# Research Papers — 2025-12 · bundle page 35 of 175 > Full-text markdown of papers #1701–1750 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/35 [← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/34.md) [Next bundle →](https://aipod.dev/papers/archive/2025-12/page/36.md) ### Information-theoretic signatures of causality in Bayesian networks and hypergraphs Authors: Sung En Chiang, Zhaolu Liu, Robert L. Peach, Mauricio Barahona Published: 2025-12-23 Categories: cs.IT, stat.ML arXiv: https://arxiv.org/abs/2512.20552v1 Analyzing causality in multivariate systems involves establishing how information is generated, distributed and combined, and thus requires tools that capture interactions beyond pairwise relations. Higher-order information theory provides such tools. In particular, Partial Information Decomposition (PID) allows the decomposition of the information that a set of sources provides about a target into redundant, unique, and synergistic components. Yet the mathematical connection between such higher-order information-theoretic measures and causal structure remains undeveloped. Here we establish the first theoretical correspondence between PID components and causal structure in both Bayesian networks and hypergraphs. We first show that in Bayesian networks unique information precisely characterizes direct causal neighbors, while synergy identifies collider relationships. This establishes a localist causal discovery paradigm in which the structure surrounding each variable can be recovered from its immediate informational footprint, eliminating the need for global search over graph space. Extending these results to higher-order systems, we prove that PID signatures in Bayesian hypergraphs differentiate parents, children, co-heads, and co-tails, revealing a higher-order collider effect unique to multi-tail hyperedges. We also present procedures by which our results can be used to characterize systematically the causal structure of Bayesian networks and hypergraphs. Our results position PID as a rigorous, model-agnostic foundation for inferring both pairwise and higher-order causal structure, and introduce a fundamentally local information-theoretic viewpoint on causal discovery. --- ### Advancing Multimodal Teacher Sentiment Analysis:The Large-Scale T-MED Dataset & The Effective AAM-TSA Model Authors: Zhiyi Duan, Xiangren Wang, Hongyu Yuan, Qianli Xing Published: 2025-12-23 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.20548v2 Teachers' emotional states are critical in educational scenarios, profoundly impacting teaching efficacy, student engagement, and learning achievements. However, existing studies often fail to accurately capture teachers' emotions due to the performative nature and overlook the critical impact of instructional information on emotional expression. In this paper, we systematically investigate teacher sentiment analysis by building both the dataset and the model accordingly. We construct the first large-scale teacher multimodal sentiment analysis dataset, T-MED. To ensure labeling accuracy and efficiency, we employ a human-machine collaborative labeling process. The T-MED dataset includes 14,938 instances of teacher emotional data from 250 real classrooms across 11 subjects ranging from K-12 to higher education, integrating multimodal text, audio, video, and instructional information. Furthermore, we propose a novel asymmetric attention-based multimodal teacher sentiment analysis model, AAM-TSA. AAM-TSA introduces an asymmetric attention mechanism and hierarchical gating unit to enable differentiated cross-modal feature fusion and precise emotional classification. Experimental results demonstrate that AAM-TSA significantly outperforms existing state-of-the-art methods in terms of accuracy and interpretability on the T-MED dataset. --- ### Advancing Multimodal Teacher Sentiment Analysis:The Large-Scale T-MED Dataset & The Effective AAM-TSA Model Authors: Zhiyi Duan, Xiangren Wang, Hongyu Yuan, Qianli Xing Published: 2025-12-23 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.20548v1 Teachers' emotional states are critical in educational scenarios, profoundly impacting teaching efficacy, student engagement, and learning achievements. However, existing studies often fail to accurately capture teachers' emotions due to the performative nature and overlook the critical impact of instructional information on emotional expression.In this paper, we systematically investigate teacher sentiment analysis by building both the dataset and the model accordingly. We construct the first large-scale teacher multimodal sentiment analysis dataset, T-MED.To ensure labeling accuracy and efficiency, we employ a human-machine collaborative labeling process.The T-MED dataset includes 14,938 instances of teacher emotional data from 250 real classrooms across 11 subjects ranging from K-12 to higher education, integrating multimodal text, audio, video, and instructional information.Furthermore, we propose a novel asymmetric attention-based multimodal teacher sentiment analysis model, AAM-TSA.AAM-TSA introduces an asymmetric attention mechanism and hierarchical gating unit to enable differentiated cross-modal feature fusion and precise emotional classification. Experimental results demonstrate that AAM-TSA significantly outperforms existing state-of-the-art methods in terms of accuracy and interpretability on the T-MED dataset. --- ### AlignPose: Generalizable 6D Pose Estimation via Multi-view Feature-metric Alignment Authors: Anna Šárová Mikeštíková, Médéric Fourmy, Martin Cífka, Josef Sivic, Vladimir Petrik Published: 2025-12-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.20538v2 Single-view RGB model-based object pose estimation methods achieve strong generalization but are fundamentally limited by depth ambiguity, clutter, and occlusions. Multi-view pose estimation methods have the potential to solve these issues, but existing works rely on precise single-view pose estimates or lack generalization to unseen objects. We address these challenges via the following three contributions. First, we introduce AlignPose, a 6D object pose estimation method that aggregates information from multiple extrinsically calibrated RGB views and does not require any object-specific training or symmetry annotation. Second, the key component of this approach is a new multi-view feature-metric refinement specifically designed for object pose. It optimizes a single, consistent world-frame object pose by minimizing the feature discrepancy between on-the-fly rendered object features and observed image features across all views simultaneously. Third, we report extensive experiments on six datasets (YCB-V, T-LESS, HouseCat6D, ITODD-MV, IPD, XYZ-IBD) using the BOP benchmark evaluation and show that AlignPose outperforms other published methods, especially on challenging industrial datasets where multiple views are readily available in practice. --- ### AlignPose: Generalizable 6D Pose Estimation via Multi-view Feature-metric Alignment Authors: Anna Šárová Mikeštíková, Médéric Fourmy, Martin Cífka, Josef Sivic, Vladimir Petrik Published: 2025-12-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.20538v1 Single-view RGB model-based object pose estimation methods achieve strong generalization but are fundamentally limited by depth ambiguity, clutter, and occlusions. Multi-view pose estimation methods have the potential to solve these issues, but existing works rely on precise single-view pose estimates or lack generalization to unseen objects. We address these challenges via the following three contributions. First, we introduce AlignPose, a 6D object pose estimation method that aggregates information from multiple extrinsically calibrated RGB views and does not require any object-specific training or symmetry annotation. Second, the key component of this approach is a new multi-view feature-metric refinement specifically designed for object pose. It optimizes a single, consistent world-frame object pose minimizing the feature discrepancy between on-the-fly rendered object features and observed image features across all views simultaneously. Third, we report extensive experiments on four datasets (YCB-V, T-LESS, ITODD-MV, HouseCat6D) using the BOP benchmark evaluation and show that AlignPose outperforms other published methods, especially on challenging industrial datasets where multiple views are readily available in practice. --- ### Over-the-Air Goal-Oriented Communications Authors: Kyriakos Stylianopoulos, Paolo Di Lorenzo, George C. Alexandropoulos Published: 2025-12-23 Categories: eess.SP, cs.ET, cs.IT, cs.LG arXiv: https://arxiv.org/abs/2512.20533v1 Goal-oriented communications offer an attractive alternative to the Shannon-based communication paradigm, where the data is never reconstructed at the Receiver (RX) side. Rather, focusing on the case of edge inference, the Transmitter (TX) and the RX cooperate to exchange features of the input data that will be used to predict an unseen attribute of them, leveraging information from collected data sets. This chapter demonstrates that the wireless channel can be used to perform computations over the data, when equipped with programmable metasurfaces. The end-to-end system of the TX, RX, and MS-based channel is treated as a single deep neural network which is trained through backpropagation to perform inference on unseen data. Using Stacked Intelligent Metasurfaces (SIM), it is shown that this Metasurfaces-Integrated Neural Network (MINN) can achieve performance comparable to fully digital neural networks under various system parameters and data sets. By offloading computations onto the channel itself, important benefits may be achieved in terms of energy consumption, arising from reduced computations at the transceivers and smaller transmission power required for successful inference. --- ### SirenPose: Dynamic Scene Reconstruction via Geometric Supervision Authors: Kaitong Cai, Jensen Zhang, Jing Yang, Keze Wang Published: 2025-12-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.20531v1 We introduce SirenPose, a geometry-aware loss formulation that integrates the periodic activation properties of sinusoidal representation networks with keypoint-based geometric supervision, enabling accurate and temporally consistent reconstruction of dynamic 3D scenes from monocular videos. Existing approaches often struggle with motion fidelity and spatiotemporal coherence in challenging settings involving fast motion, multi-object interaction, occlusion, and rapid scene changes. SirenPose incorporates physics inspired constraints to enforce coherent keypoint predictions across both spatial and temporal dimensions, while leveraging high frequency signal modeling to capture fine grained geometric details. We further expand the UniKPT dataset to 600,000 annotated instances and integrate graph neural networks to model keypoint relationships and structural correlations. Extensive experiments on benchmarks including Sintel, Bonn, and DAVIS demonstrate that SirenPose consistently outperforms state-of-the-art methods. On DAVIS, SirenPose achieves a 17.8 percent reduction in FVD, a 28.7 percent reduction in FID, and a 6.0 percent improvement in LPIPS compared to MoSCA. It also improves temporal consistency, geometric accuracy, user score, and motion smoothness. In pose estimation, SirenPose outperforms Monst3R with lower absolute trajectory error as well as reduced translational and rotational relative pose error, highlighting its effectiveness in handling rapid motion, complex dynamics, and physically plausible reconstruction. --- ### ScoreMatchingRiesz: Score Matching for Debiased Machine Learning and Policy Path Estimation Authors: Masahiro Kato Published: 2025-12-23 Categories: econ.EM, cs.LG, math.ST, stat.ME, stat.ML arXiv: https://arxiv.org/abs/2512.20523v2 We propose ScoreMatchingRiesz, a family of Riesz representer estimators based on score matching. The Riesz representer is a key nuisance component in debiased machine learning, enabling $\sqrt{n}$-consistent and asymptotically efficient estimation of causal and structural targets via Neyman-orthogonal scores. We formulate Riesz representer estimation as a score estimation problem. This perspective stabilizes representer estimation by allowing us to leverage denoising score matching and telescoping density ratio estimation. We also introduce the policy path, a parameter that captures how policy effects evolve under continuous treatments. We show that the policy path can be estimated via score matching by smoothly connecting average marginal effect (AME) and average policy effect (APE) estimation, which improves the interpretability of policy effects. --- ### ScoreMatchingRiesz: Auto-DML with Infinitesimal Classification Authors: Masahiro Kato Published: 2025-12-23 Categories: econ.EM, cs.LG, math.ST, stat.ME, stat.ML arXiv: https://arxiv.org/abs/2512.20523v1 This study proposes Riesz representer estimation methods based on score matching. The Riesz representer is a key component in debiased machine learning for constructing $\sqrt{n}$-consistent and efficient estimators in causal inference and structural parameter estimation. To estimate the Riesz representer, direct approaches have garnered attention, such as Riesz regression and the covariate balancing propensity score. These approaches can also be interpreted as variants of direct density ratio estimation (DRE) in several applications such as average treatment effect estimation. In DRE, it is well known that flexible models can easily overfit the observed data due to the estimand and the form of the loss function. To address this issue, recent work has proposed modeling the density ratio as a product of multiple intermediate density ratios and estimating it using score-matching techniques, which are often used in the diffusion model literature. We extend score-matching-based DRE methods to Riesz representer estimation. Our proposed method not only mitigates overfitting but also provides insights for causal inference by bridging marginal effects and average policy effects through time score functions. --- ### Benchmarking LLMs for Predictive Applications in the Intensive Care Units Authors: Chehak Malhotra, Mehak Gopal, Akshaya Devadiga, Pradeep Singh, Ridam Pal, Ritwik Kashyap, Tavpritesh Sethi Published: 2025-12-23 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.20520v1 With the advent of LLMs, various tasks across the natural language processing domain have been transformed. However, their application in predictive tasks remains less researched. This study compares large language models, including GatorTron-Base (trained on clinical data), Llama 8B, and Mistral 7B, against models like BioBERT, DocBERT, BioClinicalBERT, Word2Vec, and Doc2Vec, setting benchmarks for predicting Shock in critically ill patients. Timely prediction of shock can enable early interventions, thus improving patient outcomes. Text data from 17,294 ICU stays of patients in the MIMIC III database were scored for length of stay > 24 hours and shock index (SI) > 0.7 to yield 355 and 87 patients with normal and abnormal SI-index, respectively. Both focal and cross-entropy losses were used during finetuning to address class imbalances. Our findings indicate that while GatorTron Base achieved the highest weighted recall of 80.5%, the overall performance metrics were comparable between SLMs and LLMs. This suggests that LLMs are not inherently superior to SLMs in predicting future clinical events despite their strong performance on text-based tasks. To achieve meaningful clinical outcomes, future efforts in training LLMs should prioritize developing models capable of predicting clinical trajectories rather than focusing on simpler tasks such as named entity recognition or phenotyping. --- ### Explainable time-series forecasting with sampling-free SHAP for Transformers Authors: Matthias Hertel, Sebastian Pütz, Ralf Mikut, Veit Hagenmeyer, Benjamin Schäfer Published: 2025-12-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.20514v1 Time-series forecasts are essential for planning and decision-making in many domains. Explainability is key to building user trust and meeting transparency requirements. Shapley Additive Explanations (SHAP) is a popular explainable AI framework, but it lacks efficient implementations for time series and often assumes feature independence when sampling counterfactuals. We introduce SHAPformer, an accurate, fast and sampling-free explainable time-series forecasting model based on the Transformer architecture. It leverages attention manipulation to make predictions based on feature subsets. SHAPformer generates explanations in under one second, several orders of magnitude faster than the SHAP Permutation Explainer. On synthetic data with ground truth explanations, SHAPformer provides explanations that are true to the data. Applied to real-world electrical load data, it achieves competitive predictive performance and delivers meaningful local and global insights, such as identifying the past load as the key predictor and revealing a distinct model behavior during the Christmas period. --- ### Recurrent Off-Policy Deep Reinforcement Learning Doesn't Have to be Slow Authors: Tyler Clark, Christine Evers, Jonathon Hare Published: 2025-12-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.20513v1 Recurrent off-policy deep reinforcement learning models achieve state-of-the-art performance but are often sidelined due to their high computational demands. In response, we introduce RISE (Recurrent Integration via Simplified Encodings), a novel approach that can leverage recurrent networks in any image-based off-policy RL setting without significant computational overheads via using both learnable and non-learnable encoder layers. When integrating RISE into leading non-recurrent off-policy RL algorithms, we observe a 35.6% human-normalized interquartile mean (IQM) performance improvement across the Atari benchmark. We analyze various implementation strategies to highlight the versatility and potential of our proposed framework. --- ### Bridging Modalities and Transferring Knowledge: Enhanced Multimodal Understanding and Recognition Authors: Gorjan Radevski Published: 2025-12-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.20501v1 This manuscript explores multimodal alignment, translation, fusion, and transference to enhance machine understanding of complex inputs. We organize the work into five chapters, each addressing unique challenges in multimodal machine learning. Chapter 3 introduces Spatial-Reasoning Bert for translating text-based spatial relations into 2D arrangements between clip-arts. This enables effective decoding of spatial language into visual representations, paving the way for automated scene generation aligned with human spatial understanding. Chapter 4 presents a method for translating medical texts into specific 3D locations within an anatomical atlas. We introduce a loss function leveraging spatial co-occurrences of medical terms to create interpretable mappings, significantly enhancing medical text navigability. Chapter 5 tackles translating structured text into canonical facts within knowledge graphs. We develop a benchmark for linking natural language to entities and predicates, addressing ambiguities in text extraction to provide clearer, actionable insights. Chapter 6 explores multimodal fusion methods for compositional action recognition. We propose a method fusing video frames and object detection representations, improving recognition robustness and accuracy. Chapter 7 investigates multimodal knowledge transference for egocentric action recognition. We demonstrate how multimodal knowledge distillation enables RGB-only models to mimic multimodal fusion-based capabilities, reducing computational requirements while maintaining performance. These contributions advance methodologies for spatial language understanding, medical text interpretation, knowledge graph enrichment, and action recognition, enhancing computational systems' ability to process complex, multimodal inputs across diverse applications. --- ### Step-DeepResearch Technical Report Authors: Chen Hu, Haikuo Du, Heng Wang, Lin Lin, Mingrui Chen, Peng Liu, Ruihang Miao, Tianchi Yue, Wang You, Wei Ji, Wei Yuan, Wenjin Deng et al. Published: 2025-12-23 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.20491v4 As LLMs shift toward autonomous agents, Deep Research has emerged as a pivotal metric. However, existing academic benchmarks like BrowseComp often fail to meet real-world demands for open-ended research, which requires robust skills in intent recognition, long-horizon decision-making, and cross-source verification. To address this, we introduce Step-DeepResearch, a cost-effective, end-to-end agent. We propose a Data Synthesis Strategy Based on Atomic Capabilities to reinforce planning and report writing, combined with a progressive training path from agentic mid-training to SFT and RL. Enhanced by a Checklist-style Judger, this approach significantly improves robustness. Furthermore, to bridge the evaluation gap in the Chinese domain, we establish ADR-Bench for realistic deep research scenarios. Experimental results show that Step-DeepResearch (32B) scores 61.4% on Scale AI Research Rubrics. On ADR-Bench, it significantly outperforms comparable models and rivals SOTA closed-source models like OpenAI and Gemini DeepResearch. These findings prove that refined training enables medium-sized models to achieve expert-level capabilities at industry-leading cost-efficiency. --- ### Step-DeepResearch Technical Report Authors: Chen Hu, Haikuo Du, Heng Wang, Lin Lin, Mingrui Chen, Peng Liu, Ruihang Miao, Tianchi Yue, Wang You, Wei Ji, Wei Yuan, Wenjin Deng et al. Published: 2025-12-23 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.20491v1 As LLMs shift toward autonomous agents, Deep Research has emerged as a pivotal metric. However, existing academic benchmarks like BrowseComp often fail to meet real-world demands for open-ended research, which requires robust skills in intent recognition, long-horizon decision-making, and cross-source verification. To address this, we introduce Step-DeepResearch, a cost-effective, end-to-end agent. We propose a Data Synthesis Strategy Based on Atomic Capabilities to reinforce planning and report writing, combined with a progressive training path from agentic mid-training to SFT and RL. Enhanced by a Checklist-style Judger, this approach significantly improves robustness. Furthermore, to bridge the evaluation gap in the Chinese domain, we establish ADR-Bench for realistic deep research scenarios. Experimental results show that Step-DeepResearch (32B) scores 61.4% on Scale AI Research Rubrics. On ADR-Bench, it significantly outperforms comparable models and rivals SOTA closed-source models like OpenAI and Gemini DeepResearch. These findings prove that refined training enables medium-sized models to achieve expert-level capabilities at industry-leading cost-efficiency. --- ### Multi-temporal Adaptive Red-Green-Blue and Long-Wave Infrared Fusion for You Only Look Once-Based Landmine Detection from Unmanned Aerial Systems Authors: James E. Gallagher, Edward J. Oughton, Jana Kosecka Published: 2025-12-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.20487v1 Landmines remain a persistent humanitarian threat, with 110 million actively deployed mines across 60 countries, claiming 26,000 casualties annually. This research evaluates adaptive Red-Green-Blue (RGB) and Long-Wave Infrared (LWIR) fusion for Unmanned Aerial Systems (UAS)-based detection of surface-laid landmines, leveraging the thermal contrast between the ordnance and the surrounding soil to enhance feature extraction. Using You Only Look Once (YOLO) architectures (v8, v10, v11) across 114 test images, generating 35,640 model-condition evaluations, YOLOv11 achieved optimal performance (86.8% mAP), with 10 to 30% thermal fusion at 5 to 10m altitude identified as the optimal detection parameters. A complementary architectural comparison revealed that while RF-DETR achieved the highest accuracy (69.2% mAP), followed by Faster R-CNN (67.6%), YOLOv11 (64.2%), and RetinaNet (50.2%), YOLOv11 trained 17.7 times faster than the transformer-based RF-DETR (41 minutes versus 12 hours), presenting a critical accuracy-efficiency tradeoff for operational deployment. Aggregated multi-temporal training datasets outperformed season-specific approaches by 1.8 to 9.6%, suggesting that models benefit from exposure to diverse thermal conditions. Anti-Tank (AT) mines achieved 61.9% detection accuracy, compared with 19.2% for Anti-Personnel (AP) mines, reflecting both the size differential and thermal-mass differences between these ordnance classes. As this research examined surface-laid mines where thermal contrast is maximized, future research should quantify thermal contrast effects for mines buried at varying depths across heterogeneous soil types. --- ### SweRank+: Multilingual, Multi-Turn Code Ranking for Software Issue Localization Authors: Revanth Gangi Reddy, Ye Liu, Wenting Zhao, JaeHyeok Doo, Tarun Suresh, Daniel Lee, Caiming Xiong, Yingbo Zhou, Semih Yavuz, Shafiq Joty Published: 2025-12-23 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2512.20482v1 Maintaining large-scale, multilingual codebases hinges on accurately localizing issues, which requires mapping natural-language error descriptions to the relevant functions that need to be modified. However, existing ranking approaches are often Python-centric and perform a single-pass search over the codebase. This work introduces SweRank+, a framework that couples SweRankMulti, a cross-lingual code ranking tool, with SweRankAgent, an agentic search setup, for iterative, multi-turn reasoning over the code repository. SweRankMulti comprises a code embedding retriever and a listwise LLM reranker, and is trained using a carefully curated large-scale issue localization dataset spanning multiple popular programming languages. SweRankAgent adopts an agentic search loop that moves beyond single-shot localization with a memory buffer to reason and accumulate relevant localization candidates over multiple turns. Our experiments on issue localization benchmarks spanning various languages demonstrate new state-of-the-art performance with SweRankMulti, while SweRankAgent further improves localization over single-pass ranking. --- ### Coherence in the brain unfolds across separable temporal regimes Authors: Davide Staub, Finn Rabe, Akhil Misra, Yves Pauli, Roya Hüppi, Ni Yang, Nils Lang, Lars Michels, Victoria Edkins, Sascha Frühholz, Iris Sommer, Wolfram Hinzen et al. Published: 2025-12-23 Categories: q-bio.NC, cs.CL arXiv: https://arxiv.org/abs/2512.20481v4 To maintain coherence in language, the brain must satisfy key competing temporal demands: the gradual accumulation of meaning across extended context (drift) and the rapid reconfiguration of representations at event boundaries (shift). How these processes are implemented in the human brain during naturalistic listening remains unclear. Here, we tested whether both can be captured by annotation-free drift and shift signals and whether their neural expression shows distinct regional preferences across the brain. These signals were derived from a large language model (LLM) processing the narrative input. To enable high-precision voxelwise encoding models with stable parameter estimates, we densely sampled one healthy adult across more than 7 hours of listening to crime stories while collecting 7 Tesla fMRI data. We then modeled the feature-informed hemodynamic response using a regularized encoding framework validated on independent stories. Drift predictions were prevalent in default-mode network hubs, whereas shift predictions were evident bilaterally in the primary auditory cortex and language association cortex. Together, these findings show that coherence during language comprehension is implemented through distinct but co-expressed neural regimes of slow contextual integration and rapid event-driven reconfiguration, offering a mechanistic entry point for understanding disturbances of language coherence in psychiatric disorders. --- ### Coherence in the brain unfolds across separable temporal regimes Authors: Davide Stauba, Finn Rabe, Akhil Misra, Yves Pauli, Roya Hüppi, Nils Lang, Lars Michels, Victoria Edkins, Sascha Frühholz, Iris Sommer, Wolfram Hinzen, Philipp Homan Published: 2025-12-23 Categories: q-bio.NC, cs.CL arXiv: https://arxiv.org/abs/2512.20481v1 Coherence in language requires the brain to satisfy two competing temporal demands: gradual accumulation of meaning across extended context and rapid reconfiguration of representations at event boundaries. Despite their centrality to language and thought, how these processes are implemented in the human brain during naturalistic listening remains unclear. Here, we tested whether these two processes can be captured by annotation-free drift and shift signals and whether their neural expression dissociates across large-scale cortical systems. These signals were derived from a large language model (LLM) and formalized contextual drift and event shifts directly from the narrative input. To enable high-precision voxelwise encoding models with stable parameter estimates, we densely sampled one healthy adult across more than 7 hours of listening to thirteen crime stories while collecting ultra high-field (7T) BOLD data. We then modeled the feature-informed hemodynamic response using a regularized encoding framework validated on independent stories. Drift predictions were prevalent in default-mode network hubs, whereas shift predictions were evident bilaterally in the primary auditory cortex and language association cortex. Furthermore, activity in default-mode and parietal networks was best explained by a signal capturing how meaning accumulates and gradually fades over the course of the narrative. Together, these findings show that coherence during language comprehension is implemented through dissociable neural regimes of slow contextual integration and rapid event-driven reconfiguration, offering a mechanistic entry point for understanding disturbances of language coherence in psychiatric disorders. --- ### UTDesign: A Unified Framework for Stylized Text Editing and Generation in Graphic Design Images Authors: Yiming Zhao, Yuanpeng Gao, Yuxuan Luo, Jiwei Duan, Shisong Lin, Longfei Xiong, Zhouhui Lian Published: 2025-12-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.20479v1 AI-assisted graphic design has emerged as a powerful tool for automating the creation and editing of design elements such as posters, banners, and advertisements. While diffusion-based text-to-image models have demonstrated strong capabilities in visual content generation, their text rendering performance, particularly for small-scale typography and non-Latin scripts, remains limited. In this paper, we propose UTDesign, a unified framework for high-precision stylized text editing and conditional text generation in design images, supporting both English and Chinese scripts. Our framework introduces a novel DiT-based text style transfer model trained from scratch on a synthetic dataset, capable of generating transparent RGBA text foregrounds that preserve the style of reference glyphs. We further extend this model into a conditional text generation framework by training a multi-modal condition encoder on a curated dataset with detailed text annotations, enabling accurate, style-consistent text synthesis conditioned on background images, prompts, and layout specifications. Finally, we integrate our approach into a fully automated text-to-design (T2D) pipeline by incorporating pre-trained text-to-image (T2I) models and an MLLM-based layout planner. Extensive experiments demonstrate that UTDesign achieves state-of-the-art performance among open-source methods in terms of stylistic consistency and text accuracy, and also exhibits unique advantages compared to proprietary commercial approaches. Code and data for this paper are available at https://github.com/ZYM-PKU/UTDesign. --- ### Bohrium + SciMaster: Building the Infrastructure and Ecosystem for Agentic Science at Scale Authors: Linfeng Zhang, Siheng Chen, Yuzhu Cai, Jingyi Chai, Junhan Chang, Kun Chen, Zhi X. Chen, Zhaohan Ding, Yuwen Du, Yuanpeng Gao, Yuan Gao, Jing Gao et al. Published: 2025-12-23 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.20469v1 AI agents are emerging as a practical way to run multi-step scientific workflows that interleave reasoning with tool use and verification, pointing to a shift from isolated AI-assisted steps toward \emph{agentic science at scale}. This shift is increasingly feasible, as scientific tools and models can be invoked through stable interfaces and verified with recorded execution traces, and increasingly necessary, as AI accelerates scientific output and stresses the peer-review and publication pipeline, raising the bar for traceability and credible evaluation. However, scaling agentic science remains difficult: workflows are hard to observe and reproduce; many tools and laboratory systems are not agent-ready; execution is hard to trace and govern; and prototype AI Scientist systems are often bespoke, limiting reuse and systematic improvement from real workflow signals. We argue that scaling agentic science requires an infrastructure-and-ecosystem approach, instantiated in Bohrium+SciMaster. Bohrium acts as a managed, traceable hub for AI4S assets -- akin to a HuggingFace of AI for Science -- that turns diverse scientific data, software, compute, and laboratory systems into agent-ready capabilities. SciMaster orchestrates these capabilities into long-horizon scientific workflows, on which scientific agents can be composed and executed. Between infrastructure and orchestration, a \emph{scientific intelligence substrate} organizes reusable models, knowledge, and components into executable building blocks for workflow reasoning and action, enabling composition, auditability, and improvement through use. We demonstrate this stack with eleven representative master agents in real workflows, achieving orders-of-magnitude reductions in end-to-end scientific cycle time and generating execution-grounded signals from real workloads at multi-million scale. --- ### Snapshot 3D image projection using a diffractive decoder Authors: Cagatay Isil, Alexander Chen, Yuhang Li, F. Onuralp Ardic, Shiqi Chen, Che-Yung Shen, Aydogan Ozcan Published: 2025-12-23 Categories: physics.optics, cs.CV, cs.NE, physics.app-ph arXiv: https://arxiv.org/abs/2512.20464v1 3D image display is essential for next-generation volumetric imaging; however, dense depth multiplexing for 3D image projection remains challenging because diffraction-induced cross-talk rapidly increases as the axial image planes get closer. Here, we introduce a 3D display system comprising a digital encoder and a diffractive optical decoder, which simultaneously projects different images onto multiple target axial planes with high axial resolution. By leveraging multi-layer diffractive wavefront decoding and deep learning-based end-to-end optimization, the system achieves high-fidelity depth-resolved 3D image projection in a snapshot, enabling axial plane separations on the order of a wavelength. The digital encoder leverages a Fourier encoder network to capture multi-scale spatial and frequency-domain features from input images, integrates axial position encoding, and generates a unified phase representation that simultaneously encodes all images to be axially projected in a single snapshot through a jointly-optimized diffractive decoder. We characterized the impact of diffractive decoder depth, output diffraction efficiency, spatial light modulator resolution, and axial encoding density, revealing trade-offs that govern axial separation and 3D image projection quality. We further demonstrated the capability to display volumetric images containing 28 axial slices, as well as the ability to dynamically reconfigure the axial locations of the image planes, performed on demand. Finally, we experimentally validated the presented approach, demonstrating close agreement between the measured results and the target images. These results establish the diffractive 3D display system as a compact and scalable framework for depth-resolved snapshot 3D image projection, with potential applications in holographic displays, AR/VR interfaces, and volumetric optical computing. --- ### The Aligned Economic Index & The State Switching Model Authors: Ilias Aarab Published: 2025-12-23 Categories: q-fin.ST, cs.LG, econ.EM, q-fin.PM, stat.AP arXiv: https://arxiv.org/abs/2512.20460v2 A growing empirical literature suggests that equity-premium predictability is state dependent, with much of the forecasting power concentrated around recessionary periods (Henkel et al., 2011; Dangl and Halling, 2012; Devpura et al., 2018). I study U.S. stock return predictability across economic regimes and document strong evidence of time-varying expected returns across both expansionary and contractionary states. I contribute in two ways. First, I introduce a state-switching predictive regression in which the market state is defined in real time using the slope of the yield curve. Relative to the standard one-state predictive regression, the state-switching specification increases both in-sample and out-of-sample performance for the set of popular predictors considered by Welch and Goyal (2008), improving the out-of-sample performance of most predictors in economically meaningful ways. Second, I propose a new aggregate predictor, the Aligned Economic Index, constructed via partial least squares (PLS). Under the state-switching model, the Aligned Economic Index exhibits statistically and economically significant predictive power in sample and out of sample, and it outperforms widely used benchmark predictors and alternative predictor-combination methods. --- ### The Aligned Economic Index & The State Switching Model Authors: Ilias Aarab Published: 2025-12-23 Categories: q-fin.ST, cs.LG, econ.EM, q-fin.PM, stat.AP arXiv: https://arxiv.org/abs/2512.20460v1 A growing empirical literature suggests that equity-premium predictability is state dependent, with much of the forecasting power concentrated around recessionary periods \parencite{Henkel2011,DanglHalling2012,Devpura2018}. I study U.S. stock return predictability across economic regimes and document strong evidence of time-varying expected returns across both expansionary and contractionary states. I contribute in two ways. First, I introduce a state-switching predictive regression in which the market state is defined in real time using the slope of the yield curve. Relative to the standard one-state predictive regression, the state-switching specification increases both in-sample and out-of-sample performance for the set of popular predictors considered by \textcite{WelchGoyal2008}, improving the out-of-sample performance of most predictors in economically meaningful ways. Second, I propose a new aggregate predictor, the Aligned Economic Index, constructed via partial least squares (PLS). Under the state-switching model, the Aligned Economic Index exhibits statistically and economically significant predictive power in sample and out of sample, and it outperforms widely used benchmark predictors and alternative predictor-combination methods. --- ### Beyond Motion Pattern: An Empirical Study of Physical Forces for Human Motion Understanding Authors: Anh Dao, Manh Tran, Yufei Zhang, Xiaoming Liu, Zijun Cui Published: 2025-12-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.20451v1 Human motion understanding has advanced rapidly through vision-based progress in recognition, tracking, and captioning. However, most existing methods overlook physical cues such as joint actuation forces that are fundamental in biomechanics. This gap motivates our study: if and when do physically inferred forces enhance motion understanding? By incorporating forces into established motion understanding pipelines, we systematically evaluate their impact across baseline models on 3 major tasks: gait recognition, action recognition, and fine-grained video captioning. Across 8 benchmarks, incorporating forces yields consistent performance gains; for example, on CASIA-B, Rank-1 gait recognition accuracy improved from 89.52% to 90.39% (+0.87), with larger gain observed under challenging conditions: +2.7% when wearing a coat and +3.0% at the side view. On Gait3D, performance also increases from 46.0% to 47.3% (+1.3). In action recognition, CTR-GCN achieved +2.00% on Penn Action, while high-exertion classes like punching/slapping improved by +6.96%. Even in video captioning, Qwen2.5-VL's ROUGE-L score rose from 0.310 to 0.339 (+0.029), indicating that physics-inferred forces enhance temporal grounding and semantic richness. These results demonstrate that force cues can substantially complement visual and kinematic features under dynamic, occluded, or appearance-varying conditions. --- ### Machine Learning to Predict Digital Frustration from Clickstream Data Authors: Jibin Joseph Published: 2025-12-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.20438v1 Many businesses depend on their mobile apps and websites, so user frustration while trying to complete a task on these channels can cause lost sales and complaints. In this research, I use clickstream data from a real e-commerce site to predict whether a session is frustrated or not. Frustration is defined using certain rules based on rage bursts, back and forth navigation (U turns), cart churn, search struggle, and long wandering sessions, and applies these rules to 5.4 million raw clickstream events (304,881 sessions). From each session, I build tabular features and train standard classifier models. I also use the full event sequence to train a discriminative LSTM classifier. XGBoost reaches about 90% accuracy, ROC AUC of 0.9579, while the LSTM performs best with about 91% accuracy and a ROC AUC of 0.9705. Finally, the research shows that with only the first 20 to 30 interactions, the LSTM already predicts frustration reliably. --- ### Dual-Encoder Transformer-Based Multimodal Learning for Ischemic Stroke Lesion Segmentation Using Diffusion MRI Authors: Muhammad Usman, Azka Rehman, Muhammad Mutti Ur Rehman, Abd Ur Rehman, Muhammad Umar Farooq Published: 2025-12-23 Categories: eess.IV, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2512.20436v1 Accurate segmentation of ischemic stroke lesions from diffusion magnetic resonance imaging (MRI) is essential for clinical decision-making and outcome assessment. Diffusion-Weighted Imaging (DWI) and Apparent Diffusion Coefficient (ADC) scans provide complementary information on acute and sub-acute ischemic changes; however, automated lesion delineation remains challenging due to variability in lesion appearance. In this work, we study ischemic stroke lesion segmentation using multimodal diffusion MRI from the ISLES 2022 dataset. Several state-of-the-art convolutional and transformer-based architectures, including U-Net variants, Swin-UNet, and TransUNet, are benchmarked. Based on performance, a dual-encoder TransUNet architecture is proposed to learn modality-specific representations from DWI and ADC inputs. To incorporate spatial context, adjacent slice information is integrated using a three-slice input configuration. All models are trained under a unified framework and evaluated using the Dice Similarity Coefficient (DSC). Results show that transformer-based models outperform convolutional baselines, and the proposed dual-encoder TransUNet achieves the best performance, reaching a Dice score of 85.4% on the test set. The proposed framework offers a robust solution for automated ischemic stroke lesion segmentation from diffusion MRI. --- ### High Dimensional Data Decomposition for Anomaly Detection of Textured Images Authors: Ji Song, Xing Wang, Jianguo Wu, Xiaowei Yue Published: 2025-12-23 Categories: cs.CV, stat.ML arXiv: https://arxiv.org/abs/2512.20432v1 In the realm of diverse high-dimensional data, images play a significant role across various processes of manufacturing systems where efficient image anomaly detection has emerged as a core technology of utmost importance. However, when applied to textured defect images, conventional anomaly detection methods have limitations including non-negligible misidentification, low robustness, and excessive reliance on large-scale and structured datasets. This paper proposes a texture basis integrated smooth decomposition (TBSD) approach, which is targeted at efficient anomaly detection in textured images with smooth backgrounds and sparse anomalies. Mathematical formulation of quasi-periodicity and its theoretical properties are investigated for image texture estimation. TBSD method consists of two principal processes: the first process learns the texture basis functions to effectively extract quasi-periodic texture patterns; the subsequent anomaly detection process utilizes that texture basis as prior knowledge to prevent texture misidentification and capture potential anomalies with high accuracy.The proposed method surpasses benchmarks with less misidentification, smaller training dataset requirement, and superior anomaly detection performance on both simulation and real-world datasets. --- ### Skin Lesion Classification Using a Soft Voting Ensemble of Convolutional Neural Networks Authors: Abdullah Al Shafi, Abdul Muntakim, Pintu Chandra Shill, Rowzatul Zannat, Abdullah Al-Amin Published: 2025-12-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.20431v1 Skin cancer can be identified by dermoscopic examination and ocular inspection, but early detection significantly increases survival chances. Artificial intelligence (AI), using annotated skin images and Convolutional Neural Networks (CNNs), improves diagnostic accuracy. This paper presents an early skin cancer classification method using a soft voting ensemble of CNNs. In this investigation, three benchmark datasets, namely HAM10000, ISIC 2016, and ISIC 2019, were used. The process involved rebalancing, image augmentation, and filtering techniques, followed by a hybrid dual encoder for segmentation via transfer learning. Accurate segmentation focused classification models on clinically significant features, reducing background artifacts and improving accuracy. Classification was performed through an ensemble of MobileNetV2, VGG19, and InceptionV3, balancing accuracy and speed for real-world deployment. The method achieved lesion recognition accuracies of 96.32\%, 90.86\%, and 93.92\% for the three datasets. The system performance was evaluated using established skin lesion detection metrics, yielding impressive results. --- ### Evasion-Resilient Detection of DNS-over-HTTPS Data Exfiltration: A Practical Evaluation and Toolkit Authors: Adam Elaoumari Published: 2025-12-23 Categories: cs.CR, cs.AI, cs.NI arXiv: https://arxiv.org/abs/2512.20423v1 The purpose of this project is to assess how well defenders can detect DNS-over-HTTPS (DoH) file exfiltration, and which evasion strategies can be used by attackers. While providing a reproducible toolkit to generate, intercept and analyze DoH exfiltration, and comparing Machine Learning vs threshold-based detection under adversarial scenarios. The originality of this project is the introduction of an end-to-end, containerized pipeline that generates configurable file exfiltration over DoH using several parameters (e.g., chunking, encoding, padding, resolver rotation). It allows for file reconstruction at the resolver side, while extracting flow-level features using a fork of DoHLyzer. The pipeline contains a prediction side, which allows the training of machine learning models based on public labelled datasets and then evaluates them side-by-side with threshold-based detection methods against malicious and evasive DNS-Over-HTTPS traffic. We train Random Forest, Gradient Boosting and Logistic Regression classifiers on a public DoH dataset and benchmark them against evasive DoH exfiltration scenarios. The toolkit orchestrates traffic generation, file capture, feature extraction, model training and analysis. The toolkit is then encapsulated into several Docker containers for easy setup and full reproducibility regardless of the platform it is run on. Future research regarding this project is directed at validating the results on mixed enterprise traffic, extending the protocol coverage to HTTP/3/QUIC request, adding a benign traffic generation, and working on real-time traffic evaluation. A key objective is to quantify when stealth constraints make DoH exfiltration uneconomical and unworthy for the attacker. --- ### Simplifying Multi-Task Architectures Through Task-Specific Normalization Authors: Mihai Suteu, Ovidiu Serban Published: 2025-12-23 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2512.20420v1 Multi-task learning (MTL) aims to leverage shared knowledge across tasks to improve generalization and parameter efficiency, yet balancing resources and mitigating interference remain open challenges. Architectural solutions often introduce elaborate task-specific modules or routing schemes, increasing complexity and overhead. In this work, we show that normalization layers alone are sufficient to address many of these challenges. Simply replacing shared normalization with task-specific variants already yields competitive performance, questioning the need for complex designs. Building on this insight, we propose Task-Specific Sigmoid Batch Normalization (TS$σ$BN), a lightweight mechanism that enables tasks to softly allocate network capacity while fully sharing feature extractors. TS$σ$BN improves stability across CNNs and Transformers, matching or exceeding performance on NYUv2, Cityscapes, CelebA, and PascalContext, while remaining highly parameter-efficient. Moreover, its learned gates provide a natural framework for analyzing MTL dynamics, offering interpretable insights into capacity allocation, filter specialization, and task relationships. Our findings suggest that complex MTL architectures may be unnecessary and that task-specific normalization offers a simple, interpretable, and efficient alternative. --- ### Chain-of-Anomaly Thoughts with Large Vision-Language Models Authors: Pedro Domingos, João Pereira, Vasco Lopes, João Neves, David Semedo Published: 2025-12-23 Categories: cs.CV, cs.MA arXiv: https://arxiv.org/abs/2512.20417v1 Automated video surveillance with Large Vision-Language Models is limited by their inherent bias towards normality, often failing to detect crimes. While Chain-of-Thought reasoning strategies show significant potential for improving performance in language tasks, the lack of inductive anomaly biases in their reasoning further steers the models towards normal interpretations. To address this, we propose Chain-of-Anomaly-Thoughts (CoAT), a multi-agent reasoning framework that introduces inductive criminal bias in the reasoning process through a final, anomaly-focused classification layer. Our method significantly improves Anomaly Detection, boosting F1-score by 11.8 p.p. on challenging low-resolution footage and Anomaly Classification by 3.78 p.p. in high-resolution videos. --- ### DETACH : Decomposed Spatio-Temporal Alignment for Exocentric Video and Ambient Sensors with Staged Learning Authors: Junho Yoon, Jaemo Jung, Hyunju Kim, Dongman Lee Published: 2025-12-23 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.20409v1 Aligning egocentric video with wearable sensors have shown promise for human action recognition, but face practical limitations in user discomfort, privacy concerns, and scalability. We explore exocentric video with ambient sensors as a non-intrusive, scalable alternative. While prior egocentric-wearable works predominantly adopt Global Alignment by encoding entire sequences into unified representations, this approach fails in exocentric-ambient settings due to two problems: (P1) inability to capture local details such as subtle motions, and (P2) over-reliance on modality-invariant temporal patterns, causing misalignment between actions sharing similar temporal patterns with different spatio-semantic contexts. To resolve these problems, we propose DETACH, a decomposed spatio-temporal framework. This explicit decomposition preserves local details, while our novel sensor-spatial features discovered via online clustering provide semantic grounding for context-aware alignment. To align the decomposed features, our two-stage approach establishes spatial correspondence through mutual supervision, then performs temporal alignment via a spatial-temporal weighted contrastive loss that adaptively handles easy negatives, hard negatives, and false negatives. Comprehensive experiments with downstream tasks on Opportunity++ and HWU-USP datasets demonstrate substantial improvements over adapted egocentric-wearable baselines. --- ### AUDRON: A Deep Learning Framework with Fused Acoustic Signatures for Drone Type Recognition Authors: Rajdeep Chatterjee, Sudip Chakrabarty, Trishaani Acharjee, Deepanjali Mishra Published: 2025-12-23 Categories: cs.SD, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.20407v2 Unmanned aerial vehicles (UAVs), commonly known as drones, are increasingly used across diverse domains, including logistics, agriculture, surveillance, and defense. While these systems provide numerous benefits, their misuse raises safety and security concerns, making effective detection mechanisms essential. Acoustic sensing offers a low-cost and non-intrusive alternative to vision or radar-based detection, as drone propellers generate distinctive sound patterns. This study introduces AUDRON (AUdio-based Drone Recognition Network), a hybrid deep learning framework for drone sound detection, employing a combination of Mel-Frequency Cepstral Coefficients (MFCC), Short-Time Fourier Transform (STFT) spectrograms processed with convolutional neural networks (CNNs), recurrent layers for temporal modeling, and autoencoder-based representations. Feature-level fusion integrates complementary information before classification. Experimental evaluation demonstrates that AUDRON effectively differentiates drone acoustic signatures from background noise, achieving high accuracy while maintaining generalizability across varying conditions. AUDRON achieves 98.51 percent and 97.11 percent accuracy in binary and multiclass classification. The results highlight the advantage of combining multiple feature representations with deep learning for reliable acoustic drone detection, suggesting the framework's potential for deployment in security and surveillance applications where visual or radar sensing may be limited. --- ### AUDRON: A Deep Learning Framework with Fused Acoustic Signatures for Drone Type Recognition Authors: Rajdeep Chatterjee, Sudip Chakrabarty, Trishaani Acharjee, Deepanjali Mishra Published: 2025-12-23 Categories: cs.SD, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.20407v1 Unmanned aerial vehicles (UAVs), commonly known as drones, are increasingly used across diverse domains, including logistics, agriculture, surveillance, and defense. While these systems provide numerous benefits, their misuse raises safety and security concerns, making effective detection mechanisms essential. Acoustic sensing offers a low-cost and non-intrusive alternative to vision or radar-based detection, as drone propellers generate distinctive sound patterns. This study introduces AUDRON (AUdio-based Drone Recognition Network), a hybrid deep learning framework for drone sound detection, employing a combination of Mel-Frequency Cepstral Coefficients (MFCC), Short-Time Fourier Transform (STFT) spectrograms processed with convolutional neural networks (CNNs), recurrent layers for temporal modeling, and autoencoder-based representations. Feature-level fusion integrates complementary information before classification. Experimental evaluation demonstrates that AUDRON effectively differentiates drone acoustic signatures from background noise, achieving high accuracy while maintaining generalizability across varying conditions. AUDRON achieves 98.51 percent and 97.11 percent accuracy in binary and multiclass classification. The results highlight the advantage of combining multiple feature representations with deep learning for reliable acoustic drone detection, suggesting the framework's potential for deployment in security and surveillance applications where visual or radar sensing may be limited. --- ### Sentiment-Aware Extractive and Abstractive Summarization for Unstructured Text Mining Authors: Junyi Liu, Stanley Kok Published: 2025-12-23 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.20404v1 With the rapid growth of unstructured data from social media, reviews, and forums, text mining has become essential in Information Systems (IS) for extracting actionable insights. Summarization can condense fragmented, emotion-rich posts, but existing methods-optimized for structured news-struggle with noisy, informal content. Emotional cues are critical for IS tasks such as brand monitoring and market analysis, yet few studies integrate sentiment modeling into summarization of short user-generated texts. We propose a sentiment-aware framework extending extractive (TextRank) and abstractive (UniLM) approaches by embedding sentiment signals into ranking and generation processes. This dual design improves the capture of emotional nuances and thematic relevance, producing concise, sentiment-enriched summaries that enhance timely interventions and strategic decision-making in dynamic online environments. --- ### BRIDGE: Budget-aware Reasoning via Intermediate Distillation with Guided Examples Authors: Xuan-An Le, Minh-Nam Tran, Son Nguyen Published: 2025-12-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.20403v1 Distilling knowledge from large proprietary models (e.g., GPT-4) to tiny deployable models (less than 1B parameters) faces a critical capacity-budget trap: the 1000x capacity gap between teachers and students prevents effective direct transfer, while API costs prohibit extensive data collection. We introduce BRIDGE (Budget-Aware Reasoning via Intermediate Distillation), a two-phase framework that resolves these constraints through strategic intermediation and budget asymmetry. In Phase 1, a mid-sized Teacher Assistant (TA; e.g., about 7B) learns from the black-box teacher on a strictly limited subset of data (e.g., 3-5%), selected via a zero-API-cost pipeline that balances entropic difficulty and semantic diversity using only local TA inference. In Phase 2, we exploit this asymmetry-teacher queries are expensive, whereas TA inference is free to amplify supervision: the refined TA generates synthetic rationales for the full dataset to train the tiny student. Crucially, we apply an instruction-tuning curriculum to establish behavioral alignment in the tiny student before transferring reasoning. Our theoretical analysis shows that BRIDGE yields tighter generalization bounds than direct distillation when data is abundant. Experiments across medical, legal, and financial benchmarks demonstrate consistent improvements: BRIDGE delivers student performance gains of 28-41%, closing the capability gap with proprietary teachers by 12-16% while using 10x fewer teacher queries. Notably, BRIDGE defies the conventional cost-performance frontier, surpassing direct distillation baselines that use 100% of the budget while consuming only 5% of the resources. --- ### GeoTransolver: Learning Physics on Irregular Domains Using Multi-scale Geometry Aware Physics Attention Transformer Authors: Corey Adams, Rishikesh Ranade, Ram Cherukuri, Sanjay Choudhry Published: 2025-12-23 Categories: cs.LG, physics.comp-ph arXiv: https://arxiv.org/abs/2512.20399v3 We present GeoTransolver, a multiscale geometry-aware physics attention transformer for Computer Aided Engineering (CAE). GeoTransolver extends the Transolver backbone with GALE (Geometry-Aware Latent Embeddings) attention, which pairs physics-aware self-attention on learned state slices with cross-attention to a shared geometry and global context computed via multi-scale ball queries (inspired by Domino) and reused in every block. Implemented and released in NVIDIA PhysicsNeMo, GeoTransolver persistently projects geometry and global parameters, into physical state spaces to anchor computations to domain structure and operating regimes. We benchmark on DrivAerML, SHIFT-SUV, and SHIFT-Wing against Domino, Transolver (PhysicsNeMo implementation), and literature-reported AB-UPT, evaluating drag/lift R2 and relative L1 errors on field variables. As an additional nonlinear structural mechanics application, we also report Transolver and GeoTransolver results on bumper-beam and full-vehicle Body-in-White (BIW) crash-dynamics benchmarks, evaluating relative L2 trajectory error and probe-level kinematic MSE. GeoTransolver delivers improved accuracy, robustness to geometry and regime shifts, and favorable data efficiency; we include DrivAerML ablations and qualitative contour and design-trend results, advancing operator learning for high-fidelity surrogates on complex, irregular, non-linear domains. --- ### GeoTransolver: Learning Physics on Irregumar Domains Using Multi-scale Geometry Aware Physics Attention Transformer Authors: Corey Adams, Rishikesh Ranade, Ram Cherukuri, Sanjay Choudhry Published: 2025-12-23 Categories: cs.LG, physics.comp-ph arXiv: https://arxiv.org/abs/2512.20399v1 We present GeoTransolver, a Multiscale Geometry-Aware Physics Attention Transformer for CAE that replaces standard attention with GALE, coupling physics-aware self-attention on learned state slices with cross-attention to a shared geometry/global/boundary-condition context computed from multi-scale ball queries (inspired by DoMINO) and reused in every block. Implemented and released in NVIDIA PhysicsNeMo, GeoTransolver persistently projects geometry, global and boundary condition parameters into physical state spaces to anchor latent computations to domain structure and operating regimes. We benchmark GeoTransolver on DrivAerML, Luminary SHIFT-SUV, and Luminary SHIFT-Wing, comparing against Domino, Transolver (as released in PhysicsNeMo), and literature-reported AB-UPT, and evaluate drag/lift R2 and Relative L1 errors for field variables. GeoTransolver delivers better accuracy, improved robustness to geometry/regime shifts, and favorable data efficiency; we include ablations on DrivAerML and qualitative results such as contour plots and design trends for the best GeoTransolver models. By unifying multiscale geometry-aware context with physics-based attention in a scalable transformer, GeoTransolver advances operator learning for high-fidelity surrogate modeling across complex, irregular domains and non-linear physical regimes. --- ### Generative Digital Twins: Vision-Language Simulation Models for Executable Industrial Systems Authors: YuChe Hsu, AnJui Wang, TsaiChing Ni, YuanFu Yang Published: 2025-12-23 Categories: cs.AI, cs.CL, cs.CV arXiv: https://arxiv.org/abs/2512.20387v4 We propose a Vision-Language Simulation Model (VLSM) that unifies visual and textual understanding to synthesize executable FlexScript from layout sketches and natural-language prompts, enabling cross-modal reasoning for industrial simulation systems. To support this new paradigm, the study constructs the first large-scale dataset for generative digital twins, comprising over 120,000 prompt-sketch-code triplets that enable multimodal learning between textual descriptions, spatial structures, and simulation logic. In parallel, three novel evaluation metrics, Structural Validity Rate (SVR), Parameter Match Rate (PMR), and Execution Success Rate (ESR), are proposed specifically for this task to comprehensively evaluate structural integrity, parameter fidelity, and simulator executability. Through systematic ablation across vision encoders, connectors, and code-pretrained language backbones, the proposed models achieve near-perfect structural accuracy and high execution robustness. This work establishes a foundation for generative digital twins that integrate visual reasoning and language understanding into executable industrial simulation systems. Project page: https://danielhsu2014.github.io/GDT-VLSM-project/ --- ### Generative Digital Twins: Vision-Language Simulation Models for Executable Industrial Systems Authors: YuChe Hsu, AnJui Wang, TsaiChing Ni, YuanFu Yang Published: 2025-12-23 Categories: cs.AI, cs.CL, cs.CV arXiv: https://arxiv.org/abs/2512.20387v1 We propose a Vision-Language Simulation Model (VLSM) that unifies visual and textual understanding to synthesize executable FlexScript from layout sketches and natural-language prompts, enabling cross-modal reasoning for industrial simulation systems. To support this new paradigm, the study constructs the first large-scale dataset for generative digital twins, comprising over 120,000 prompt-sketch-code triplets that enable multimodal learning between textual descriptions, spatial structures, and simulation logic. In parallel, three novel evaluation metrics, Structural Validity Rate (SVR), Parameter Match Rate (PMR), and Execution Success Rate (ESR), are proposed specifically for this task to comprehensively evaluate structural integrity, parameter fidelity, and simulator executability. Through systematic ablation across vision encoders, connectors, and code-pretrained language backbones, the proposed models achieve near-perfect structural accuracy and high execution robustness. This work establishes a foundation for generative digital twins that integrate visual reasoning and language understanding into executable industrial simulation systems. --- ### Identifying Appropriately-Sized Services with Deep Reinforcement Learning Authors: Syeda Tasnim Fabiha, Saad Shafiq, Wesley Klewerton Guez Assunção, Nenad Medvidović Published: 2025-12-23 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2512.20381v1 Service-based architecture (SBA) has gained attention in industry and academia as a means to modernize legacy systems. It refers to a design style that enables systems to be developed as suites of small, loosely coupled, and autonomous components (services) that encapsulate functionality and communicate via language-agnostic APIs. However, defining appropriately sized services that capture cohesive subsets of system functionality remains challenging. Existing work often relies on the availability of documentation, access to project personnel, or a priori knowledge of the target number of services, assumptions that do not hold in many real-world scenarios. Our work addresses these limitations using a deep reinforcement learning-based approach to identify appropriately sized services directly from implementation artifacts. We present Rake, a reinforcement learning-based technique that leverages available system documentation and source code to guide service decomposition at the level of implementation methods. Rake does not require specific documentation or access to project personnel and is language-agnostic. It also supports a customizable objective function that balances modularization quality and business capability alignment, i.e., the degree to which a service covers the targeted business capability. We applied Rake to four open-source legacy projects and compared it with two state-of-the-art techniques. On average, Rake achieved 7-14 percent higher modularization quality and 18-22 percent stronger business capability alignment. Our results further show that optimizing solely for business context can degrade decomposition quality in tightly coupled systems, highlighting the need for balanced objectives. --- ### SmartSplat: Feature-Smart Gaussians for Scalable Compression of Ultra-High-Resolution Images Authors: Linfei Li, Lin Zhang, Zhong Wang, Ying Shen Published: 2025-12-23 Categories: cs.CV, cs.MM arXiv: https://arxiv.org/abs/2512.20377v1 Recent advances in generative AI have accelerated the production of ultra-high-resolution visual content, posing significant challenges for efficient compression and real-time decoding on end-user devices. Inspired by 3D Gaussian Splatting, recent 2D Gaussian image models improve representation efficiency, yet existing methods struggle to balance compression ratio and reconstruction fidelity in ultra-high-resolution scenarios. To address this issue, we propose SmartSplat, a highly adaptive and feature-aware GS-based image compression framework that supports arbitrary image resolutions and compression ratios. SmartSplat leverages image-aware features such as gradients and color variances, introducing a Gradient-Color Guided Variational Sampling strategy together with an Exclusion-based Uniform Sampling scheme to improve the non-overlapping coverage of Gaussian primitives in pixel space. In addition, we propose a Scale-Adaptive Gaussian Color Sampling method to enhance color initialization across scales. Through joint optimization of spatial layout, scale, and color initialization, SmartSplat efficiently captures both local structures and global textures using a limited number of Gaussians, achieving high reconstruction quality under strong compression. Extensive experiments on DIV8K and a newly constructed 16K dataset demonstrate that SmartSplat consistently outperforms state-of-the-art methods at comparable compression ratios and exceeds their compression limits, showing strong scalability and practical applicability. The code is publicly available at https://github.com/lif314/SmartSplat. --- ### Linking Faces and Voices Across Languages: Insights from the FAME 2026 Challenge Authors: Marta Moscati, Ahmed Abdullah, Muhammad Saad Saeed, Shah Nawaz, Rohan Kumar Das, Muhammad Zaigham Zaheer, Junaid Mir, Muhammad Haroon Yousaf, Khalid Mahmood Malik, Markus Schedl Published: 2025-12-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.20376v1 Over half of the world's population is bilingual and people often communicate under multilingual scenarios. The Face-Voice Association in Multilingual Environments (FAME) 2026 Challenge, held at ICASSP 2026, focuses on developing methods for face-voice association that are effective when the language at test-time is different than the training one. This report provides a brief summary of the challenge. --- ### CLIP Based Region-Aware Feature Fusion for Automated BBPS Scoring in Colonoscopy Images Authors: Yujia Fu, Zhiyu Dong, Tianwen Qian, Chenye Zheng, Danian Ji, Linhai Zhuo Published: 2025-12-23 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2512.20374v2 Accurate assessment of bowel cleanliness is essential for effective colonoscopy procedures. The Boston Bowel Preparation Scale (BBPS) offers a standardized scoring system but suffers from subjectivity and inter-observer variability when performed manually. In this paper, to support robust training and evaluation, we construct a high-quality colonoscopy dataset comprising 2,240 images from 517 subjects, annotated with expert-agreed BBPS scores. We propose a novel automated BBPS scoring framework that leverages the CLIP model with adapter-based transfer learning and a dedicated fecal-feature extraction branch. Our method fuses global visual features with stool-related textual priors to improve the accuracy of bowel cleanliness evaluation without requiring explicit segmentation. Extensive experiments on both our dataset and the public NERTHU dataset demonstrate the superiority of our approach over existing baselines, highlighting its potential for clinical deployment in computer-aided colonoscopy analysis. --- ### CLIP Based Region-Aware Feature Fusion for Automated BBPS Scoring in Colonoscopy Images Authors: Yujia Fu, Zhiyu Dong, Tianwen Qian, Chenye Zheng, Danian Ji, Linhai Zhuo Published: 2025-12-23 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2512.20374v1 Accurate assessment of bowel cleanliness is essential for effective colonoscopy procedures. The Boston Bowel Preparation Scale (BBPS) offers a standardized scoring system but suffers from subjectivity and inter-observer variability when performed manually. In this paper, to support robust training and evaluation, we construct a high-quality colonoscopy dataset comprising 2,240 images from 517 subjects, annotated with expert-agreed BBPS scores. We propose a novel automated BBPS scoring framework that leverages the CLIP model with adapter-based transfer learning and a dedicated fecal-feature extraction branch. Our method fuses global visual features with stool-related textual priors to improve the accuracy of bowel cleanliness evaluation without requiring explicit segmentation. Extensive experiments on both our dataset and the public NERTHU dataset demonstrate the superiority of our approach over existing baselines, highlighting its potential for clinical deployment in computer-aided colonoscopy analysis. --- ### Cross-Population White Matter Atlas Creation for Concurrent Mapping of Brain Connections in Neonates and Adults with Diffusion MRI Tractography Authors: Wei Zhang, Yijie Li, Ruixi Zheng, Nir A. Sochen, Yuqian Chen, Leo R. Zekelman, Ofer Pasternak, Jarrett Rushmore, Yogesh Rathi, Nikos Makris, Lauren J. O'Donnell, Fan Zhang Published: 2025-12-23 Categories: cs.NE arXiv: https://arxiv.org/abs/2512.20370v1 Comparing white matter (WM) connections between adults and neonates using diffusion MRI (dMRI) can advance our understanding of typical brain development and potential biomarkers for neurological disorders. However, existing WM atlases are population-specific (adult or neonatal) and reside in separate spaces, preventing direct cross-population comparisons. A unified WM atlas spanning both neonates and adults is still lacking. In this study, we propose a neonatal/adult brain atlas (NABA), a WM tractography atlas built from dMRI data of both neonates and adults. NABA is constructed using a robust, data-driven fiber clustering pipeline, enabling group-wise WM atlasing across populations despite substantial anatomical variability. The atlas provides a standardized template for WM parcellation, allowing direct comparison of WM tracts between neonates and adults. Using NABA, we conduct four analyses: (1) evaluating the feasibility of joint WM mapping across populations, (2) characterizing WM development across neonatal ages relative to adults, (3) assessing sex-related differences in neonatal WM development, and (4) examining the effects of preterm birth. Our results show that NABA robustly identifies WM tracts in both populations. We observe rapid fractional anisotropy (FA) development in long-range association tracts, including the arcuate fasciculus and superior longitudinal fasciculus II, whereas intra-cerebellar tracts develop more slowly. Neonatal females exhibit faster overall FA development than males. Although preterm neonates show lower overall FA development rates, they demonstrate relatively higher FA growth in specific tracts, including the corticospinal tract, corona radiata-pontine pathway, and intracerebellar tracts. These findings demonstrate that NABA is a useful tool for investigating WM development across neonates and adults. --- ### Avoiding the Price of Adaptivity: Inference in Linear Contextual Bandits via Stability Authors: Samya Praharaj, Koulik Khamaru Published: 2025-12-23 Categories: stat.ML, cs.IT, cs.LG, math.ST arXiv: https://arxiv.org/abs/2512.20368v2 Statistical inference in contextual bandits is challenging due to the adaptive, non-i.i.d. nature of the data. A growing body of work shows that classical least-squares inference can fail under adaptive sampling, and that valid confidence intervals for linear functionals typically require an inflation of order $\sqrt{d \log T}$. This phenomenon -- often termed the price of adaptivity -- reflects the intrinsic difficulty of reliable inference under general contextual bandit policies. A key structural condition that overcomes this limitation is the stability condition of Lai and Wei, which requires the empirical feature covariance to converge to a deterministic limit. When stability holds, the ordinary least-squares estimator satisfies a central limit theorem, and classical Wald-type confidence intervals remain asymptotically valid under adaptation, without incurring the $\sqrt{d \log T}$ price of adaptivity. In this paper, we propose and analyze a regularized EXP4 algorithm for linear contextual bandits. Our first main result shows that this procedure satisfies the Lai--Wei stability condition and therefore admits valid Wald-type confidence intervals for linear functionals. We additionally provide quantitative rates of convergence in the associated central limit theorem. Our second result establishes that the same algorithm achieves regret guarantees that are minimax optimal up to logarithmic factors, demonstrating that stability and statistical efficiency can coexist within a single contextual bandit method. As an application of our theory, we show how it can be used to construct confidence intervals for the conditional average treatment effect (CATE) under adaptively collected data. Finally, we complement our theory with simulations illustrating the empirical normality of the resulting estimators and the sharpness of the corresponding confidence intervals. --- ### Avoiding the Price of Adaptivity: Inference in Linear Contextual Bandits via Stability Authors: Samya Praharaj, Koulik Khamaru Published: 2025-12-23 Categories: stat.ML, cs.IT, cs.LG, math.ST arXiv: https://arxiv.org/abs/2512.20368v1 Statistical inference in contextual bandits is complicated by the adaptive, non-i.i.d. nature of the data. A growing body of work has shown that classical least-squares inference may fail under adaptive sampling, and that constructing valid confidence intervals for linear functionals of the model parameter typically requires paying an unavoidable inflation of order $\sqrt{d \log T}$. This phenomenon -- often referred to as the price of adaptivity -- highlights the inherent difficulty of reliable inference under general contextual bandit policies. A key structural property that circumvents this limitation is the \emph{stability} condition of Lai and Wei, which requires the empirical feature covariance to concentrate around a deterministic limit. When stability holds, the ordinary least-squares estimator satisfies a central limit theorem, and classical Wald-type confidence intervals -- designed for i.i.d. data -- become asymptotically valid even under adaptation, \emph{without} incurring the $\sqrt{d \log T}$ price of adaptivity. In this paper, we propose and analyze a penalized EXP4 algorithm for linear contextual bandits. Our first main result shows that this procedure satisfies the Lai--Wei stability condition and therefore admits valid Wald-type confidence intervals for linear functionals. Our second result establishes that the same algorithm achieves regret guarantees that are minimax optimal up to logarithmic factors, demonstrating that stability and statistical efficiency can coexist within a single contextual bandit method. Finally, we complement our theory with simulations illustrating the empirical normality of the resulting estimators and the sharpness of the corresponding confidence intervals. --- ### Clust-PSI-PFL: A Population Stability Index Approach for Clustered Non-IID Personalized Federated Learning Authors: Daniel M. Jimenez-Gutierrez, Mehrdad Hassanzadeh, David Solans, Mohammed Elbamby, Nicolas Kourtellis, Aris Anagnostopoulos, Ioannis Chatzigiannakis, Andrea Vitaletti Published: 2025-12-23 Categories: cs.LG, cs.AI, cs.DC, stat.AP, stat.ML arXiv: https://arxiv.org/abs/2512.20363v2 Federated learning (FL) supports privacy-preserving, decentralized machine learning (ML) model training by keeping data on client devices. However, non-independent and identically distributed (non-IID) data across clients biases updates and degrades performance. To alleviate these issues, we propose Clust-PSI-PFL, a clustering-based personalized FL framework that uses the Population Stability Index (PSI) to quantify the level of non-IID data. We compute a weighted PSI metric, $WPSI^L$, which we show to be more informative than common non-IID metrics (Hellinger, Jensen-Shannon, and Earth Mover's distance). Using PSI features, we form distributionally homogeneous groups of clients via K-means++; the number of optimal clusters is chosen by a systematic silhouette-based procedure, typically yielding few clusters with modest overhead. Across six datasets (tabular, image, and text modalities), two partition protocols (Dirichlet with parameter $α$ and Similarity with parameter S), and multiple client sizes, Clust-PSI-PFL delivers up to 18% higher global accuracy than state-of-the-art baselines and markedly improves client fairness by a relative improvement of 37% under severe non-IID data. These results establish PSI-guided clustering as a principled, lightweight mechanism for robust PFL under label skew. ---