
Published: 2025-12-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.19534v1

Poor adaptation of orbital implants remains a major contributor to postoperative complications and revision surgery. Although preformed orbital plates are widely used to reduce cost and operative time compared with customized implants, surgeons currently lack publicly available tools and standardized metrics to quantitatively compare plate fit across vendors, sizes, and patient anatomy. We developed SlicerOrbitSurgerySim, an open-source extension for the 3D Slicer platform that enables interactive virtual registration, evaluation, and comparison of multiple preformed orbital plates in a patient-specific virtual planning environment. The software generates reproducible quantitative plate-to-orbit distance metrics and visualization tools that support both patient-specific planning and population-level statistical analysis of plate adaptability. By facilitating objective comparison of implant designs and placement strategies, this tool aims to improve preoperative decision-making, reduce intraoperative plate modification, and promote collaborative research and surgical education. Pilot studies, sample datasets, and detailed tutorials are provided to support testing, transparency, and reproducibility.

---

### Learning Continuous Solvent Effects from Transient Flow Data: A Graph Neural Network Benchmark on Catechol Rearrangement

Authors: Hongsheng Xing, Qiuxin Si
Published: 2025-12-22
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.19530v1

Predicting reaction outcomes across continuous solvent composition ranges remains a critical challenge in organic synthesis and process chemistry. Traditional machine learning approaches often treat solvent identity as a discrete categorical variable, which prevents systematic interpolation and extrapolation across the solvent space. This work introduces the \textbf{Catechol Benchmark}, a high-throughput transient flow chemistry dataset comprising 1,227 experimental yield measurements for the rearrangement of allyl-substituted catechol in 24 pure solvents and their binary mixtures, parameterized by continuous volume fractions ($\% B$). We evaluate various architectures under rigorous leave-one-solvent-out and leave-one-mixture-out protocols to test generalization to unseen chemical environments. Our results demonstrate that classical tabular methods (e.g., Gradient-Boosted Decision Trees) and large language model embeddings (e.g., Qwen-7B) struggle with quantitative precision, yielding Mean Squared Errors (MSE) of 0.099 and 0.129, respectively. In contrast, we propose a hybrid GNN-based architecture that integrates Graph Attention Networks (GATs) with Differential Reaction Fingerprints (DRFP) and learned mixture-aware solvent encodings. This approach achieves an \textbf{MSE of 0.0039} ($\pm$ 0.0003), representing a 60\% error reduction over competitive baselines and a $>25\times$ improvement over tabular ensembles. Ablation studies confirm that explicit molecular graph message-passing and continuous mixture encoding are essential for robust generalization. The complete dataset, evaluation protocols, and reference implementations are released to facilitate data-efficient reaction prediction and continuous solvent representation learning.

---

### Multi-Modal Soccer Scene Analysis with Masked Pre-Training

Authors: Marc Peral, Guillem Capellera, Luis Ferraz, Antonio Rubio, Antonio Agudo
Published: 2025-12-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.19528v1

In this work we propose a multi-modal architecture for analyzing soccer scenes from tactical camera footage, with a focus on three core tasks: ball trajectory inference, ball state classification, and ball possessor identification. To this end, our solution integrates three distinct input modalities (player trajectories, player types and image crops of individual players) into a unified framework that processes spatial and temporal dynamics using a cascade of sociotemporal transformer blocks. Unlike prior methods, which rely heavily on accurate ball tracking or handcrafted heuristics, our approach infers the ball trajectory without direct access to its past or future positions, and robustly identifies the ball state and ball possessor under noisy or occluded conditions from real top league matches. We also introduce CropDrop, a modality-specific masking pre-training strategy that prevents over-reliance on image features and encourages the model to rely on cross-modal patterns during pre-training. We show the effectiveness of our approach on a large-scale dataset providing substantial improvements over state-of-the-art baselines in all tasks. Our results highlight the benefits of combining structured and visual cues in a transformer-based architecture, and the importance of realistic masking strategies in multi-modal learning.

---

### Deep Learning for Unrelated-Machines Scheduling: Handling Variable Dimensions

Authors: Diego Hitzges, Guillaume Sagnol
Published: 2025-12-22
Categories: cs.LG, cs.DM
arXiv: https://arxiv.org/abs/2512.19527v1

Deep learning has been effectively applied to many discrete optimization problems. However, learning-based scheduling on unrelated parallel machines remains particularly difficult to design. Not only do the numbers of jobs and machines vary, but each job-machine pair has a unique processing time, dynamically altering feature dimensions. We propose a novel approach with a neural network tailored for offline deterministic scheduling of arbitrary sizes on unrelated machines. The goal is to minimize a complex objective function that includes the makespan and the weighted tardiness of jobs and machines. Unlike existing online approaches, which process jobs sequentially, our method generates a complete schedule considering the entire input at once. The key contribution of this work lies in the sophisticated architecture of our model. By leveraging various NLP-inspired architectures, it effectively processes any number of jobs and machines with varying feature dimensions imposed by unrelated processing times. Our approach enables supervised training on small problem instances while demonstrating strong generalization to much larger scheduling environments. Trained and tested on instances with 8 jobs and 4 machines, costs were only 2.51% above optimal. Across all tested configurations of up to 100 jobs and 10 machines, our network consistently outperformed an advanced dispatching rule, which incurred 22.22% higher costs on average. As our method allows fast retraining with simulated data and adaptation to various scheduling conditions, we believe it has the potential to become a standard approach for learning-based scheduling on unrelated machines and similar problem environments.

---

### QuantiPhy: A Quantitative Benchmark Evaluating Physical Reasoning Abilities of Vision-Language Models

Authors: Li Puyin, Tiange Xiang, Ella Mao, Shirley Wei, Xinye Chen, Adnan Masood, Li Fei-fei, Ehsan Adeli
Published: 2025-12-22
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.19526v1

Understanding the physical world is essential for generalist AI agents. However, it remains unclear whether state-of-the-art vision perception models (e.g., large VLMs) can reason physical properties quantitatively. Existing evaluations are predominantly VQA-based and qualitative, offering limited insight into whether these models can infer the kinematic quantities of moving objects from video observations. To address this, we present QuantiPhy, the first benchmark designed to quantitatively measure a VLM's physical reasoning ability. Comprising more than 3.3K video-text instances with numerical ground truth, QuantiPhy evaluates a VLM's performance on estimating an object's size, velocity, and acceleration at a given timestamp, using one of these properties as an input prior. The benchmark standardizes prompts and scoring to assess numerical accuracy, enabling fair comparisons across models. Our experiments on state-of-the-art VLMs reveal a consistent gap between their qualitative plausibility and actual numerical correctness. We further provide an in-depth analysis of key factors like background noise, counterfactual priors, and strategic prompting and find that state-of-the-art VLMs lean heavily on pre-trained world knowledge rather than faithfully using the provided visual and textual inputs as references when reasoning kinematic properties quantitatively. QuantiPhy offers the first rigorous, scalable testbed to move VLMs beyond mere verbal plausibility toward a numerically grounded physical understanding.

---

### Initialization of a Polyharmonic Cascade, Launch and Testing

Authors: Yuriy N. Bakhvalov
Published: 2025-12-22
Categories: cs.LG, math.NA
arXiv: https://arxiv.org/abs/2512.19524v1

This paper concludes a series of studies on the polyharmonic cascade, a deep machine learning architecture theoretically derived from indifference principles and the theory of random functions. A universal initialization procedure is proposed, based on symmetric constellations in the form of hyperoctahedra with a central point. This initialization not only ensures stable training of cascades with tens and hundreds of layers (up to 500 layers without skip connections), but also radically simplifies the computations. Scalability and robustness are demonstrated on MNIST (98.3% without convolutions or augmentations), HIGGS (AUC approximately 0.885 on 11M examples), and Epsilon (AUC approximately 0.963 with 2000 features). All linear algebra is reduced to 2D operations and is efficiently executed on GPUs. A public repository and an archived snapshot are provided for full reproducibility.

---

### A Convolutional Neural Deferred Shader for Physics Based Rendering

Authors: Zhuo He, Yingdong Ru, Qianying Liu, Paul Henderson, Nicolas Pugeault
Published: 2025-12-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.19522v1

Recent advances in neural rendering have achieved impressive results on photorealistic shading and relighting, by using a multilayer perceptron (MLP) as a regression model to learn the rendering equation from a real-world dataset. Such methods show promise for photorealistically relighting real-world objects, which is difficult to classical rendering, as there is no easy-obtained material ground truth. However, significant challenges still remain the dense connections in MLPs result in a large number of parameters, which requires high computation resources, complicating the training, and reducing performance during rendering. Data driven approaches require large amounts of training data for generalization; unbalanced data might bias the model to ignore the unusual illumination conditions, e.g. dark scenes. This paper introduces pbnds+: a novel physics-based neural deferred shading pipeline utilizing convolution neural networks to decrease the parameters and improve the performance in shading and relighting tasks; Energy regularization is also proposed to restrict the model reflection during dark illumination. Extensive experiments demonstrate that our approach outperforms classical baselines, a state-of-the-art neural shading model, and a diffusion-based method.

---

### LacaDM: A Latent Causal Diffusion Model for Multiobjective Reinforcement Learning

Authors: Xueming Yan, Bo Yin, Yaochu Jin
Published: 2025-12-22
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.19516v1

Multiobjective reinforcement learning (MORL) poses significant challenges due to the inherent conflicts between objectives and the difficulty of adapting to dynamic environments. Traditional methods often struggle to generalize effectively, particularly in large and complex state-action spaces. To address these limitations, we introduce the Latent Causal Diffusion Model (LacaDM), a novel approach designed to enhance the adaptability of MORL in discrete and continuous environments. Unlike existing methods that primarily address conflicts between objectives, LacaDM learns latent temporal causal relationships between environmental states and policies, enabling efficient knowledge transfer across diverse MORL scenarios. By embedding these causal structures within a diffusion model-based framework, LacaDM achieves a balance between conflicting objectives while maintaining strong generalization capabilities in previously unseen environments. Empirical evaluations on various tasks from the MOGymnasium framework demonstrate that LacaDM consistently outperforms the state-of-art baselines in terms of hypervolume, sparsity, and expected utility maximization, showcasing its effectiveness in complex multiobjective tasks.

---

### Anatomy-R1: Enhancing Anatomy Reasoning in Multimodal Large Language Models via Anatomical Similarity Curriculum and Group Diversity Augmentation

Authors: Ziyang Song, Zelin Zang, Zuyao Chen, Xusheng Liang, Dong Yi, Jinlin Wu, Hongbin Liu, Jiebo Luo, Zhen. Lei
Published: 2025-12-22
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2512.19512v2

Multimodal Large Language Models (MLLMs) have achieved impressive progress in natural image reasoning, yet their potential in medical imaging remains underexplored, especially in clinical anatomical surgical images. Anatomy understanding tasks demand precise understanding and clinically coherent answers, which are difficult to achieve due to the complexity of medical data and the scarcity of high-quality expert annotations. These challenges limit the effectiveness of conventional Supervised Fine-Tuning (SFT) strategies. While recent work has demonstrated that Group Relative Policy Optimization (GRPO) can enhance reasoning in MLLMs without relying on large amounts of data, we find two weaknesses that hinder GRPO's reasoning performance in anatomy recognition: 1) knowledge cannot be effectively shared between different anatomical structures, resulting in uneven information gain and preventing the model from converging, and 2) the model quickly converges to a single reasoning path, suppressing the exploration of diverse strategies. To overcome these challenges, we propose two novel methods. First, we implement a progressive learning strategy called Anatomical Similarity Curriculum Learning by controlling question difficulty via the similarity of answer choices, enabling the model to master complex problems incrementally. Second, we utilize question augmentation referred to as Group Diversity Question Augmentation to expand the model's search space for difficult queries, mitigating the tendency to produce uniform responses. Comprehensive experiments on the SGG-VQA and OmniMedVQA benchmarks show our method achieves a significant improvement across the two benchmarks, demonstrating its effectiveness in enhancing the medical reasoning capabilities of MLLMs. The code can be found in https://github.com/tomato996/Anatomy-R1

---

### Toward Scalable and Valid Conditional Independence Testing with Spectral Representations

Authors: Alek Fröhlich, Vladimir R. Kostic, Karim Lounici, Daniel Perazzo, Daniel Tiezzi, Massimiliano Pontil
Published: 2025-12-22
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2512.19510v2

Conditional independence (CI) is central to causal inference, feature selection, and graphical modeling, yet it is untestable in many settings without additional assumptions. Existing CI tests often rely on restrictive structural conditions, limiting their validity. Kernel methods using partial covariance operators offer a more principled approach but suffer from limited adaptivity and scalability. In this work, we explore whether representation learning can help address these limitations. Specifically, we focus on representations derived from the singular value decomposition of partial covariance operators and use them to construct a simple test statistic. We also introduce a bi-level contrastive algorithm to learn these representations. Our theory links representation learning error to test performance and establishes asymptotic validity and power guarantees. Experiments on real and synthetic data suggest that this approach offers a principled and statistically grounded path toward scalable CI testing, bridging kernel-based theory with modern representation learning.

---

### DK-STN: A Domain Knowledge Embedded Spatio-Temporal Network Model for MJO Forecast

Authors: Hongliang Li, Nong Zhang, Zhewen Xu, Xiang Li, Changzheng Liu, Chongbo Zhao, Jie Wu
Published: 2025-12-22
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.19506v1

Understanding and predicting the Madden-Julian Oscillation (MJO) is fundamental for precipitation forecasting and disaster prevention. To date, long-term and accurate MJO prediction has remained a challenge for researchers. Conventional MJO prediction methods using Numerical Weather Prediction (NWP) are resource-intensive, time-consuming, and highly unstable (most NWP methods are sensitive to seasons, with better MJO forecast results in winter). While existing Artificial Neural Network (ANN) methods save resources and speed forecasting, their accuracy never reaches the 28 days predicted by the state-of-the-art NWP method, i.e., the operational forecasts from ECMWF, since neural networks cannot handle climate data effectively. In this paper, we present a Domain Knowledge Embedded Spatio-Temporal Network (DK-STN), a stable neural network model for accurate and efficient MJO forecasting. It combines the benefits of NWP and ANN methods and successfully improves the forecast accuracy of ANN methods while maintaining a high level of efficiency and stability. We begin with a spatial-temporal network (STN) and embed domain knowledge in it using two key methods: (i) applying a domain knowledge enhancement method and (ii) integrating a domain knowledge processing method into network training. We evaluated DK-STN with the 5th generation of ECMWF reanalysis (ERA5) data and compared it with ECMWF. Given 7 days of climate data as input, DK-STN can generate reliable forecasts for the following 28 days in 1-2 seconds, with an error of only 2-3 days in different seasons. DK-STN significantly exceeds ECMWF in that its forecast accuracy is equivalent to ECMWF's, while its efficiency and stability are significantly superior.

---

### FusionNet: Physics-Aware Representation Learning for Multi-Spectral and Thermal Data via Trainable Signal-Processing Priors

Authors: Georgios Voulgaris
Published: 2025-12-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.19504v2

Cement production underpins global infrastructure but contributes approximately 7% of anthropogenic CO2 emissions, making accurate monitoring of production facilities essential for sustainable development. Existing remote sensing approaches rely predominantly on thermal signatures from kiln operations, which can be confounded by background heat sources and fail to capture persistent environmental alterations. This study introduces a physics-informed methodology that exploits multi-spectral features, particularly a geological Short Wave Infrared (SWIR) ratio, to detect soil property changes induced by sustained industrial heat emissions. This work proposes FusionNet, an intermediate multi-spectral data fusion framework that integrates Thermal Infrared (TIR) and SWIR inputs through a specialised backbone, embedding differential signal processing priors within a convolutional layer, mixed pooling, and wider receptive field. Systematic ablation studies confirm that each architectural component contributes to performance gains, with DGCNN achieving a 4.1-6.8% accuracy improvement over conventional CNNs. On the SWIR ratio dataset, FusionNet attains a maximum of 90.6%, outperforming state-of-the-art baselines across five spectral configurations and exceeding the strongest unimodal model by 1.1%. Transfer learning experiments reveal that ImageNet pretraining degrades TIR and SWIR performance, underscoring the importance of modality-aware training for cross-spectral applications. Overall, the results demonstrate that combining physics-aware feature selection with principled deep learning architectures enables robust, high-accuracy detection of cement production facilities, offering a reliable framework for industrial infrastructure monitoring

---

### Kolmogorov-Arnold graph neural networks for chemically informed prediction tasks on inorganic nanomaterials

Authors: Nikita Volzhin, Soowhan Yoon
Published: 2025-12-22
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.19494v2

The recent development of Kolmogorov-Arnold Networks (KANs) has found its application in the field of Graph Neural Networks (GNNs) particularly in molecular data modeling and potential drug discovery. Kolmogorov-Arnold Graph Neural Networks (KAGNNs) expand on the existing set of GNN models with KAN-based counterparts. KAGNNs have been demonstrably successful in surpassing the accuracy of MultiLayer Perceptron (MLP)-based GNNs in the task of molecular property prediction. These models were widely tested on the graph datasets consisting of organic molecules. In this study, we explore the application of KAGNNs towards inorganic nanomaterials. In 2024, a large scale inorganic nanomaterials dataset was published under the title CHILI (Chemically-Informed Large-scale Inorganic Nanomaterials Dataset), and various MLP-based GNNs have been tested on this dataset. We adapt and test our own KAGNNs appropriate for eight defined tasks. Our experiments reveal that, KAGNNs frequently surpass the performance of their counterpart GNNs. Most notably, on crystal system and space group classification tasks in CHILI-3K, KAGNNs achieve the new state-of-the-art results of 99.5 percent and 96.6 percent accuracy, respectively, compared to the previous 65.7 and 73.3 percent each.

---

### Learning from sanctioned government suppliers: A machine learning and network science approach to detecting fraud and corruption in Mexico

Authors: Martí Medina-Hernández, Janos Kertész, Mihály Fazekas
Published: 2025-12-22
Categories: cs.LG, cs.CY
arXiv: https://arxiv.org/abs/2512.19491v2

Detecting fraud and corruption in public procurement remains a major challenge for governments worldwide. Most research to-date builds on domain-knowledge-based corruption risk indicators of individual contract-level features and some also analyzes contracting network patterns. A critical barrier for supervised machine learning is the absence of confirmed non-corrupt, negative, examples, which makes conventional machine learning inappropriate for this task. Using publicly available data on federally funded procurement in Mexico and company sanction records, this study implements positive-unlabeled (PU) learning algorithms that integrate domain-knowledge-based red flags with network-derived features to identify likely corrupt and fraudulent contracts. The best-performing PU model on average captures 32 percent more known positives and performs on average 2.3 times better than random guessing, substantially outperforming approaches based solely on traditional red flags. The analysis of the Shapley Additive Explanations reveals that network-derived features, particularly those associated with contracts in the network core or suppliers with high eigenvector centrality, are the most important. Traditional red flags further enhance model performance in line with expectations, albeit mainly for contracts awarded through competitive tenders. This methodology can support law enforcement in Mexico, and it can be adapted to other national contexts too.

---

### Rethinking Coupled Tensor Analysis for Hyperspectral Super-Resolution: Recoverable Modeling Under Endmember Variability

Authors: Meng Ding, Xiao Fu
Published: 2025-12-22
Categories: eess.IV, cs.CV
arXiv: https://arxiv.org/abs/2512.19489v1

This work revisits the hyperspectral super-resolution (HSR) problem, i.e., fusing a pair of spatially co-registered hyperspectral (HSI) and multispectral (MSI) images to recover a super-resolution image (SRI) that enhances the spatial resolution of the HSI. Coupled tensor decomposition (CTD)-based methods have gained traction in this domain, offering recoverability guarantees under various assumptions. Existing models such as canonical polyadic decomposition (CPD) and Tucker decomposition provide strong expressive power but lack physical interpretability. The block-term decomposition model with rank-$(L_r, L_r, 1)$ terms (the LL1 model) yields interpretable factors under the linear mixture model (LMM) of spectral images, but LMM assumptions are often violated in practice -- primarily due to nonlinear effects such as endmember variability (EV). To address this, we propose modeling spectral images using a more flexible block-term tensor decomposition with rank-$(L_r, M_r, N_r)$ terms (the LMN model). This modeling choice retains interpretability, subsumes CPD, Tucker, and LL1 as special cases, and robustly accounts for non-ideal effects such as EV, offering a balanced tradeoff between expressiveness and interpretability for HSR. Importantly, under the LMN model for HSI and MSI, recoverability of the SRI can still be established under proper conditions -- providing strong theoretical support. Extensive experiments on synthetic and real datasets further validate the effectiveness and robustness of the proposed method compared with existing CTD-based approaches.

---

### Lightweight Intrusion Detection in IoT via SHAP-Guided Feature Pruning and Knowledge-Distilled Kronecker Networks

Authors: Hafsa Benaddi, Mohammed Jouhari, Nouha Laamech, Anas Motii, Khalil Ibrahimi
Published: 2025-12-22
Categories: cs.LG, cs.NI
arXiv: https://arxiv.org/abs/2512.19488v1

The widespread deployment of Internet of Things (IoT) devices requires intrusion detection systems (IDS) with high accuracy while operating under strict resource constraints. Conventional deep learning IDS are often too large and computationally intensive for edge deployment. We propose a lightweight IDS that combines SHAP-guided feature pruning with knowledge-distilled Kronecker networks. A high-capacity teacher model identifies the most relevant features through SHAP explanations, and a compressed student leverages Kronecker-structured layers to minimize parameters while preserving discriminative inputs. Knowledge distillation transfers softened decision boundaries from teacher to student, improving generalization under compression. Experiments on the TON\_IoT dataset show that the student is nearly three orders of magnitude smaller than the teacher yet sustains macro-F1 above 0.986 with millisecond-level inference latency. The results demonstrate that explainability-driven pruning and structured compression can jointly enable scalable, low-latency, and energy-efficient IDS for heterogeneous IoT environments.

---

### Dynamic Stream Network for Combinatorial Explosion Problem in Deformable Medical Image Registration

Authors: Shaochen Bi, Yuting He, Weiming Wang, Hao Chen
Published: 2025-12-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.19486v1

Combinatorial explosion problem caused by dual inputs presents a critical challenge in Deformable Medical Image Registration (DMIR). Since DMIR processes two images simultaneously as input, the combination relationships between features has grown exponentially, ultimately the model considers more interfering features during the feature modeling process. Introducing dynamics in the receptive fields and weights of the network enable the model to eliminate the interfering features combination and model the potential feature combination relationships. In this paper, we propose the Dynamic Stream Network (DySNet), which enables the receptive fields and weights to be dynamically adjusted. This ultimately enables the model to ignore interfering feature combinations and model the potential feature relationships. With two key innovations: 1) Adaptive Stream Basin (AdSB) module dynamically adjusts the shape of the receptive field, thereby enabling the model to focus on the feature relationships with greater correlation. 2) Dynamic Stream Attention (DySA) mechanism generates dynamic weights to search for more valuable feature relationships. Extensive experiments have shown that DySNet consistently outperforms the most advanced DMIR methods, highlighting its outstanding generalization ability. Our code will be released on the website: https://github.com/ShaochenBi/DySNet.

---

### Structured Event Representation and Stock Return Predictability

Authors: Gang Li, Dandan Qiao, Mingxuan Zheng
Published: 2025-12-22
Categories: econ.GN, cs.CE, stat.ML
arXiv: https://arxiv.org/abs/2512.19484v1

We find that event features extracted by large language models (LLMs) are effective for text-based stock return prediction. Using a pre-trained LLM to extract event features from news articles, we propose a novel deep learning model based on structured event representation (SER) and attention mechanisms to predict stock returns in the cross-section. Our SER-based model provides superior performance compared with other existing text-driven models to forecast stock returns out of sample and offers highly interpretable feature structures to examine the mechanisms underlying the stock return predictability. We further provide various implications based on SER and highlight the crucial benefit of structured model inputs in stock return predictability.

---

### A Dataset and Preliminary Study of Using GPT-5 for Code-change Impact Analysis

Authors: Katharina Stengg, Christian Macho, Martin Pinzger
Published: 2025-12-22
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2512.19481v1

Understanding source code changes and their impact on other code entities is a crucial skill in software development. However, the analysis of code changes and their impact is often performed manually and therefore is time-consuming. Recent advancements in AI, and in particular large language models (LLMs) show promises to help developers in various code analysis tasks. However, the extent to which this potential can be utilized for understanding code changes and their impact is underexplored. To address this gap, we study the capabilities of GPT-5 and GPT-5-mini to predict the code entities impacted by given source code changes. We construct a dataset containing information about seed-changes, change pairs, and change types for each commit. Existing datasets lack crucial information about seed changes and impacted code entities. Our experiments evaluate the LLMs in two configurations: (1) seed-change information and the parent commit tree and (2) seed-change information, the parent commit tree, and the diff hunk of each seed change. We found that both LLMs perform poorly in the two experiments, whereas GPT-5 outperforms GPT-5-mini. Furthermore, the provision of the diff hunks helps both models to slightly improve their performance.

---

### Emotion-Director: Bridging Affective Shortcut in Emotion-Oriented Image Generation

Authors: Guoli Jia, Junyao Hu, Xinwei Long, Kai Tian, Kaiyan Zhang, KaiKai Zhao, Ning Ding, Bowen Zhou
Published: 2025-12-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.19479v1

Image generation based on diffusion models has demonstrated impressive capability, motivating exploration into diverse and specialized applications. Owing to the importance of emotion in advertising, emotion-oriented image generation has attracted increasing attention. However, current emotion-oriented methods suffer from an affective shortcut, where emotions are approximated to semantics. As evidenced by two decades of research, emotion is not equivalent to semantics. To this end, we propose Emotion-Director, a cross-modal collaboration framework consisting of two modules. First, we propose a cross-Modal Collaborative diffusion model, abbreviated as MC-Diffusion. MC-Diffusion integrates visual prompts with textual prompts for guidance, enabling the generation of emotion-oriented images beyond semantics. Further, we improve the DPO optimization by a negative visual prompt, enhancing the model's sensitivity to different emotions under the same semantics. Second, we propose MC-Agent, a cross-Modal Collaborative Agent system that rewrites textual prompts to express the intended emotions. To avoid template-like rewrites, MC-Agent employs multi-agents to simulate human subjectivity toward emotions, and adopts a chain-of-concept workflow that improves the visual expressiveness of the rewritten prompts. Extensive qualitative and quantitative experiments demonstrate the superiority of Emotion-Director in emotion-oriented image generation.

---

### A Large-Language-Model Framework for Automated Humanitarian Situation Reporting

Authors: Ivan Decostanzi, Yelena Mejova, Kyriaki Kalimeri
Published: 2025-12-22
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.19475v1

Timely and accurate situational reports are essential for humanitarian decision-making, yet current workflows remain largely manual, resource intensive, and inconsistent. We present a fully automated framework that uses large language models (LLMs) to transform heterogeneous humanitarian documents into structured and evidence-grounded reports. The system integrates semantic text clustering, automatic question generation, retrieval augmented answer extraction with citations, multi-level summarization, and executive summary generation, supported by internal evaluation metrics that emulate expert reasoning. We evaluated the framework across 13 humanitarian events, including natural disasters and conflicts, using more than 1,100 documents from verified sources such as ReliefWeb. The generated questions achieved 84.7 percent relevance, 84.0 percent importance, and 76.4 percent urgency. The extracted answers reached 86.3 percent relevance, with citation precision and recall both exceeding 76 percent. Agreement between human and LLM based evaluations surpassed an F1 score of 0.80. Comparative analysis shows that the proposed framework produces reports that are more structured, interpretable, and actionable than existing baselines. By combining LLM reasoning with transparent citation linking and multi-level evaluation, this study demonstrates that generative AI can autonomously produce accurate, verifiable, and operationally useful humanitarian situation reports.

---

### Multi-Layer Confidence Scoring for Detection of Out-of-Distribution Samples, Adversarial Attacks, and In-Distribution Misclassifications

Authors: Lorenzo Capelli, Leandro de Souza Rosa, Gianluca Setti, Mauro Mangia, Riccardo Rovatti
Published: 2025-12-22
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.19472v1

The recent explosive growth in Deep Neural Networks applications raises concerns about the black-box usage of such models, with limited trasparency and trustworthiness in high-stakes domains, which have been crystallized as regulatory requirements such as the European Union Artificial Intelligence Act. While models with embedded confidence metrics have been proposed, such approaches cannot be applied to already existing models without retraining, limiting their broad application. On the other hand, post-hoc methods, which evaluate pre-trained models, focus on solving problems related to improving the confidence in the model's predictions, and detecting Out-Of-Distribution or Adversarial Attacks samples as independent applications. To tackle the limited applicability of already existing methods, we introduce Multi-Layer Analysis for Confidence Scoring (MACS), a unified post-hoc framework that analyzes intermediate activations to produce classification-maps. From the classification-maps, we derive a score applicable for confidence estimation, detecting distributional shifts and adversarial attacks, unifying the three problems in a common framework, and achieving performances that surpass the state-of-the-art approaches in our experiments with the VGG16 and ViTb16 models with a fraction of their computational overhead.

---

### GLUE: Coordinating Pre-Trained Generative Models for System-Level Design

Authors: Tim Aebersold, Soheyl Massoudi, Mark D. Fuge
Published: 2025-12-22
Categories: cs.CE, cs.LG
arXiv: https://arxiv.org/abs/2512.19469v2

Engineering complex systems (aircraft, buildings, vehicles) requires coordinating geometric and performance couplings across subsystems. As generative models proliferate for specialized domains, a key research gap is how to coordinate frozen, pre-trained submodels to generate full-system designs that are feasible, diverse, and high-performing. We introduce GLUE, which orchestrates pre-trained, frozen generators while enforcing system-level feasibility, optimality, and diversity. Compatible models must be end-to-end differentiable with a smooth, well-behaved latent-to-output mapping. We propose and benchmark (i) data-driven GLUE models trained on pre-generated system-level designs and (ii) a data-free GLUE model trained on a differentiable geometry layer. On a UAV design problem with five coupling constraints, we find that data-driven approaches yield diverse, high-performing designs but require large datasets to satisfy constraints reliably. The data-free approach is competitive with Bayesian optimization and gradient-based optimization in performance and feasibility while training a full generative model in only ~10 min on an RTX 4090 GPU, requiring more than two orders of magnitude fewer geometry evaluations and FLOPs than the data-driven method. We identify equality constraint satisfaction as a key difficulty and remaining limitation, and ablate approaches that improve this for the data-free approach. As a first step toward scaling generative design to complex, real-world engineering systems, this work explores how unmodified, domain-informed submodels can be integrated into a modular generative workflow.

---

### Epistemological Fault Lines Between Human and Artificial Intelligence

Authors: Walter Quattrociocchi, Valerio Capraro, Matjaž Perc
Published: 2025-12-22
Categories: cs.CY, cs.CL, cs.HC
arXiv: https://arxiv.org/abs/2512.19466v1

Large language models (LLMs) are widely described as artificial intelligence, yet their epistemic profile diverges sharply from human cognition. Here we show that the apparent alignment between human and machine outputs conceals a deeper structural mismatch in how judgments are produced. Tracing the historical shift from symbolic AI and information filtering systems to large-scale generative transformers, we argue that LLMs are not epistemic agents but stochastic pattern-completion systems, formally describable as walks on high-dimensional graphs of linguistic transitions rather than as systems that form beliefs or models of the world. By systematically mapping human and artificial epistemic pipelines, we identify seven epistemic fault lines, divergences in grounding, parsing, experience, motivation, causal reasoning, metacognition, and value. We call the resulting condition Epistemia: a structural situation in which linguistic plausibility substitutes for epistemic evaluation, producing the feeling of knowing without the labor of judgment. We conclude by outlining consequences for evaluation, governance, and epistemic literacy in societies increasingly organized around generative AI.

---

### VASP Agent: An Agentic Framework for Autonomous First-principles Calculations

Authors: Zeyu Xia, Jinzhe Ma, Congjie Zheng, Zhongyao Wang, Shufei Zhang, Yuqiang Li, Hang Su, P. Hu, Changshui Zhang, Xingao Gong, Wanli Ouyang, Lei Bai et al.
Published: 2025-12-22
Categories: cs.AI, cond-mat.mtrl-sci
arXiv: https://arxiv.org/abs/2512.19458v2

Large Language Models (LLMs) are increasingly embedded in agentic frameworks for scientific discovery. First-principles materials computation imposes a demanding standard for autonomy: successful execution depends on internally consistent inputs, supervision of long-running calculations, and verified outputs. Here we present VASP Agent, a coding-agent-centered system that combines reusable domain skills, deterministic tools, workspace-state inspection, runtime evidence, and scientific guardrails to execute multi-step VASP calculations. The system is evaluated across multiple tasks including structural relaxation, bandgap calculation, equilibrium lattice constant determination, and CO/Pt(111) adsorption. VASP Agent completes all evaluated cases, and its computed numerical results are compared with those obtained using pymatgen and other agentic tools. When large deviations occur, the calculation parameters produced by VASP Agent are more appropriate than those produced by LLM-based workflows. Failure analysis shows that errors that terminate fixed pipelines can be diagnosed and recovered under agentic control.

---

### Activations as Features: Probing LLMs for Generalizable Essay Scoring Representations

Authors: Jinwei Chi, Ke Wang, Yu Chen, Xuanye Lin, Qiang Xu
Published: 2025-12-22
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2512.19456v1

Automated essay scoring (AES) is a challenging task in cross-prompt settings due to the diversity of scoring criteria. While previous studies have focused on the output of large language models (LLMs) to improve scoring accuracy, we believe activations from intermediate layers may also provide valuable information. To explore this possibility, we evaluated the discriminative power of LLMs' activations in cross-prompt essay scoring task. Specifically, we used activations to fit probes and further analyzed the effects of different models and input content of LLMs on this discriminative power. By computing the directions of essays across various trait dimensions under different prompts, we analyzed the variation in evaluation perspectives of large language models concerning essay types and traits. Results show that the activations possess strong discriminative power in evaluating essay quality and that LLMs can adapt their evaluation perspectives to different traits and essay types, effectively handling the diversity of scoring criteria in cross-prompt settings.

---

### SiamGPT: Quality-First Fine-Tuning for Stable Thai Text Generation

Authors: Thittipat Pairatsuppawat, Abhibhu Tachaapornchai, Paweekorn Kusolsomboon, Chutikan Chaiwong, Thodsaporn Chay-intr, Kobkrit Viriyayudhakorn, Nongnuch Ketui, Aslan B. Wong
Published: 2025-12-22
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.19455v3

Open-weights large language models remain difficult to deploy for Thai due to unstable generation under complex instructions, despite strong English performance. To mitigate these limitations, We present SiamGPT-32B, an open-weights model based on Qwen3-32B, fine-tuned with a Quality-First strategy emphasizing curated supervision over data scale. The fine-tuning pipeline combines high-complexity English instruction data with a Thai-adapted AutoIF framework for instruction and linguistic constraints. Using supervised fine-tuning only, without continual pretraining or corpus expansion, SiamGPT-32B improves instruction adherence, multi-turn robustness, and linguistic stability. Evaluations on the SEA-HELM benchmark show that SiamGPT-32B achieves the strongest overall performance among similar-scale open-weights Thai models, with consistent gains in instruction following, multi-turn dialogue, and natural language understanding.

---