# Research Papers — 2025-12 · bundle page 105 of 175 > Full-text markdown of papers #5201–5250 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/105 [← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/104.md) [Next bundle →](https://aipod.dev/papers/archive/2025-12/page/106.md) ### Enhancing Radiology Report Generation and Visual Grounding using Reinforcement Learning Authors: Benjamin Gundersen, Nicolas Deperrois, Samuel Ruiperez-Campillo, Thomas M. Sutter, Julia E. Vogt, Michael Moor, Farhad Nooralahzadeh, Michael Krauthammer Published: 2025-12-11 Categories: cs.AI, cs.CV arXiv: https://arxiv.org/abs/2512.10691v1 Recent advances in vision-language models (VLMs) have improved Chest X-ray (CXR) interpretation in multiple aspects. However, many medical VLMs rely solely on supervised fine-tuning (SFT), which optimizes next-token prediction without evaluating answer quality. In contrast, reinforcement learning (RL) can incorporate task-specific feedback, and its combination with explicit intermediate reasoning ("thinking") has demonstrated substantial gains on verifiable math and coding tasks. To investigate the effects of RL and thinking in a CXR VLM, we perform large-scale SFT on CXR data to build an updated RadVLM based on Qwen3-VL, followed by a cold-start SFT stage that equips the model with basic thinking ability. We then apply Group Relative Policy Optimization (GRPO) with clinically grounded, task-specific rewards for report generation and visual grounding, and run matched RL experiments on both domain-specific and general-domain Qwen3-VL variants, with and without thinking. Across these settings, we find that while strong SFT remains crucial for high base performance, RL provides additional gains on both tasks, whereas explicit thinking does not appear to further improve results. Under a unified evaluation pipeline, the RL-optimized RadVLM models outperform their baseline counterparts and reach state-of-the-art performance on both report generation and grounding, highlighting clinically aligned RL as a powerful complement to SFT for medical VLMs. --- ### Rethinking Popularity Bias in Collaborative Filtering via Analytical Vector Decomposition Authors: Lingfeng Liu, Yixin Song, Dazhong Shen, Bing Yin, Hao Li, Yanyong Zhang, Chao Wang Published: 2025-12-11 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2512.10688v6 Popularity bias fundamentally undermines the personalization capabilities of collaborative filtering (CF) models, causing them to disproportionately recommend popular items while neglecting users' genuine preferences for niche content. While existing approaches treat this as an external confounding factor, we reveal that popularity bias is an intrinsic geometric artifact of Bayesian Pairwise Ranking (BPR) optimization in CF models. Through rigorous mathematical analysis, we prove that BPR systematically organizes item embeddings along a dominant "popularity direction" where embedding magnitudes directly correlate with interaction frequency. This geometric distortion forces user embeddings to simultaneously handle two conflicting tasks-expressing genuine preference and calibrating against global popularity-trapping them in suboptimal configurations that favor popular items regardless of individual tastes. We propose Directional Decomposition and Correction (DDC), a universally applicable framework that surgically corrects this embedding geometry through asymmetric directional updates. DDC guides positive interactions along personalized preference directions while steering negative interactions away from the global popularity direction, disentangling preference from popularity at the geometric source. Extensive experiments across multiple BPR-based architectures demonstrate that DDC significantly outperforms state-of-the-art debiasing methods, reducing training loss to less than 5% of heavily-tuned baselines while achieving superior recommendation quality and fairness. Code is available in https://github.com/LingFeng-Liu-AI/DDC. --- ### Rethinking Popularity Bias in Collaborative Filtering via Analytical Vector Decomposition Authors: Lingfeng Liu, Yixin Song, Dazhong Shen, Bing Yin, Hao Li, Yanyong Zhang, Chao Wang Published: 2025-12-11 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2512.10688v1 Popularity bias fundamentally undermines the personalization capabilities of collaborative filtering (CF) models, causing them to disproportionately recommend popular items while neglecting users' genuine preferences for niche content. While existing approaches treat this as an external confounding factor, we reveal that popularity bias is an intrinsic geometric artifact of Bayesian Pairwise Ranking (BPR) optimization in CF models. Through rigorous mathematical analysis, we prove that BPR systematically organizes item embeddings along a dominant "popularity direction" where embedding magnitudes directly correlate with interaction frequency. This geometric distortion forces user embeddings to simultaneously handle two conflicting tasks-expressing genuine preference and calibrating against global popularity-trapping them in suboptimal configurations that favor popular items regardless of individual tastes. We propose Directional Decomposition and Correction (DDC), a universally applicable framework that surgically corrects this embedding geometry through asymmetric directional updates. DDC guides positive interactions along personalized preference directions while steering negative interactions away from the global popularity direction, disentangling preference from popularity at the geometric source. Extensive experiments across multiple BPR-based architectures demonstrate that DDC significantly outperforms state-of-the-art debiasing methods, reducing training loss to less than 5% of heavily-tuned baselines while achieving superior recommendation quality and fairness. Code is available in https://github.com/LingFeng-Liu-AI/DDC. --- ### Safe for Whom? Rethinking How We Evaluate the Safety of LLMs for Real Users Authors: Manon Kempermann, Sai Suresh Macharla Vasu, Mahalakshmi Raveenthiran, Theo Farrell, Ingmar Weber Published: 2025-12-11 Categories: cs.AI, cs.CY arXiv: https://arxiv.org/abs/2512.10687v2 Safety evaluations of large language models (LLMs) typically focus on universal risks like dangerous capabilities or undesirable propensities. However, millions use LLMs for personal advice on high-stakes topics like finance and health, where harms are context-dependent rather than universal. While frameworks like the OECD's AI classification recognize the need to assess individual risks, user-welfare safety evaluations remain underdeveloped. We argue that developing such evaluations is non-trivial due to fundamental questions about accounting for user context in evaluation design. In this exploratory study, we evaluated advice on finance and health from GPT-5, Claude Sonnet 4, and Gemini 2.5 Pro across user profiles of varying vulnerability. First, we demonstrate that evaluators must have access to rich user context: identical LLM responses were rated significantly safer by context-blind evaluators than by those aware of user circumstances, with safety scores for high-vulnerability users dropping from safe (5/7) to somewhat unsafe (3/7). One might assume this gap could be addressed by creating realistic user prompts containing key contextual information. However, our second study challenges this: we rerun the evaluation on prompts containing context users report they would disclose, finding no significant improvement. Our work establishes that effective user-welfare safety evaluation requires evaluators to assess responses against diverse user profiles, as realistic user context disclosure alone proves insufficient, particularly for vulnerable populations. By demonstrating a methodology for context-aware evaluation, this study provides both a starting point for such assessments and foundational evidence that evaluating individual welfare demands approaches distinct from existing universal-risk frameworks. We publish our code and dataset to aid future developments. --- ### Challenges of Evaluating LLM Safety for User Welfare Authors: Manon Kempermann, Sai Suresh Macharla Vasu, Mahalakshmi Raveenthiran, Theo Farrell, Ingmar Weber Published: 2025-12-11 Categories: cs.AI, cs.CY arXiv: https://arxiv.org/abs/2512.10687v1 Safety evaluations of large language models (LLMs) typically focus on universal risks like dangerous capabilities or undesirable propensities. However, millions use LLMs for personal advice on high-stakes topics like finance and health, where harms are context-dependent rather than universal. While frameworks like the OECD's AI classification recognize the need to assess individual risks, user-welfare safety evaluations remain underdeveloped. We argue that developing such evaluations is non-trivial due to fundamental questions about accounting for user context in evaluation design. In this exploratory study, we evaluated advice on finance and health from GPT-5, Claude Sonnet 4, and Gemini 2.5 Pro across user profiles of varying vulnerability. First, we demonstrate that evaluators must have access to rich user context: identical LLM responses were rated significantly safer by context-blind evaluators than by those aware of user circumstances, with safety scores for high-vulnerability users dropping from safe (5/7) to somewhat unsafe (3/7). One might assume this gap could be addressed by creating realistic user prompts containing key contextual information. However, our second study challenges this: we rerun the evaluation on prompts containing context users report they would disclose, finding no significant improvement. Our work establishes that effective user-welfare safety evaluation requires evaluators to assess responses against diverse user profiles, as realistic user context disclosure alone proves insufficient, particularly for vulnerable populations. By demonstrating a methodology for context-aware evaluation, this study provides both a starting point for such assessments and foundational evidence that evaluating individual welfare demands approaches distinct from existing universal-risk frameworks. We publish our code and dataset to aid future developments. --- ### Sharp Monocular View Synthesis in Less Than a Second Authors: Lars Mescheder, Wei Dong, Shiwei Li, Xuyang Bai, Marcel Santos, Peiyun Hu, Bruno Lecouat, Mingmin Zhen, Amaël Delaunoy, Tian Fang, Yanghai Tsin, Stephan R. Richter et al. Published: 2025-12-11 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2512.10685v2 We present SHARP, an approach to photorealistic view synthesis from a single image. Given a single photograph, SHARP regresses the parameters of a 3D Gaussian representation of the depicted scene. This is done in less than a second on a standard GPU via a single feedforward pass through a neural network. The 3D Gaussian representation produced by SHARP can then be rendered in real time, yielding high-resolution photorealistic images for nearby views. The representation is metric, with absolute scale, supporting metric camera movements. Experimental results demonstrate that SHARP delivers robust zero-shot generalization across datasets. It sets a new state of the art on multiple datasets, reducing LPIPS by 25-34% and DISTS by 21-43% versus the best prior model, while lowering the synthesis time by three orders of magnitude. Code and weights are provided at https://github.com/apple/ml-sharp --- ### Sharp Monocular View Synthesis in Less Than a Second Authors: Lars Mescheder, Wei Dong, Shiwei Li, Xuyang Bai, Marcel Santos, Peiyun Hu, Bruno Lecouat, Mingmin Zhen, Amaël Delaunoy, Tian Fang, Yanghai Tsin, Stephan R. Richter et al. Published: 2025-12-11 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2512.10685v1 We present SHARP, an approach to photorealistic view synthesis from a single image. Given a single photograph, SHARP regresses the parameters of a 3D Gaussian representation of the depicted scene. This is done in less than a second on a standard GPU via a single feedforward pass through a neural network. The 3D Gaussian representation produced by SHARP can then be rendered in real time, yielding high-resolution photorealistic images for nearby views. The representation is metric, with absolute scale, supporting metric camera movements. Experimental results demonstrate that SHARP delivers robust zero-shot generalization across datasets. It sets a new state of the art on multiple datasets, reducing LPIPS by 25-34% and DISTS by 21-43% versus the best prior model, while lowering the synthesis time by three orders of magnitude. Code and weights are provided at https://github.com/apple/ml-sharp --- ### Optimal transport unlocks end-to-end learning for single-molecule localization Authors: Romain Seailles, Jean-Baptiste Masson, Jean Ponce, Julien Mairal Published: 2025-12-11 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2512.10683v2 Single-molecule localization microscopy (SMLM) allows reconstructing biology-relevant structures beyond the diffraction limit by detecting and localizing individual fluorophores -- fluorescent molecules stained onto the observed specimen -- over time to reconstruct super-resolved images. Currently, efficient SMLM requires non-overlapping emitting fluorophores, leading to long acquisition times that hinders live-cell imaging. Recent deep-learning approaches can handle denser emissions, but they rely on variants of non-maximum suppression (NMS) layers, which are unfortunately non-differentiable and may discard true positives with their local fusion strategy. In this presentation, we reformulate the SMLM training objective as a set-matching problem, deriving an optimal-transport loss that eliminates the need for NMS during inference and enables end-to-end training. Additionally, we propose an iterative neural network that integrates knowledge of the microscope's optical system inside our model. Experiments on synthetic benchmarks and real biological data show that both our new loss function and architecture surpass the state of the art at moderate and high emitter densities. Code is available at https://github.com/RSLLES/SHOT. --- ### Optimal transport unlocks end-to-end learning for single-molecule localization Authors: Romain Seailles, Jean-Baptiste Masson, Jean Ponce, Julien Mairal Published: 2025-12-11 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2512.10683v1 Single-molecule localization microscopy (SMLM) allows reconstructing biology-relevant structures beyond the diffraction limit by detecting and localizing individual fluorophores -- fluorescent molecules stained onto the observed specimen -- over time to reconstruct super-resolved images. Currently, efficient SMLM requires non-overlapping emitting fluorophores, leading to long acquisition times that hinders live-cell imaging. Recent deep-learning approaches can handle denser emissions, but they rely on variants of non-maximum suppression (NMS) layers, which are unfortunately non-differentiable and may discard true positives with their local fusion strategy. In this presentation, we reformulate the SMLM training objective as a set-matching problem, deriving an optimal-transport loss that eliminates the need for NMS during inference and enables end-to-end training. Additionally, we propose an iterative neural network that integrates knowledge of the microscope's optical system inside our model. Experiments on synthetic benchmarks and real biological data show that both our new loss function and architecture surpass the state of the art at moderate and high emitter densities. Code is available at https://github.com/RSLLES/SHOT. --- ### Evaluating Gemini Robotics Policies in a Veo World Simulator Authors: Gemini Robotics Team, Krzysztof Choromanski, Coline Devin, Yilun Du, Debidatta Dwibedi, Ruiqi Gao, Abhishek Jindal, Thomas Kipf, Sean Kirmani, Isabel Leal, Fangchen Liu, Anirudha Majumdar et al. Published: 2025-12-11 Categories: cs.RO, cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2512.10675v2 Generative world models hold significant potential for simulating interactions with visuomotor policies in varied environments. Frontier video models can enable generation of realistic observations and environment interactions in a scalable and general manner. However, the use of video models in robotics has been limited primarily to in-distribution evaluations, i.e., scenarios that are similar to ones used to train the policy or fine-tune the base video model. In this report, we demonstrate that video models can be used for the entire spectrum of policy evaluation use cases in robotics: from assessing nominal performance to out-of-distribution (OOD) generalization, and probing physical and semantic safety. We introduce a generative evaluation system built upon a frontier video foundation model (Veo). The system is optimized to support robot action conditioning and multi-view consistency, while integrating generative image-editing and multi-view completion to synthesize realistic variations of real-world scenes along multiple axes of generalization. We demonstrate that the system preserves the base capabilities of the video model to enable accurate simulation of scenes that have been edited to include novel interaction objects, novel visual backgrounds, and novel distractor objects. This fidelity enables accurately predicting the relative performance of different policies in both nominal and OOD conditions, determining the relative impact of different axes of generalization on policy performance, and performing red teaming of policies to expose behaviors that violate physical or semantic safety constraints. We validate these capabilities through 1600+ real-world evaluations of eight Gemini Robotics policy checkpoints and five tasks for a bimanual manipulator. --- ### Evaluating Gemini Robotics Policies in a Veo World Simulator Authors: Gemini Robotics Team, Coline Devin, Yilun Du, Debidatta Dwibedi, Ruiqi Gao, Abhishek Jindal, Thomas Kipf, Sean Kirmani, Fangchen Liu, Anirudha Majumdar, Andrew Marmon, Carolina Parada et al. Published: 2025-12-11 Categories: cs.RO, cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2512.10675v1 Generative world models hold significant potential for simulating interactions with visuomotor policies in varied environments. Frontier video models can enable generation of realistic observations and environment interactions in a scalable and general manner. However, the use of video models in robotics has been limited primarily to in-distribution evaluations, i.e., scenarios that are similar to ones used to train the policy or fine-tune the base video model. In this report, we demonstrate that video models can be used for the entire spectrum of policy evaluation use cases in robotics: from assessing nominal performance to out-of-distribution (OOD) generalization, and probing physical and semantic safety. We introduce a generative evaluation system built upon a frontier video foundation model (Veo). The system is optimized to support robot action conditioning and multi-view consistency, while integrating generative image-editing and multi-view completion to synthesize realistic variations of real-world scenes along multiple axes of generalization. We demonstrate that the system preserves the base capabilities of the video model to enable accurate simulation of scenes that have been edited to include novel interaction objects, novel visual backgrounds, and novel distractor objects. This fidelity enables accurately predicting the relative performance of different policies in both nominal and OOD conditions, determining the relative impact of different axes of generalization on policy performance, and performing red teaming of policies to expose behaviors that violate physical or semantic safety constraints. We validate these capabilities through 1600+ real-world evaluations of eight Gemini Robotics policy checkpoints and five tasks for a bimanual manipulator. --- ### Geo6DPose: Fast Zero-Shot 6D Object Pose Estimation via Geometry-Filtered Feature Matching Authors: Javier Villena Toro, Mehdi Tarkian Published: 2025-12-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.10674v1 Recent progress in zero-shot 6D object pose estimation has been driven largely by large-scale models and cloud-based inference. However, these approaches often introduce high latency, elevated energy consumption, and deployment risks related to connectivity, cost, and data governance; factors that conflict with the practical constraints of real-world robotics, where compute is limited and on-device inference is frequently required. We introduce Geo6DPose, a lightweight, fully local, and training-free pipeline for zero-shot 6D pose estimation that trades model scale for geometric reliability. Our method combines foundation model visual features with a geometric filtering strategy: Similarity maps are computed between onboarded template DINO descriptors and scene patches, and mutual correspondences are established by projecting scene patch centers to 3D and template descriptors to the object model coordinate system. Final poses are recovered via correspondence-driven RANSAC and ranked using a weighted geometric alignment metric that jointly accounts for reprojection consistency and spatial support, improving robustness to noise, clutter, and partial visibility. Geo6DPose achieves sub-second inference on a single commodity GPU while matching the average recall of significantly larger zero-shot baselines (53.7 AR, 1.08 FPS). It requires no training, fine-tuning, or network access, and remains compatible with evolving foundation backbones, advancing practical, fully local 6D perception for robotic deployment. --- ### AEBNAS: Strengthening Exit Branches in Early-Exit Networks through Hardware-Aware Neural Architecture Search Authors: Oscar Robben, Saeed Khalilian, Nirvana Meratnia Published: 2025-12-11 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.10671v1 Early-exit networks are effective solutions for reducing the overall energy consumption and latency of deep learning models by adjusting computation based on the complexity of input data. By incorporating intermediate exit branches into the architecture, they provide less computation for simpler samples, which is particularly beneficial for resource-constrained devices where energy consumption is crucial. However, designing early-exit networks is a challenging and time-consuming process due to the need to balance efficiency and performance. Recent works have utilized Neural Architecture Search (NAS) to design more efficient early-exit networks, aiming to reduce average latency while improving model accuracy by determining the best positions and number of exit branches in the architecture. Another important factor affecting the efficiency and accuracy of early-exit networks is the depth and types of layers in the exit branches. In this paper, we use hardware-aware NAS to strengthen exit branches, considering both accuracy and efficiency during optimization. Our performance evaluation on the CIFAR-10, CIFAR-100, and SVHN datasets demonstrates that our proposed framework, which considers varying depths and layers for exit branches along with adaptive threshold tuning, designs early-exit networks that achieve higher accuracy with the same or lower average number of MACs compared to the state-of-the-art approaches. --- ### Learning by Analogy: A Causal Framework for Composition Generalization Authors: Lingjing Kong, Shaoan Xie, Yang Jiao, Yetian Chen, Yanhui Guo, Simone Shao, Yan Gao, Guangyi Chen, Kun Zhang Published: 2025-12-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.10669v1 Compositional generalization -- the ability to understand and generate novel combinations of learned concepts -- enables models to extend their capabilities beyond limited experiences. While effective, the data structures and principles that enable this crucial capability remain poorly understood. We propose that compositional generalization fundamentally requires decomposing high-level concepts into basic, low-level concepts that can be recombined across similar contexts, similar to how humans draw analogies between concepts. For example, someone who has never seen a peacock eating rice can envision this scene by relating it to their previous observations of a chicken eating rice. In this work, we formalize these intuitive processes using principles of causal modularity and minimal changes. We introduce a hierarchical data-generating process that naturally encodes different levels of concepts and their interaction mechanisms. Theoretically, we demonstrate that this approach enables compositional generalization supporting complex relations between composed concepts, advancing beyond prior work that assumes simpler interactions like additive effects. Critically, we also prove that this latent hierarchical structure is provably recoverable (identifiable) from observable data like text-image pairs, a necessary step for learning such a generative process. To validate our theory, we apply insights from our theoretical framework and achieve significant improvements on benchmark datasets. --- ### XDen-1K: A Density Field Dataset of Real-World Objects Authors: Jingxuan Zhang, Tianqi Yu, Yatu Zhang, Jinze Wu, Kaixin Yao, Jingyang Liu, Yuyao Zhang, Jiayuan Gu, Jingyi Yu Published: 2025-12-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.10668v2 A deep understanding of the physical world is essential for robotic manipulation and physically realistic simulation. While current methods, including VLM-based and other learning-based approaches, have shown promise in physical property inference, their evaluation is often hindered by the lack of physically grounded reference data. To address this gap, we introduce XDen-1K, the first large-scale multimodal dataset that provides physically grounded density field for real-world objects. XDen-1K comprises 1,000 real-world objects spanning 137 categories, with comprehensive data for each object, including a high-resolution, carefully curated 3D geometric model with part-level annotations and paired real-world biplanar X-ray scans. In addition, XDen-1K includes high-fidelity volumetric density field reconstructed from sparse biplanar X-ray views via a novel optimization framework. XDen-1K also provides a benchmark for density estimation and enables X-ray-conditioned volumetric segmentation. Experiments further demonstrate that the center-of-mass prior derived by XDen-1K can improve robotic manipulation performance. By providing real-world X-ray scans and physics-consistent density field, XDen-1K establishes a foundation for advancing physical property inference and embodied AI. --- ### XDen-1K: A Density Field Dataset of Real-World Objects Authors: Jingxuan Zhang, Tianqi Yu, Yatu Zhang, Jinze Wu, Kaixin Yao, Jingyang Liu, Yuyao Zhang, Jiayuan Gu, Jingyi Yu Published: 2025-12-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.10668v1 A deep understanding of the physical world is a central goal for embodied AI and realistic simulation. While current models excel at capturing an object's surface geometry and appearance, they largely neglect its internal physical properties. This omission is critical, as properties like volumetric density are fundamental for predicting an object's center of mass, stability, and interaction dynamics in applications ranging from robotic manipulation to physical simulation. The primary bottleneck has been the absence of large-scale, real-world data. To bridge this gap, we introduce XDen-1K, the first large-scale, multi-modal dataset designed for real-world physical property estimation, with a particular focus on volumetric density. The core of this dataset consists of 1,000 real-world objects across 148 categories, for which we provide comprehensive multi-modal data, including a high-resolution 3D geometric model with part-level annotations and a corresponding set of real-world biplanar X-ray scans. Building upon this data, we introduce a novel optimization framework that recovers a high-fidelity volumetric density field of each object from its sparse X-ray views. To demonstrate its practical value, we add X-ray images as a conditioning signal to an existing segmentation network and perform volumetric segmentation. Furthermore, we conduct experiments on downstream robotics tasks. The results show that leveraging the dataset can effectively improve the accuracy of center-of-mass estimation and the success rate of robotic manipulation. We believe XDen-1K will serve as a foundational resource and a challenging new benchmark, catalyzing future research in physically grounded visual inference and embodied AI. --- ### On the Dynamics of Multi-Agent LLM Communities Driven by Value Diversity Authors: Muhua Huang, Qinlin Zhao, Xiaoyuan Yi, Xing Xie Published: 2025-12-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.10665v1 As Large Language Models (LLM) based multi-agent systems become increasingly prevalent, the collective behaviors, e.g., collective intelligence, of such artificial communities have drawn growing attention. This work aims to answer a fundamental question: How does diversity of values shape the collective behavior of AI communities? Using naturalistic value elicitation grounded in the prevalent Schwartz's Theory of Basic Human Values, we constructed multi-agent simulations where communities with varying numbers of agents engaged in open-ended interactions and constitution formation. The results show that value diversity enhances value stability, fosters emergent behaviors, and brings more creative principles developed by the agents themselves without external guidance. However, these effects also show diminishing returns: extreme heterogeneity induces instability. This work positions value diversity as a new axis of future AI capability, bridging AI ability and sociological studies of institutional emergence. --- ### Closing the Navigation Compliance Gap in End-to-end Autonomous Driving Authors: Hanfeng Wu, Marlon Steiner, Michael Schmidt, Alvaro Marcos-Ramiro, Christoph Stiller Published: 2025-12-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.10660v2 Trajectory-scoring planners achieve high navigation compliance when following the expert's original command, yet they struggle at intersections when presented with alternative commands; over 30 percent of such commands are ignored. We attribute this navigation compliance gap to two root causes: (1) existing metrics like Ego Progress do not explicitly measure navigation adherence, diluting the gap between on-route and off-route trajectories; and (2) current datasets pair each scenario with a single command, preventing models from learning command-dependent behavior. We address the metric gap by introducing the binary Navigation Compliance metric (NAVI) and the derived Controllability Measure (CM), and the data gap with the NavControl dataset, 14,918 intersection scenarios augmented with all feasible alternative commands and routing annotations, yielding over 34,000 direction samples. Building on these, we propose NaviHydra, a trajectory-scoring planner incorporating NAVI distillation and Bird's Eye View (BEV)-based trajectory gathering for context-position-aware trajectory feature extraction. NaviHydra achieves 92.7 PDM score on NAVSIM navtest split and 77.5 CM on NavControl test split. Training with NavControl improves controllability across diverse architectures, confirming it as a broadly effective augmentation for navigation compliance. --- ### NaviHydra: Controllable Navigation-guided End-to-end Autonomous Driving with Hydra-distillation Authors: Hanfeng Wu, Marlon Steiner, Michael Schmidt, Alvaro Marcos-Ramiro, Christoph Stiller Published: 2025-12-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.10660v1 The complexity of autonomous driving scenarios requires robust models that can interpret high-level navigation commands and generate safe trajectories. While traditional rule-based systems can react to these commands, they often struggle in dynamic environments, and end-to-end methods face challenges in complying with explicit navigation commands. To address this, we present NaviHydra, a controllable navigation-guided end-to-end model distilled from an existing rule-based simulator. Our framework accepts high-level navigation commands as control signals, generating trajectories that align with specified intentions. We utilize a Bird's Eye View (BEV) based trajectory gathering method to enhance the trajectory feature extraction. Additionally, we introduce a novel navigation compliance metric to evaluate adherence to intended route, improving controllability and navigation safety. To comprehensively assess our model's controllability, we design a test that evaluates its response to various navigation commands. Our method significantly outperforms baseline models, achieving state-of-the-art results in the NAVSIM benchmark, demonstrating its effectiveness in advancing autonomous driving. --- ### DCFO: Density-Based Counterfactuals for Outliers -- Additional Material Authors: Tommaso Amico, Pernille Matthews, Lena Krieger, Arthur Zimek, Ira Assent Published: 2025-12-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.10659v3 Outlier detection identifies data points that significantly deviate from the majority of the data distribution. Explaining outliers is crucial for understanding the underlying factors that contribute to their detection, validating their significance, and identifying potential biases or errors. Effective explanations provide actionable insights, facilitating preventive measures to avoid similar outliers in the future. Counterfactual explanations clarify why specific data points are classified as outliers by identifying minimal changes required to alter their prediction. Although valuable, most existing counterfactual explanation methods overlook the unique challenges posed by outlier detection, and fail to target classical, widely adopted outlier detection algorithms. Local Outlier Factor (LOF) is one the most popular unsupervised outlier detection methods, quantifying outlierness through relative local density. Despite LOF's widespread use across diverse applications, it lacks interpretability. To address this limitation, we introduce Density-based Counterfactuals for Outliers (DCFO), a novel method specifically designed to generate counterfactual explanations for LOF. DCFO partitions the data space into regions where LOF behaves smoothly, enabling efficient gradient-based optimisation. Extensive experimental validation on 50 OpenML datasets demonstrates that DCFO consistently outperforms benchmarked competitors, offering superior proximity and validity of generated counterfactuals. --- ### DCFO Additional Material Authors: Tommaso Amico, Pernille Matthews, Lena Krieger, Arthur Zimek, Ira Assent Published: 2025-12-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.10659v1 Outlier detection identifies data points that significantly deviate from the majority of the data distribution. Explaining outliers is crucial for understanding the underlying factors that contribute to their detection, validating their significance, and identifying potential biases or errors. Effective explanations provide actionable insights, facilitating preventive measures to avoid similar outliers in the future. Counterfactual explanations clarify why specific data points are classified as outliers by identifying minimal changes required to alter their prediction. Although valuable, most existing counterfactual explanation methods overlook the unique challenges posed by outlier detection, and fail to target classical, widely adopted outlier detection algorithms. Local Outlier Factor (LOF) is one the most popular unsupervised outlier detection methods, quantifying outlierness through relative local density. Despite LOF's widespread use across diverse applications, it lacks interpretability. To address this limitation, we introduce Density-based Counterfactuals for Outliers (DCFO), a novel method specifically designed to generate counterfactual explanations for LOF. DCFO partitions the data space into regions where LOF behaves smoothly, enabling efficient gradient-based optimisation. Extensive experimental validation on 50 OpenML datasets demonstrates that DCFO consistently outperforms benchmarked competitors, offering superior proximity and validity of generated counterfactuals. --- ### Token Sample Complexity of Attention Authors: Léa Bohbot, Cyril Letrouit, Gabriel Peyré, François-Xavier Vialard Published: 2025-12-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.10656v3 As context windows in large language models continue to expand, it is essential to characterize how attention behaves at extreme sequence lengths. We introduce token sample complexity: the rate at which attention computed on $n$ tokens converges to its infinite-token limit. We estimate finite-$n$ convergence bounds at two levels: pointwise uniform convergence of the attention map, and convergence of moments for the transformed token distribution. For compactly supported (and more generally sub-Gaussian) distributions, our first result shows that the attention map converges uniformly on a ball of radius $R$ at rate $C(R)/\sqrt{n}$, where $C(R)$ grows exponentially with $R$. For large $R$, this estimate loses practical value, and our second result addresses this issue by establishing convergence rates for the moments of the transformed distribution (the token output of the attention layer). In this case, the rate is $C'(R)/n^β$ with $β<\tfrac{1}{2}$, and $C'(R)$ depends polynomially on the size of the support of the distribution. The exponent $β$ depends on the attention geometry and the spectral properties of the token distribution. We also examine the regime in which the attention parameter tends to infinity and the softmax approaches a hardmax, and in this setting, we establish a logarithmic rate of convergence. Experiments on synthetic and real data support our predictions and show that the predicted slowdown is reflected in downstream accuracy. --- ### Token Sample Complexity of Attention Authors: Léa Bohbot, Cyril Letrouit, Gabriel Peyré, François-Xavier Vialard Published: 2025-12-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.10656v1 As context windows in large language models continue to expand, it is essential to characterize how attention behaves at extreme sequence lengths. We introduce token-sample complexity: the rate at which attention computed on $n$ tokens converges to its infinite-token limit. We estimate finite-$n$ convergence bounds at two levels: pointwise uniform convergence of the attention map, and convergence of moments for the transformed token distribution. For compactly supported (and more generally sub-Gaussian) distributions, our first result shows that the attention map converges uniformly on a ball of radius $R$ at rate $C(R)/\sqrt{n}$, where $C(R)$ grows exponentially with $R$. For large $R$, this estimate loses practical value, and our second result addresses this issue by establishing convergence rates for the moments of the transformed distribution (the token output of the attention layer). In this case, the rate is $C'(R)/n^β$ with $β<\tfrac{1}{2}$, and $C'(R)$ depends polynomially on the size of the support of the distribution. The exponent $β$ depends on the attention geometry and the spectral properties of the tokens distribution. We also examine the regime in which the attention parameter tends to infinity and the softmax approaches a hardmax, and in this setting, we establish a logarithmic rate of convergence. Experiments on synthetic Gaussian data and real BERT models on Wikipedia text confirm our predictions. --- ### CAPTAIN: Semantic Feature Injection for Memorization Mitigation in Text-to-Image Diffusion Models Authors: Tong Zhang, Carlos Hinojosa, Bernard Ghanem Published: 2025-12-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.10655v1 Diffusion models can unintentionally reproduce training examples, raising privacy and copyright concerns as these systems are increasingly deployed at scale. Existing inference-time mitigation methods typically manipulate classifier-free guidance (CFG) or perturb prompt embeddings; however, they often struggle to reduce memorization without compromising alignment with the conditioning prompt. We introduce CAPTAIN, a training-free framework that mitigates memorization by directly modifying latent features during denoising. CAPTAIN first applies frequency-based noise initialization to reduce the tendency to replicate memorized patterns early in the denoising process. It then identifies the optimal denoising timesteps for feature injection and localizes memorized regions. Finally, CAPTAIN injects semantically aligned features from non-memorized reference images into localized latent regions, suppressing memorization while preserving prompt fidelity and visual quality. Our experiments show that CAPTAIN achieves substantial reductions in memorization compared to CFG-based baselines while maintaining strong alignment with the intended prompt. --- ### Virtual camera detection: Catching video injection attacks in remote biometric systems Authors: Daniyar Kurmankhojayev, Andrei Shadrikov, Dmitrii Gordin, Mikhail Shkorin, Danijar Gabdullin, Aigerim Kambetbayeva, Kanat Kuatov Published: 2025-12-11 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2512.10653v1 Face anti-spoofing (FAS) is a vital component of remote biometric authentication systems based on facial recognition, increasingly used across web-based applications. Among emerging threats, video injection attacks -- facilitated by technologies such as deepfakes and virtual camera software -- pose significant challenges to system integrity. While virtual camera detection (VCD) has shown potential as a countermeasure, existing literature offers limited insight into its practical implementation and evaluation. This study introduces a machine learning-based approach to VCD, with a focus on its design and validation. The model is trained on metadata collected during sessions with authentic users. Empirical results demonstrate its effectiveness in identifying video injection attempts and reducing the risk of malicious users bypassing FAS systems. --- ### TriDF: Evaluating Perception, Detection, and Hallucination for Interpretable DeepFake Detection Authors: Jian-Yu Jiang-Lin, Kang-Yang Huang, Ling Zou, Ling Lo, Sheng-Ping Yang, Yu-Wen Tseng, Kun-Hsiang Lin, Chia-Ling Chen, Yu-Ting Ta, Yan-Tsung Wang, Po-Ching Chen, Hongxia Xie et al. Published: 2025-12-11 Categories: cs.CV, cs.CR arXiv: https://arxiv.org/abs/2512.10652v3 Advances in generative modeling have made it increasingly easy to fabricate realistic portrayals of individuals, creating serious risks for security, communication, and public trust. Detecting such person-driven manipulations requires systems that not only distinguish altered content from authentic media but also provide clear and reliable reasoning. In this paper, we introduce TriDF, a comprehensive benchmark for interpretable DeepFake detection. TriDF contains high-quality forgeries from advanced synthesis models, covering 16 DeepFake types across image, video, and audio modalities. The benchmark evaluates three key aspects: Perception, which measures the ability of a model to identify fine-grained manipulation artifacts using human-annotated evidence; Detection, which assesses classification performance across diverse forgery families and generators; and Hallucination, which quantifies the reliability of model-generated explanations. Experiments on state-of-the-art multimodal large language models show that accurate perception is essential for reliable detection, but hallucination can severely disrupt decision-making, revealing the interdependence of these three aspects. TriDF provides a unified framework for understanding the interaction between detection accuracy, evidence identification, and explanation reliability, offering a foundation for building trustworthy systems that address real-world synthetic media threats. --- ### TriDF: Evaluating Perception, Detection, and Hallucination for Interpretable DeepFake Detection Authors: Jian-Yu Jiang-Lin, Kang-Yang Huang, Ling Zou, Ling Lo, Sheng-Ping Yang, Yu-Wen Tseng, Kun-Hsiang Lin, Chia-Ling Chen, Yu-Ting Ta, Yan-Tsung Wang, Po-Ching Chen, Hongxia Xie et al. Published: 2025-12-11 Categories: cs.CV, cs.CR arXiv: https://arxiv.org/abs/2512.10652v1 Advances in generative modeling have made it increasingly easy to fabricate realistic portrayals of individuals, creating serious risks for security, communication, and public trust. Detecting such person-driven manipulations requires systems that not only distinguish altered content from authentic media but also provide clear and reliable reasoning. In this paper, we introduce TriDF, a comprehensive benchmark for interpretable DeepFake detection. TriDF contains high-quality forgeries from advanced synthesis models, covering 16 DeepFake types across image, video, and audio modalities. The benchmark evaluates three key aspects: Perception, which measures the ability of a model to identify fine-grained manipulation artifacts using human-annotated evidence; Detection, which assesses classification performance across diverse forgery families and generators; and Hallucination, which quantifies the reliability of model-generated explanations. Experiments on state-of-the-art multimodal large language models show that accurate perception is essential for reliable detection, but hallucination can severely disrupt decision-making, revealing the interdependence of these three aspects. TriDF provides a unified framework for understanding the interaction between detection accuracy, evidence identification, and explanation reliability, offering a foundation for building trustworthy systems that address real-world synthetic media threats. --- ### Refinement Contrastive Learning of Cell-Gene Associations for Unsupervised Cell Type Identification Authors: Liang Peng, Haopeng Liu, Yixuan Ye, Cheng Liu, Wenjun Shen, Si Wu, Hau-San Wong Published: 2025-12-11 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.10640v1 Unsupervised cell type identification is crucial for uncovering and characterizing heterogeneous populations in single cell omics studies. Although a range of clustering methods have been developed, most focus exclusively on intrinsic cellular structure and ignore the pivotal role of cell-gene associations, which limits their ability to distinguish closely related cell types. To this end, we propose a Refinement Contrastive Learning framework (scRCL) that explicitly incorporates cell-gene interactions to derive more informative representations. Specifically, we introduce two contrastive distribution alignment components that reveal reliable intrinsic cellular structures by effectively exploiting cell-cell structural relationships. Additionally, we develop a refinement module that integrates gene-correlation structure learning to enhance cell embeddings by capturing underlying cell-gene associations. This module strengthens connections between cells and their associated genes, refining the representation learning to exploiting biologically meaningful relationships. Extensive experiments on several single-cell RNA-seq and spatial transcriptomics benchmark datasets demonstrate that our method consistently outperforms state-of-the-art baselines in cell-type identification accuracy. Moreover, downstream biological analyses confirm that the recovered cell populations exhibit coherent gene-expression signatures, further validating the biological relevance of our approach. The code is available at https://github.com/THPengL/scRCL. --- ### A Spiking Neural Network Implementation of Gaussian Belief Propagation Authors: Sepideh Adamiat, Wouter M. Kouw, Bert de Vries Published: 2025-12-11 Categories: cs.NE arXiv: https://arxiv.org/abs/2512.10638v1 Bayesian inference offers a principled account of information processing in natural agents. However, it remains an open question how neural mechanisms perform their abstract operations. We investigate a hypothesis where a distributed form of Bayesian inference, namely message passing on factor graphs, is performed by a simulated network of leaky-integrate-and-fire neurons. Specifically, we perform Gaussian belief propagation by encoding messages that come into factor nodes as spike-based signals, propagating these signals through a spiking neural network (SNN) and decoding the spike-based signal back to an outgoing message. Three core linear operations, equality (branching), addition, and multiplication, are realized in networks of leaky integrate-and-fire models. Validation against the standard sum-product algorithm shows accurate message updates, while applications to Kalman filtering and Bayesian linear regression demonstrate the framework's potential for both static and dynamic inference tasks. Our results provide a step toward biologically grounded, neuromorphic implementations of probabilistic reasoning. --- ### Adaptive Intrusion Detection System Leveraging Dynamic Neural Models with Adversarial Learning for 5G/6G Networks Authors: Neha, Tarunpreet Bhatia Published: 2025-12-11 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2512.10637v2 Intrusion Detection Systems (IDS) are critical components in safeguarding 5G/6G networks from both internal and external cyber threats. While traditional IDS approaches rely heavily on signature-based methods, they struggle to detect novel and evolving attacks. This paper presents an advanced IDS framework that leverages adversarial training and dynamic neural networks in 5G/6G networks to enhance network security by providing robust, real-time threat detection and response capabilities. Unlike conventional models, which require costly retraining to update knowledge, the proposed framework integrates incremental learning algorithms, reducing the need for frequent retraining. Adversarial training is used to fortify the IDS against poisoned data. By using fewer features and incorporating statistical properties, the system can efficiently detect potential threats. Extensive evaluations using the NSL- KDD dataset demonstrate that the proposed approach provides better accuracy of 82.33% for multiclass classification of various network attacks while resisting dataset poisoning. This research highlights the potential of adversarial-trained, dynamic neural networks for building resilient IDS solutions. --- ### Adaptive Intrusion Detection System Leveraging Dynamic Neural Models with Adversarial Learning for 5G/6G Networks Authors: Neha, Tarunpreet Bhatia Published: 2025-12-11 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2512.10637v1 Intrusion Detection Systems (IDS) are critical components in safeguarding 5G/6G networks from both internal and external cyber threats. While traditional IDS approaches rely heavily on signature-based methods, they struggle to detect novel and evolving attacks. This paper presents an advanced IDS framework that leverages adversarial training and dynamic neural networks in 5G/6G networks to enhance network security by providing robust, real-time threat detection and response capabilities. Unlike conventional models, which require costly retraining to update knowledge, the proposed framework integrates incremental learning algorithms, reducing the need for frequent retraining. Adversarial training is used to fortify the IDS against poisoned data. By using fewer features and incorporating statistical properties, the system can efficiently detect potential threats. Extensive evaluations using the NSL- KDD dataset demonstrate that the proposed approach provides better accuracy of 82.33% for multiclass classification of various network attacks while resisting dataset poisoning. This research highlights the potential of adversarial-trained, dynamic neural networks for building resilient IDS solutions. --- ### Supporting Migration Policies with Forecasts: Illegal Border Crossings in Europe through a Mixed Approach Authors: C. Bosco, U. Minora, D. de Rigo, J. Pingsdorf, R. Cortinovis Published: 2025-12-11 Categories: cs.LG, cs.SI, stat.AP arXiv: https://arxiv.org/abs/2512.10633v2 This paper presents a mixed-methodology to forecast illegal border crossings in Europe across five key migratory routes, with a one-year time horizon. The methodology integrates machine learning techniques with qualitative insights from migration experts. This approach aims at improving the predictive capacity of data-driven models through the inclusion of a human-assessed covariate, an innovation that addresses challenges posed by sudden shifts in migration patterns and limitations in traditional datasets. The proposed methodology responds directly to the forecasting needs outlined in the EU Pact on Migration and Asylum, supporting the Asylum and Migration Management Regulation (AMMR). It is designed to provide policy-relevant forecasts that inform strategic decisions, early warning systems, and solidarity mechanisms among EU Member States. By joining data-driven modeling with expert judgment, this work aligns with existing academic recommendations and introduces a novel operational tool tailored for EU migration governance. The methodology is tested and validated with known data to demonstrate its applicability and reliability in migration-related policy context. --- ### Supporting Migration Policies with Forecasts: Illegal Border Crossings in Europe through a Mixed Approach Authors: C. Bosco, U. Minora, D. de Rigo, J. Pingsdorf, R. Cortinovis Published: 2025-12-11 Categories: cs.LG, cs.SI, stat.AP arXiv: https://arxiv.org/abs/2512.10633v1 This paper presents a mixed-methodology to forecast illegal border crossings in Europe across five key migratory routes, with a one-year time horizon. The methodology integrates machine learning techniques with qualitative insights from migration experts. This approach aims at improving the predictive capacity of data-driven models through the inclusion of a human-assessed covariate, an innovation that addresses challenges posed by sudden shifts in migration patterns and limitations in traditional datasets. The proposed methodology responds directly to the forecasting needs outlined in the EU Pact on Migration and Asylum, supporting the Asylum and Migration Management Regulation (AMMR). It is designed to provide policy-relevant forecasts that inform strategic decisions, early warning systems, and solidarity mechanisms among EU Member States. By joining data-driven modeling with expert judgment, this work aligns with existing academic recommendations and introduces a novel operational tool tailored for EU migration governance. The methodology is tested and validated with known data to demonstrate its applicability and reliability in migration-related policy context. --- ### Unified Smart Factory Model: A model-based Approach for Integrating Industry 4.0 and Sustainability for Manufacturing Systems Authors: Ishaan Kaushal, Amaresh Chakrabarti Published: 2025-12-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.10631v2 This paper presents the Unified Smart Factory Model (USFM), a comprehensive framework designed to translate high-level sustainability goals into measurable factory-level indicators with a systematic information map of manufacturing activities. The manufacturing activities were modelled as set of manufacturing, assembly and auxiliary processes using Object Process Methodology, a Model Based Systems Engineering (MBSE) language. USFM integrates Manufacturing Process and System, Data Process, and Key Performance Indicator (KPI) Selection and Assessment in a single framework. Through a detailed case study of Printed Circuit Board (PCB) assembly factory, the paper demonstrates how environmental sustainability KPIs can be selected, modelled, and mapped to the necessary data, highlighting energy consumption and environmental impact metrics. The model's systematic approach can reduce redundancy, minimize the risk of missing critical information, and enhance data collection. The paper concluded that the USFM bridges the gap between sustainability goals and practical implementation, providing significant benefits for industries specifically SMEs aiming to achieve sustainability targets. --- ### From Data Scarcity to Data Care: Reimagining Language Technologies for Serbian and other Low-Resource Languages Authors: Smiljana Antonijevic Ubois Published: 2025-12-11 Categories: cs.CL, cs.CY arXiv: https://arxiv.org/abs/2512.10630v1 Large language models are commonly trained on dominant languages like English, and their representation of low resource languages typically reflects cultural and linguistic biases present in the source language materials. Using the Serbian language as a case, this study examines the structural, historical, and sociotechnical factors shaping language technology development for low resource languages in the AI age. Drawing on semi structured interviews with ten scholars and practitioners, including linguists, digital humanists, and AI developers, it traces challenges rooted in historical destruction of Serbian textual heritage, intensified by contemporary issues that drive reductive, engineering first approaches prioritizing functionality over linguistic nuance. These include superficial transliteration, reliance on English-trained models, data bias, and dataset curation lacking cultural specificity. To address these challenges, the study proposes Data Care, a framework grounded in CARE principles (Collective Benefit, Authority to Control, Responsibility, and Ethics), that reframes bias mitigation from a post hoc technical fix to an integral component of corpus design, annotation, and governance, and positions Data Care as a replicable model for building inclusive, sustainable, and culturally grounded language technologies in contexts where traditional LLM development reproduces existing power imbalances and cultural blind spots. --- ### K-Track: Kalman-Enhanced Tracking for Accelerating Deep Point Trackers on Edge Devices Authors: Bishoy Galoaa, Pau Closas, Sarah Ostadabbas Published: 2025-12-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.10628v1 Point tracking in video sequences is a foundational capability for real-world computer vision applications, including robotics, autonomous systems, augmented reality, and video analysis. While recent deep learning-based trackers achieve state-of-the-art accuracy on challenging benchmarks, their reliance on per-frame GPU inference poses a major barrier to deployment on resource-constrained edge devices, where compute, power, and connectivity are limited. We introduce K-Track (Kalman-enhanced Tracking), a general-purpose, tracker-agnostic acceleration framework designed to bridge this deployment gap. K-Track reduces inference cost by combining sparse deep learning keyframe updates with lightweight Kalman filtering for intermediate frame prediction, using principled Bayesian uncertainty propagation to maintain temporal coherence. This hybrid strategy enables 5-10X speedup while retaining over 85% of the original trackers' accuracy. We evaluate K-Track across multiple state-of-the-art point trackers and demonstrate real-time performance on edge platforms such as the NVIDIA Jetson Nano and RTX Titan. By preserving accuracy while dramatically lowering computational requirements, K-Track provides a practical path toward deploying high-quality point tracking in real-world, resource-limited settings, closing the gap between modern tracking algorithms and deployable vision systems. --- ### AgriGPT-Omni: A Unified Speech-Vision-Text Framework for Multilingual Agricultural Intelligence Authors: Bo Yang, Lanfei Feng, Yunkui Chen, Yu Zhang, Jianyu Zhang, Xiao Xu, Nueraili Aierken, Shijian Li Published: 2025-12-11 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.10624v1 Despite rapid advances in multimodal large language models, agricultural applications remain constrained by the lack of multilingual speech data, unified multimodal architectures, and comprehensive evaluation benchmarks. To address these challenges, we present AgriGPT-Omni, an agricultural omni-framework that integrates speech, vision, and text in a unified framework. First, we construct a scalable data synthesis and collection pipeline that converts agricultural texts and images into training data, resulting in the largest agricultural speech dataset to date, including 492K synthetic and 1.4K real speech samples across six languages. Second, based on this, we train the first agricultural omni-model via a three-stage paradigm: textual knowledge injection, progressive multimodal alignment, and GRPO-based reinforcement learning, enabling unified reasoning across languages and modalities. Third, we propose AgriBench-Omni-2K, the first tri-modal benchmark for agriculture, covering diverse speech-vision-text tasks and multilingual slices, with standardized protocols and reproducible tools. Experiments show that AgriGPT-Omni significantly outperforms general-purpose baselines on multilingual and multimodal reasoning as well as real-world speech understanding. All models, data, benchmarks, and code will be released to promote reproducible research, inclusive agricultural intelligence, and sustainable AI development for low-resource regions. --- ### DOCR-Inspector: Fine-Grained and Automated Evaluation of Document Parsing with VLM Authors: Qintong Zhang, Junyuan Zhang, Zhifei Ren, Linke Ouyang, Zichen Wen, Junbo Niu, Yuan Qu, Bin Wang, Ka-Ho Chow, Conghui He, Wentao Zhang Published: 2025-12-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.10619v1 Document parsing aims to transform unstructured PDF images into semi-structured data, facilitating the digitization and utilization of information in diverse domains. While vision language models (VLMs) have significantly advanced this task, achieving reliable, high-quality parsing in real-world scenarios remains challenging. Common practice often selects the top-performing model on standard benchmarks. However, these benchmarks may carry dataset-specific biases, leading to inconsistent model rankings and limited correlation with real-world performance. Moreover, benchmark metrics typically provide only overall scores, which can obscure distinct error patterns in output. This raises a key challenge: how can we reliably and comprehensively assess document parsing quality in the wild? We address this problem with DOCR-Inspector, which formalizes document parsing assessment as fine-grained error detection and analysis. Leveraging VLM-as-a-Judge, DOCR-Inspector analyzes a document image and its parsed output, identifies all errors, assigns them to one of 28 predefined types, and produces a comprehensive quality assessment. To enable this capability, we construct DOCRcase-200K for training and propose the Chain-of-Checklist reasoning paradigm to enable the hierarchical structure of parsing quality assessment. For empirical validation, we introduce DOCRcaseBench, a set of 882 real-world document parsing cases with manual annotations. On this benchmark, DOCR-Inspector-7B outperforms commercial models like Gemini 2.5 Pro, as well as leading open-source models. Further experiments demonstrate that its quality assessments provide valuable guidance for parsing results refinement, making DOCR-Inspector both a practical evaluator and a driver for advancing document parsing systems at scale. Model and code are released at: https://github.com/ZZZZZQT/DOCR-Inspector. --- ### Lang2Motion: Bridging Language and Motion through Joint Embedding Spaces Authors: Bishoy Galoaa, Xiangyu Bai, Sarah Ostadabbas Published: 2025-12-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.10617v1 We present Lang2Motion, a framework for language-guided point trajectory generation by aligning motion manifolds with joint embedding spaces. Unlike prior work focusing on human motion or video synthesis, we generate explicit trajectories for arbitrary objects using motion extracted from real-world videos via point tracking. Our transformer-based auto-encoder learns trajectory representations through dual supervision: textual motion descriptions and rendered trajectory visualizations, both mapped through CLIP's frozen encoders. Lang2Motion achieves 34.2% Recall@1 on text-to-trajectory retrieval, outperforming video-based methods by 12.5 points, and improves motion accuracy by 33-52% (12.4 ADE vs 18.3-25.3) compared to video generation baselines. We demonstrate 88.3% Top-1 accuracy on human action recognition despite training only on diverse object motions, showing effective transfer across motion domains. Lang2Motion supports style transfer, semantic interpolation, and latent-space editing through CLIP-aligned trajectory representations. --- ### Phythesis: Physics-Guided Evolutionary Scene Synthesis for Energy-Efficient Data Center Design via LLMs Authors: Minghao LI, Ruihang Wang, Rui Tan, Yonggang Wen Published: 2025-12-11 Categories: cs.AI, cs.NE arXiv: https://arxiv.org/abs/2512.10611v2 Data center (DC) infrastructure serves as the backbone to support the escalating demand for computing capacity. Traditional design methodologies that blend human expertise with specialized simulation tools scale poorly with the increasing system complexity. Recent studies adopt generative artificial intelligence to design plausible human-centric indoor layouts. However, they do not consider the underlying physics, making them unsuitable for the DC design that sets quantifiable operational objectives and strict physical constraints. To bridge the gap, we propose Phythesis, a novel framework that synergizes large language models (LLMs) and physics-guided evolutionary optimization to automate simulation-ready (SimReady) scene synthesis for energy-efficient DC design. Phythesis employs an iterative bi-level optimization architecture, where (i) the LLM-driven optimization level generates physically plausible three-dimensional layouts and self-criticizes them to refine the scene topology, and (ii) the physics-informed optimization level identifies the optimal asset parameters and selects the best asset combination. Experiments on three generation scales show that Phythesis achieves 57.3% generation success rate increase and 11.5% power usage effectiveness (PUE) improvement, compared with the vanilla LLM-based solution. --- ### Phythesis: Physics-Guided Evolutionary Scene Synthesis for Energy-Efficient Data Center Design via LLMs Authors: Minghao LI, Ruihang Wang, Rui Tan, Yonggang Wen Published: 2025-12-11 Categories: cs.AI, cs.NE arXiv: https://arxiv.org/abs/2512.10611v1 Data center (DC) infrastructure serves as the backbone to support the escalating demand for computing capacity. Traditional design methodologies that blend human expertise with specialized simulation tools scale poorly with the increasing system complexity. Recent studies adopt generative artificial intelligence to design plausible human-centric indoor layouts. However, they do not consider the underlying physics, making them unsuitable for the DC design that sets quantifiable operational objectives and strict physical constraints. To bridge the gap, we propose Phythesis, a novel framework that synergizes large language models (LLMs) and physics-guided evolutionary optimization to automate simulation-ready (SimReady) scene synthesis for energy-efficient DC design. Phythesis employs an iterative bi-level optimization architecture, where (i) the LLM-driven optimization level generates physically plausible three-dimensional layouts and self-criticizes them to refine the scene topology, and (ii) the physics-informed optimization level identifies the optimal asset parameters and selects the best asset combination. Experiments on three generation scales show that Phythesis achieves 57.3% generation success rate increase and 11.5% power usage effectiveness (PUE) improvement, compared with the vanilla LLM-based solution. --- ### Robust Multi-Disease Retinal Classification via Xception-Based Transfer Learning and W-Net Vessel Segmentation Authors: Mohammad Sadegh Gholizadeh, Amir Arsalan Rezapour Published: 2025-12-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.10608v1 In recent years, the incidence of vision-threatening eye diseases has risen dramatically, necessitating scalable and accurate screening solutions. This paper presents a comprehensive study on deep learning architectures for the automated diagnosis of ocular conditions. To mitigate the "black-box" limitations of standard convolutional neural networks (CNNs), we implement a pipeline that combines deep feature extraction with interpretable image processing modules. Specifically, we focus on high-fidelity retinal vessel segmentation as an auxiliary task to guide the classification process. By grounding the model's predictions in clinically relevant morphological features, we aim to bridge the gap between algorithmic output and expert medical validation, thereby reducing false positives and improving deployment viability in clinical settings. --- ### Track and Caption Any Motion: Open-Vocabulary Spatiotemporal Captioning via Trajectory-Conditioned Generation Authors: Bishoy Galoaa, Sarah Ostadabbas Published: 2025-12-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.10607v2 We present TCAM (Track and Caption Any Motion), a generative framework that watches a video and with no text query and no region prompt decides what is moving, describes each motion in open vocabulary, locates it in time, and points to the exact trajectories that carry it. Two mature lines of work make this possible yet leave it unsolved: dense point trackers follow pixels with sub-object precision but emit no language, while video-language models produce fluent descriptions only when handed a query and only from clip-level features that cannot resolve which pixels move. Object-level captioners narrow the gap but still reason over detector boxes or masks, never reaching individual trajectories. TCAM couples tracking and language at point granularity through a Caption-Aware Resampler, where a small set of learnable queries cross-attends to dense point trajectory tokens and distills them into a fixed-length motion context that conditions a language decoder. The decoder generates an entire video's events in a single pass, each with a free-form caption, a start and end time, and a pointer to the trajectories it refers to, for sequential events and several subjects active at once. Training uses only existing segmentation annotations, with no extra event labeling, to supervise caption quality, pointer-mask alignment, and pointer diversity. On over 50K clips, TCAM outperforms dense video captioning baselines and matches dedicated, query-based grounding and point-tracking methods despite using no query, showing that trajectory-conditioned generation is a direct route to motion-driven video understanding. --- ### Track and Caption Any Motion: Query-Free Motion Discovery and Description in Videos Authors: Bishoy Galoaa, Sarah Ostadabbas Published: 2025-12-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.10607v1 We propose Track and Caption Any Motion (TCAM), a motion-centric framework for automatic video understanding that discovers and describes motion patterns without user queries. Understanding videos in challenging conditions like occlusion, camouflage, or rapid movement often depends more on motion dynamics than static appearance. TCAM autonomously observes a video, identifies multiple motion activities, and spatially grounds each natural language description to its corresponding trajectory through a motion-field attention mechanism. Our key insight is that motion patterns, when aligned with contrastive vision-language representations, provide powerful semantic signals for recognizing and describing actions. Through unified training that combines global video-text alignment with fine-grained spatial correspondence, TCAM enables query-free discovery of multiple motion expressions via multi-head cross-attention. On the MeViS benchmark, TCAM achieves 58.4% video-to-text retrieval, 64.9 JF for spatial grounding, and discovers 4.8 relevant expressions per video with 84.7% precision, demonstrating strong cross-task generalization. --- ### Uncertainty-Preserving QBNNs: Multi-Level Quantization of SVI-Based Bayesian Neural Networks for Image Classification Authors: Hendrik Borras, Yong Wu, Bernhard Klein, Holger Fröning Published: 2025-12-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.10602v1 Bayesian Neural Networks (BNNs) provide principled uncertainty quantification but suffer from substantial computational and memory overhead compared to deterministic networks. While quantization techniques have successfully reduced resource requirements in standard deep learning models, their application to probabilistic models remains largely unexplored. We introduce a systematic multi-level quantization framework for Stochastic Variational Inference based BNNs that distinguishes between three quantization strategies: Variational Parameter Quantization (VPQ), Sampled Parameter Quantization (SPQ), and Joint Quantization (JQ). Our logarithmic quantization for variance parameters, and specialized activation functions to preserve the distributional structure are essential for calibrated uncertainty estimation. Through comprehensive experiments on Dirty-MNIST, we demonstrate that BNNs can be quantized down to 4-bit precision while maintaining both classification accuracy and uncertainty disentanglement. At 4 bits, Joint Quantization achieves up to 8x memory reduction compared to floating-point implementations with minimal degradation in epistemic and aleatoric uncertainty estimation. These results enable deployment of BNNs on resource-constrained edge devices and provide design guidelines for future analog "Bayesian Machines" operating at inherently low precision. --- ### Multi-Objective Reward and Preference Optimization: Theory and Algorithms Authors: Akhil Agnihotri Published: 2025-12-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.10601v1 This thesis develops theoretical frameworks and algorithms that advance constrained reinforcement learning (RL) across control, preference learning, and alignment of large language models. The first contribution addresses constrained Markov Decision Processes (CMDPs) under the average-cost criterion through the Average-Constrained Policy Optimization (ACPO) algorithm. ACPO integrates sensitivity analysis with trust-region updates to ensure stable constraint handling, achieving state-of-the-art empirical performance with theoretical guarantees. Constrained RL is then extended to finite-horizon settings via e-COP, the first policy optimization method for episodic CMDPs. Built on an episodic policy difference lemma, e-COP offers provable performance, simplicity, and scalability in safety-critical environments. The thesis then investigates reinforcement learning from human preferences. warmPref-PS introduces a posterior sampling strategy for linear bandits that integrates offline preference data from heterogeneous raters into online learning. Explicit modeling of rater competence yields substantial regret reduction and more efficient data collection for RLHF. The PSPL algorithm further advances preference-based RL by jointly sampling reward models and transition dynamics from pairwise trajectory comparisons, providing Bayesian simple-regret guarantees and robust empirical identification of optimal policies. The final contribution applies these methods to large-scale model alignment. A multi-objective constrained optimization view yields MOPO, an iterative algorithm with closed-form updates that scales to multi-billion-parameter language models and remains robust across alignment settings. Collectively, the thesis unifies constrained RL across average-cost, episodic, and preference-driven paradigms, delivering theoretical advances and practical tools for safe and aligned decision-making. --- ### Authority Backdoor: A Certifiable Backdoor Mechanism for Authoring DNNs Authors: Han Yang, Shaofeng Li, Tian Dong, Xiangyu Xu, Guangchi Liu, Zhen Ling Published: 2025-12-11 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2512.10600v1 Deep Neural Networks (DNNs), as valuable intellectual property, face unauthorized use. Existing protections, such as digital watermarking, are largely passive; they provide only post-hoc ownership verification and cannot actively prevent the illicit use of a stolen model. This work proposes a proactive protection scheme, dubbed ``Authority Backdoor," which embeds access constraints directly into the model. In particular, the scheme utilizes a backdoor learning framework to intrinsically lock a model's utility, such that it performs normally only in the presence of a specific trigger (e.g., a hardware fingerprint). But in its absence, the DNN's performance degrades to be useless. To further enhance the security of the proposed authority scheme, the certifiable robustness is integrated to prevent an adaptive attacker from removing the implanted backdoor. The resulting framework establishes a secure authority mechanism for DNNs, combining access control with certifiable robustness against adversarial attacks. Extensive experiments on diverse architectures and datasets validate the effectiveness and certifiable robustness of the proposed framework. --- ### Beyond Pixels: A Training-Free, Text-to-Text Framework for Remote Sensing Image Retrieval Authors: J. Xiao, Y. Guo, X. Zi, K. Thiyagarajan, C. Moreira, M. Prasad Published: 2025-12-11 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2512.10596v1 Semantic retrieval of remote sensing (RS) images is a critical task fundamentally challenged by the \textquote{semantic gap}, the discrepancy between a model's low-level visual features and high-level human concepts. While large Vision-Language Models (VLMs) offer a promising path to bridge this gap, existing methods often rely on costly, domain-specific training, and there is a lack of benchmarks to evaluate the practical utility of VLM-generated text in a zero-shot retrieval context. To address this research gap, we introduce the Remote Sensing Rich Text (RSRT) dataset, a new benchmark featuring multiple structured captions per image. Based on this dataset, we propose a fully training-free, text-only retrieval reference called TRSLLaVA. Our methodology reformulates cross-modal retrieval as a text-to-text (T2T) matching problem, leveraging rich text descriptions as queries against a database of VLM-generated captions within a unified textual embedding space. This approach completely bypasses model training or fine-tuning. Experiments on the RSITMD and RSICD benchmarks show our training-free method is highly competitive with state-of-the-art supervised models. For instance, on RSITMD, our method achieves a mean Recall of 42.62\%, nearly doubling the 23.86\% of the standard zero-shot CLIP baseline and surpassing several top supervised models. This validates that high-quality semantic representation through structured text provides a powerful and cost-effective paradigm for remote sensing image retrieval. --- ### Salient Object Detection in Complex Weather Conditions via Noise Indicators Authors: Quan Chen, Xiaokai Yang, Tingyu Wang, Rongfeng Lu, Xichun Sheng, Yaoqi Sun, Chenggang Yan Published: 2025-12-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.10592v1 Salient object detection (SOD), a foundational task in computer vision, has advanced from single-modal to multi-modal paradigms to enhance generalization. However, most existing SOD methods assume low-noise visual conditions, overlooking the degradation of segmentation accuracy caused by weather-induced noise in real-world scenarios. In this paper, we propose a SOD framework tailored for diverse weather conditions, encompassing a specific encoder and a replaceable decoder. To enable handling of varying weather noises, we introduce a one-hot vector as a noise indicator to represent different weather types and design a Noise Indicator Fusion Module (NIFM). The NIFM takes both semantic features and the noise indicator as dual inputs and is inserted between consecutive stages of the encoder to embed weather-aware priors via adaptive feature modulation. Critically, the proposed specific encoder retains compatibility with mainstream SOD decoders. Extensive experiments are conducted on the WXSOD dataset under varying training data scales (100%, 50%, 30% of the full training set), three encoder and seven decoder configurations. Results show that the proposed SOD framework (particularly the NIFM-enhanced specific encoder) improves segmentation accuracy under complex weather conditions compared to a vanilla encoder. --- ### THeGAU: Type-Aware Heterogeneous Graph Autoencoder and Augmentation Authors: Ming-Yi Hong, Miao-Chen Chiang, Youchen Teng, Yu-Hsiang Wang, Chih-Yu Wang, Che Lin Published: 2025-12-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.10589v1 Heterogeneous Graph Neural Networks (HGNNs) are effective for modeling Heterogeneous Information Networks (HINs), which encode complex multi-typed entities and relations. However, HGNNs often suffer from type information loss and structural noise, limiting their representational fidelity and generalization. We propose THeGAU, a model-agnostic framework that combines a type-aware graph autoencoder with guided graph augmentation to improve node classification. THeGAU reconstructs schema-valid edges as an auxiliary task to preserve node-type semantics and introduces a decoder-driven augmentation mechanism to selectively refine noisy structures. This joint design enhances robustness, accuracy, and efficiency while significantly reducing computational overhead. Extensive experiments on three benchmark HIN datasets (IMDB, ACM, and DBLP) demonstrate that THeGAU consistently outperforms existing HGNN methods, achieving state-of-the-art performance across multiple backbones. ---