# Research Papers — 2025-12 · bundle page 58 of 175 > Full-text markdown of papers #2851–2900 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/58 [← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/57.md) [Next bundle →](https://aipod.dev/papers/archive/2025-12/page/59.md) ### Robust Scene Coordinate Regression via Geometrically-Consistent Global Descriptors Authors: Son Tung Nguyen, Alejandro Fontan, Michael Milford, Tobias Fischer Published: 2025-12-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.17226v2 Recent learning-based visual localization methods use global descriptors to disambiguate visually similar places, but existing approaches often derive these descriptors from geometric cues alone (e.g., covisibility graphs), limiting their discriminative power and reducing robustness in the presence of noisy geometric constraints. We propose an aggregator module that learns global descriptors consistent with both geometrical structure and visual similarity, ensuring that images are close in descriptor space only when they are visually similar and spatially connected. This corrects erroneous associations caused by unreliable overlap scores. Using a batch-mining strategy based solely on the overlap scores and a modified contrastive loss, our method trains without manual place labels and generalizes across diverse environments. Experiments on challenging benchmarks show substantial localization gains in large-scale environments while preserving computational and memory efficiency. Code is available at https://github.com/sontung/robust_scr. --- ### Any-Optical-Model: A Universal Foundation Model for Optical Remote Sensing Authors: Xuyang Li, Chenyu Li, Danfeng Hong Published: 2025-12-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.17224v1 Optical satellites, with their diverse band layouts and ground sampling distances, supply indispensable evidence for tasks ranging from ecosystem surveillance to emergency response. However, significant discrepancies in band composition and spatial resolution across different optical sensors present major challenges for existing Remote Sensing Foundation Models (RSFMs). These models are typically pretrained on fixed band configurations and resolutions, making them vulnerable to real world scenarios involving missing bands, cross sensor fusion, and unseen spatial scales, thereby limiting their generalization and practical deployment. To address these limitations, we propose Any Optical Model (AOM), a universal RSFM explicitly designed to accommodate arbitrary band compositions, sensor types, and resolution scales. To preserve distinctive spectral characteristics even when bands are missing or newly introduced, AOM introduces a spectrum-independent tokenizer that assigns each channel a dedicated band embedding, enabling explicit encoding of spectral identity. To effectively capture texture and contextual patterns from sub-meter to hundred-meter imagery, we design a multi-scale adaptive patch embedding mechanism that dynamically modulates the receptive field. Furthermore, to maintain global semantic consistency across varying resolutions, AOM incorporates a multi-scale semantic alignment mechanism alongside a channel-wise self-supervised masking and reconstruction pretraining strategy that jointly models spectral-spatial relationships. Extensive experiments on over 10 public datasets, including those from Sentinel-2, Landsat, and HLS, demonstrate that AOM consistently achieves state-of-the-art (SOTA) performance under challenging conditions such as band missing, cross sensor, and cross resolution settings. --- ### DAVE: A VLM Vision Encoder for Document Understanding and Web Agents Authors: Brandon Huang, Hang Hua, Zhuoran Yu, Trevor Darrell, Rogerio Feris, Roei Herzig Published: 2025-12-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.17221v3 While Vision-language models (VLMs) have demonstrated remarkable performance across multi-modal tasks, their choice of vision encoders presents a fundamental weakness: their low-level features lack the robust structural and spatial information essential for document understanding and web agents. To bridge this gap, we introduce DAVE, a vision encoder purpose-built for VLMs and tailored for these tasks. Our training pipeline is designed to leverage abundant unlabeled data to bypass the need for costly large-scale annotations for document and web images. We begin with a self-supervised pretraining stage on unlabeled images, followed by a supervised autoregressive pretraining stage, where the model learns tasks like parsing and localization from limited, high-quality data. Within the supervised stage, we adopt two strategies to improve our encoder's alignment with both general visual knowledge and diverse document and web agentic tasks: (i) We introduce a novel model-merging scheme, combining encoders trained with different text decoders to ensure broad compatibility with different web agentic architectures. (ii) We use ensemble training to fuse features from pretrained generalist encoders (e.g., SigLIP2) with our own document and web-specific representations. Extensive experiments on classic document tasks, VQAs, web localization, and agent-based benchmarks validate the effectiveness of our approach, establishing DAVE as a strong vision encoder for document and web applications. --- ### Mindscape-Aware Retrieval Augmented Generation for Improved Long Context Understanding Authors: Yuqing Li, Jiangnan Li, Zheng Lin, Ziyan Zhou, Junjie Wu, Weiping Wang, Jie Zhou, Mo Yu Published: 2025-12-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.17220v2 Humans understand long and complex texts by relying on a holistic semantic representation of the content. This global view helps organize prior knowledge, interpret new information, and integrate evidence dispersed across a document, as revealed by the Mindscape-Aware Capability of humans in psychology. Current Retrieval-Augmented Generation (RAG) systems lack such guidance and therefore struggle with long-context tasks. In this paper, we propose Mindscape-Aware RAG (MiA-RAG), the first framework to formulate mindscape-aware retrieval and generation as a unified conditioning paradigm for LLM-based RAG. MiA-RAG builds a mindscape through hierarchical summarization and conditions both retrieval and generation on this global semantic representation. This enables the retriever to form enriched query embeddings and the generator to reason over retrieved evidence within a coherent global context. We evaluate MiA-RAG across diverse long-context and bilingual benchmarks for evidence-based understanding and global sense-making. It consistently surpasses baselines, and further analysis shows that it aligns local details with a coherent global representation, enabling more human-like long-context retrieval and reasoning. --- ### Preventing AI Deepfake Abuse: An Islamic Ethics Framework Authors: Wisnu Uriawan, Imany Fauzy Rahman, Muhamad Zidan, Irma Rohmatillah, Muhammad Arkan Raihan, Irma Dwiyanti Published: 2025-12-19 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2512.17218v2 The rapid development of deepfake technology powered by AI has raised global concerns regarding the manipulation of information, the usurpation of digital identities, and the erosion of public trust in the authenticity of online content. These challenges extend beyond technical issues and involve complex moral dimensions, rendering conventional, technologically driven, and reactive management approaches insufficient to address underlying causes such as intent, ethical responsibility, and intangible social harm. In response to these challenges, this study aims to formulate a comprehensive Islamic ethical framework as a preventive approach to mitigate the misuse of deepfake technology. This study employed a Systematic Literature Review (SLR) guided by the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA), selecting ten primary sources published between 2018 and 2025 to identify ethical gaps, regulatory needs, and appropriate normative solutions. The analysis demonstrates that integrating the principles of Maqasid al-Shariah, particularly hifz al-ird and hifz al-nafs, provides a strong normative foundation for governing the responsible use of digital technology. Based on the findings, this study proposes three strategic recommendations: regulatory reforms that recognize the intangible and psychological harms resulting from reputational damage; strengthened technology governance grounded in moral accountability and the values of adl, amanah, and transparency; and enhanced public digital literacy based on the principle of tabayyun. Overall, the findings suggest that the application of Islamic ethical principles shifts governance paradigms from punitive mechanisms toward preventive approaches that emphasize the protection of human dignity, the prevention of harm, and the promotion of the common good in the digital age. --- ### Research on Dead Reckoning Algorithm for Self-Propelled Pipeline Robots in Three-Dimensional Complex Pipelines Authors: Yan Gao, Jiliang Wang, Minghan Wang, Xiaohua Chen, Demin Chen, Zhiyong Ren, Tian-Yun Huang Published: 2025-12-19 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2512.17215v2 In the field of gas pipeline location, existing pipeline location methods mostly rely on pipeline location instruments. However, when faced with complex and curved pipeline scenarios, these methods often fail due to problems such as cable entanglement and insufficient equipment flexibility. To address this pain point, we designed a self-propelled pipeline robot. This robot can autonomously complete the location work of complex and curved pipelines in complex pipe networks without external dragging. In terms of pipeline mapping technology, traditional visual mapping and laser mapping methods are easily affected by lighting conditions and insufficient features in the confined space of pipelines, resulting in mapping drift and divergence problems. In contrast, the pipeline location method that integrates inertial navigation and wheel odometers is less affected by pipeline environmental factors. Based on this, this paper proposes a pipeline robot location method based on extended Kalman filtering (EKF). Firstly, the body attitude angle is initially obtained through an inertial measurement unit (IMU). Then, the extended Kalman filtering algorithm is used to improve the accuracy of attitude angle estimation. Finally, high-precision pipeline location is achieved by combining wheel odometers. During the testing phase, the roll wheels of the pipeline robot needed to fit tightly against the pipe wall to reduce slippage. However, excessive tightness would reduce the flexibility of motion control due to excessive friction. Therefore, a balance needed to be struck between the robot's motion capability and positioning accuracy. Experiments were conducted using the self-propelled pipeline robot in a rectangular loop pipeline, and the results verified the effectiveness of the proposed dead reckoning algorithm. --- ### CheXPO-v2: Preference Optimization for Chest X-ray VLMs with Knowledge Graph Consistency Authors: Xiao Liang, Yuxuan An, Di Wang, Jiawei Hu, Zhicheng Jiao, Bin Jing, Quan Wang Published: 2025-12-19 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2512.17213v1 Medical Vision-Language Models (VLMs) are prone to hallucinations, compromising clinical reliability. While reinforcement learning methods like Group Relative Policy Optimization (GRPO) offer a low-cost alignment solution, their reliance on sparse, outcome-based rewards inadvertently encourages models to "overthink" -- generating verbose, convoluted, and unverifiable Chain-of-Thought reasoning to justify answers. This focus on outcomes obscures factual errors and poses significant safety risks. To address this, we propose CheXPO-v2, a novel alignment framework that shifts from outcome to process supervision. Our core innovation is a Knowledge Graph Consistency Reward mechanism driven by Entity-Relation Matching. By explicitly parsing reasoning steps into structured "Disease, Relation, Anatomy" triplets, we provide fine-grained supervision that penalizes incoherent logic and hallucinations at the atomic level. Integrating this with a hard-example mining strategy, our approach significantly outperforms GRPO and state-of-the-art models on benchmarks like MIMIC-CXR-VQA. Crucially, CheXPO-v2 achieves new state-of-the-art accuracy using only 5k samples, demonstrating exceptional data efficiency while producing clinically sound and verifiable reasoning. The project source code is publicly available at: https://github.com/ecoxial2007/CheX-Phi4MM. --- ### Do Foundational Audio Encoders Understand Music Structure? Authors: Keisuke Toyama, Zhi Zhong, Akira Takahashi, Shusuke Takahashi, Yuki Mitsufuji Published: 2025-12-19 Categories: cs.SD, cs.LG, eess.AS arXiv: https://arxiv.org/abs/2512.17209v2 In music information retrieval (MIR) research, the use of pretrained foundational audio encoders (FAEs) has recently become a trend. FAEs pretrained on large amounts of music and audio data have been shown to improve performance on MIR tasks such as music tagging and automatic music transcription. However, their use for music structure analysis (MSA) remains underexplored: only a small subset of FAEs has been examined for MSA, and the impact of factors such as learning methods, training data, and model context length on MSA performance remains unclear. In this study, we conduct comprehensive experiments on 11 types of FAEs to investigate how these factors affect MSA performance. Our results demonstrate that FAEs using self-supervised learning with masked language modeling on music data are particularly effective for MSA. These findings pave the way for future research in FAE and MSA. --- ### Reasoning Palette: Modulating Reasoning via Latent Contextualization for Controllable Exploration for (V)LMs Authors: Rujiao Long, Yang Li, Xingyao Zhang, Weixun Wang, Tianqianjin Lin, Xi Zhao, Yuchi Xu, Wenbo Su, Junchi Yan, Bo Zheng Published: 2025-12-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.17206v1 Exploration capacity shapes both inference-time performance and reinforcement learning (RL) training for large (vision-) language models, as stochastic sampling often yields redundant reasoning paths with little high-level diversity. This paper proposes Reasoning Palette, a novel latent-modulation framework that endows the model with a stochastic latent variable for strategic contextualization, guiding its internal planning prior to token generation. This latent context is inferred from the mean-pooled embedding of a question-answer pair via a variational autoencoder (VAE), where each sampled latent potentially encodes a distinct reasoning context. During inference, a sampled latent is decoded into learnable token prefixes and prepended to the input prompt, modulating the model's internal reasoning trajectory. In this way, the model performs internal sampling over reasoning strategies prior to output generation, which shapes the style and structure of the entire response sequence. A brief supervised fine-tuning (SFT) warm-up phase allows the model to adapt to this latent conditioning. Within RL optimization, Reasoning Palette facilitates structured exploration by enabling on-demand injection for diverse reasoning modes, significantly enhancing exploration efficiency and sustained learning capability. Experiments across multiple reasoning benchmarks demonstrate that our method enables interpretable and controllable control over the (vision-) language model's strategic behavior, thereby achieving consistent performance gains over standard RL methods. --- ### Learning solution operator of dynamical systems with diffusion maps kernel ridge regression Authors: Jiwoo Song, Daning Huang, John Harlim Published: 2025-12-19 Categories: cs.LG, math.NA arXiv: https://arxiv.org/abs/2512.17203v2 In this work, we propose a simple kernel ridge regression (KRR) framework with a dynamic-aware validation strategy for long-term prediction of complex dynamical systems. By employing a data-driven kernel derived from diffusion maps, the proposed Diffusion Maps Kernel Ridge Regression (DM-KRR) method implicitly adapts to the intrinsic geometry of the system's invariant set, without requiring explicit manifold reconstruction or attractor modeling, procedures that often limit predictive performance. Across a broad range of systems, including smooth manifolds, chaotic attractors, and high-dimensional spatiotemporal flows, DM-KRR consistently outperforms state-of-the-art random feature, neural-network and operator-learning methods in both accuracy and data efficiency. These findings underscore that long-term predictive skill depends not only on model expressiveness, but critically on respecting the geometric constraints encoded in the data through dynamically consistent model selection. Together, simplicity, geometry awareness, and strong empirical performance point to a promising path for reliable and efficient learning of complex dynamical systems. --- ### Fose: Fusion of One-Step Diffusion and End-to-End Network for Pansharpening Authors: Kai Liu, Zeli Lin, Weibo Wang, Linghe Kong, Yulun Zhang Published: 2025-12-19 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.17202v1 Pansharpening is a significant image fusion task that fuses low-resolution multispectral images (LRMSI) and high-resolution panchromatic images (PAN) to obtain high-resolution multispectral images (HRMSI). The development of the diffusion models (DM) and the end-to-end models (E2E model) has greatly improved the frontier of pansharping. DM takes the multi-step diffusion to obtain an accurate estimation of the residual between LRMSI and HRMSI. However, the multi-step process takes large computational power and is time-consuming. As for E2E models, their performance is still limited by the lack of prior and simple structure. In this paper, we propose a novel four-stage training strategy to obtain a lightweight network Fose, which fuses one-step DM and an E2E model. We perform one-step distillation on an enhanced SOTA DM for pansharping to compress the inference process from 50 steps to only 1 step. Then we fuse the E2E model with one-step DM with lightweight ensemble blocks. Comprehensive experiments are conducted to demonstrate the significant improvement of the proposed Fose on three commonly used benchmarks. Moreover, we achieve a 7.42 speedup ratio compared to the baseline DM while achieving much better performance. The code and model are released at https://github.com/Kai-Liu001/Fose. --- ### BumpNet: A Sparse MLP Framework for Learning PDE Solutions Authors: Shao-Ting Chiu, Ioannis G. Kevrekidis, Ulisses Braga-Neto Published: 2025-12-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.17198v2 We introduce BumpNet, a sparse multilayer perceptron (MLP) framework for PDE numerical solution and operator learning. BumpNet is based on basis function expansion, which makes them superficially similar to radial-basis function (RBF) networks. However, the basis functions in BumpNet are constructed from ordinary sigmoid activation functions in a sparse multi-layer framework. This makes BumpNet a MLP, not a RBF neural network, enabling the efficient use of modern training techniques optimized for MLPs. All parameters of the basis functions, including shape, location, and amplitude, are fully trainable. Model parsimony is encouraged through a basis function pruning scheme. BumpNet is a general meshless framework that can be combined with existing neural architectures for learning PDE solutions: here, we propose Bump-PINNs (BumpNet with physics-informed neural networks) for solving general PDEs; Bump-EDNN (BumpNet with evolutionary deep neural networks) to solve time-evolution PDEs; and Bump-DeepONet (BumpNet with deep operator networks) for PDE operator learning. We prove that BumpNets and Bump-DeepONets are universal approximators of continuous functions and continuous operators, respectively. Bump-PINNs are trained using the same collocation-based approach used by PINNs; Bump-EDNN uses a BumpNet only in the spatial domain and uses EDNNs to advance the solution in time; while Bump-DeepONets employ a BumpNet regression network as the trunk network of a DeepONet. Extensive numerical experiments demonstrate the efficiency and accuracy of BumpNets. --- ### UmniBench: Unified Understand and Generation Model Oriented Omni-dimensional Benchmark Authors: Kai Liu, Leyang Chen, Wenbo Li, Zhikai Chen, Zhixin Wang, Renjing Pei, Linghe Kong, Yulun Zhang Published: 2025-12-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.17196v1 Unifying multimodal understanding and generation has shown impressive capabilities in cutting-edge proprietary systems. However, evaluations of unified multimodal models (UMMs) remain decoupled, assessing their understanding and generation abilities separately with corresponding datasets. To address this, we propose UmniBench, a benchmark tailored for UMMs with omni-dimensional evaluation. First, UmniBench can assess the understanding, generation, and editing ability within a single evaluation process. Based on human-examined prompts and QA pairs, UmniBench leverages UMM itself to evaluate its generation and editing ability with its understanding ability. This simple but effective paradigm allows comprehensive evaluation of UMMs. Second, UmniBench covers 13 major domains and more than 200 concepts, ensuring a thorough inspection of UMMs. Moreover, UmniBench can also decouple and separately evaluate understanding, generation, and editing abilities, providing a fine-grained assessment. Based on UmniBench, we benchmark 24 popular models, including both UMMs and single-ability large models. We hope this benchmark provides a more comprehensive and objective view of unified models and logistical support for improving the performance of the community model. --- ### MMRAG-RFT: Two-stage Reinforcement Fine-tuning for Explainable Multi-modal Retrieval-augmented Generation Authors: Shengwei Zhao, Jingwen Yao, Sitong Wei, Linhai Xu, Yuying Liu, Dong Zhang, Zhiqiang Tian, Shaoyi Du Published: 2025-12-19 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.17194v1 Multi-modal Retrieval-Augmented Generation (MMRAG) enables highly credible generation by integrating external multi-modal knowledge, thus demonstrating impressive performance in complex multi-modal scenarios. However, existing MMRAG methods fail to clarify the reasoning logic behind retrieval and response generation, which limits the explainability of the results. To address this gap, we propose to introduce reinforcement learning into multi-modal retrieval-augmented generation, enhancing the reasoning capabilities of multi-modal large language models through a two-stage reinforcement fine-tuning framework to achieve explainable multi-modal retrieval-augmented generation. Specifically, in the first stage, rule-based reinforcement fine-tuning is employed to perform coarse-grained point-wise ranking of multi-modal documents, effectively filtering out those that are significantly irrelevant. In the second stage, reasoning-based reinforcement fine-tuning is utilized to jointly optimize fine-grained list-wise ranking and answer generation, guiding multi-modal large language models to output explainable reasoning logic in the MMRAG process. Our method achieves state-of-the-art results on WebQA and MultimodalQA, two benchmark datasets for multi-modal retrieval-augmented generation, and its effectiveness is validated through comprehensive ablation experiments. --- ### Anatomical Region-Guided Contrastive Decoding: A Plug-and-Play Strategy for Mitigating Hallucinations in Medical VLMs Authors: Xiao Liang, Chenxi Liu, Zhi Ma, Di Wang, Bin Jing, Quan Wang, Yuanyuan Shi Published: 2025-12-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.17189v1 Medical Vision-Language Models (MedVLMs) show immense promise in clinical applicability. However, their reliability is hindered by hallucinations, where models often fail to derive answers from visual evidence, instead relying on learned textual priors. Existing mitigation strategies for MedVLMs have distinct limitations: training-based methods rely on costly expert annotations, limiting scalability, while training-free interventions like contrastive decoding, though data-efficient, apply a global, untargeted correction whose effects in complex real-world clinical settings can be unreliable. To address these challenges, we introduce Anatomical Region-Guided Contrastive Decoding (ARCD), a plug-and-play strategy that mitigates hallucinations by providing targeted, region-specific guidance. Our module leverages an anatomical mask to direct a three-tiered contrastive decoding process. By dynamically re-weighting at the token, attention, and logits levels, it verifiably steers the model's focus onto specified regions, reinforcing anatomical understanding and suppressing factually incorrect outputs. Extensive experiments across diverse datasets, including chest X-ray, CT, brain MRI, and ocular ultrasound, demonstrate our method's effectiveness in improving regional understanding, reducing hallucinations, and enhancing overall diagnostic accuracy. --- ### Globally Optimal Solution to the Generalized Relative Pose Estimation Problem using Affine Correspondences Authors: Zhenbao Yu, Banglei Guan, Shunkun Liang, Zibin Liu, Yang Shang, Qifeng Yu Published: 2025-12-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.17188v1 Mobile devices equipped with a multi-camera system and an inertial measurement unit (IMU) are widely used nowadays, such as self-driving cars. The task of relative pose estimation using visual and inertial information has important applications in various fields. To improve the accuracy of relative pose estimation of multi-camera systems, we propose a globally optimal solver using affine correspondences to estimate the generalized relative pose with a known vertical direction. First, a cost function about the relative rotation angle is established after decoupling the rotation matrix and translation vector, which minimizes the algebraic error of geometric constraints from affine correspondences. Then, the global optimization problem is converted into two polynomials with two unknowns based on the characteristic equation and its first derivative is zero. Finally, the relative rotation angle can be solved using the polynomial eigenvalue solver, and the translation vector can be obtained from the eigenvector. Besides, a new linear solution is proposed when the relative rotation is small. The proposed solver is evaluated on synthetic data and real-world datasets. The experiment results demonstrate that our method outperforms comparable state-of-the-art methods in accuracy. --- ### It is not always greener on the other side: Greenery perception across demographics and personalities in multiple cities Authors: Matias Quintana, Fangqi Liu, Jussi Torkko, Youlong Gu, Xiucheng Liang, Yujun Hou, Koichi Ito, Yihan Zhu, Mahmoud Abdelrahman, Tuuli Toivonen, Yi Lu, Filip Biljecki Published: 2025-12-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.17186v2 Quantifying and assessing urban greenery is consequential for planning and development, reflecting the everlasting importance of green spaces for multiple climate and well-being dimensions of cities. Evaluation can be broadly grouped into objective (e.g., measuring the amount of greenery) and subjective (e.g., polling the perception of people) approaches, which may differ -- what people see and feel about how green a place is might not match the measurements of the actual amount of vegetation. In this work, we advance the state of the art by measuring such differences and explaining them through human, geographic, and spatial dimensions. The experiments rely on contextual information extracted from street view imagery and a comprehensive urban visual perception survey collected from 1,000 people across five countries with their extensive demographic and personality information. We analyze the discrepancies between objective measures (e.g., Green View Index (GVI)) and subjective scores (e.g., pairwise ratings), examining whether they can be explained by a variety of human and visual factors such as age group and spatial variation of greenery in the scene. The findings reveal that such discrepancies are comparable around the world and that demographics and personality do not play a significant role in perception. Further, while perceived and measured greenery correlate consistently across geographies (both where people and where imagery are from), where people live plays a significant role in explaining perceptual differences, with these two, as the top among seven, features that influences perceived greenery the most. This location influence suggests that cultural, environmental, and experiential factors substantially shape how individuals observe greenery in cities. --- ### Systemic Risk Radar: A Multi-Layer Graph Framework for Early Market Crash Warning Authors: Sandeep Neela Published: 2025-12-19 Categories: q-fin.RM, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.17185v1 Financial crises emerge when structural vulnerabilities accumulate across sectors, markets, and investor behavior. Predicting these systemic transitions is challenging because they arise from evolving interactions between market participants, not isolated price movements alone. We present Systemic Risk Radar (SRR), a framework that models financial markets as multi-layer graphs to detect early signs of systemic fragility and crash-regime transitions. We evaluate SRR across three major crises: the Dot-com crash, the Global Financial Crisis, and the COVID-19 shock. Our experiments compare snapshot GNNs, a simplified temporal GNN prototype, and standard baselines (logistic regression and Random Forest). Results show that structural network information provides useful early-warning signals compared to feature-based models alone. This correlation-based instantiation of SRR demonstrates that graph-derived features capture meaningful changes in market structure during stress events. The findings motivate extending SRR with additional graph layers (sector/factor exposure, sentiment) and more expressive temporal architectures (LSTM/GRU or Transformer encoders) to better handle diverse crisis types. --- ### Conservative Bias in Multi-Teacher Learning: Why Agents Prefer Low-Reward Advisors Authors: Maher Mesto, Francisco Cruz Published: 2025-12-19 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2512.17180v2 Interactive reinforcement learning (IRL) has shown promise in enabling autonomous agents and robots to learn complex behaviours from human teachers, yet the dynamics of teacher selection remain poorly understood. This paper reveals an unexpected phenomenon in IRL: when given a choice between teachers with different reward structures, learning agents overwhelmingly prefer conservative, low-reward teachers (93.16% selection rate) over those offering 20x higher rewards. Through 1,250 experimental runs in navigation tasks with multiple expert teachers, we discovered: (1) Conservative bias dominates teacher selection: agents systematically choose the lowest-reward teacher, prioritising consistency over optimality; (2) Critical performance thresholds exist at teacher availability rho >= 0.6 and accuracy omega >= 0.6, below which the framework fails catastrophically; (3) The framework achieves 159% improvement over baseline Q-learning under concept drift. These findings challenge fundamental assumptions about optimal teaching in RL and suggest potential implications for human-robot collaboration, where human preferences for safety and consistency may align with the observed agent selection behaviour, potentially informing training paradigms for safety-critical robotic applications. --- ### Enhancing Long Document Long Form Summarisation with Self-Planning Authors: Xiaotang Du, Rohit Saxena, Laura Perez-Beltrachini, Pasquale Minervini, Ivan Titov Published: 2025-12-19 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.17179v1 We introduce a novel approach for long context summarisation, highlight-guided generation, that leverages sentence-level information as a content plan to improve the traceability and faithfulness of generated summaries. Our framework applies self-planning methods to identify important content and then generates a summary conditioned on the plan. We explore both an end-to-end and two-stage variants of the approach, finding that the two-stage pipeline performs better on long and information-dense documents. Experiments on long-form summarisation datasets demonstrate that our method consistently improves factual consistency while preserving relevance and overall quality. On GovReport, our best approach has improved ROUGE-L by 4.1 points and achieves about 35% gains in SummaC scores. Qualitative analysis shows that highlight-guided summarisation helps preserve important details, leading to more accurate and insightful summaries across domains. --- ### ABE-CLIP: Training-Free Attribute Binding Enhancement for Compositional Image-Text Matching Authors: Qi Zhang, Yuxu Chen, Lei Deng, Lili Shen Published: 2025-12-19 Categories: cs.CV, cs.IR arXiv: https://arxiv.org/abs/2512.17178v1 Contrastive Language-Image Pretraining (CLIP) has achieved remarkable performance in various multimodal tasks. However, it still struggles with compositional image-text matching, particularly in accurately associating objects with their corresponding attributes, because its inherent global representation often overlooks fine-grained semantics for attribute binding. Existing methods often require additional training or extensive hard negative sampling, yet they frequently show limited generalization to novel compositional concepts and fail to fundamentally address the drawbacks of global representations. In this paper, we propose ABE-CLIP, a novel training-free Attribute Binding Enhancement method designed to strengthen attribute-object binding in CLIP-like models. Specifically, we employ a Semantic Refinement Mechanism to refine token embeddings for both object and attribute phrases in the text, thereby mitigating attribute confusion and improving semantic precision. We further introduce a Local Token-Patch Alignment strategy that computes similarity scores between refined textual tokens and their most relevant image patches. By aggregating localized similarity scores, ABE-CLIP computes the final image-text similarity. Experiments on multiple datasets demonstrate that ABE-CLIP significantly improves attribute-object binding performance, even surpassing methods that require extensive training. --- ### PILAR: Personalizing Augmented Reality Interactions with LLM-based Human-Centric and Trustworthy Explanations for Daily Use Cases Authors: Ripan Kumar Kundu, Istiak Ahmed, Khaza Anuarul Hoque Published: 2025-12-19 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2512.17172v1 Artificial intelligence (AI)-driven augmented reality (AR) systems are becoming increasingly integrated into daily life, and with this growth comes a greater need for explainability in real-time user interactions. Traditional explainable AI (XAI) methods, which often rely on feature-based or example-based explanations, struggle to deliver dynamic, context-specific, personalized, and human-centric insights for everyday AR users. These methods typically address separate explainability dimensions (e.g., when, what, how) with different explanation techniques, resulting in unrealistic and fragmented experiences for seamless AR interactions. To address this challenge, we propose PILAR, a novel framework that leverages a pre-trained large language model (LLM) to generate context-aware, personalized explanations, offering a more intuitive and trustworthy experience in real-time AI-powered AR systems. Unlike traditional methods, which rely on multiple techniques for different aspects of explanation, PILAR employs a unified LLM-based approach that dynamically adapts explanations to the user's needs, fostering greater trust and engagement. We implement the PILAR concept in a real-world AR application (e.g., personalized recipe recommendations), an open-source prototype that integrates real-time object detection, recipe recommendation, and LLM-based personalized explanations of the recommended recipes based on users' dietary preferences. We evaluate the effectiveness of PILAR through a user study with 16 participants performing AR-based recipe recommendation tasks, comparing an LLM-based explanation interface to a traditional template-based one. Results show that the LLM-based interface significantly enhances user performance and experience, with participants completing tasks 40% faster and reporting greater satisfaction, ease of use, and perceived transparency. --- ### Application of machine learning to predict food processing level using Open Food Facts Authors: Nalin Arora, Aviral Chauhan, Siddhant Rana, Mahansh Aditya, Sumit Bhagat, Aditya Kumar, Akash Kumar, Akanksh Semar, Ayush Vikram Singh, Ganesh Bagler Published: 2025-12-19 Categories: q-bio.BM, cs.LG arXiv: https://arxiv.org/abs/2512.17169v1 Ultra-processed foods are increasingly linked to health issues like obesity, cardiovascular disease, type 2 diabetes, and mental health disorders due to poor nutritional quality. This first-of-its-kind study at such a scale uses machine learning to classify food processing levels (NOVA) based on the Open Food Facts dataset of over 900,000 products. Models including LightGBM, Random Forest, and CatBoost were trained on nutrient concentration data. LightGBM performed best, achieving 80-85% accuracy across different nutrient panels and effectively distinguishing minimally from ultra-processed foods. Exploratory analysis revealed strong associations between higher NOVA classes and lower Nutri-Scores, indicating poorer nutritional quality. Products in NOVA 3 and 4 also had higher carbon footprints and lower Eco-Scores, suggesting greater environmental impact. Allergen analysis identified gluten and milk as common in ultra-processed items, posing risks to sensitive individuals. Categories like Cakes and Snacks were dominant in higher NOVA classes, which also had more additives, highlighting the role of ingredient modification. This study, leveraging the largest dataset of NOVA-labeled products, emphasizes the health, environmental, and allergenic implications of food processing and showcases machine learning's value in scalable classification. A user-friendly web tool is available for NOVA prediction using nutrient data: https://cosylab.iiitd.edu.in/foodlabel/. --- ### Distributed Learning in Markovian Restless Bandits over Interference Graphs for Stable Spectrum Sharing Authors: Liad Lea Didi, Kobi Cohen Published: 2025-12-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.17161v1 We study distributed learning for spectrum access and sharing among multiple cognitive communication entities, such as cells, subnetworks, or cognitive radio users (collectively referred to as cells), in communication-constrained wireless networks modeled by interference graphs. Our goal is to achieve a globally stable and interference-aware channel allocation. Stability is defined through a generalized Gale-Shapley multi-to-one matching, a well-established solution concept in wireless resource allocation. We consider wireless networks where L cells share S orthogonal channels and cannot simultaneously use the same channel as their neighbors. Each channel evolves as an unknown restless Markov process with cell-dependent rewards, making this the first work to establish global Gale-Shapley stability for channel allocation in a stochastic, temporally varying restless environment. To address this challenge, we develop SMILE (Stable Multi-matching with Interference-aware LEarning), a communication-efficient distributed learning algorithm that integrates restless bandit learning with graph-constrained coordination. SMILE enables cells to distributedly balance exploration of unknown channels with exploitation of learned information. We prove that SMILE converges to the optimal stable allocation and achieves logarithmic regret relative to a genie with full knowledge of expected utilities. Simulations validate the theoretical guarantees and demonstrate SMILE's robustness, scalability, and efficiency across diverse spectrum-sharing scenarios. --- ### Can Synthetic Images Serve as Effective and Efficient Class Prototypes? Authors: Dianxing Shi, Dingjie Fu, Yuqiao Liu, Jun Wang Published: 2025-12-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.17160v2 Vision-Language Models (VLMs) have shown strong performance in zero-shot image classification tasks. However, existing methods, including Contrastive Language-Image Pre-training (CLIP), all rely on annotated text-to-image pairs for aligning visual and textual modalities. This dependency introduces substantial cost and accuracy requirement in preparing high-quality datasets. At the same time, processing data from two modes also requires dual-tower encoders for most models, which also hinders their lightweight. To address these limitations, we introduce a ``Contrastive Language-Image Pre-training via Large-Language-Model-based Generation (LGCLIP)" framework. LGCLIP leverages a Large Language Model (LLM) to generate class-specific prompts that guide a diffusion model in synthesizing reference images. Afterwards these generated images serve as visual prototypes, and the visual features of real images are extracted and compared with the visual features of these prototypes to achieve comparative prediction. By optimizing prompt generation through the LLM and employing only a visual encoder, LGCLIP remains lightweight and efficient. Crucially, our framework requires only class labels as input during whole experimental procedure, eliminating the need for manually annotated image-text pairs and extra pre-processing. Experimental results validate the feasibility and efficiency of LGCLIP, demonstrating great performance in zero-shot classification tasks and establishing a novel paradigm for classification. --- ### PhysFire-WM: A Physics-Informed World Model for Emulating Fire Spread Dynamics Authors: Nan Zhou, Huandong Wang, Jiahao Li, Yang Li, Xiao-Ping Zhang, Yong Li, Xinlei Chen Published: 2025-12-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.17152v1 Fine-grained fire prediction plays a crucial role in emergency response. Infrared images and fire masks provide complementary thermal and boundary information, yet current methods are predominantly limited to binary mask modeling with inherent signal sparsity, failing to capture the complex dynamics of fire. While world models show promise in video generation, their physical inconsistencies pose significant challenges for fire forecasting. This paper introduces PhysFire-WM, a Physics-informed World Model for emulating Fire spread dynamics. Our approach internalizes combustion dynamics by encoding structured priors from a Physical Simulator to rectify physical discrepancies, coupled with a Cross-task Collaborative Training strategy (CC-Train) that alleviates the issue of limited information in mask-based modeling. Through parameter sharing and gradient coordination, CC-Train effectively integrates thermal radiation dynamics and spatial boundary delineation, enhancing both physical realism and geometric accuracy. Extensive experiments on a fine-grained multimodal fire dataset demonstrate the superior accuracy of PhysFire-WM in fire spread prediction. Validation underscores the importance of physical priors and cross-task collaboration, providing new insights for applying physics-informed world models to disaster prediction. --- ### Text-Conditioned Background Generation for Editable Multi-Layer Documents Authors: Taewon Kang, Joseph K J, Chris Tensmeyer, Jihyung Kil, Wanrong Zhu, Ming C. Lin, Vlad I. Morariu Published: 2025-12-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.17151v2 We present a framework for document-centric background generation with multi-page editing and thematic continuity. To ensure text regions remain readable, we employ a latent masking formulation that softly attenuates updates in the diffusion space, inspired by smooth barrier functions in physics and numerical optimization. In addition, we introduce Automated Readability Optimization (ARO), which automatically places semi-transparent, rounded backing shapes behind text regions. ARO determines the minimal opacity needed to satisfy perceptual contrast standards (WCAG 2.2) relative to the underlying background, ensuring readability while maintaining aesthetic harmony without human intervention. Multi-page consistency is maintained through a summarization-and-instruction process, where each page is distilled into a compact representation that recursively guides subsequent generations. This design reflects how humans build continuity by retaining prior context, ensuring that visual motifs evolve coherently across an entire document. Our method further treats a document as a structured composition in which text, figures, and backgrounds are preserved or regenerated as separate layers, allowing targeted background editing without compromising readability. Finally, user-provided prompts allow stylistic adjustments in color and texture, balancing automated consistency with flexible customization. Our training-free framework produces visually coherent, text-preserving, and thematically aligned documents, bridging generative modeling with natural design workflows. --- ### Biosecurity-Aware AI: Agentic Risk Auditing of Soft Prompt Attacks on ESM-Based Variant Predictors Authors: Huixin Zhan Published: 2025-12-19 Categories: cs.CR, cs.LG, q-bio.QM arXiv: https://arxiv.org/abs/2512.17146v1 Genomic Foundation Models (GFMs), such as Evolutionary Scale Modeling (ESM), have demonstrated remarkable success in variant effect prediction. However, their security and robustness under adversarial manipulation remain largely unexplored. To address this gap, we introduce the Secure Agentic Genomic Evaluator (SAGE), an agentic framework for auditing the adversarial vulnerabilities of GFMs. SAGE functions through an interpretable and automated risk auditing loop. It injects soft prompt perturbations, monitors model behavior across training checkpoints, computes risk metrics such as AUROC and AUPR, and generates structured reports with large language model-based narrative explanations. This agentic process enables continuous evaluation of embedding-space robustness without modifying the underlying model. Using SAGE, we find that even state-of-the-art GFMs like ESM2 are sensitive to targeted soft prompt attacks, resulting in measurable performance degradation. These findings reveal critical and previously hidden vulnerabilities in genomic foundation models, showing the importance of agentic risk auditing in securing biomedical applications such as clinical variant interpretation. --- ### Solomonoff-Inspired Hypothesis Ranking with LLMs for Prediction Under Uncertainty Authors: Josh Barber, Rourke Young, Cameron Coombe, Will Browne Published: 2025-12-19 Categories: cs.AI, cs.IT arXiv: https://arxiv.org/abs/2512.17145v2 Reasoning under uncertainty is a key challenge in AI, especially for real-world tasks, where problems with sparse data demands systematic generalisation. Existing approaches struggle to balance accuracy and simplicity when evaluating multiple candidate solutions. We propose a Solomonoff-inspired method that weights LLM-generated hypotheses by simplicity and predictive fit. Applied to benchmark (Mini-ARC) tasks, our method produces Solomonoff-weighted mixtures for per-cell predictions, yielding conservative, uncertainty-aware outputs even when hypotheses are noisy or partially incorrect. Compared to Bayesian Model Averaging (BMA), Solomonoff scoring spreads probability more evenly across competing hypotheses, while BMA concentrates weight on the most likely but potentially flawed candidates. Across tasks, this highlights the value of algorithmic information-theoretic priors for interpretable, reliable multi-hypothesis reasoning under uncertainty. --- ### Pro-Pose: Unpaired Full-Body Portrait Synthesis via Canonical UV Maps Authors: Sandeep Mishra, Yasamin Jafarian, Andreas Lugmayr, Yingwei Li, Varsha Ramakrishnan, Srivatsan Varadharajan, Alan C. Bovik, Ira Kemelmacher-Shlizerman Published: 2025-12-19 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.17143v3 Photographs of people taken by professional photographers typically present the person in beautiful lighting, with an interesting pose, and flattering quality. This is unlike common photos people take of themselves in uncontrolled conditions. In this paper, we explore how to canonicalize a person's 'in-the-wild' photograph into a controllable, high-fidelity avatar -- reposed in a simple environment with standardized minimal clothing. A key challenge is preserving the person's unique whole-body identity, facial features, and body shape while stripping away the complex occlusions of their original garments. While a large paired dataset of the same person in varied clothing and poses would simplify this, such data does not exist. To that end, we propose two key insights: 1) Our method transforms the input photo into a canonical full-body UV space, which we couple with a novel reposing methodology to model occlusions and synthesize novel views. Operating in UV space allows us to decouple pose from appearance and leverage massive unpaired datasets. 2) We personalize the output photo via multi-image finetuning to ensure robust identity preservation under extreme pose changes. Our approach yields high-quality, reposed portraits that achieve strong quantitative performance on real-world imagery, providing an ideal, clean biometric canvas that significantly improves the fidelity of downstream applications like Virtual Try-On (VTO). --- ### SDUM: A Scalable Deep Unrolled Model for Universal MRI Reconstruction Authors: Puyang Wang, Pengfei Guo, Keyi Chai, Jinyuan Zhou, Daguang Xu, Shanshan Jiang Published: 2025-12-19 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.17137v2 Clinical MRI encompasses diverse imaging protocols--spanning anatomical targets (cardiac, brain, knee), contrasts (T1, T2, mapping), sampling patterns (Cartesian, radial, spiral, kt-space), and acceleration factors--yet current deep learning reconstructions are typically protocol-specific, hindering generalization and deployment. We introduce Scalable Deep Unrolled Model (SDUM), a universal framework combining a Restormer-based reconstructor, a learned coil sensitivity map estimator (CSME), sampling-aware weighted data consistency (SWDC), universal conditioning (UC) on cascade index and protocol metadata, and progressive cascade expansion training. SDUM exhibits foundation-model-like scaling behavior: reconstruction quality follows PSNR ${\sim}$ log(parameters) with correlation $r{=}0.986$ ($R^2{=}0.973$) up to 18 cascades, demonstrating predictable performance gains with model depth. A single SDUM trained on heterogeneous data achieves state-of-the-art results across all four CMRxRecon2025 challenge tracks--multi-center, multi-disease, 5T, and pediatric--without task-specific fine-tuning, surpassing specialized baselines by up to ${+}1.0$~dB. On CMRxRecon2024, SDUM outperforms the winning method PromptMR+ by ${+}0.55$~dB; on fastMRI brain, it exceeds PC-RNN by ${+}1.8$~dB. Ablations validate each component: SWDC ${+}0.43$~dB over standard DC, per-cascade CSME ${+}0.51$~dB, UC ${+}0.38$~dB. These results establish SDUM as a practical path toward universal, scalable MRI reconstruction. --- ### HumanMCP: A Human-Like Query Dataset for Evaluating MCP Tool Retrieval Performance Authors: Shubh Laddha, Lucas Changbencharoen, Win Kuptivej, Surya Shringla, Archana Vaidheeswaran, Yash Bhaskar Published: 2025-12-18 Categories: cs.AI, cs.IR arXiv: https://arxiv.org/abs/2602.23367v1 Model Context Protocol (MCP) servers contain a collection of thousands of open-source standardized tools, linking LLMs to external systems; however, existing datasets and benchmarks lack realistic, human-like user queries, remaining a critical gap in evaluating the tool usage and ecosystems of MCP servers. Existing datasets often do contain tool descriptions but fail to represent how different users portray their requests, leading to poor generalization and inflated reliability of certain benchmarks. This paper introduces the first large-scale MCP dataset featuring diverse, high-quality diverse user queries generated specifically to match 2800 tools across 308 MCP servers, developing on the MCP Zero dataset. Each tool is paired with multiple unique user personas that we have generated, to capture varying levels of user intent ranging from precise task requests, and ambiguous, exploratory commands, reflecting the complexity of real-world interaction patterns. --- ### HybridQuestion: Human-AI Collaboration for Identifying High-Impact Research Questions Authors: Keyu Zhao, Fengli Xu, Yong Li, Tie-Yan Liu Published: 2025-12-18 Categories: cs.HC, cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2602.03849v1 The "AI Scientist" paradigm is transforming scientific research by automating key stages of the research process, from idea generation to scholarly writing. This shift is expected to accelerate discovery and expand the scope of scientific inquiry. However, a key question remains unclear: can AI scientists identify meaningful research questions? While Large Language Models (LLMs) have been applied successfully to task-specific ideation, their potential to conduct strategic, long-term assessments of past breakthroughs and future questions remains largely unexplored. To address this gap, we explore a human-AI hybrid solution that integrates the scalable data processing capabilities of AI with the value judgment of human experts. Our methodology is structured in three phases. The first phase, AI-Accelerated Information Gathering, leverages AI's advantage in processing vast amounts of literature to generate a hybrid information base. The second phase, Candidate Question Proposing, utilizes this synthesized data to prompt an ensemble of six diverse LLMs to propose an initial candidate pool, filtered via a cross-model voting mechanism. The third phase, Hybrid Question Selection, refines this pool through a multi-stage filtering process that progressively increases human oversight. To validate this system, we conducted an experiment aiming to identify the Top 10 Scientific Breakthroughs of 2025 and the Top 10 Scientific Questions for 2026 across five major disciplines. Our analysis reveals that while AI agents demonstrate high alignment with human experts in recognizing established breakthroughs, they exhibit greater divergence in forecasting prospective questions, suggesting that human judgment remains crucial for evaluating subjective, forward-looking challenges. --- ### MIMIC-RD: Can LLMs differentially diagnose rare diseases in real-world clinical settings? Authors: Zilal Eiz AlDin, John Wu, Jeffrey Paul Fung, Jennifer King, Mya Watts, Lauren ONeill, Adam Richard Cross, Jimeng Sun Published: 2025-12-18 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2601.11559v1 Despite rare diseases affecting 1 in 10 Americans, their differential diagnosis remains challenging. Due to their impressive recall abilities, large language models (LLMs) have been recently explored for differential diagnosis. Existing approaches to evaluating LLM-based rare disease diagnosis suffer from two critical limitations: they rely on idealized clinical case studies that fail to capture real-world clinical complexity, or they use ICD codes as disease labels, which significantly undercounts rare diseases since many lack direct mappings to comprehensive rare disease databases like Orphanet. To address these limitations, we explore MIMIC-RD, a rare disease differential diagnosis benchmark constructed by directly mapping clinical text entities to Orphanet. Our methodology involved an initial LLM-based mining process followed by validation from four medical annotators to confirm identified entities were genuine rare diseases. We evaluated various models on our dataset of 145 patients and found that current state-of-the-art LLMs perform poorly on rare disease differential diagnosis, highlighting the substantial gap between existing capabilities and clinical needs. From our findings, we outline several future steps towards improving differential diagnosis of rare diseases. --- ### The Violation State: Safety State Persistence in a Multimodal Language Model Interface Authors: Bentley DeVilling Published: 2025-12-18 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2601.06049v1 Multimodal AI systems integrate text generation, image generation, and other capabilities within a single conversational interface. These systems employ safety mechanisms to prevent disallowed actions, including the removal of watermarks from copyrighted images. While single-turn refusals are expected, the interaction between safety filters and conversation-level state is not well understood. This study documents a reproducible behavioral effect in the ChatGPT (GPT-5.1) web interface. Manual execution was chosen to capture the exact user-facing safety behavior of the production system, rather than isolated API components. When a conversation begins with an uploaded copyrighted image and a request to remove a watermark, which the model correctly refuses, subsequent prompts to generate unrelated, benign images are refused for the remainder of the session. Importantly, text-only requests (e.g., generating a Python function) continue to succeed. Across 40 manually run sessions (30 contaminated and 10 controls), contaminated threads showed 116/120 image-generation refusals (96.67%), while control threads showed 0/40 refusals (Fisher's exact p < 0.0001). All sessions used an identical fixed prompt order, ensuring sequence uniformity across conditions. We describe this as safety-state persistence: a form of conversational over-generalization in which a copyright refusal influences subsequent, unrelated image-generation behavior. We present these findings as behavioral observations, not architectural claims. We discuss possible explanations, methodological limitations (single model, single interface), and implications for multimodal reliability, user experience, and the design of session-level safety systems. These results motivate further examination of session-level safety interactions in multimodal AI systems. --- ### Active Sensing Shapes Real-World Decision-Making through Dynamic Evidence Accumulation Authors: Hongliang Lu, Yunmeng Liu, Junjie Yang Published: 2025-12-18 Categories: cs.AI, cs.HC, cs.RO, q-bio.NC arXiv: https://arxiv.org/abs/2601.04214v1 Human decision-making heavily relies on active sensing, a well-documented cognitive behaviour for evidence gathering to accommodate ever-changing environments. However, its operational mechanism in the real world remains non-trivial. Currently, an in-laboratory paradigm, called evidence accumulation modelling (EAM), points out that human decision-making involves transforming external evidence into internal mental beliefs. However, the gap in evidence affordance between real-world contexts and laboratory settings hinders the effective application of EAM. Here we generalize EAM to the real world and conduct analysis in real-world driving scenarios. A cognitive scheme is proposed to formalize real-world evidence affordance and capture active sensing through eye movements. Empirically, our scheme can plausibly portray the accumulation of drivers' mental beliefs, explaining how active sensing transforms evidence into mental beliefs from the perspective of information utility. Also, our results demonstrate a negative correlation between evidence affordance and attention recruited by individuals, revealing how human drivers adapt their evidence-collection patterns across various contexts. Moreover, we reveal the positive influence of evidence affordance and attention distribution on decision-making propensity. In a nutshell, our computational scheme generalizes EAM to real-world contexts and provides a comprehensive account of how active sensing underlies real-world decision-making, unveiling multifactorial, integrated characteristics in real-world decision-making. --- ### Benchmarking and Adapting On-Device LLMs for Clinical Decision Support Authors: Alif Munim, Jun Ma, Omar Ibrahim, Alhusain Abdalla, Shuolin Yin, Leo Chen, Bo Wang Published: 2025-12-18 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.03266v2 Large language models (LLMs) have rapidly advanced in clinical decision-making, yet the deployment of proprietary systems is hindered by privacy concerns and reliance on cloud-based infrastructure. Open-source alternatives allow local inference but often have large model sizes that limit their use in resource-constrained clinical settings. Here, we benchmark on-device LLMs from the gpt-oss (20b, 120b), Qwen3.5 (9B, 27B, 35B), and Gemma 4 (31B) families across three representative clinical tasks: general disease diagnosis, specialty-specific (ophthalmology) diagnosis and management, and simulation of human expert grading and evaluation. We compare their performance with state-of-the-art proprietary models (GPT-5.1, GPT-5-mini, and Gemini 3.1 Pro) and a leading open-source model (DeepSeek-R1), and we further evaluate the adaptability of on-device systems by fine-tuning gpt-oss-20b and Qwen3.5-35B on general diagnostic data. Across tasks, on-device models achieve performance comparable to or exceeding DeepSeek-R1 and GPT-5-mini despite being substantially smaller. In addition, fine-tuning remarkably improves diagnostic accuracy, with the fine-tuned Qwen3.5-35B reaching 87.9% and approaching the proprietary GPT-5.1 (89.4%). Among base on-device models, Gemma 4 31B achieved the strongest general diagnostic accuracy at 86.5%, exceeding GPT-5-mini and approaching the fine-tuned Qwen3.5-35B. Error characterization revealed that 87.2% of diagnostic errors across all models were clinically plausible differentials rather than off-topic predictions, and upper-bound analysis showed up to 93.2% attainable accuracy through improved answer selection. These findings highlight the potential of on-device LLMs to deliver accurate, adaptable, and privacy-preserving clinical decision support, offering a practical pathway for broader integration of LLMs into routine clinical practice. --- ### Jailbreak-Zero: A Path to Pareto Optimal Red Teaming for Large Language Models Authors: Kai Hu, Abhinav Aggarwal, Mehran Khodabandeh, David Zhang, Eric Hsin, Li Chen, Ankit Jain, Matt Fredrikson, Akash Bharadwaj Published: 2025-12-18 Categories: cs.CL, cs.CR, cs.LG arXiv: https://arxiv.org/abs/2601.03265v1 This paper introduces Jailbreak-Zero, a novel red teaming methodology that shifts the paradigm of Large Language Model (LLM) safety evaluation from a constrained example-based approach to a more expansive and effective policy-based framework. By leveraging an attack LLM to generate a high volume of diverse adversarial prompts and then fine-tuning this attack model with a preference dataset, Jailbreak-Zero achieves Pareto optimality across the crucial objectives of policy coverage, attack strategy diversity, and prompt fidelity to real user inputs. The empirical evidence demonstrates the superiority of this method, showcasing significantly higher attack success rates against both open-source and proprietary models like GPT-40 and Claude 3.5 when compared to existing state-of-the-art techniques. Crucially, Jailbreak-Zero accomplishes this while producing human-readable and effective adversarial prompts with minimal need for human intervention, thereby presenting a more scalable and comprehensive solution for identifying and mitigating the safety vulnerabilities of LLMs. --- ### How to Discover Knowledge for FutureG: Contextual RAG and LLM Prompting for O-RAN Authors: Nathan Conger, Nathan Scollar, Kemal Davaslioglu, Yalin E. Sagduyu, Sastry Kompella Published: 2025-12-18 Categories: cs.NI, cs.AI, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2601.02382v1 We present a retrieval-augmented question answering framework for 5G/6G networks, where the Open Radio Access Network (O-RAN) has become central to disaggregated, virtualized, and AI-driven wireless systems. While O-RAN enables multi-vendor interoperability and cloud-native deployments, its fast-changing specifications and interfaces pose major challenges for researchers and practitioners. Manual navigation of these complex documents is labor-intensive and error-prone, slowing system design, integration, and deployment. To address this challenge, we adopt Contextual Retrieval-Augmented Generation (Contextual RAG), a strategy in which candidate answer choices guide document retrieval and chunk-specific context to improve large language model (LLM) performance. This improvement over traditional RAG achieves more targeted and context-aware retrieval, which improves the relevance of documents passed to the LLM, particularly when the query alone lacks sufficient context for accurate grounding. Our framework is designed for dynamic domains where data evolves rapidly and models must be continuously updated or redeployed, all without requiring LLM fine-tuning. We evaluate this framework using the ORANBenchmark-13K dataset, and compare three LLMs, namely, Llama3.2, Qwen2.5-7B, and Qwen3.0-4B, across both Direct Question Answering (Direct Q&A) and Chain-of-Thought (CoT) prompting strategies. We show that Contextual RAG consistently improves accuracy over standard RAG and base prompting, while maintaining competitive runtime and CO2 emissions. These results highlight the potential of Contextual RAG to serve as a scalable and effective solution for domain-specific Q&A in ORAN and broader 5G/6G environments, enabling more accurate interpretation of evolving standards while preserving efficiency and sustainability. --- ### LLMs, Reasoning and Plagiarism Authors: Elchanan Mossel Published: 2025-12-18 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2601.02380v5 Recent reports claim that Large Language Models (LLMs) derive new science and exhibit human-level general intelligence. Such claims are entangled with two different narratives about what LLMs do: one in which they are an engine of synthesis that genuinely reasons to new knowledge, and one in which they retrieve and re-emit the work of others without attribution. In the scientific setting these are best understood as a contrast between \emph{reasoning} and \emph{plagiarism}. Finding where the truth lies between these two narratives is very challenging, as central components of the model -- the training data and the interaction transcript -- remain opaque. Thus claims of LLM reasoning do not satisfy Popper's refutability principle. We propose guidelines for transparency and reproducibility that will allow reasoning claims to be studied using the scientific method. The dominance of the reasoning narrative, we suggest, is in practice encouraging plagiarism in the scientific literature; we discuss what might be done about it. --- ### Yahtzee: Reinforcement Learning Techniques for Stochastic Combinatorial Games Authors: Nicholas A. Pape Published: 2025-12-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.00007v1 Yahtzee is a classic dice game with a stochastic, combinatorial structure and delayed rewards, making it an interesting mid-scale RL benchmark. While an optimal policy for solitaire Yahtzee can be computed using dynamic programming methods, multiplayer is intractable, motivating approximation methods. We formulate Yahtzee as a Markov Decision Process (MDP), and train self-play agents using various policy gradient methods: REINFORCE, Advantage Actor-Critic (A2C), and Proximal Policy Optimization (PPO), all using a multi-headed network with a shared trunk. We ablate feature and action encodings, architecture, return estimators, and entropy regularization to understand their impact on learning. Under a fixed training budget, REINFORCE and PPO prove sensitive to hyperparameters and fail to reach near-optimal performance, whereas A2C trains robustly across a range of settings. Our agent attains a median score of 241.78 points over 100,000 evaluation games, within 5.0\% of the optimal DP score of 254.59, achieving the upper section bonus and Yahtzee at rates of 24.9\% and 34.1\%, respectively. All models struggle to learn the upper bonus strategy, overindexing on four-of-a-kind's, highlighting persistent long-horizon credit-assignment and exploration challenges. --- ### Emergent World Beliefs: Exploring Transformers in Stochastic Games Authors: Adam Kamel, Tanish Rastogi, Michael Ma, Kailash Ranganathan, Kevin Zhu Published: 2025-12-18 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.23722v1 Transformer-based large language models (LLMs) have demonstrated strong reasoning abilities across diverse fields, from solving programming challenges to competing in strategy-intensive games such as chess. Prior work has shown that LLMs can develop emergent world models in games of perfect information, where internal representations correspond to latent states of the environment. In this paper, we extend this line of investigation to domains of incomplete information, focusing on poker as a canonical partially observable Markov decision process (POMDP). We pretrain a GPT-style model on Poker Hand History (PHH) data and probe its internal activations. Our results demonstrate that the model learns both deterministic structure, such as hand ranks, and stochastic features, such as equity, without explicit instruction. Furthermore, by using primarily nonlinear probes, we demonstrated that these representations are decodeable and correlate with theoretical belief states, suggesting that LLMs are learning their own representation of the stochastic environment of Texas Hold'em Poker. --- ### Field strength-dependent performance variability in deep learning-based analysis of magnetic resonance imaging Authors: Muhammad Ibtsaam Qadir, Duane Schonlau, Ulrike Dydak, Fiona R. Kolbinger Published: 2025-12-18 Categories: eess.IV, cs.AI, cs.CV, physics.med-ph arXiv: https://arxiv.org/abs/2512.22176v1 This study quantitatively evaluates the impact of MRI scanner magnetic field strength on the performance and generalizability of deep learning-based segmentation algorithms. Three publicly available MRI datasets (breast tumor, pancreas, and cervical spine) were stratified by scanner field strength (1.5T vs. 3.0T). For each segmentation task, three nnU-Net-based models were developed: A model trained on 1.5T data only (m-1.5T), a model trained on 3.0T data only (m-3.0T), and a model trained on pooled 1.5T and 3.0T data (m-combined). Each model was evaluated on both 1.5T and 3.0T validation sets. Field-strength-dependent performance differences were investigated via Uniform Manifold Approximation and Projection (UMAP)-based clustering and radiomic analysis, including 23 first-order and texture features. For breast tumor segmentation, m-3.0T (DSC: 0.494 (1.5T) and 0.433 (3.0T)) significantly outperformed m-1.5T (DSC: 0.411 (1.5T) and 0.289 (3.0T)) and m-combined (DSC: 0.373 (1.5T) and 0.268(3.0T)) on both validation sets (p<0.0001). Pancreas segmentation showed similar trends: m-3.0T achieved the highest DSC (0.774 (1.5T), 0.840 (3.0T)), while m-1.5T underperformed significantly (p<0.0001). For cervical spine, models performed optimally on same-field validation sets with minimal cross-field performance degradation (DSC>0.92 for all comparisons). Radiomic analysis revealed moderate field-strength-dependent clustering in soft tissues (silhouette scores 0.23-0.29) but minimal separation in osseous structures (0.12). These results indicate that magnetic field strength in the training data substantially influences the performance of deep learning-based segmentation models, particularly for soft-tissue structures (e.g., small lesions). This warrants consideration of magnetic field strength as a confounding factor in studies evaluating AI performance on MRI. --- ### Characterizing Motion Encoding in Video Diffusion Timesteps Authors: Vatsal Baherwani, Yixuan Ren, Abhinav Shrivastava Published: 2025-12-18 Categories: cs.CV, cs.AI, eess.IV arXiv: https://arxiv.org/abs/2512.22175v1 Text-to-video diffusion models synthesize temporal motion and spatial appearance through iterative denoising, yet how motion is encoded across timesteps remains poorly understood. Practitioners often exploit the empirical heuristic that early timesteps mainly shape motion and layout while later ones refine appearance, but this behavior has not been systematically characterized. In this work, we proxy motion encoding in video diffusion timesteps by the trade-off between appearance editing and motion preservation induced when injecting new conditions over specified timestep ranges, and characterize this proxy through a large-scale quantitative study. This protocol allows us to factor motion from appearance by quantitatively mapping how they compete along the denoising trajectory. Across diverse architectures, we consistently identify an early, motion-dominant regime and a later, appearance-dominant regime, yielding an operational motion-appearance boundary in timestep space. Building on this characterization, we simplify current one-shot motion customization paradigm by restricting training and inference to the motion-dominant regime, achieving strong motion transfer without auxiliary debiasing modules or specialized objectives. Our analysis turns a widely used heuristic into a spatiotemporal disentanglement principle, and our timestep-constrained recipe can serve as ready integration into existing motion transfer and editing methods. --- ### BitFlipScope: Scalable Fault Localization and Recovery for Bit-Flip Corruptions in LLMs Authors: Muhammad Zeeshan Karamat, Sadman Saif, Christiana Chamon Garcia Published: 2025-12-18 Categories: cs.DC, cs.AI, cs.AR, cs.CR, cs.LG arXiv: https://arxiv.org/abs/2512.22174v2 Large Language Models (LLMs) deployed in practical and safety-critical settings are increasingly susceptible to bit-flip faults caused by hardware degradation, cosmic radiation, or deliberate fault-injection attacks such as Rowhammer. These faults silently corrupt internal parameters and can lead to unpredictable or dangerous model behavior. Localizing these corruptions is essential: without identifying the affected region, it is impossible to diagnose the source of degradation, apply targeted corrective measures, or restore model functionality without resorting to costly fine-tuning or full retraining. This work introduces BitFlipScope, a scalable, software-based framework for identifying fault-affected regions within transformer architectures under two deployment scenarios. When a clean reference model is available, BitFlipScope performs differential analysis of outputs, hidden states, and internal activations for detecting anomalous behavior indicative of corruption to pinpoint or localize faults. When no reference model exists, it uses residual-path perturbation and loss-sensitivity profiling to infer the fault-impacted region directly from the corrupted model. In both settings, the framework not only enables effective fault diagnosis but also supports lightweight performance recovery without fine-tuning, offering a practical path to restoring corrupted models. Together, these capabilities make BitFlipScope an important step toward trustworthy, fault-resilient LLM deployment in hardware-prone and adversarial environments. --- ### The Dual-State Architecture for Reliable LLM Agents Authors: Matthew Thompson Published: 2025-12-18 Categories: cs.LG, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2512.20660v2 Large Language Models deployed as code generation agents exhibit stochastic behavior incompatible with the deterministic guarantees required by software engineering. We formalize the Dual-State Action Pair (DSAP), an execution primitive that couples stochastic generation with deterministic post-condition verification. Guard functions act as sensing actions that project opaque LLM outputs onto observable workflow state, enabling a dual-state decomposition: finite, deterministic S_workflow paired with infinite, stochastic S_env. We prove that for epsilon-capable generators, failure probability P(fail) <= (1-epsilon)^R_max -> 0. To prevent naive O(R^K) retry explosion across multi-step workflows, we introduce a three-level recovery hierarchy: context refinement (retry within step), informed backtracking (stagnation detection with cascade invalidation and context injection to upstream steps), and human escalation. Experimental validation across 13 LLMs (1.3B-15B parameters) on three diagnostic probes demonstrates reliability gains of up to 66 percentage points at 1.2-2.1x baseline cost. Recovery mechanism evaluation on 99 SWE-Bench Pro instance-arm pairs (Qwen3-Coder-Next) demonstrates 100% context injection effectiveness (upstream output changed in all 71 escalation events) with step-specific recovery asymmetry -- 37.5% for test generation vs. 0% for patch generation -- and 0% end-to-end patch production, establishing the boundary between execution architecture and plan synthesis: execution recovery is necessary but not sufficient for autonomous software engineering. --- ### Graph Neural Networks for Source Detection: A Review and Benchmark Study Authors: Martin Sterchi, Nathan Brack, Lorenz Hilfiker Published: 2025-12-18 Categories: cs.SI, cs.LG arXiv: https://arxiv.org/abs/2512.20657v2 The source detection problem arises when an epidemic process unfolds over a contact network, and the objective is to identify its point of origin, i.e., the source node. Research on this problem began with the seminal work of Shah and Zaman in 2010, who formally defined it and introduced the notion of rumor centrality. With the emergence of Graph Neural Networks (GNNs), several studies have proposed GNN-based approaches to source detection. However, there is room to strengthen methodological clarity and reproducibility across these works. As a result, it remains unclear whether GNNs truly outperform more traditional source detection methods across comparable settings. In this paper, we first systematically review existing GNN-based methods for source detection, clearly outlining the specific settings each addresses and the architectures they employ. We then reproduce and benchmark four representative GNN architectures against a diverse set of traditional and MLP-based baselines under controlled, comparable conditions. We also investigate key questions surrounding this problem, including how detectability evolves over time, how performance scales with training set size, and how sensitive methods are to uncertainty in observation timing and epidemic parameters. Our experiments show that GNNs substantially outperform all other methods we test across a variety of network topologies. Although we initially set out to challenge the notion of GNNs as a solution to source detection, our results instead demonstrate their remarkable effectiveness for this task. To ensure full reproducibility, we release all code and data on GitHub. Finally, we argue that epidemic source detection constitutes a natural and attractive benchmark task for evaluating GNN architectures. --- ### MaskOpt: A Large-Scale Mask Optimization Dataset to Advance AI in Integrated Circuit Manufacturing Authors: Yuting Hu, Lei Zhuang, Hua Xiang, Jinjun Xiong, Gi-Joon Nam Published: 2025-12-18 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2512.20655v1 As integrated circuit (IC) dimensions shrink below the lithographic wavelength, optical lithography faces growing challenges from diffraction and process variability. Model-based optical proximity correction (OPC) and inverse lithography technique (ILT) remain indispensable but computationally expensive, requiring repeated simulations that limit scalability. Although deep learning has been applied to mask optimization, existing datasets often rely on synthetic layouts, disregard standard-cell hierarchy, and neglect the surrounding contexts around the mask optimization targets, thereby constraining their applicability to practical mask optimization. To advance deep learning for cell- and context-aware mask optimization, we present MaskOpt, a large-scale benchmark dataset constructed from real IC designs at the 45$\mathrm{nm}$ node. MaskOpt includes 104,714 metal-layer tiles and 121,952 via-layer tiles. Each tile is clipped at a standard-cell placement to preserve cell information, exploiting repeated logic gate occurrences. Different context window sizes are supported in MaskOpt to capture the influence of neighboring shapes from optical proximity effects. We evaluate state-of-the-art deep learning models for IC mask optimization to build up benchmarks, and the evaluation results expose distinct trade-offs across baseline models. Further context size analysis and input ablation studies confirm the importance of both surrounding geometries and cell-aware inputs in achieving accurate mask generation. --- ### Q-RUN: Quantum-Inspired Data Re-uploading Networks Authors: Wenbo Qiao, Shuaixian Wang, Peng Zhang, Yan Ming, Jiaming Zhao Published: 2025-12-18 Categories: cs.LG, quant-ph arXiv: https://arxiv.org/abs/2512.20654v1 Data re-uploading quantum circuits (DRQC) are a key approach to implementing quantum neural networks and have been shown to outperform classical neural networks in fitting high-frequency functions. However, their practical application is limited by the scalability of current quantum hardware. In this paper, we introduce the mathematical paradigm of DRQC into classical models by proposing a quantum-inspired data re-uploading network (Q-RUN), which retains the Fourier-expressive advantages of quantum models without any quantum hardware. Experimental results demonstrate that Q-RUN delivers superior performance across both data modeling and predictive modeling tasks. Compared to the fully connected layers and the state-of-the-art neural network layers, Q-RUN reduces model parameters while decreasing error by approximately one to three orders of magnitude on certain tasks. Notably, Q-RUN can serve as a drop-in replacement for standard fully connected layers, improving the performance of a wide range of neural architectures. This work illustrates how principles from quantum machine learning can guide the design of more expressive artificial intelligence. --- ### Robust Causal Directionality Inference in Quantum Inference under MNAR Observation and High-Dimensional Noise Authors: Joonsung Kang Published: 2025-12-18 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2512.19746v1 In quantum mechanics, observation actively shapes the system, paralleling the statistical notion of Missing Not At Random (MNAR). This study introduces a unified framework for \textbf{robust causal directionality inference} in quantum engineering, determining whether relations are system$\to$observation, observation$\to$system, or bidirectional. The method integrates CVAE-based latent constraints, MNAR-aware selection models, GEE-stabilized regression, penalized empirical likelihood, and Bayesian optimization. It jointly addresses quantum and classical noise while uncovering causal directionality, with theoretical guarantees for double robustness, perturbation stability, and oracle inequalities. Simulation and real-data analyses (TCGA gene expression, proteomics) show that the proposed MNAR-stabilized CVAE+GEE+AIPW+PEL framework achieves lower bias and variance, near-nominal coverage, and superior quantum-specific diagnostics. This establishes robust causal directionality inference as a key methodological advance for reliable quantum engineering. ---