# Research Papers — 2025-11 · bundle page 182 of 197

> Full-text markdown of papers #9051–9100 of 9830 published in 2025-11, newest first. AI-readable mirrors of the full 9830-paper 2025-11 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2025-11/page/182
[← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/181.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-11/page/183.md)

### Keeping it Local, Tiny and Real: Automated Report Generation on Edge Computing Devices for Mechatronic-Based Cognitive Systems

Authors: Nicolas Schuler, Lea Dewald, Jürgen Graf
Published: 2025-11-04
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2511.02507v1

Recent advancements in Deep Learning enable hardware-based cognitive systems, that is, mechatronic systems in general and robotics in particular with integrated Artificial Intelligence, to interact with dynamic and unstructured environments. While the results are impressive, the application of such systems to critical tasks like autonomous driving as well as service and care robotics necessitate the evaluation of large amount of heterogeneous data. Automated report generation for Mobile Robotics can play a crucial role in facilitating the evaluation and acceptance of such systems in various domains. In this paper, we propose a pipeline for generating automated reports in natural language utilizing various multi-modal sensors that solely relies on local models capable of being deployed on edge computing devices, thus preserving the privacy of all actors involved and eliminating the need for external services. In particular, we evaluate our implementation on a diverse dataset spanning multiple domains including indoor, outdoor and urban environments, providing quantitative as well as qualitative evaluation results. Various generated example reports and other supplementary materials are available via a public repository.

---

### ESA: Energy-Based Shot Assembly Optimization for Automatic Video Editing

Authors: Yaosen Chen, Wei Wang, Tianheng Zheng, Xuming Wen, Han Yang, Yanru Zhang
Published: 2025-11-04
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.02505v2

Shot assembly is a crucial step in film production and video editing, involving the sequencing and arrangement of shots to construct a narrative, convey information, or evoke emotions. Traditionally, this process has been manually executed by experienced editors. While current intelligent video editing technologies can handle some automated video editing tasks, they often fail to capture the creator's unique artistic expression in shot assembly. To address this challenge, we propose an energy-based optimization method for video shot assembly. Specifically, we first perform visual-semantic matching between the script generated by a large language model and a video library to obtain subsets of candidate shots aligned with the script semantics. Next, we segment and label the shots from reference videos, extracting attributes such as shot size, camera motion, and semantics. We then employ energy-based models to learn from these attributes, scoring candidate shot sequences based on their alignment with reference styles. Finally, we achieve shot assembly optimization by combining multiple syntax rules, producing videos that align with the assembly style of the reference videos. Our method not only automates the arrangement and combination of independent shots according to specific logic, narrative requirements, or artistic styles but also learns the assembly style of reference videos, creating a coherent visual sequence or holistic visual expression. With our system, even users with no prior video editing experience can create visually compelling videos. Project page: https://sobeymil.github.io/esa.com

---

### Adapting General-Purpose Foundation Models for X-ray Ptychography in Low-Data Regimes

Authors: Robinson Umeike, Neil Getty, Yin Xiangyu, Yi Jiang
Published: 2025-11-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.02503v2

The automation of workflows in advanced microscopy is a key goal where foundation models like Language Models (LLMs) and Vision-Language Models (VLMs) show great potential. However, adapting these general-purpose models for specialized scientific tasks is critical, and the optimal domain adaptation strategy is often unclear. To address this, we introduce PtychoBench, a new multi-modal, multi-task benchmark for ptychographic analysis. Using this benchmark, we systematically compare two specialization strategies: Supervised Fine-Tuning (SFT) and In-Context Learning (ICL). We evaluate these strategies on a visual artifact detection task with VLMs and a textual parameter recommendation task with LLMs in a data-scarce regime. Our findings reveal that the optimal specialization pathway is task-dependent. For the visual task, SFT and ICL are highly complementary, with a fine-tuned model guided by context-aware examples achieving the highest mean performance (Micro-F1 of 0.728). Conversely, for the textual task, ICL on a large base model is the superior strategy, reaching a peak Micro-F1 of 0.847 and outperforming a powerful "super-expert" SFT model (0-shot Micro-F1 of 0.839). We also confirm the superiority of context-aware prompting and identify a consistent contextual interference phenomenon in fine-tuned models. These results, benchmarked against strong baselines including GPT-4o and a DINOv3-based classifier, offer key observations for AI in science: the optimal specialization path in our benchmark is dependent on the task modality, offering a clear framework for developing more effective science-based agentic systems.

---

### Evolutionary Algorithm for Chance Constrained Quadratic Multiple Knapsack Problem

Authors: Kokila Kasuni Perera, Aneta Neumann
Published: 2025-11-04
Categories: cs.NE
arXiv: https://arxiv.org/abs/2511.02500v1

Quadratic multiple knapsack problem (QMKP) is a combinatorial optimisation problem characterised by multiple weight capacity constraints and a profit function that combines linear and quadratic profits. We study a stochastic variant of this problem where profits are considered as random variables. This problem reflects complex resource allocation problems in real-world scenarios where randomness is inherent. We model this problem using chance constraints to capture the stochastic profits. We propose a hybrid approach for this problem, which combines an evolutionary algorithm (EA) with a local optimisation strategy inspired by multi-factorial optimisation (MFO). EAs are used for global search due to their effectiveness in handling large, complex solution spaces. In the hybrid approach, EA periodically passes interim solutions to the local optimiser for refinement. The local optimiser applies MFO principles, which are typically used in multi-tasking problems. The local optimiser models the local problem as a multi-tasking problem by constructing disjoint search spaces for each knapsack based on an input solution. For each item, its assignment across all knapsacks is considered to determine the preferred knapsack. Items are then divided into disjoint groups corresponding to each knapsack, allowing each knapsack to be treated as a separate optimisation task. This structure enables effective application of MFO-based local refinements. We consider two EAs for the problem, (1+1) EA and ($μ+λ$) EA. We conduct experiments to explore the effectiveness of these EAs on their own and also with the proposed local optimiser. Experimental results suggest that hybrid approaches, particularly those incorporating MFO, perform well on instances where chance constraints and capacity constraints are tight.

---

### Geometry as a Missing Axis of Representation Quality: The Variational Geometric Information Bottleneck under Data Scarcity

Authors: Ronald Katende
Published: 2025-11-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.02496v2

We study latent geometry as an explicit component of representation quality in data-scarce learning. For an encoder (φ), we define (Q_{β,γ}(φ)=I(φ(X);Y)-β\mathcal C(φ)-γd_{\mathrm{int}}(φ)), combining task-relevant information with penalties for curvature and intrinsic latent dimension. Thus geometry becomes part of the bottleneck criterion, not only a post hoc diagnostic. Under smooth-manifold, loss-transfer, and estimator-concentration assumptions, we derive non-asymptotic low-label generalization bounds where intrinsic dimension and covering complexity enter explicitly. We characterize the information--geometry frontier and prove empirical-surrogate consistency. The analysis links encoder geometry to learning through latent covering numbers, loss-class entropy, and uniform deviation. We instantiate the theory as \texttt{V-GIB}, adding curvature and dimension penalties to variational bottleneck training. Real low-label benchmarks compare \texttt{V-GIB} with ERM, VIB, and ablations across (1%)--(20%) label fractions. Results show improved performance and reduced geometric complexity in several regimes, especially FashionMNIST and CIFAR-10, while confirming that no fixed regularizer is universally dominant.

---

### DetectiumFire: A Comprehensive Multi-modal Dataset Bridging Vision and Language for Fire Understanding

Authors: Zixuan Liu, Siavash H. Khajavi, Guangkai Jiang
Published: 2025-11-04
Categories: cs.CV, cs.CL
arXiv: https://arxiv.org/abs/2511.02495v1

Recent advances in multi-modal models have demonstrated strong performance in tasks such as image generation and reasoning. However, applying these models to the fire domain remains challenging due to the lack of publicly available datasets with high-quality fire domain annotations. To address this gap, we introduce DetectiumFire, a large-scale, multi-modal dataset comprising of 22.5k high-resolution fire-related images and 2.5k real-world fire-related videos covering a wide range of fire types, environments, and risk levels. The data are annotated with both traditional computer vision labels (e.g., bounding boxes) and detailed textual prompts describing the scene, enabling applications such as synthetic data generation and fire risk reasoning. DetectiumFire offers clear advantages over existing benchmarks in scale, diversity, and data quality, significantly reducing redundancy and enhancing coverage of real-world scenarios. We validate the utility of DetectiumFire across multiple tasks, including object detection, diffusion-based image generation, and vision-language reasoning. Our results highlight the potential of this dataset to advance fire-related research and support the development of intelligent safety systems. We release DetectiumFire to promote broader exploration of fire understanding in the AI community. The dataset is available at https://kaggle.com/datasets/38b79c344bdfc55d1eed3d22fbaa9c31fad45e27edbbe9e3c529d6e5c4f93890

---

### BRAINS: A Retrieval-Augmented System for Alzheimer's Detection and Monitoring

Authors: Rajan Das Gupta, Md Kishor Morol, Nafiz Fahad, Md Tanzib Hosain, Sumaya Binte Zilani Choya, Md Jakir Hossen
Published: 2025-11-04
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.02490v1

As the global burden of Alzheimer's disease (AD) continues to grow, early and accurate detection has become increasingly critical, especially in regions with limited access to advanced diagnostic tools. We propose BRAINS (Biomedical Retrieval-Augmented Intelligence for Neurodegeneration Screening) to address this challenge. This novel system harnesses the powerful reasoning capabilities of Large Language Models (LLMs) for Alzheimer's detection and monitoring. BRAINS features a dual-module architecture: a cognitive diagnostic module and a case-retrieval module. The Diagnostic Module utilizes LLMs fine-tuned on cognitive and neuroimaging datasets -- including MMSE, CDR scores, and brain volume metrics -- to perform structured assessments of Alzheimer's risk. Meanwhile, the Case Retrieval Module encodes patient profiles into latent representations and retrieves similar cases from a curated knowledge base. These auxiliary cases are fused with the input profile via a Case Fusion Layer to enhance contextual understanding. The combined representation is then processed with clinical prompts for inference. Evaluations on real-world datasets demonstrate BRAINS effectiveness in classifying disease severity and identifying early signs of cognitive decline. This system not only shows strong potential as an assistive tool for scalable, explainable, and early-stage Alzheimer's disease detection, but also offers hope for future applications in the field.

---

### Object-aware graph matching network for cross-domain remote sensing image localization

Authors: Tao Liu, Kan Ren, Qian Chen
Published: 2025-11-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.02489v2

Cross-domain and cross-modal remote sensing image geo-localization remains challenging due to large appearance discrepancies and unstable semantic correspondence across heterogeneous sensors and platforms. Existing methods mainly rely on scene-level or global representations, which often struggle to achieve reliable alignment in complex environments, especially under severe modality gaps such as infrared-to-visible matching. To facilitate research in this setting, this study introduces IRVL328, a new infrared-visible remote sensing localization dataset designed to reflect challenging cross-modal variations. Meanwhile, this study proposes an object-aware graph matching framework that integrates object detection with dual-graph neural reasoning, where salient structural regions are represented as graph nodes and both inter-image correspondences and intra-image relations are jointly modeled; a training-only node alignment strategy is further introduced to enhance supervision without increasing inference complexity. Experimental results show that the proposed method achieves competitive performance on SUES-200 and strong performance on IRVL328 and DenseUAV, particularly in challenging cross-modal settings.

---

### Learning CNF formulas from uniform random solutions in the local lemma regime

Authors: Weiming Feng, Xiongxin Yang, Yixiao Yu, Yiyao Zhang
Published: 2025-11-04
Categories: cs.DS, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2511.02487v1

We study the problem of learning a $n$-variables $k$-CNF formula $Φ$ from its i.i.d. uniform random solutions, which is equivalent to learning a Boolean Markov random field (MRF) with $k$-wise hard constraints. Revisiting Valiant's algorithm (Commun. ACM'84), we show that it can exactly learn (1) $k$-CNFs with bounded clause intersection size under Lovász local lemma type conditions, from $O(\log n)$ samples; and (2) random $k$-CNFs near the satisfiability threshold, from $\widetilde{O}(n^{\exp(-\sqrt{k})})$ samples. These results significantly improve the previous $O(n^k)$ sample complexity. We further establish new information-theoretic lower bounds on sample complexity for both exact and approximate learning from i.i.d. uniform random solutions.

---

### OLATverse: A Large-scale Real-world Object Dataset with Precise Lighting Control

Authors: Xilong Zhou, Jianchun Chen, Pramod Rao, Timo Teufel, Linjie Lyu, Tigran Minasian, Oleksandr Sotnychenko, Xiao-Xiao Long, Marc Habermann, Christian Theobalt
Published: 2025-11-04
Categories: cs.CV, cs.GR
arXiv: https://arxiv.org/abs/2511.02483v3

We introduce OLATverse, a large-scale dataset comprising around 9M images of 765 real-world objects, captured from multiple viewpoints under a diverse set of precisely controlled lighting conditions. While recent advances in object-centric inverse rendering, novel view synthesis and relighting have shown promising results, most techniques still heavily rely on the synthetic datasets for training and small-scale real-world datasets for benchmarking, which limits their realism and generalization. To address this gap, OLATverse offers two key advantages over existing datasets: large-scale coverage of real objects and high-fidelity appearance under precisely controlled illuminations. Specifically, OLATverse contains 765 common and uncommon real-world objects, spanning a wide range of material categories. Each object is captured using 35 DSLR cameras and 331 individually controlled light sources, enabling the simulation of diverse illumination conditions. In addition, for each object, we provide well-calibrated camera parameters, accurate object masks, photometric surface normals, and diffuse albedo as auxiliary resources. We also construct an extensive evaluation set, establishing the first comprehensive real-world object-centric benchmark for inverse rendering and normal estimation. We believe that OLATverse represents a pivotal step toward integrating the next generation of inverse rendering and relighting methods with real-world data. The full dataset, along with all post-processing workflows, will be publicly released at https://vcai.mpi-inf.mpg.de/projects/OLATverse/.

---

### NOWS: Neural Operator Warm Starts for Accelerating Iterative Solvers

Authors: Mohammad Sadegh Eshaghi, Cosmin Anitescu, Navid Valizadeh, Yizheng Wang, Xiaoying Zhuang, Timon Rabczuk
Published: 2025-11-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.02481v4

Partial differential equations (PDEs) underpin quantitative descriptions across the physical sciences and engineering, yet high-fidelity simulation remains a major computational bottleneck for many-query, real-time, and design tasks. Data-driven surrogates can be strikingly fast but are often unreliable when applied outside their training distribution. Here we introduce Neural Operator Warm Starts (NOWS), a hybrid strategy that harnesses learned solution operators to accelerate classical iterative solvers by producing high-quality initial guesses for Krylov methods such as conjugate gradient and GMRES. NOWS leaves existing discretizations and solver infrastructures intact, integrating seamlessly with finite-difference, finite-element, isogeometric analysis, finite volume method, etc. Across our benchmarks, the learned initialization consistently reduces iteration counts and end-to-end runtime, resulting in a reduction of the computational time of up to 90 %, while preserving the stability and convergence guarantees of the underlying numerical algorithms. By combining the rapid inference of neural operators with the rigor of traditional solvers, NOWS provides a practical and trustworthy approach to accelerate high-fidelity PDE simulations.

---

### Wireless Video Semantic Communication with Decoupled Diffusion Multi-frame Compensation

Authors: Bingyan Xie, Yongpeng Wu, Yuxuan Shi, Biqian Feng, Wenjun Zhang, Jihong Park, Tony Quek
Published: 2025-11-04
Categories: cs.MM, cs.AI
arXiv: https://arxiv.org/abs/2511.02478v1

Existing wireless video transmission schemes directly conduct video coding in pixel level, while neglecting the inner semantics contained in videos. In this paper, we propose a wireless video semantic communication framework with decoupled diffusion multi-frame compensation (DDMFC), abbreviated as WVSC-D, which integrates the idea of semantic communication into wireless video transmission scenarios. WVSC-D first encodes original video frames as semantic frames and then conducts video coding based on such compact representations, enabling the video coding in semantic level rather than pixel level. Moreover, to further reduce the communication overhead, a reference semantic frame is introduced to substitute motion vectors of each frame in common video coding methods. At the receiver, DDMFC is proposed to generate compensated current semantic frame by a two-stage conditional diffusion process. With both the reference frame transmission and DDMFC frame compensation, the bandwidth efficiency improves with satisfying video transmission performance. Experimental results verify the performance gain of WVSC-D over other DL-based methods e.g. DVSC about 1.8 dB in terms of PSNR.

---

### MVAFormer: RGB-based Multi-View Spatio-Temporal Action Recognition with Transformer

Authors: Taiga Yamane, Satoshi Suzuki, Ryo Masumura, Shotaro Tora
Published: 2025-11-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.02473v1

Multi-view action recognition aims to recognize human actions using multiple camera views and deals with occlusion caused by obstacles or crowds. In this task, cooperation among views, which generates a joint representation by combining multiple views, is vital. Previous studies have explored promising cooperation methods for improving performance. However, since their methods focus only on the task setting of recognizing a single action from an entire video, they are not applicable to the recently popular spatio-temporal action recognition~(STAR) setting, in which each person's action is recognized sequentially. To address this problem, this paper proposes a multi-view action recognition method for the STAR setting, called MVAFormer. In MVAFormer, we introduce a novel transformer-based cooperation module among views. In contrast to previous studies, which utilize embedding vectors with lost spatial information, our module utilizes the feature map for effective cooperation in the STAR setting, which preserves the spatial information. Furthermore, in our module, we divide the self-attention for the same and different views to model the relationship between multiple views effectively. The results of experiments using a newly collected dataset demonstrate that MVAFormer outperforms the comparison baselines by approximately $4.4$ points on the F-measure.

---

### Modeling Hawkish-Dovish Latent Beliefs in Multi-Agent Debate-Based LLMs for Monetary Policy Decision Classification

Authors: Kaito Takano, Masanori Hirano, Kei Nakagawa
Published: 2025-11-04
Categories: q-fin.CP, cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2511.02469v1

Accurately forecasting central bank policy decisions, particularly those of the Federal Open Market Committee(FOMC) has become increasingly important amid heightened economic uncertainty. While prior studies have used monetary policy texts to predict rate changes, most rely on static classification models that overlook the deliberative nature of policymaking. This study proposes a novel framework that structurally imitates the FOMC's collective decision-making process by modeling multiple large language models(LLMs) as interacting agents. Each agent begins with a distinct initial belief and produces a prediction based on both qualitative policy texts and quantitative macroeconomic indicators. Through iterative rounds, agents revise their predictions by observing the outputs of others, simulating deliberation and consensus formation. To enhance interpretability, we introduce a latent variable representing each agent's underlying belief(e.g., hawkish or dovish), and we theoretically demonstrate how this belief mediates the perception of input information and interaction dynamics. Empirical results show that this debate-based approach significantly outperforms standard LLMs-based baselines in prediction accuracy. Furthermore, the explicit modeling of beliefs provides insights into how individual perspectives and social influence shape collective policy forecasts.

---

### HAGI++: Head-Assisted Gaze Imputation and Generation

Authors: Chuhan Jiao, Zhiming Hu, Andreas Bulling
Published: 2025-11-04
Categories: cs.HC, cs.CV
arXiv: https://arxiv.org/abs/2511.02468v2

Mobile eye-tracking is crucial for capturing human visual attention in real-world and XR settings, supporting research and human-computer interaction. Yet blinks, pupil-detection errors and lighting changes create missing values that hinder gaze analysis. We present HAGI++, a multi-modal diffusion-based imputation method that, for the first time, leverages integrated head-orientation sensors to exploit the natural correlation between head and eye movements. Using a transformer-based diffusion model, it learns cross-modal dependencies between eye and head data and can additionally incorporate wrist/hand motion when such wearable signals are available. Evaluations on the large-scale Nymeria, Ego-Exo4D and HOT3D datasets show that HAGI++ consistently outperforms traditional interpolation and deep-learning time-series imputation baselines. Statistical analysis confirms that its gaze-velocity distributions closely match real human behaviour, yielding realistic imputations. Even when 100% of gaze data are missing (pure gaze generation), HAGI++ exceeds methods that rely on the visual inputs and the methods rely on full-body motion capture by incorporating wrist motion from commercial wearables. Our approach enables more complete, accurate eye-gaze recordings in real-world contexts, enhancing gaze-based analysis and interaction across many applications. Our code is available at https://git.cai.simtech.uni-stuttgart.de/public-projects/HAGI

---

### Extending RLVR to Open-Ended Tasks via Verifiable Multiple-Choice Reformulation

Authors: Mengyu Zhang, Siyu Ding, Weichong Yin, Yu Sun, Hua Wu
Published: 2025-11-04
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.02463v3

Reinforcement Learning with Verifiable Rewards(RLVR) has demonstrated great potential in enhancing the reasoning capabilities of large language models (LLMs). However, its success has thus far been largely confined to the mathematical and programming domains with clear and automatically checkable outcomes. Reinforcement learning on open-ended tasks (e.g., creative writing and subjective Q&A) continues to rely on reward models due to the absence of verifiable solutions. This raises a key question: how can we extend RLVR to strengthen reasoning in open-ended tasks regardless of the absence of the unambiguous ground truth? To overcome this challenge, we introduce Verifiable Multiple-Choice Reformulation for Reinforcement Learning from Verifiable Rewards (VMR-RLVR), a novel training strategy that restructures open-ended data into verifiable multiple-choice formats, enabling effective training even in the absence of explicit ground truth. Experimental results on multiple benchmarks validate the effectiveness of our method in improving LLM performance on open-ended tasks. Notably, across seven open-ended benchmarks, our VMR-RLVR training delivers an average gain of 3.29 points over the RL with reward model.

---

### KAO: Kernel-Adaptive Optimization in Diffusion for Satellite Image

Authors: Teerapong Panboonyuen
Published: 2025-11-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.02462v1

Satellite image inpainting is a crucial task in remote sensing, where accurately restoring missing or occluded regions is essential for robust image analysis. In this paper, we propose KAO, a novel framework that utilizes Kernel-Adaptive Optimization within diffusion models for satellite image inpainting. KAO is specifically designed to address the challenges posed by very high-resolution (VHR) satellite datasets, such as DeepGlobe and the Massachusetts Roads Dataset. Unlike existing methods that rely on preconditioned models requiring extensive retraining or postconditioned models with significant computational overhead, KAO introduces a Latent Space Conditioning approach, optimizing a compact latent space to achieve efficient and accurate inpainting. Furthermore, we incorporate Explicit Propagation into the diffusion process, facilitating forward-backward fusion, which improves the stability and precision of the method. Experimental results demonstrate that KAO sets a new benchmark for VHR satellite image restoration, providing a scalable, high-performance solution that balances the efficiency of preconditioned models with the flexibility of postconditioned models.

---

### SKGE: Spherical Knowledge Graph Embedding with Geometric Regularization

Authors: Xuan-Truong Quan, Xuan-Son Quan, Duc Do Minh, Vinh Nguyen Van
Published: 2025-11-04
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.02460v1

Knowledge graph embedding (KGE) has become a fundamental technique for representation learning on multi-relational data. Many seminal models, such as TransE, operate in an unbounded Euclidean space, which presents inherent limitations in modeling complex relations and can lead to inefficient training. In this paper, we propose Spherical Knowledge Graph Embedding (SKGE), a model that challenges this paradigm by constraining entity representations to a compact manifold: a hypersphere. SKGE employs a learnable, non-linear Spherization Layer to map entities onto the sphere and interprets relations as a hybrid translate-then-project transformation. Through extensive experiments on three benchmark datasets, FB15k-237, CoDEx-S, and CoDEx-M, we demonstrate that SKGE consistently and significantly outperforms its strong Euclidean counterpart, TransE, particularly on large-scale benchmarks such as FB15k-237 and CoDEx-M, demonstrating the efficacy of the spherical geometric prior. We provide an in-depth analysis to reveal the sources of this advantage, showing that this geometric constraint acts as a powerful regularizer, leading to comprehensive performance gains across all relation types. More fundamentally, we prove that the spherical geometry creates an "inherently hard negative sampling" environment, naturally eliminating trivial negatives and forcing the model to learn more robust and semantically coherent representations. Our findings compellingly demonstrate that the choice of manifold is not merely an implementation detail but a fundamental design principle, advocating for geometric priors as a cornerstone for designing the next generation of powerful and stable KGE models.

---

### Prompting for Policy: Forecasting Macroeconomic Scenarios with Synthetic LLM Personas

Authors: Giulia Iadisernia, Carolina Camassa
Published: 2025-11-04
Categories: cs.CL, cs.CE, econ.GN
arXiv: https://arxiv.org/abs/2511.02458v1

We evaluate whether persona-based prompting improves Large Language Model (LLM) performance on macroeconomic forecasting tasks. Using 2,368 economics-related personas from the PersonaHub corpus, we prompt GPT-4o to replicate the ECB Survey of Professional Forecasters across 50 quarterly rounds (2013-2025). We compare the persona-prompted forecasts against the human experts panel, across four target variables (HICP, core HICP, GDP growth, unemployment) and four forecast horizons. We also compare the results against 100 baseline forecasts without persona descriptions to isolate its effect. We report two main findings. Firstly, GPT-4o and human forecasters achieve remarkably similar accuracy levels, with differences that are statistically significant yet practically modest. Our out-of-sample evaluation on 2024-2025 data demonstrates that GPT-4o can maintain competitive forecasting performance on unseen events, though with notable differences compared to the in-sample period. Secondly, our ablation experiment reveals no measurable forecasting advantage from persona descriptions, suggesting these prompt components can be omitted to reduce computational costs without sacrificing accuracy. Our results provide evidence that GPT-4o can achieve competitive forecasting accuracy even on out-of-sample macroeconomic events, if provided with relevant context data, while revealing that diverse prompts produce remarkably homogeneous forecasts compared to human panels.

---

### Accounting for Underspecification in Statistical Claims of Model Superiority

Authors: Thomas Sanchez, Pedro M. Gordaliza, Meritxell Bach Cuadra
Published: 2025-11-04
Categories: cs.LG, eess.IV
arXiv: https://arxiv.org/abs/2511.02453v1

Machine learning methods are increasingly applied in medical imaging, yet many reported improvements lack statistical robustness: recent works have highlighted that small but significant performance gains are highly likely to be false positives. However, these analyses do not take \emph{underspecification} into account -- the fact that models achieving similar validation scores may behave differently on unseen data due to random initialization or training dynamics. Here, we extend a recent statistical framework modeling false outperformance claims to include underspecification as an additional variance component. Our simulations demonstrate that even modest seed variability ($\sim1\%$) substantially increases the evidence required to support superiority claims. Our findings underscore the need for explicit modeling of training variance when validating medical imaging systems.

---

### An Adaptive Sampling Framework for Detecting Localized Concept Drift under Label Scarcity

Authors: Junghee Pyeon, Davide Cacciarelli, Kamran Paynabar
Published: 2025-11-04
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2511.02452v1

Concept drift and label scarcity are two critical challenges limiting the robustness of predictive models in dynamic industrial environments. Existing drift detection methods often assume global shifts and rely on dense supervision, making them ill-suited for regression tasks with local drifts and limited labels. This paper proposes an adaptive sampling framework that combines residual-based exploration and exploitation with EWMA monitoring to efficiently detect local concept drift under labeling budget constraints. Empirical results on synthetic benchmarks and a case study on electricity market demonstrate superior performance in label efficiency and drift detection accuracy.

---

### Merging Continual Pretraining Models for Domain-Specialized LLMs: A Case Study in Finance

Authors: Kentaro Ueda, François Portet, Hirohiko Suwa, Keiichi Yasumoto
Published: 2025-11-04
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.02451v1

While LLMs excel at general tasks, they struggle in specialized domains like finance, requiring diverse skills in domain knowledge, mathematical reasoning, and multilingual processing. Merging domain-specific Continual Pre-training (CPT) "experts" offers a practical alternative to costly and unstable multi-skill training. However, unlike established Supervised Fine-Tuning (SFT) model-based merging, CPT model merging remains largely unexplored. We address this gap by creating financial LLMs from experts in finance, math, and Japanese. We propose a three-stage evaluation focusing on knowledge recovery, complementarity, and emergence, and assess three merging methods (Task Arithmetic, TIES, and DARE-TIES) on a comprehensive financial benchmark curated from 18 tasks across 8 established datasets. Results show that merging an expert with its base model recovers general knowledge lost during CPT, while merging experts improves performance and can yield emergent cross-domain skills. Among the methods, Task Arithmetic performs strongly but is hyperparameter-sensitive, whereas TIES is more robust. Our findings also suggest that while model similarity correlates with merging success, emergent skills depend on more complex factors. This work presents the first foundational analysis of CPT model merging, establishing a principled framework and providing clear guidance for building multi-skill LLMs from existing assets.

---

### Improving Unlearning with Model Updates Probably Aligned with Gradients

Authors: Virgile Dine, Teddy Furon, Charly Faure
Published: 2025-11-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.02435v1

We formulate the machine unlearning problem as a general constrained optimization problem. It unifies the first-order methods from the approximate machine unlearning literature. This paper then introduces the concept of feasible updates as the model's parameter update directions that help with unlearning while not degrading the utility of the initial model. Our design of feasible updates is based on masking, \ie\ a careful selection of the model's parameters worth updating. It also takes into account the estimation noise of the gradients when processing each batch of data to offer a statistical guarantee to derive locally feasible updates. The technique can be plugged in, as an add-on, to any first-order approximate unlearning methods. Experiments with computer vision classifiers validate this approach.

---

### Efficient Solvers for SLOPE in R, Python, Julia, and C++

Authors: Johan Larsson, Malgorzata Bogdan, Krystyna Grzesiak, Mathurin Massias, Jonas Wallin
Published: 2025-11-04
Categories: stat.CO, cs.MS, cs.SE, stat.ML
arXiv: https://arxiv.org/abs/2511.02430v4

We present a suite of packages in R, Python, Julia, and C++ that efficiently solve the Sorted L-One Penalized Estimation (SLOPE) problem. The packages feature a highly efficient hybrid coordinate descent algorithm that fits generalized linear models (GLMs) and supports a variety of loss functions, including Gaussian, binomial, Poisson, and multinomial logistic regression. Our implementation is designed to be fast, memory-efficient, and flexible. The packages support a variety of data structures (dense, sparse, and out-of-memory matrices) and are designed to efficiently fit the full SLOPE path as well as handle cross-validation of SLOPE models, including the relaxed SLOPE. We present examples of how to use the packages and benchmarks that demonstrate the performance of the packages on both real and simulated data and show that our packages outperform existing implementations of SLOPE in terms of speed.

---

### From the Laboratory to Real-World Application: Evaluating Zero-Shot Scene Interpretation on Edge Devices for Mobile Robotics

Authors: Nicolas Schuler, Lea Dewald, Nick Baldig, Jürgen Graf
Published: 2025-11-04
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2511.02427v2

Video Understanding, Scene Interpretation and Commonsense Reasoning are highly challenging tasks enabling the interpretation of visual information, allowing agents to perceive, interact with and make rational decisions in its environment. Large Language Models (LLMs) and Visual Language Models (VLMs) have shown remarkable advancements in these areas in recent years, enabling domain-specific applications as well as zero-shot open vocabulary tasks, combining multiple domains. However, the required computational complexity poses challenges for their application on edge devices and in the context of Mobile Robotics, especially considering the trade-off between accuracy and inference time. In this paper, we investigate the capabilities of state-of-the-art VLMs for the task of Scene Interpretation and Action Recognition, with special regard to small VLMs capable of being deployed to edge devices in the context of Mobile Robotics. The proposed pipeline is evaluated on a diverse dataset consisting of various real-world cityscape, on-campus and indoor scenarios. The experimental evaluation discusses the potential of these small models on edge devices, with particular emphasis on challenges, weaknesses, inherent model biases and the application of the gained information. Supplementary material is provided via the following repository: https://datahub.rz.rptu.de/hstr-csrl-public/publications/scene-interpretation-on-edge-devices/

---

### A Kullback-Leibler divergence method for input-system-state identification

Authors: Marios Impraimakis
Published: 2025-11-04
Categories: eess.SP, cs.AI, cs.CV, cs.IT, eess.SY
arXiv: https://arxiv.org/abs/2511.02426v1

The capability of a novel Kullback-Leibler divergence method is examined herein within the Kalman filter framework to select the input-parameter-state estimation execution with the most plausible results. This identification suffers from the uncertainty related to obtaining different results from different initial parameter set guesses, and the examined approach uses the information gained from the data in going from the prior to the posterior distribution to address the issue. Firstly, the Kalman filter is performed for a number of different initial parameter sets providing the system input-parameter-state estimation. Secondly, the resulting posterior distributions are compared simultaneously to the initial prior distributions using the Kullback-Leibler divergence. Finally, the identification with the least Kullback-Leibler divergence is selected as the one with the most plausible results. Importantly, the method is shown to select the better performed identification in linear, nonlinear, and limited information applications, providing a powerful tool for system monitoring.

---

### ReAcTree: Hierarchical LLM Agent Trees with Control Flow for Long-Horizon Task Planning

Authors: Jae-Woo Choi, Hyungmin Kim, Hyobin Ong, Youngwoo Yoon, Minsu Jang, Dohyung Kim, Jaehong Kim
Published: 2025-11-04
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.02424v2

Recent advancements in large language models (LLMs) have enabled significant progress in decision-making and task planning for embodied autonomous agents. However, most existing methods struggle with complex, long-horizon tasks because they rely on a monolithic trajectory that entangles all past decisions and observations to solve the entire task in a single unified process. To address this limitation, we propose ReAcTree, a hierarchical task-planning method that decomposes a complex goal into manageable subgoals within a dynamically constructed agent tree. Each subgoal is handled by an LLM agent node capable of reasoning, acting, and further expanding the tree, while control flow nodes coordinate the execution strategies of agent nodes. In addition, we integrate two complementary memory systems: each agent node retrieves goal-specific, subgoal-level examples from episodic memory and shares environment-specific observations through working memory. Experiments on the WAH-NL and ALFRED show ReAcTree consistently outperforms strong task-planning baselines such as ReAct across diverse LLMs. Notably, on WAH-NL, ReAcTree achieves a 61% goal success rate with Qwen 2.5 72B, nearly doubling ReAct's 31%. The code is available at https://github.com/Choi-JaeWoo/ReAcTree.git.

---

### Wasserstein Convergence of Critically Damped Langevin Diffusions

Authors: Stanislas Strasman, Sobihan Surendran, Claire Boyer, Sylvain Le Corff, Vincent Lemaire, Antonio Ocello
Published: 2025-11-04
Categories: math.ST, stat.ML
arXiv: https://arxiv.org/abs/2511.02419v1

Score-based Generative Models (SGMs) have achieved impressive performance in data generation across a wide range of applications and benefit from strong theoretical guarantees. Recently, methods inspired by statistical mechanics, in particular, Hamiltonian dynamics, have introduced Critically-damped Langevin Diffusions (CLDs), which define diffusion processes on extended spaces by coupling the data with auxiliary variables. These approaches, along with their associated score-matching and sampling procedures, have been shown to outperform standard diffusion-based samplers numerically. In this paper, we analyze a generalized dynamic that extends classical CLDs by introducing an additional hyperparameter controlling the noise applied to the data coordinate, thereby better exploiting the extended space. We further derive a novel upper bound on the sampling error of CLD-based generative models in the Wasserstein metric. This additional hyperparameter influences the smoothness of sample paths, and our discretization error analysis provides practical guidance for its tuning, leading to improved sampling performance.

---

### CropCraft: A Procedural World Generator for Robotic Simulation of Agricultural Tasks

Authors: Riccardo Bertoglio, Cyrille Pierre, Johann Laconte, Roland Lenain
Published: 2025-11-04
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2511.02417v2

The adoption of agroecological practices in modern agriculture requires robotic systems capable of operating in highly diverse and complex field environments. Developing and evaluating such systems relies heavily on simulation, yet generating realistic and configurable 3D environments representative of agroecological diversity remains a major challenge. This paper presents CropCraft, an open-source procedural world generator built on Blender and Python, designed to produce 3D simulation environments tailored to agricultural robotics. CropCraft generates crop fields from a simple YAML configuration file, supporting a wide range of scenarios including intercropping, vineyards, and weed-infested fields. The tool includes a library of 3D plant models (crops, grasses, and weeds) at multiple growth stages, and uses stochastic placement algorithms to realistically reproduce the spatial variability observed in real fields. Generated worlds are directly importable into the Gazebo simulator and include ground-truth annotations for all placed elements, supporting both perception and navigation algorithm development. To demonstrate the practical utility of CropCraft, we apply it to the task of crop-weed semantic segmentation using deep learning. A dataset of 10,000 synthetic images of maize fields with varying weed densities, growth stages, and lighting conditions was generated and used to train several segmentation architectures. Models trained exclusively on synthetic data achieve a sim-to-real gap of approximately 10% mean Intersection over Union (mIoU) on real field images, outperforming previous state-of-the-art synthetic generation approaches. We further show that combining even a few real images with synthetic data improves generalization across domains, providing new insights into the effective use of synthetic data for agricultural perception tasks.

---

### ChartM$^3$: A Multi-Stage Code-Driven Pipeline for Constructing Multi-Dimensional and Multi-Step Visual Reasoning Data in Chart Comprehension

Authors: Duo Xu, Hao Cheng, Xin Lin, Zhen Xie, Hao Wang
Published: 2025-11-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.02415v1

Complex chart understanding tasks demand advanced visual recognition and reasoning capabilities from multimodal large language models (MLLMs). However, current research provides limited coverage of complex chart scenarios and computation-intensive reasoning tasks prevalent in real-world applications. This study proposes an automated multi-stage code-driven pipeline for systematically generating visual reasoning datasets to address these limitations. The pipeline integrates retrieval-augmented generation (RAG) to retrieve professional chart templates and employs chain-of-thought (CoT) strategies to generate reasoning codes that simulate real data distributions, thereby driving chart rendering and question-related statistical computations. Through model-based evaluation, the pipeline enhances chart diversity and data quality. Using this framework, we construct ChartM$^3$, a multi-dimensional and multi-step dataset containing 38K charts and 142K Q&A pairs for training, along with 2,871 high-quality evaluation samples for enabling practical performance assessment. Supervised fine-tuning (SFT) and reinforcement learning (RL) experiments demonstrate that our dataset significantly improves reasoning capabilities and cross-domain generalization performance, enabling smaller models to achieve performance comparable to larger-scale models in complex chart comprehension.

---

### A New Perspective on Precision and Recall for Generative Models

Authors: Benjamin Sykes, Loïc Simon, Julien Rabin, Jalal Fadili
Published: 2025-11-04
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.02414v3

With the recent success of generative models in image and text, the question of their evaluation has recently gained a lot of attention. While most methods from the state of the art rely on scalar metrics, the introduction of Precision and Recall (PR) for generative model has opened up a new avenue of research. The associated PR curve allows for a richer analysis, but their estimation poses several challenges. In this paper, we present a new framework for estimating entire PR curves based on a binary classification standpoint. We conduct a thorough statistical analysis of the proposed estimates. As a byproduct, we obtain a minimax upper bound on the PR estimation risk. We also show that our framework extends several landmark PR metrics of the literature which by design are restrained to the extreme values of the curve. Finally, we study the different behaviors of the curves obtained experimentally in various settings.

---

### IllumFlow: Illumination-Adaptive Low-Light Enhancement via Conditional Rectified Flow and Retinex Decomposition

Authors: Wenyang Wei, Yang yang, Xixi Jia, Xiangchu Feng, Weiwei Wang, Renzhen Wang
Published: 2025-11-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.02411v1

We present IllumFlow, a novel framework that synergizes conditional Rectified Flow (CRF) with Retinex theory for low-light image enhancement (LLIE). Our model addresses low-light enhancement through separate optimization of illumination and reflectance components, effectively handling both lighting variations and noise. Specifically, we first decompose an input image into reflectance and illumination components following Retinex theory. To model the wide dynamic range of illumination variations in low-light images, we propose a conditional rectified flow framework that represents illumination changes as a continuous flow field. While complex noise primarily resides in the reflectance component, we introduce a denoising network, enhanced by flow-derived data augmentation, to remove reflectance noise and chromatic aberration while preserving color fidelity. IllumFlow enables precise illumination adaptation across lighting conditions while naturally supporting customizable brightness enhancement. Extensive experiments on low-light enhancement and exposure correction demonstrate superior quantitative and qualitative performance over existing methods.

---

### Arithmetic Circuits and Neural Networks for Regular Matroids

Authors: Christoph Hertrich, Stefan Kober, Georg Loho
Published: 2025-11-04
Categories: math.CO, cs.CC, cs.DM, cs.LG, math.OC
arXiv: https://arxiv.org/abs/2511.02406v2

We prove that there exist uniform $(+,\times,/)$-circuits of size $O(n^3)$ to compute the basis generating polynomial of regular matroids on $n$ elements. By tropicalization, this implies that there exist uniform $(\max,+,-)$-circuits and ReLU neural networks of the same size for weighted basis maximization of regular matroids. As a consequence in linear programming theory, we obtain a first example where taking the difference of two extended formulations can be more efficient than the best known individual extended formulation for the base polytope of regular matroids of size $O(n^6)$ by Aprile and Fiorini. Such differences have recently been introduced as virtual extended formulations. The proof of our main result relies on a fine-tuned version of Seymour's decomposition of regular matroids which allows us to identify and maintain graphic substructures to which we can apply a local version of the star-mesh transformation.

---

### Purrturbed but Stable: Human-Cat Invariant Representations Across CNNs, ViTs and Self-Supervised ViTs

Authors: Arya Shah, Vaibhav Tripathi
Published: 2025-11-04
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.02404v1

Cats and humans differ in ocular anatomy. Most notably, Felis Catus (domestic cats) have vertically elongated pupils linked to ambush predation; yet, how such specializations manifest in downstream visual representations remains incompletely understood. We present a unified, frozen-encoder benchmark that quantifies feline-human cross-species representational alignment in the wild, across convolutional networks, supervised Vision Transformers, windowed transformers, and self-supervised ViTs (DINO), using layer-wise Centered Kernel Alignment (linear and RBF) and Representational Similarity Analysis, with additional distributional and stability tests reported in the paper. Across models, DINO ViT-B/16 attains the most substantial alignment (mean CKA-RBF $\approx0.814$, mean CKA-linear $\approx0.745$, mean RSA $\approx0.698$), peaking at early blocks, indicating that token-level self-supervision induces early-stage features that bridge species-specific statistics. Supervised ViTs are competitive on CKA yet show weaker geometric correspondence than DINO (e.g., ViT-B/16 RSA $\approx0.53$ at block8; ViT-L/16 $\approx0.47$ at block14), revealing depth-dependent divergences between similarity and representational geometry. CNNs remain strong baselines but below plain ViTs on alignment, and windowed transformers underperform plain ViTs, implicating architectural inductive biases in cross-species alignment. Results indicate that self-supervision coupled with ViT inductive biases yields representational geometries that more closely align feline and human visual systems than widely used CNNs and windowed Transformers, providing testable neuroscientific hypotheses about where and how cross-species visual computations converge. We release our code and dataset for reference and reproducibility.

---

### Generalization in Representation Models via Random Matrix Theory: Application to Recurrent Networks

Authors: Yessin Moakher, Malik Tiomoko, Cosme Louart, Zhenyu Liao
Published: 2025-11-04
Categories: math.ST, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2511.02401v1

We first study the generalization error of models that use a fixed feature representation (frozen intermediate layers) followed by a trainable readout layer. This setting encompasses a range of architectures, from deep random-feature models to echo-state networks (ESNs) with recurrent dynamics. Working in the high-dimensional regime, we apply Random Matrix Theory to derive a closed-form expression for the asymptotic generalization error. We then apply this analysis to recurrent representations and obtain concise formula that characterize their performance. Surprisingly, we show that a linear ESN is equivalent to ridge regression with an exponentially time-weighted (''memory'') input covariance, revealing a clear inductive bias toward recent inputs. Experiments match predictions: ESNs win in low-sample, short-memory regimes, while ridge prevails with more data or long-range dependencies. Our methodology provides a general framework for analyzing overparameterized models and offers insights into the behavior of deep learning networks.

---

### MammoClean: Toward Reproducible and Bias-Aware AI in Mammography through Dataset Harmonization

Authors: Yalda Zafari, Hongyi Pan, Gorkem Durak, Ulas Bagci, Essam A. Rashed, Mohamed Mabrok
Published: 2025-11-04
Categories: eess.IV, cs.AI, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2511.02400v1

The development of clinically reliable artificial intelligence (AI) systems for mammography is hindered by profound heterogeneity in data quality, metadata standards, and population distributions across public datasets. This heterogeneity introduces dataset-specific biases that severely compromise the generalizability of the model, a fundamental barrier to clinical deployment. We present MammoClean, a public framework for standardization and bias quantification in mammography datasets. MammoClean standardizes case selection, image processing (including laterality and intensity correction), and unifies metadata into a consistent multi-view structure. We provide a comprehensive review of breast anatomy, imaging characteristics, and public mammography datasets to systematically identify key sources of bias. Applying MammoClean to three heterogeneous datasets (CBIS-DDSM, TOMPEI-CMMD, VinDr-Mammo), we quantify substantial distributional shifts in breast density and abnormality prevalence. Critically, we demonstrate the direct impact of data corruption: AI models trained on corrupted datasets exhibit significant performance degradation compared to their curated counterparts. By using MammoClean to identify and mitigate bias sources, researchers can construct unified multi-dataset training corpora that enable development of robust models with superior cross-domain generalization. MammoClean provides an essential, reproducible pipeline for bias-aware AI development in mammography, facilitating fairer comparisons and advancing the creation of safe, effective systems that perform equitably across diverse patient populations and clinical settings. The open-source code is publicly available from: https://github.com/Minds-R-Lab/MammoClean.

---

### Towards Iterative End-to-End Software Development: A Feature-Driven Multi-Agent Framework

Authors: Junwei Liu, Chen Xu, Chong Wang, Tong Bai, Weitong Chen, Kaseng Wong, Yiling Lou, Xin Peng
Published: 2025-11-04
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2511.02399v3

Recent advances in large language model agents offer the promise of automating end-to-end software development from natural language requirements. However, existing approaches largely adopt linear, waterfall-style pipelines, which oversimplify the iterative nature of real-world development and struggle with complex, large-scale projects. To address these limitations, we propose EvoDev, an iterative software development framework inspired by feature-driven development. EvoDev decomposes user requirements into a set of user-valued features and constructs a Feature Map, a directed acyclic graph that explicitly models dependencies between features. Each feature node in the feature map maintains multi-layer contexts, including business logic, software design, and code implementation, which are propagated along dependencies to provide context for subsequent development iterations. We evaluate EvoDev on challenging Android development tasks and show that it outperforms the best-performing baseline, Claude Code, by 57.3%, while improving single-agent performance by 16.0%-58.5% across different base LLMs, highlighting the importance of feature decomposition, dependency modeling, context propagation, and workflow-aware agent design for end-to-end software development. Moreover, our work summarizes practical insights for designing iterative, LLM-driven development frameworks and informs future training of base LLMs to better support iterative software development.

---

### A Spatially Informed Gaussian Process UCB Method for Decentralized Coverage Control

Authors: Gennaro Guidone, Luca Monegaglia, Elia Raimondi, Han Wang, Mattia Bianchi, Florian Dörfler
Published: 2025-11-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.02398v2

We present a novel decentralized algorithm for coverage control in unknown spatial environments modeled by Gaussian Processes (GPs). To trade-off between exploration and exploitation, each agent autonomously determines its trajectory by minimizing a local cost function. Inspired by the GP-UCB (Upper Confidence Bound for GPs) acquisition function, the proposed cost combines the expected locational cost with a variance-based exploration term, guiding agents toward regions that are both high in predicted density and model uncertainty. Compared to previous work, our algorithm operates in a fully decentralized fashion, relying only on local observations and communication with neighboring agents. In particular, agents periodically update their inducing points using a greedy selection strategy, enabling scalable online GP updates. We demonstrate the effectiveness of our algorithm in simulation.

---

### A Novel Grouping-Based Hybrid Color Correction Algorithm for Color Point Clouds

Authors: Kuo-Liang Chung, Ting-Chung Tang
Published: 2025-11-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.02397v1

Color consistency correction for color point clouds is a fundamental yet important task in 3D rendering and compression applications. In the past, most previous color correction methods aimed at correcting color for color images. The purpose of this paper is to propose a grouping-based hybrid color correction algorithm for color point clouds. Our algorithm begins by estimating the overlapping rate between the aligned source and target point clouds, and then adaptively partitions the target points into two groups, namely the close proximity group Gcl and the moderate proximity group Gmod, or three groups, namely Gcl, Gmod, and the distant proximity group Gdist, when the estimated overlapping rate is low or high, respectively. To correct color for target points in Gcl, a K-nearest neighbors based bilateral interpolation (KBI) method is proposed. To correct color for target points in Gmod, a joint KBI and the histogram equalization (JKHE) method is proposed. For target points in Gdist, a histogram equalization (HE) method is proposed for color correction. Finally, we discuss the grouping-effect free property and the ablation study in our algorithm. The desired color consistency correction benefit of our algorithm has been justified through 1086 testing color point cloud pairs against the state-of-the-art methods. The C++ source code of our algorithm can be accessed from the website: https://github.com/ivpml84079/Point-cloud-color-correction.

---

### Self-Supervised Moving Object Segmentation of Sparse and Noisy Radar Point Clouds

Authors: Leon Schwarzer, Matthias Zeller, Daniel Casado Herraez, Simon Dierl, Michael Heidingsfeld, Cyrill Stachniss
Published: 2025-11-04
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2511.02395v1

Moving object segmentation is a crucial task for safe and reliable autonomous mobile systems like self-driving cars, improving the reliability and robustness of subsequent tasks like SLAM or path planning. While the segmentation of camera or LiDAR data is widely researched and achieves great results, it often introduces an increased latency by requiring the accumulation of temporal sequences to gain the necessary temporal context. Radar sensors overcome this problem with their ability to provide a direct measurement of a point's Doppler velocity, which can be exploited for single-scan moving object segmentation. However, radar point clouds are often sparse and noisy, making data annotation for use in supervised learning very tedious, time-consuming, and cost-intensive. To overcome this problem, we address the task of self-supervised moving object segmentation of sparse and noisy radar point clouds. We follow a two-step approach of contrastive self-supervised representation learning with subsequent supervised fine-tuning using limited amounts of annotated data. We propose a novel clustering-based contrastive loss function with cluster refinement based on dynamic points removal to pretrain the network to produce motion-aware representations of the radar data. Our method improves label efficiency after fine-tuning, effectively boosting state-of-the-art performance by self-supervised pretraining.

---

### Fuzzy Soft Set Theory based Expert System for the Risk Assessment in Breast Cancer Patients

Authors: Muhammad Sheharyar Liaqat
Published: 2025-11-04
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.02392v1

Breast cancer remains one of the leading causes of mortality among women worldwide, with early diagnosis being critical for effective treatment and improved survival rates. However, timely detection continues to be a challenge due to the complex nature of the disease and variability in patient risk factors. This study presents a fuzzy soft set theory-based expert system designed to assess the risk of breast cancer in patients using measurable clinical and physiological parameters. The proposed system integrates Body Mass Index, Insulin Level, Leptin Level, Adiponectin Level, and age as input variables to estimate breast cancer risk through a set of fuzzy inference rules and soft set computations. These parameters can be obtained from routine blood analyses, enabling a non-invasive and accessible method for preliminary assessment. The dataset used for model development and validation was obtained from the UCI Machine Learning Repository. The proposed expert system aims to support healthcare professionals in identifying high-risk patients and determining the necessity of further diagnostic procedures such as biopsies.

---

### RxnCaption: Reformulating Reaction Diagram Parsing as Visual Prompt Guided Captioning

Authors: Jiahe Song, Chuang Wang, Bowen Jiang, Yinfan Wang, Hao Zheng, Xingjian Wei, Chengjin Liu, Rui Nie, Junyuan Gao, Jiaxing Sun, Yubin Wang, Lijun Wu et al.
Published: 2025-11-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.02384v2

Large-scale chemical reaction datasets are crucial for AI research in chemistry. However, existing chemical reaction data often exist as images within papers, making them not machine-readable and unusable for training machine learning models. In response to this challenge, we propose the RxnCaption framework for the task of chemical Reaction Diagram Parsing (RxnDP). Our framework reformulates the traditional coordinate prediction driven parsing process into an image captioning problem, which Large Vision Language Models (LVLMs) handle naturally. We introduce a strategy termed BBox and Index as Visual Prompt (BIVP), which uses our state-of-the-art molecular detector, MolYOLO, to pre-draw molecular bounding boxes and indices directly onto the input image. This turns the downstream parsing into a natural-language description problem. Extensive experiments show that the BIVP strategy significantly improves structural extraction quality while simplifying model design. We further construct the RxnCaption-15k dataset, an order of magnitude larger than prior real-world literature benchmarks, with a balanced test subset across four layout archetypes. Experiments demonstrate that RxnCaption-VL achieves state-of-the-art performance on multiple metrics. We believe our method, dataset, and models will advance structured information extraction from chemical literature and catalyze broader AI applications in chemistry. We will release data, models, and code on GitHub.

---

### H-Infinity Filter Enhanced CNN-LSTM for Arrhythmia Detection from Heart Sound Recordings

Authors: Rohith Shinoj Kumar, Rushdeep Dinda, Aditya Tyagi, Annappa B., Naveen Kumar M. R
Published: 2025-11-04
Categories: cs.LG, cs.AI, cs.SD, eess.SY
arXiv: https://arxiv.org/abs/2511.02379v1

Early detection of heart arrhythmia can prevent severe future complications in cardiac patients. While manual diagnosis still remains the clinical standard, it relies heavily on visual interpretation and is inherently subjective. In recent years, deep learning has emerged as a powerful tool to automate arrhythmia detection, offering improved accuracy, consistency, and efficiency. Several variants of convolutional and recurrent neural network architectures have been widely explored to capture spatial and temporal patterns in physiological signals. However, despite these advancements, current models often struggle to generalize well in real-world scenarios, especially when dealing with small or noisy datasets, which are common challenges in biomedical applications. In this paper, a novel CNN-H-Infinity-LSTM architecture is proposed to identify arrhythmic heart signals from heart sound recordings. This architecture introduces trainable parameters inspired by the H-Infinity filter from control theory, enhancing robustness and generalization. Extensive experimentation on the PhysioNet CinC Challenge 2016 dataset, a public benchmark of heart audio recordings, demonstrates that the proposed model achieves stable convergence and outperforms existing benchmarks, with a test accuracy of 99.42% and an F1 score of 98.85%.

---

### AutoAdv: Automated Adversarial Prompting for Multi-Turn Jailbreaking of Large Language Models

Authors: Aashray Reddy, Andrew Zagula, Nicholas Saban
Published: 2025-11-04
Categories: cs.CL, cs.AI, cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2511.02376v3

Large Language Models (LLMs) remain vulnerable to jailbreaking attacks where adversarial prompts elicit harmful outputs. Yet most evaluations focus on single-turn interactions while real-world attacks unfold through adaptive multi-turn conversations. We present AutoAdv, a training-free framework for automated multi-turn jailbreaking that achieves an attack success rate of up to 95% on Llama-3.1-8B within six turns, a 24% improvement over single-turn baselines. AutoAdv uniquely combines three adaptive mechanisms: a pattern manager that learns from successful attacks to enhance future prompts, a temperature manager that dynamically adjusts sampling parameters based on failure modes, and a two-phase rewriting strategy that disguises harmful requests and then iteratively refines them. Extensive evaluation across commercial and open-source models (Llama-3.1-8B, GPT-4o mini, Qwen3-235B, Mistral-7B) reveals persistent vulnerabilities in current safety mechanisms, with multi-turn attacks consistently outperforming single-turn approaches. These findings demonstrate that alignment strategies optimized for single-turn interactions fail to maintain robustness across extended conversations, highlighting an urgent need for multi-turn-aware defenses.

---

### AyurParam: A State-of-the-Art Bilingual Language Model for Ayurveda

Authors: Sravan Gorugantu, Mohd Nauman, Vijay Devane, Shyam Pawar, Viraj Thakur, Kundeshwar Pundalik, Piyush Sawarkar, Rohit Saluja, Maunendra Desarkar, Ganesh Ramakrishnan
Published: 2025-11-04
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.02374v2

Current large language models excel at broad, general-purpose tasks, but consistently underperform when exposed to highly specialized domains that require deep cultural, linguistic, and subject-matter expertise. In particular, traditional medical systems such as Ayurveda embody centuries of nuanced textual and clinical knowledge that mainstream LLMs fail to accurately interpret or apply. We introduce AyurParam-2.9B, a domain-specialized, bilingual language model fine-tuned from Param-1-2.9B using an extensive, expertly curated Ayurveda dataset spanning classical texts and clinical guidance. AyurParam's dataset incorporates context-aware, reasoning, and objective-style Q&A in both English and Hindi, with rigorous annotation protocols for factual precision and instructional clarity. Benchmarked on BhashaBench-Ayur, AyurParam not only surpasses all open-source instruction-tuned models in its size class (1.5--3B parameters), but also demonstrates competitive or superior performance compared to much larger models. The results from AyurParam highlight the necessity for authentic domain adaptation and high-quality supervision in delivering reliable, culturally congruent AI for specialized medical knowledge.

---

### A new class of Markov random fields enabling lightweight sampling

Authors: Jean-Baptiste Courbot, Hugo Gangloff, Bruno Colicchio
Published: 2025-11-04
Categories: stat.ML, cs.LG, eess.SP, stat.CO
arXiv: https://arxiv.org/abs/2511.02373v1

This work addresses the problem of efficient sampling of Markov random fields (MRF). The sampling of Potts or Ising MRF is most often based on Gibbs sampling, and is thus computationally expensive. We consider in this work how to circumvent this bottleneck through a link with Gaussian Markov Random fields. The latter can be sampled in several cost-effective ways, and we introduce a mapping from real-valued GMRF to discrete-valued MRF. The resulting new class of MRF benefits from a few theoretical properties that validate the new model. Numerical results show the drastic performance gain in terms of computational efficiency, as we sample at least 35x faster than Gibbs sampling using at least 37x less energy, all the while exhibiting empirical properties close to classical MRFs.

---

### LUMA-RAG: Lifelong Multimodal Agents with Provably Stable Streaming Alignment

Authors: Rohan Wandre, Yash Gajewar, Namrata Patel, Vivek Dhalkari
Published: 2025-11-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.02371v1

Retrieval-Augmented Generation (RAG) has emerged as the dominant paradigm for grounding large language model outputs in verifiable evidence. However, as modern AI agents transition from static knowledge bases to continuous multimodal streams encompassing text, images, video, and audio, two critical challenges arise: maintaining index freshness without prohibitive re-indexing costs, and preserving cross-modal semantic consistency across heterogeneous embedding spaces. We present LUMA-RAG, a lifelong multimodal agent architecture featuring three key innovations: (i) a streaming, multi-tier memory system that dynamically spills embeddings from a hot HNSW tier to a compressed IVFPQ tier under strict memory budgets; (ii) a streaming CLAP->CLIP alignment bridge that maintains cross-modal consistency through incremental orthogonal Procrustes updates; and (iii) stability-aware retrieval telemetry providing Safe@k guarantees by jointly bounding alignment drift and quantization error. Experiments demonstrate robust text-to-image retrieval (Recall@10 = 0.94), graceful performance degradation under product quantization offloading, and provably stable audio-to-image rankings (Safe@1 = 1.0), establishing LUMA-RAG as a practical framework for production multimodal RAG systems.

---

### AI Credibility Signals Outrank Institutions and Engagement in Shaping News Perception on Social Media

Authors: Adnan Hoq, Matthew Facciani, Tim Weninger
Published: 2025-11-04
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2511.02370v1

AI-generated content is rapidly becoming a salient component of online information ecosystems, yet its influence on public trust and epistemic judgments remains poorly understood. We present a large-scale mixed-design experiment (N = 1,000) investigating how AI-generated credibility scores affect user perception of political news. Our results reveal that AI feedback significantly moderates partisan bias and institutional distrust, surpassing traditional engagement signals such as likes and shares. These findings demonstrate the persuasive power of generative AI and suggest a need for design strategies that balance epistemic influence with user autonomy.

---

### LiveSecBench: A Dynamic and Event-Driven Safety Benchmark for Chinese Language Model Applications

Authors: Yudong Li, Peiru Yang, Feng Huang, Zhongliang Yang, Kecheng Wang, Haitian Li, Baocheng Chen, Xingyu An, Ziyu Liu, Youdan Yang, Kejiang Chen, Sifang Wan et al.
Published: 2025-11-04
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.02366v2

We introduce LiveSecBench, a continuously updated safety benchmark specifically for Chinese-language LLM application scenarios. LiveSecBench constructs a high-quality and unique dataset through a pipeline that combines automated generation with human verification. By periodically releasing new versions to expand the dataset and update evaluation metrics, LiveSecBench provides a robust and up-to-date standard for AI safety. In this report, we introduce our second release v251215, which evaluates across five dimensions (Public Safety, Fairness & Bias, Privacy, Truthfulness, and Mental Health Safety.) We evaluate 57 representative LLMs using an ELO rating system, offering a leaderboard of the current state of Chinese LLM safety. The result is available at https://livesecbench.intokentech.cn/.

---

### LaRe: Latent Refocusing for Multimodal Reasoning

Authors: Jizheng Ma, Xiaofei Zhou, Geyuan Zhang, Yanlong Song, Han Yan
Published: 2025-11-04
Categories: cs.CV, cs.CL
arXiv: https://arxiv.org/abs/2511.02360v4

Chain of Thought (CoT) reasoning enhances logical performance by decomposing complex tasks, yet its multimodal extension faces a trade-off. The prevailing Thinking with Images paradigm achieves visual refocusing by explicitly cropping image regions, yet incurs rapidly growing computational overhead. The emerging line of latent-space reasoning reduces token consumption, but lacks the capacity for dynamic refocusing. We argue that this trade-off stems from a tacitly accepted premise that effective visual refocusing must occur in the form of explicit tokens. Building on this, we propose Latent Refocusing (LaRe), a new multimodal reasoning paradigm in which visual refocusing takes place entirely within the latent space. We further design a semantic augmentation training strategy that ensures the semantic structure of the latent space through visual reconstruction objective. Experimental evaluations demonstrate that LaRe improves average accuracy by 7.6% compared to existing baselines while reducing the number of tokens required for inference by 59.7%. When scaled to a 8B-parameter Vision-Language Model backbone, LaRe achieves performance comparable to state-of-the-art methods, demonstrating the efficacy of our proposed latent refocusing paradigm for multimodal reasoning.

---