# Research Papers — 2025-10 · bundle page 206 of 217

> Full-text markdown of papers #10251–10300 of 10843 published in 2025-10, newest first. AI-readable mirrors of the full 10843-paper 2025-10 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2025-10/page/206
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/205.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/207.md)

### Nav-EE: Navigation-Guided Early Exiting for Efficient Vision-Language Models in Autonomous Driving

Authors: Haibo Hu, Lianming Huang, Xinyu Wang, Yufei Cui, Shangyu Wu, Nan Guan, Chun Jason Xue
Published: 2025-10-02
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2510.01795v2

Vision-Language Models (VLMs) are increasingly applied in autonomous driving for unified perception and reasoning, but high inference latency hinders real-time deployment. Early-exit reduces latency by terminating inference at intermediate layers, yet its task-dependent nature limits generalization across diverse scenarios. We observe that this limitation aligns with autonomous driving: navigation systems can anticipate upcoming contexts (e.g., intersections, traffic lights), indicating which tasks will be required. We propose Nav-EE, a navigation-guided early-exit framework that precomputes task-specific exit layers offline and dynamically applies them online based on navigation priors. Experiments on CODA, Waymo, and BOSCH show that Nav-EE achieves accuracy comparable to full inference while reducing latency by up to 63.9%. Real-vehicle integration with Autoware Universe further demonstrates reduced inference latency (600ms to 300ms), supporting faster decision-making in complex scenarios. These results suggest that coupling navigation foresight with early-exit offers a viable path toward efficient deployment of large models in autonomous systems. Code and data are available at our anonymous repository: https://anonymous.4open.science/r/Nav-EE-BBC4

---

### Sensitivity, Specificity, and Consistency: A Tripartite Evaluation of Privacy Filters for Synthetic Data Generation

Authors: Adil Koeken, Alexander Ziller, Moritz Knolle, Daniel Rueckert
Published: 2025-10-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.01793v1

The generation of privacy-preserving synthetic datasets is a promising avenue for overcoming data scarcity in medical AI research. Post-hoc privacy filtering techniques, designed to remove samples containing personally identifiable information, have recently been proposed as a solution. However, their effectiveness remains largely unverified. This work presents a rigorous evaluation of a filtering pipeline applied to chest X-ray synthesis. Contrary to claims from the original publications, our results demonstrate that current filters exhibit limited specificity and consistency, achieving high sensitivity only for real images while failing to reliably detect near-duplicates generated from training data. These results demonstrate a critical limitation of post-hoc filtering: rather than effectively safeguarding patient privacy, these methods may provide a false sense of security while leaving unacceptable levels of patient information exposed. We conclude that substantial advances in filter design are needed before these methods can be confidently deployed in sensitive applications.

---

### Comparison of Unsupervised Metrics for Evaluating Judicial Decision Extraction

Authors: Ivan Leonidovich Litvak, Anton Kostin, Fedor Lashkin, Tatiana Maksiyan, Sergey Lagutin
Published: 2025-10-02
Categories: cs.CL, cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2510.01792v1

The rapid advancement of artificial intelligence in legal natural language processing demands scalable methods for evaluating text extraction from judicial decisions. This study evaluates 16 unsupervised metrics, including novel formulations, to assess the quality of extracting seven semantic blocks from 1,000 anonymized Russian judicial decisions, validated against 7,168 expert reviews on a 1--5 Likert scale. These metrics, spanning document-based, semantic, structural, pseudo-ground truth, and legal-specific categories, operate without pre-annotated ground truth. Bootstrapped correlations, Lin's concordance correlation coefficient (CCC), and mean absolute error (MAE) reveal that Term Frequency Coherence (Pearson $r = 0.540$, Lin CCC = 0.512, MAE = 0.127) and Coverage Ratio/Block Completeness (Pearson $r = 0.513$, Lin CCC = 0.443, MAE = 0.139) best align with expert ratings, while Legal Term Density (Pearson $r = -0.479$, Lin CCC = -0.079, MAE = 0.394) show strong negative correlations. The LLM Evaluation Score (mean = 0.849, Pearson $r = 0.382$, Lin CCC = 0.325, MAE = 0.197) showed moderate alignment, but its performance, using gpt-4.1-mini via g4f, suggests limited specialization for legal textse. These findings highlight that unsupervised metrics, including LLM-based approaches, enable scalable screening but, with moderate correlations and low CCC values, cannot fully replace human judgment in high-stakes legal contexts. This work advances legal NLP by providing annotation-free evaluation tools, with implications for judicial analytics and ethical AI deployment.

---

### Neural non-canonical Hamiltonian dynamics for long-time simulations

Authors: Clémentine Courtès, Emmanuel Franck, Michael Kraus, Laurent Navoret, Léopold Trémant
Published: 2025-10-02
Categories: cs.LG, math.NA
arXiv: https://arxiv.org/abs/2510.01788v2

This work focuses on learning non-canonical Hamiltonian dynamics from data, where long-term predictions require the preservation of structure both in the learned model and in numerical schemes. Previous research focused on either facet, respectively with a potential-based architecture and with degenerate variational integrators, but new issues arise when combining both. In experiments, the learnt model is sometimes numerically unstable due to the gauge dependency of the scheme, rendering long-time simulations impossible. In this paper, we identify this problem and propose two different training strategies to address it, either by directly learning the vector field or by learning a time-discrete dynamics through the scheme. Several numerical test cases assess the ability of the methods to learn complex physical dynamics, like the guiding center from gyrokinetic plasma physics.

---

### Pack and Force Your Memory: Long-form and Consistent Video Generation

Authors: Xiaofei Wu, Guozhen Zhang, Zhiyong Xu, Yuan Zhou, Qinglin Lu, Xuming He
Published: 2025-10-02
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.01784v2

Long-form video generation presents a dual challenge: models must capture long-range dependencies while preventing the error accumulation inherent in autoregressive decoding. To address these challenges, we make two contributions. First, for dynamic context modeling, we propose MemoryPack, a learnable context-retrieval mechanism that leverages both textual and image information as global guidance to jointly model short- and long-term dependencies, achieving minute-level temporal consistency. This design scales gracefully with video length, preserves computational efficiency, and maintains linear complexity. Second, to mitigate error accumulation, we introduce Direct Forcing, an efficient single-step approximating strategy that improves training-inference alignment and thereby curtails error propagation during inference. Together, MemoryPack and Direct Forcing substantially enhance the context consistency and reliability of long-form video generation, advancing the practical usability of autoregressive video models.

---

### Can LLMs Refuse Questions They Do Not Know? Measuring Knowledge-Aware Refusal in Factual Tasks

Authors: Wenbo Pan, Jie Xu, Qiguang Chen, Junhao Dong, Libo Qin, Xinfeng Li, Haining Yu, Xiaohua Jia
Published: 2025-10-02
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.01782v2

Large Language Models (LLMs) should refuse to answer questions beyond their knowledge. This capability, which we term knowledge-aware refusal, is crucial for factual reliability, while existing metrics fail to capture this ability. In this work, we propose the Refusal Index (RI), a novel and principled metric that measures how accurately LLMs refuse questions they do not know. We define RI as Spearman's rank correlation between refusal probability and error probability. RI is practically measurable with a lightweight two-pass evaluation method which only require observed refusal rates across two standard evaluation runs. Extensive experiments across 16 models and 5 datasets demonstrate that RI accurately quantifies a model's knowledge-aware refusal capability. Notably, RI remains stable across different refusal rates and provides consistent model rankings independent of a model's overall accuracy and refusal rates. These properties suggest RI captures a stable, intrinsic aspect of model knowledge calibration. More importantly, RI provides insight into an important but previously overlooked aspect of LLM factuality: while LLMs achieve high accuracy on factual tasks, their refusal behavior can be unreliable and fragile.

---

### Secure Multi-Modal Data Fusion in Federated Digital Health Systems via MCP

Authors: Aueaphum Aueawatthanaphisut
Published: 2025-10-02
Categories: cs.CR, cs.AI, cs.CY, cs.LG
arXiv: https://arxiv.org/abs/2510.01780v1

Secure and interoperable integration of heterogeneous medical data remains a grand challenge in digital health. Current federated learning (FL) frameworks offer privacy-preserving model training but lack standardized mechanisms to orchestrate multi-modal data fusion across distributed and resource-constrained environments. This study introduces a novel framework that leverages the Model Context Protocol (MCP) as an interoperability layer for secure, cross-agent communication in multi-modal federated healthcare systems. The proposed architecture unifies three pillars: (i) multi-modal feature alignment for clinical imaging, electronic medical records, and wearable IoT data; (ii) secure aggregation with differential privacy to protect patient-sensitive updates; and (iii) energy-aware scheduling to mitigate dropouts in mobile clients. By employing MCP as a schema-driven interface, the framework enables adaptive orchestration of AI agents and toolchains while ensuring compliance with privacy regulations. Experimental evaluation on benchmark datasets and pilot clinical cohorts demonstrates up to 9.8\% improvement in diagnostic accuracy compared with baseline FL, a 54\% reduction in client dropout rates, and clinically acceptable privacy--utility trade-offs. These results highlight MCP-enabled multi-modal fusion as a scalable and trustworthy pathway toward equitable, next-generation federated health infrastructures.

---

### Scalable Asynchronous Federated Modeling for Spatial Data

Authors: Jianwei Shi, Sameh Abdulah, Ying Sun, Marc G. Genton
Published: 2025-10-02
Categories: stat.ME, cs.LG, stat.CO, stat.ML
arXiv: https://arxiv.org/abs/2510.01771v1

Spatial data are central to applications such as environmental monitoring and urban planning, but are often distributed across devices where privacy and communication constraints limit direct sharing. Federated modeling offers a practical solution that preserves data privacy while enabling global modeling across distributed data sources. For instance, environmental sensor networks are privacy- and bandwidth-constrained, motivating federated spatial modeling that shares only privacy-preserving summaries to produce timely, high-resolution pollution maps without centralizing raw data. However, existing federated modeling approaches either ignore spatial dependence or rely on synchronous updates that suffer from stragglers in heterogeneous environments. This work proposes an asynchronous federated modeling framework for spatial data based on low-rank Gaussian process approximations. The method employs block-wise optimization and introduces strategies for gradient correction, adaptive aggregation, and stabilized updates. We establish linear convergence with explicit dependence on staleness, a result of standalone theoretical significance. Moreover, numerical experiments demonstrate that the asynchronous algorithm achieves synchronous performance under balanced resource allocation and significantly outperforms it in heterogeneous settings, showcasing superior robustness and scalability.

---

### LoBE-GS: Load-Balanced and Efficient 3D Gaussian Splatting for Large-Scale Scene Reconstruction

Authors: Sheng-Hsiang Hung, Ting-Yu Yen, Wei-Fang Sun, Simon See, Shih-Hsuan Hung, Hung-Kuo Chu
Published: 2025-10-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.01767v2

3D Gaussian Splatting (3DGS) has established itself as an efficient representation for real-time, high-fidelity 3D scene reconstruction. However, scaling 3DGS to large and unbounded scenes such as city blocks remains difficult. Existing divide-and-conquer methods alleviate memory pressure by partitioning the scene into blocks and training on multiple, non-communicating GPUs, but introduce new bottlenecks: (i) partitions suffer from severe load imbalance since uniform or heuristic splits do not reflect actual computational demands, and (ii) coarse-to-fine pipelines fail to exploit the coarse stage efficiently, often reloading the entire model and incurring high overhead. In this work, we introduce LoBE-GS, a novel Load-Balanced and Efficient 3D Gaussian Splatting framework, that re-engineers the large-scale 3DGS pipeline. Specifically, LoBE-GS introduces a load-balanced KD-tree scene partitioning scheme with optimized cutlines that balance per-block camera counts. To accelerate preprocessing, it employs depth-based back-projection for fast camera assignment, reducing processing time from hours to minutes. It further reduces training cost through two lightweight techniques: visibility cropping and selective densification. Evaluations on large-scale urban and outdoor datasets show that LoBE-GS consistently achieves up to 2 times faster end-to-end training time than state-of-the-art baselines, while maintaining reconstruction quality and enabling scalability to scenes infeasible with vanilla 3DGS.

---

### Octax: Accelerated CHIP-8 Arcade Environments for Reinforcement Learning in JAX

Authors: Waris Radji, Thomas Michel, Hector Piteau
Published: 2025-10-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.01764v3

Reinforcement learning (RL) research requires diverse, challenging environments that are both tractable and scalable. While modern video games may offer rich dynamics, they are computationally expensive and poorly suited for large-scale experimentation due to their CPU-bound execution. We introduce Octax, a high-performance suite of classic arcade game environments implemented in JAX, based on CHIP-8 emulation, a predecessor to Atari, which is widely adopted as a benchmark in RL research. Octax provides the JAX community with a long-awaited end-to-end GPU alternative to Atari games, offering image-based environments, spanning puzzle, action, and strategy genres, all executable at massive scale on modern GPUs. Our JAX-based implementation achieves orders-of-magnitude speedups over traditional CPU emulators. We demonstrate Octax's capabilities by training RL agents across multiple games, showing significant improvements in training speed and scalability compared to existing solutions. The environment's modular design enables researchers to easily extend the suite with new games or generate novel environments using large language models, making it an ideal platform for large-scale RL experimentation. Our open-source framework is available at https://github.com/riiswa/octax/.

---

### Unsupervised Dynamic Feature Selection for Robust Latent Spaces in Vision Tasks

Authors: Bruno Corcuera, Carlos Eiras-Franco, Brais Cancela
Published: 2025-10-02
Categories: cs.LG, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2510.01758v1

Latent representations are critical for the performance and robustness of machine learning models, as they encode the essential features of data in a compact and informative manner. However, in vision tasks, these representations are often affected by noisy or irrelevant features, which can degrade the model's performance and generalization capabilities. This paper presents a novel approach for enhancing latent representations using unsupervised Dynamic Feature Selection (DFS). For each instance, the proposed method identifies and removes misleading or redundant information in images, ensuring that only the most relevant features contribute to the latent space. By leveraging an unsupervised framework, our approach avoids reliance on labeled data, making it broadly applicable across various domains and datasets. Experiments conducted on image datasets demonstrate that models equipped with unsupervised DFS achieve significant improvements in generalization performance across various tasks, including clustering and image generation, while incurring a minimal increase in the computational cost.

---

### Learning Regularization Functionals for Inverse Problems: A Comparative Study

Authors: Johannes Hertrich, Hok Shing Wong, Alexander Denker, Stanislas Ducotterd, Zhenghan Fang, Markus Haltmeier, Željko Kereta, Erich Kobler, Oscar Leong, Mohammad Sadegh Salehi, Carola-Bibiane Schönlieb, Johannes Schwab et al.
Published: 2025-10-02
Categories: cs.LG, math.NA, math.OC
arXiv: https://arxiv.org/abs/2510.01755v2

In recent years, a variety of learned regularization frameworks for solving inverse problems in imaging have emerged. These offer flexible modeling together with mathematical insights. The proposed methods differ in their architectural design and training strategies, making direct comparison challenging due to non-modular implementations. We address this gap by collecting and unifying the available code into a common framework. This unified view allows us to systematically compare the approaches and highlight their strengths and limitations, providing valuable insights into their future potential. We also provide concise descriptions of each method, complemented by practical guidelines.

---

### A cybersecurity AI agent selection and decision support framework

Authors: Masike Malatji
Published: 2025-10-02
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.01751v1

This paper presents a novel, structured decision support framework that systematically aligns diverse artificial intelligence (AI) agent architectures, reactive, cognitive, hybrid, and learning, with the comprehensive National Institute of Standards and Technology (NIST) Cybersecurity Framework (CSF) 2.0. By integrating agent theory with industry guidelines, this framework provides a transparent and stepwise methodology for selecting and deploying AI solutions to address contemporary cyber threats. Employing a granular decomposition of NIST CSF 2.0 functions into specific tasks, the study links essential AI agent properties such as autonomy, adaptive learning, and real-time responsiveness to each subcategory's security requirements. In addition, it outlines graduated levels of autonomy (assisted, augmented, and fully autonomous) to accommodate organisations at varying stages of cybersecurity maturity. This holistic approach transcends isolated AI applications, providing a unified detection, incident response, and governance strategy. Through conceptual validation, the framework demonstrates how tailored AI agent deployments can align with real-world constraints and risk profiles, enhancing situational awareness, accelerating response times, and fortifying long-term resilience via adaptive risk management. Ultimately, this research bridges the gap between theoretical AI constructs and operational cybersecurity demands, establishing a foundation for robust, empirically validated multi-agent systems that adhere to industry standards.

---

### Towards Photonic Band Diagram Generation with Transformer-Latent Diffusion Models

Authors: Valentin Delchevalerie, Nicolas Roy, Arnaud Bougaham, Alexandre Mayer, Benoît Frénay, Michaël Lobet
Published: 2025-10-02
Categories: physics.optics, cs.CV
arXiv: https://arxiv.org/abs/2510.01749v1

Photonic crystals enable fine control over light propagation at the nanoscale, and thus play a central role in the development of photonic and quantum technologies. Photonic band diagrams (BDs) are a key tool to investigate light propagation into such inhomogeneous structured materials. However, computing BDs requires solving Maxwell's equations across many configurations, making it numerically expensive, especially when embedded in optimization loops for inverse design techniques, for example. To address this challenge, we introduce the first approach for BD generation based on diffusion models, with the capacity to later generalize and scale to arbitrary three dimensional structures. Our method couples a transformer encoder, which extracts contextual embeddings from the input structure, with a latent diffusion model to generate the corresponding BD. In addition, we provide insights into why transformers and diffusion models are well suited to capture the complex interference and scattering phenomena inherent to photonics, paving the way for new surrogate modeling strategies in this domain.

---

### Private and Fair Machine Learning: Revisiting the Disparate Impact of Differentially Private SGD

Authors: Lea Demelius, Dominik Kowald, Simone Kopeinik, Roman Kern, Andreas Trügler
Published: 2025-10-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.01744v1

Differential privacy (DP) is a prominent method for protecting information about individuals during data analysis. Training neural networks with differentially private stochastic gradient descent (DPSGD) influences the model's learning dynamics and, consequently, its output. This can affect the model's performance and fairness. While the majority of studies on the topic report a negative impact on fairness, it has recently been suggested that fairness levels comparable to non-private models can be achieved by optimizing hyperparameters for performance directly on differentially private models (rather than re-using hyperparameters from non-private models, as is common practice). In this work, we analyze the generalizability of this claim by 1) comparing the disparate impact of DPSGD on different performance metrics, and 2) analyzing it over a wide range of hyperparameter settings. We highlight that a disparate impact on one metric does not necessarily imply a disparate impact on another. Most importantly, we show that while optimizing hyperparameters directly on differentially private models does not mitigate the disparate impact of DPSGD reliably, it can still lead to improved utility-fairness trade-offs compared to re-using hyperparameters from non-private models. We stress, however, that any form of hyperparameter tuning entails additional privacy leakage, calling for careful considerations of how to balance privacy, utility and fairness. Finally, we extend our analyses to DPSGD-Global-Adapt, a variant of DPSGD designed to mitigate the disparate impact on accuracy, and conclude that this alternative may not be a robust solution with respect to hyperparameter choice.

---

### Machine-interpretable Engineering Design Standards for Valve Specification

Authors: Anders Gjerver, Rune Frostad, Vedrana Barisic, Melinda Hodkiewicz, Caitlin Woods, Mihaly Fekete, Arild Braathen Torjusen, Johan Wilhelm Kluwer
Published: 2025-10-02
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.01736v1

Engineering design processes use technical specifications and must comply with standards. Product specifications, product type data sheets, and design standards are still mainly document-centric despite the ambition to digitalize industrial work. In this paper, we demonstrate how to transform information held in engineering design standards into modular, reusable, machine-interpretable ontologies and use the ontologies in quality assurance of the plant design and equipment selection process. We use modelling patterns to create modular ontologies for knowledge captured in the text and in frequently referenced tables in International Standards for piping, material and valve design. These modules are exchangeable, as stored in a W3C compliant format, and interoperable as they are aligned with the top-level ontology ISO DIS 23726-3: Industrial Data Ontology (IDO). We test these ontologies, created based on international material and piping standards and industry norms, on a valve selection process. Valves are instantiated in semantic asset models as individuals along with a semantic representation of the environmental condition at their location on the asset. We create "functional location tags" as OWL individuals that become instances of OWL class Valve Data Sheet (VDS) specified valves. Similarly we create instances of manufacturer product type. Our approach enables automated validation that a specific VDS is compliant with relevant industry standards. Using semantic reasoning and executable design rules, we also determine whether the product type meets the valve specification. Creation of shared, reusable IDO-based modular ontologies for design standards enables semantic reasoning to be applied to equipment selection processes and demonstrates the potential of this approach for Standards Bodies wanting to transition to digitized Smart Standards.

---

### Reducing Simulation Dependence in Neutrino Telescopes with Masked Point Transformers

Authors: Felix J. Yu, Nicholas Kamp, Carlos A. Argüelles
Published: 2025-10-02
Categories: hep-ex, astro-ph.IM, cs.LG
arXiv: https://arxiv.org/abs/2510.01733v2

Machine learning techniques in neutrino physics have traditionally relied on simulated data, which provides access to ground-truth labels. However, the accuracy of these simulations and the discrepancies between simulated and real data remain significant concerns, particularly for large-scale neutrino telescopes that operate in complex natural media. In recent years, self-supervised learning has emerged as a powerful paradigm for reducing dependence on labeled datasets. Here, we present the first self-supervised training pipeline for neutrino telescopes, leveraging point cloud transformers and masked autoencoders. By shifting the majority of training to real data, this approach minimizes reliance on simulations, thereby mitigating associated systematic uncertainties. This represents a fundamental departure from previous machine learning applications in neutrino telescopes, paving the way for substantial improvements in event reconstruction and classification.

---

### MetaboT: An LLM-based Multi-Agent Frameworkfor Interactive Analysis of Mass SpectrometryMetabolomics Knowledge Graphs

Authors: Madina Bekbergenova, Lucas Pradi, Benjamin Navet, Emma Tysinger, Franck Michel, Matthieu Feraud, Yousouf Taghzouti, Yan Zhou Chen, Olivier Kirchhoffer, Florence Mehl, Martin Legrand, Tao Jiang et al.
Published: 2025-10-02
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.01724v2

Mass spectrometry-based metabolomics generates complex, high-dimensional data that holds vast potential for biological discovery but remains difficult to integrate and interpret. Knowledge graphs (KGs) unify this heterogeneous information by representing spectra, annotations, taxa, chemical classes, and biological activities as a single interoperable network; however, their practical use is limited by the steep learning curve of corresponding specialized representation and query languages. Here we introduce MetaboT, an open-source multi-agent Large Language Model (LLM) framework that translates natural-language questions into executable SPARQL queries over metabolomics knowledge graphs. MetaboT mitigates the hallucination and schema-compliance limitations of single-model approaches through a modular architecture in which specialised agents handle scope validation, entity resolution against authoritative resources, schema-aware query generation, iterative refinement, and result interpretation. We validated MetaboT on the Experimental Natural Products Knowledge Graph (ENPKG), using an expert-authored benchmark of natural-language questions paired with reference SPARQL queries, and demonstrate its ability to answer complex questions about plant--metabolite relationships and biological activities. MetaboT lowers the technical barrier for metabolomics researchers and enables semantic data mining without specialised programming expertise.

---

### Workplace Location Choice Model based on Deep Neural Network

Authors: Tanay Rastogi, Anders Karlström
Published: 2025-10-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.01723v1

Discrete choice models (DCMs) have long been used to analyze workplace location decisions, but they face challenges in accurately mirroring individual decision-making processes. This paper presents a deep neural network (DNN) method for modeling workplace location choices, which aims to better understand complex decision patterns and provides better results than traditional discrete choice models (DCMs). The study demonstrates that DNNs show significant potential as a robust alternative to DCMs in this domain. While both models effectively replicate the impact of job opportunities on workplace location choices, the DNN outperforms the DCM in certain aspects. However, the DCM better aligns with data when assessing the influence of individual attributes on workplace distance. Notably, DCMs excel at shorter distances, while DNNs perform comparably to both data and DCMs for longer distances. These findings underscore the importance of selecting the appropriate model based on specific application requirements in workplace location choice analysis.

---

### Emotional Text-To-Speech Based on Mutual-Information-Guided Emotion-Timbre Disentanglement

Authors: Jianing Yang, Sheng Li, Takahiro Shinozaki, Yuki Saito, Hiroshi Saruwatari
Published: 2025-10-02
Categories: cs.SD, cs.AI, eess.AS
arXiv: https://arxiv.org/abs/2510.01722v1

Current emotional Text-To-Speech (TTS) and style transfer methods rely on reference encoders to control global style or emotion vectors, but do not capture nuanced acoustic details of the reference speech. To this end, we propose a novel emotional TTS method that enables fine-grained phoneme-level emotion embedding prediction while disentangling intrinsic attributes of the reference speech. The proposed method employs a style disentanglement method to guide two feature extractors, reducing mutual information between timbre and emotion features, and effectively separating distinct style components from the reference speech. Experimental results demonstrate that our method outperforms baseline TTS systems in generating natural and emotionally rich speech. This work highlights the potential of disentangled and fine-grained representations in advancing the quality and flexibility of emotional TTS systems.

---

### Finite-Time Convergence of Single-Trajectory Chi-Square Robust Q-Learning With Linear Function Approximation

Authors: Saptarshi Mandal, Yashaswini Murthy, R. Srikant
Published: 2025-10-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.01721v4

Distributionally robust reinforcement learning seeks policies that remain effective when the deployment environment differs from the one that generated the training data. We study model-free robust Q-learning with $χ^2$ uncertainty sets and linear function approximation, using data from a single trajectory of an unknown nominal MDP. Evaluating the $χ^2$ robust Bellman target introduces the square root of a conditional second moment, which cannot be estimated unbiasedly from one transition, while the projected robust Bellman operator need not be contractive. We address these obstacles through a variational reformulation of the robust Bellman target and a blockwise frozen-target scheme, and establish a finite-time error bound relative to the optimal robust Q-function for every $γ\in(0,1)$. A neural-network experiment illustrates how the variational target can be used in a continuous-state nonlinear-control task.

---

### What MLLMs Learn about When they Learn about Multimodal Reasoning

Authors: Jiwan Chung, Neel Joshi, Pratyusha Sharma, Youngjae Yu, Vibhav Vineet
Published: 2025-10-02
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.01719v4

Evaluation of multimodal reasoning models is typically reduced to a single accuracy score, implicitly treating reasoning as a unitary capability. We introduce MathLens, a benchmark of textbook-style geometry problems that exposes this assumption by operationally decomposing performance into perception, reasoning, and multimodal-specific components. Each problem is derived from a symbolic specification and accompanied by visual diagrams, text-only variants, multimodal questions, and targeted perceptual probes, enabling controlled measurement of each component. Using this decomposition, we show that common training strategies induce systematically different capability profiles that are invisible under aggregate accuracy. Reinforcement learning primarily improves perceptual grounding and robustness to diagram variation, while textual SFT yields gains through reflective reasoning. In contrast, as perception and reasoning improve, a growing fraction of remaining errors fall outside these components and are categorized as multimodal-specific. These results suggest that apparent progress in multimodal reasoning reflects shifting balances among subskills rather than uniform advancement, motivating evaluation beyond scalar accuracy.

---

### Accelerating Attention with Basis Decomposition

Authors: Jialin Zhao
Published: 2025-10-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.01718v2

Attention is a core operation in large language models (LLMs). We present BD Attention (BDA), a lossless algorithmic reformulation of attention. BDA is enabled by a simple matrix identity from Basis Decomposition (BD), which restructures multi-head projections into a compact form while preserving exact outputs. Unlike I/O-aware system optimizations such as FlashAttention, BDA provides a mathematically guaranteed acceleration that is architecture-agnostic. On DeepSeek-V2-Lite (16B, FP16), BDA requires only 4s of offline preparation with no retraining required and, on modern GPUs, achieves 34% faster key/value projections and 25% smaller weights, while increasing perplexity (PPL) by just 0.02% (FP16) or 0.0004% (FP32), a negligible effect on model performance. These results position BDA as a theoretically exact method for lossless attention acceleration that is complementary to existing engineering-level optimizations. Our code is available at https://github.com/abcbdf/basis-decomposition-official.

---

### Latency-aware Multimodal Federated Learning over UAV Networks

Authors: Shaba Shaon, Dinh C. Nguyen
Published: 2025-10-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.01717v1

This paper investigates federated multimodal learning (FML) assisted by unmanned aerial vehicles (UAVs) with a focus on minimizing system latency and providing convergence analysis. In this framework, UAVs are distributed throughout the network to collect data, participate in model training, and collaborate with a base station (BS) to build a global model. By utilizing multimodal sensing, the UAVs overcome the limitations of unimodal systems, enhancing model accuracy, generalization, and offering a more comprehensive understanding of the environment. The primary objective is to optimize FML system latency in UAV networks by jointly addressing UAV sensing scheduling, power control, trajectory planning, resource allocation, and BS resource management. To address the computational complexity of our latency minimization problem, we propose an efficient iterative optimization algorithm combining block coordinate descent and successive convex approximation techniques, which provides high-quality approximate solutions. We also present a theoretical convergence analysis for the UAV-assisted FML framework under a non-convex loss function. Numerical experiments demonstrate that our FML framework outperforms existing approaches in terms of system latency and model training performance under different data settings.

---

### PyramidStyler: Transformer-Based Neural Style Transfer with Pyramidal Positional Encoding and Reinforcement Learning

Authors: Raahul Krishna Durairaju, K. Saruladha
Published: 2025-10-02
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.01715v1

Neural Style Transfer (NST) has evolved from Gatys et al.'s (2015) CNN-based algorithm, enabling AI-driven artistic image synthesis. However, existing CNN and transformer-based models struggle to scale efficiently to complex styles and high-resolution inputs. We introduce PyramidStyler, a transformer framework with Pyramidal Positional Encoding (PPE): a hierarchical, multi-scale encoding that captures both local details and global context while reducing computational load. We further incorporate reinforcement learning to dynamically optimize stylization, accelerating convergence. Trained on Microsoft COCO and WikiArt, PyramidStyler reduces content loss by 62.6% (to 2.07) and style loss by 57.4% (to 0.86) after 4000 epochs--achieving 1.39 s inference--and yields further improvements (content 2.03; style 0.75) with minimal speed penalty (1.40 s) when using RL. These results demonstrate real-time, high-quality artistic rendering, with broad applications in media and design.

---

### ActiNet: An Open-Source Tool for Activity Intensity Classification of Wrist-Worn Accelerometry Using Self-Supervised Deep Learning

Authors: Aidan Acquah, Shing Chan, Aiden Doherty
Published: 2025-10-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.01712v2

The use of accurate and reliable open-source human activity recognition (HAR) models on passively collected wrist-accelerometer data is essential in large-scale epidemiological studies that investigate the association between physical activity and health outcomes. While self-supervised learning has generated considerable excitement in improving HAR, the extent to which these models, coupled with hidden Markov models (HMMs), would make a tangible improvement to classification performance and the effect this may have on the predicted daily activity intensity compositions is unknown. Using up to 24 hours of wrist-worn accelerometer data from 151 CAPTURE-24 participants (aged 18 - 91, mean age 42, 66% female), we trained the ActiNet model, consisting HARNet, a self-supervised, 18-layer, modified ResNet-V2 model, followed by hidden Markov model (HMM) smoothing to classify labels of activity intensity. The performance of this model, evaluated using 5-fold stratified group cross-validation, was then compared to a baseline random forest (RF) + HMM, established in existing literature. Differences in performance and classification outputs were compared with different subgroups of age and sex within the CAPTURE-24 population. The ActiNet model was able to distinguish labels of activity intensity with a mean macro F1 score of 0.82 and a mean Cohen's kappa score of 0.86. This exceeded the performance of the RF + HMM, trained and validated on the same dataset, with mean scores of 0.76 and 0.80, respectively. The improvements in performance were consistent across subgroups of age and sex. These findings encourage the use of ActiNet for the extraction of activity intensity labels from wrist-accelerometer data in future epidemiological studies.

---

### Contrastive Representation Regularization for Vision-Language-Action Models

Authors: Taeyoung Kim, Jimin Lee, Myungkyu Koo, Dongyoung Kim, Kyungmin Lee, Changyeon Kim, Younggyo Seo, Jinwoo Shin
Published: 2025-10-02
Categories: cs.RO, cs.LG
arXiv: https://arxiv.org/abs/2510.01711v4

Vision-Language-Action (VLA) models have shown strong capabilities in robot manipulation by leveraging rich representations from pre-trained Vision-Language Models (VLMs). However, their representations arguably remain suboptimal, lacking sensitivity to robotic signals such as control actions and proprioceptive information. To address the issue, we introduce Robot State-aware Contrastive Loss (RS-CL), a simple and effective representation regularization for VLA models, designed to bridge the gap between VLM representations and robotic signals. In particular, RS-CL aligns the representations more closely with the robot's proprioceptive states by using relative distances between the states as soft supervision. Complementing the original action prediction objective, RS-CL enhances control-relevant representation learning, while being lightweight and fully compatible with standard VLA training pipelines. Our empirical results demonstrate that RS-CL substantially improves the performance of state-of-the-art VLA models; it pushes the prior art to 69.7% achieving the state-of-the-art performance on the RoboCasa-Kitchen benchmark, and boosts success rates from 45.0% to 58.3% on challenging real-robot manipulation tasks.

---

### PolySim: Bridging the Sim-to-Real Gap for Humanoid Control via Multi-Simulator Dynamics Randomization

Authors: Zixing Lei, Zibo Zhou, Sheng Yin, Yueru Chen, Qingyao Xu, Weixin Li, Yunhong Wang, Bowei Tang, Wei Jing, Siheng Chen
Published: 2025-10-02
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2510.01708v3

Humanoid whole-body control (WBC) policies trained in simulation often suffer from the sim-to-real gap, which fundamentally arises from simulator inductive bias, the inherent assumptions and limitations of any single simulator. These biases lead to nontrivial discrepancies both across simulators and between simulation and the real world. To mitigate the effect of simulator inductive bias, the key idea is to train policies jointly across multiple simulators, encouraging the learned controller to capture dynamics that generalize beyond any single simulator's assumptions. We thus introduce PolySim, a WBC training platform that integrates multiple heterogeneous simulators. PolySim can launch parallel environments from different engines simultaneously within a single training run, thereby realizing dynamics-level domain randomization. Theoretically, we show that PolySim yields a tighter upper bound on simulator inductive bias than single-simulator training. In experiments, PolySim substantially reduces motion-tracking error in sim-to-sim evaluations; for example, on MuJoCo, it improves execution success by 52.8 over an IsaacSim baseline. PolySim further enables zero-shot deployment on a real Unitree G1 without additional fine-tuning, showing effective transfer from simulation to the real world. We will release the PolySim code upon acceptance of this work.

---

### Representational Alignment Across Model Layers and Brain Regions with Multi-Level Optimal Transport

Authors: Shaan Shah, Meenakshi Khosla
Published: 2025-10-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.01706v2

Standard representational similarity methods align each layer of a network to its best match in another independently, producing asymmetric results, lacking a global alignment score, and struggling with networks of different depths. These limitations arise from ignoring global activation structure and restricting mappings to rigid one-to-one layer correspondences. We propose Multi-Level Optimal Transport (MOT), a unified framework that jointly infers soft, globally consistent layer-to-layer couplings and neuron-level transport plans. MOT allows source neurons to distribute mass across multiple target layers while minimizing total transport cost under marginal constraints. This yields both a single alignment score for the entire network comparison and a soft transport plan that naturally handles depth mismatches through mass distribution. We evaluate MOT on vision models, large language models, and human visual cortex recordings. Across all domains, MOT matches or surpasses standard pairwise matching in alignment quality. Moreover, it reveals smooth, fine-grained hierarchical correspondences: early layers map to early layers, deeper layers maintain relative positions, and depth mismatches are resolved by distributing representations across multiple layers. These structured patterns emerge naturally from global optimization without being imposed, yet are absent in greedy layer-wise methods. MOT thus enables richer, more interpretable comparisons between representations, particularly when networks differ in architecture or depth. We further extend our method to a three-level MOT framework, providing a proof-of-concept alignment of two networks across their training trajectories and demonstrating that MOT uncovers checkpoint-wise correspondences missed by greedy layer-wise matching.

---

### Holistic Order Prediction in Natural Scenes

Authors: Pierre Musacchio, Hyunmin Lee, Jaesik Park
Published: 2025-10-02
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.01704v2

Even in controlled settings, understanding instance-wise geometries is a challenging task for a wide range of visual models. Although specialized systems exist, modern arts rely on expensive input formats (category labels, binary segmentation masks) and inference costs (a quadratic amount of forward passes). We mitigate these limitations by proposing InstaFormer, a network capable of holistic order prediction. That is, solely given an input RGB image, InstaFormer returns the full occlusion and depth orderings for all the instances in the scene in a single forward pass. At its core, InstaFormer relies on interactions between object queries and latent mask descriptors that semantically represent the same objects while carrying complementary information. We comprehensively benchmark and ablate our approach to highlight its effectiveness. Our code and models are open-source and available at this URL: https://github.com/SNU-VGILab/InstaOrder.

---

### VaPR -- Vision-language Preference alignment for Reasoning

Authors: Rohan Wadhawan, Fabrice Y Harel-Canada, Zi-Yi Dou, Suhaila Shakiah, Robinson Piramuthu, Nanyun Peng
Published: 2025-10-02
Categories: cs.AI, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.01700v1

Preference finetuning methods like Direct Preference Optimization (DPO) with AI-generated feedback have shown promise in aligning Large Vision-Language Models (LVLMs) with human preferences. However, existing techniques overlook the prevalence of noise in synthetic preference annotations in the form of stylistic and length biases. To this end, we introduce a hard-negative response generation framework based on LLM-guided response editing, that produces rejected responses with targeted errors, maintaining stylistic and length similarity to the accepted ones. Using this framework, we develop the VaPR dataset, comprising 30K high-quality samples, to finetune three LVLM families: LLaVA-V1.5, Qwen2VL & Qwen2.5VL (2B-13B sizes). Our VaPR models deliver significant performance improvements across ten benchmarks, achieving average gains of 6.5% (LLaVA), 4.0% (Qwen2VL), and 1.5% (Qwen2.5VL), with notable improvements on reasoning tasks. A scaling analysis shows that performance consistently improves with data size, with LLaVA models benefiting even at smaller scales. Moreover, VaPR reduces the tendency to answer "Yes" in binary questions - addressing a common failure mode in LVLMs like LLaVA. Lastly, we show that the framework generalizes to open-source LLMs as editors, with models trained on VaPR-OS achieving ~99% of the performance of models trained on \name, which is synthesized using GPT-4o. Our data, models, and code can be found on the project page https://vap-r.github.io

---

### PASTA: A Unified Framework for Offline Assortment Learning

Authors: Juncheng Dong, Weibin Mo, Zhengling Qi, Cong Shi, Ethan X. Fang, Vahid Tarokh
Published: 2025-10-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.01693v1

We study a broad class of assortment optimization problems in an offline and data-driven setting. In such problems, a firm lacks prior knowledge of the underlying choice model, and aims to determine an optimal assortment based on historical customer choice data. The combinatorial nature of assortment optimization often results in insufficient data coverage, posing a significant challenge in designing provably effective solutions. To address this, we introduce a novel Pessimistic Assortment Optimization (PASTA) framework that leverages the principle of pessimism to achieve optimal expected revenue under general choice models. Notably, PASTA requires only that the offline data distribution contains an optimal assortment, rather than providing the full coverage of all feasible assortments. Theoretically, we establish the first finite-sample regret bounds for offline assortment optimization across several widely used choice models, including the multinomial logit and nested logit models. Additionally, we derive a minimax regret lower bound, proving that PASTA is minimax optimal in terms of sample and model complexity. Numerical experiments further demonstrate that our method outperforms existing baseline approaches.

---

### MedQ-Bench: Evaluating and Exploring Medical Image Quality Assessment Abilities in MLLMs

Authors: Jiyao Liu, Jinjie Wei, Wanying Qu, Chenglong Ma, Junzhi Ning, Yunheng Li, Ying Chen, Xinzhe Luo, Pengcheng Chen, Xin Gao, Ming Hu, Huihui Xu et al.
Published: 2025-10-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.01691v1

Medical Image Quality Assessment (IQA) serves as the first-mile safety gate for clinical AI, yet existing approaches remain constrained by scalar, score-based metrics and fail to reflect the descriptive, human-like reasoning process central to expert evaluation. To address this gap, we introduce MedQ-Bench, a comprehensive benchmark that establishes a perception-reasoning paradigm for language-based evaluation of medical image quality with Multi-modal Large Language Models (MLLMs). MedQ-Bench defines two complementary tasks: (1) MedQ-Perception, which probes low-level perceptual capability via human-curated questions on fundamental visual attributes; and (2) MedQ-Reasoning, encompassing both no-reference and comparison reasoning tasks, aligning model evaluation with human-like reasoning on image quality. The benchmark spans five imaging modalities and over forty quality attributes, totaling 2,600 perceptual queries and 708 reasoning assessments, covering diverse image sources including authentic clinical acquisitions, images with simulated degradations via physics-based reconstructions, and AI-generated images. To evaluate reasoning ability, we propose a multi-dimensional judging protocol that assesses model outputs along four complementary axes. We further conduct rigorous human-AI alignment validation by comparing LLM-based judgement with radiologists. Our evaluation of 14 state-of-the-art MLLMs demonstrates that models exhibit preliminary but unstable perceptual and reasoning skills, with insufficient accuracy for reliable clinical use. These findings highlight the need for targeted optimization of MLLMs in medical IQA. We hope that MedQ-Bench will catalyze further exploration and unlock the untapped potential of MLLMs for medical image quality evaluation.

---

### Format Inertia: A Failure Mechanism of LLMs in Medical Pre-Consultation

Authors: Seungseop Lim, Gibaeg Kim, Wooseok Han, Jean Seo, Hyunkyung Lee, Jaehyo Yoo, Eunho Yang
Published: 2025-10-02
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.01688v2

Recent advances in Large Language Models (LLMs) have brought significant improvements to various service domains, including chatbots and medical pre-consultation applications. In the healthcare domain, the most common approach for adapting LLMs to multi-turn dialogue generation is Supervised Fine-Tuning (SFT). However, datasets for SFT in tasks like medical pre-consultation typically exhibit a skewed turn-count distribution. Training on such data induces a novel failure mechanism we term Format Inertia, where models tend to generate repetitive, format-correct, but diagnostically uninformative questions in long medical dialogues. To mitigate this observed failure mechanism, we adopt a simple, data-centric method that rebalances the turn-count distribution of the training dataset. Experimental results show that our approach substantially alleviates Format Inertia in medical pre-consultation.

---

### Improving AGI Evaluation: A Data Science Perspective

Authors: John Hawkins
Published: 2025-10-02
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.01687v1

Evaluation of potential AGI systems and methods is difficult due to the breadth of the engineering goal. We have no methods for perfect evaluation of the end state, and instead measure performance on small tests designed to provide directional indication that we are approaching AGI. In this work we argue that AGI evaluation methods have been dominated by a design philosophy that uses our intuitions of what intelligence is to create synthetic tasks, that have performed poorly in the history of AI. Instead we argue for an alternative design philosophy focused on evaluating robust task execution that seeks to demonstrate AGI through competence. This perspective is developed from common practices in data science that are used to show that a system can be reliably deployed. We provide practical examples of what this would mean for AGI evaluation.

---

### FreeViS: Training-free Video Stylization with Inconsistent References

Authors: Jiacong Xu, Yiqun Mei, Ke Zhang, Vishal M. Patel
Published: 2025-10-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.01686v1

Video stylization plays a key role in content creation, but it remains a challenging problem. Naïvely applying image stylization frame-by-frame hurts temporal consistency and reduces style richness. Alternatively, training a dedicated video stylization model typically requires paired video data and is computationally expensive. In this paper, we propose FreeViS, a training-free video stylization framework that generates stylized videos with rich style details and strong temporal coherence. Our method integrates multiple stylized references to a pretrained image-to-video (I2V) model, effectively mitigating the propagation errors observed in prior works, without introducing flickers and stutters. In addition, it leverages high-frequency compensation to constrain the content layout and motion, together with flow-based motion cues to preserve style textures in low-saliency regions. Through extensive evaluations, FreeViS delivers higher stylization fidelity and superior temporal consistency, outperforming recent baselines and achieving strong human preference. Our training-free pipeline offers a practical and economic solution for high-quality, temporally coherent video stylization. The code and videos can be accessed via https://xujiacong.github.io/FreeViS/

---

### How Do Language Models Compose Functions?

Authors: Apoorv Khandelwal, Ellie Pavlick
Published: 2025-10-02
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.01685v2

While large language models (LLMs) appear to be increasingly capable of solving compositional tasks, it is an open question whether they do so using compositional mechanisms. In this work, we investigate how feedforward LLMs solve two-hop factual recall tasks, which can be expressed compositionally as $g(f(x))$. We first confirm that modern LLMs continue to suffer from the "compositionality gap", i.e. their ability to compute both $z = f(x)$ and $y = g(z)$ does not entail their ability to compute the composition $y = g(f(x))$. We then decode residual stream representations and identify two processing mechanisms: one which solves tasks $\textit{compositionally}$, computing $f(x)$ along the way to $g(f(x))$, and one which solves them $\textit{directly}$, without any detectable signature of the intermediate variable $f(x)$. Finally, we find that embedding space geometry is strongly related to which mechanism is employed, where the idiomatic mechanism is dominant when tasks are represented by translations from $x$ to $g(f(x))$ in the embedding spaces. We fully release our data and code at: https://github.com/apoorvkh/composing-functions.

---

### Uncovering Overconfident Failures in CXR Models via Augmentation-Sensitivity Risk Scoring

Authors: Han-Jay Shu, Wei-Ning Chiu, Shun-Ting Chang, Meng-Ping Huang, Takeshi Tohyama, Ahram Han, Po-Chih Kuo
Published: 2025-10-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.01683v1

Deep learning models achieve strong performance in chest radiograph (CXR) interpretation, yet fairness and reliability concerns persist. Models often show uneven accuracy across patient subgroups, leading to hidden failures not reflected in aggregate metrics. Existing error detection approaches -- based on confidence calibration or out-of-distribution (OOD) detection -- struggle with subtle within-distribution errors, while image- and representation-level consistency-based methods remain underexplored in medical imaging. We propose an augmentation-sensitivity risk scoring (ASRS) framework to identify error-prone CXR cases. ASRS applies clinically plausible rotations ($\pm 15^\circ$/$\pm 30^\circ$) and measures embedding shifts with the RAD-DINO encoder. Sensitivity scores stratify samples into stability quartiles, where highly sensitive cases show substantially lower recall ($-0.2$ to $-0.3$) despite high AUROC and confidence. ASRS provides a label-free means for selective prediction and clinician review, improving fairness and safety in medical AI.

---

### Look Less, Reason More: Rollout-Guided Adaptive Pixel-Space Reasoning

Authors: Xuchen Li, Xuzhao Li, Jiahui Gao, Renjie Pi, Shiyu Hu, Wentao Zhang
Published: 2025-10-02
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.01681v1

Vision-Language Models (VLMs) excel at many multimodal tasks, yet they frequently struggle with tasks requiring precise understanding and handling of fine-grained visual elements. This is mainly due to information loss during image encoding or insufficient attention to critical regions. Recent work has shown promise by incorporating pixel-level visual information into the reasoning process, enabling VLMs to access high-resolution visual details during their thought process. However, this pixel-level information is often overused, leading to inefficiency and distraction from irrelevant visual details. To address these challenges, we propose the first framework for adaptive pixel reasoning that dynamically determines necessary pixel-level operations based on the input query. Specifically, we first apply operation-aware supervised fine-tuning to establish baseline competence in textual reasoning and visual operations, then design a novel rollout-guided reinforcement learning framework relying on feedback of the model's own responses, which enables the VLM to determine when pixel operations should be invoked based on query difficulty. Experiments on extensive multimodal reasoning benchmarks show that our model achieves superior performance while significantly reducing unnecessary visual operations. Impressively, our model achieves 73.4\% accuracy on HR-Bench 4K while maintaining a tool usage ratio of only 20.1\%, improving accuracy and simultaneously reducing tool usage by 66.5\% compared to the previous methods.

---

### An Efficient Deep Template Matching and In-Plane Pose Estimation Method via Template-Aware Dynamic Convolution

Authors: Ke Jia, Ji Zhou, Hanxin Li, Zhigan Zhou, Haojie Chu, Xiaojie Li
Published: 2025-10-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.01678v1

In industrial inspection and component alignment tasks, template matching requires efficient estimation of a target's position and geometric state (rotation and scaling) under complex backgrounds to support precise downstream operations. Traditional methods rely on exhaustive enumeration of angles and scales, leading to low efficiency under compound transformations. Meanwhile, most deep learning-based approaches only estimate similarity scores without explicitly modeling geometric pose, making them inadequate for real-world deployment. To overcome these limitations, we propose a lightweight end-to-end framework that reformulates template matching as joint localization and geometric regression, outputting the center coordinates, rotation angle, and independent horizontal and vertical scales. A Template-Aware Dynamic Convolution Module (TDCM) dynamically injects template features at inference to guide generalizable matching. The compact network integrates depthwise separable convolutions and pixel shuffle for efficient matching. To enable geometric-annotation-free training, we introduce a rotation-shear-based augmentation strategy with structure-aware pseudo labels. A lightweight refinement module further improves angle and scale precision via local optimization. Experiments show our 3.07M model achieves high precision and 14ms inference under compound transformations. It also demonstrates strong robustness in small-template and multi-object scenarios, making it highly suitable for deployment in real-time industrial applications. The code is available at:https://github.com/ZhouJ6610/PoseMatch-TDCM.

---

### Beyond Simple Fusion: Adaptive Gated Fusion for Robust Multimodal Sentiment Analysis

Authors: Han Wu, Yanming Sun, Yunhe Yang, Derek F. Wong
Published: 2025-10-02
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2510.01677v1

Multimodal sentiment analysis (MSA) leverages information fusion from diverse modalities (e.g., text, audio, visual) to enhance sentiment prediction. However, simple fusion techniques often fail to account for variations in modality quality, such as those that are noisy, missing, or semantically conflicting. This oversight leads to suboptimal performance, especially in discerning subtle emotional nuances. To mitigate this limitation, we introduce a simple yet efficient \textbf{A}daptive \textbf{G}ated \textbf{F}usion \textbf{N}etwork that adaptively adjusts feature weights via a dual gate fusion mechanism based on information entropy and modality importance. This mechanism mitigates the influence of noisy modalities and prioritizes informative cues following unimodal encoding and cross-modal interaction. Experiments on CMU-MOSI and CMU-MOSEI show that AGFN significantly outperforms strong baselines in accuracy, effectively discerning subtle emotions with robust performance. Visualization analysis of feature representations demonstrates that AGFN enhances generalization by learning from a broader feature distribution, achieved by reducing the correlation between feature location and prediction error, thereby decreasing reliance on specific locations and creating more robust multimodal feature representations.

---

### Evaluating the Robustness of a Production Malware Detection System to Transferable Adversarial Attacks

Authors: Milad Nasr, Yanick Fratantonio, Luca Invernizzi, Ange Albertini, Loua Farah, Alex Petit-Bianco, Andreas Terzis, Kurt Thomas, Elie Bursztein, Nicholas Carlini
Published: 2025-10-02
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2510.01676v1

As deep learning models become widely deployed as components within larger production systems, their individual shortcomings can create system-level vulnerabilities with real-world impact. This paper studies how adversarial attacks targeting an ML component can degrade or bypass an entire production-grade malware detection system, performing a case study analysis of Gmail's pipeline where file-type identification relies on a ML model. The malware detection pipeline in use by Gmail contains a machine learning model that routes each potential malware sample to a specialized malware classifier to improve accuracy and performance. This model, called Magika, has been open sourced. By designing adversarial examples that fool Magika, we can cause the production malware service to incorrectly route malware to an unsuitable malware detector thereby increasing our chance of evading detection. Specifically, by changing just 13 bytes of a malware sample, we can successfully evade Magika in 90% of cases and thereby allow us to send malware files over Gmail. We then turn our attention to defenses, and develop an approach to mitigate the severity of these types of attacks. For our defended production model, a highly resourced adversary requires 50 bytes to achieve just a 20% attack success rate. We implement this defense, and, thanks to a collaboration with Google engineers, it has already been deployed in production for the Gmail classifier.

---

### FOR-Prompting: From Objection to Revision via an Asymmetric Prompting Protocol

Authors: He Zhang, Anzhou Zhang, Jian Dai
Published: 2025-10-02
Categories: cs.CL, cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2510.01674v2

Reasoning protocols such as Chain of Thought (CoT) and Tree of Thought (ToT) organize internal deliberation but lack an explicit mechanism for external questioning that elicits self-revision. We present FOR-Prompting (From Objection to Revision Prompting), an asymmetric protocol where a Defender proposes an answer, an Debater (Questioner) raises question-style objections with no direct fixes, and a Host optionally synthesizes the final output. Across GSM8K, FOR-Prompting matches the accuracy of CoT and consistently improves over single-prompting when evaluated under identical model backbones. On small-scale open-source models (e.g., LLaMA-3.2-1B), FOR-Prompting yields substantial gains over direct prompting and performs comparably to lightweight reasoning baselines, highlighting its promise for low-resource and on-device settings. Cross-model role-swapping further shows that performance is primarily determined by the Defender, enabling small models to act effectively as Questioners. Beyond structured math tasks, FOR-Prompting supports refinement in open-ended and multi-stage tasks: qualitative analysis shows improved exploration, coverage, and specificity, and a blind study of human preferences found that participants preferred FOR-Prompting outputs over strong LLM baselines in an itinerary-planning scenario. The protocol is model-agnostic and operates purely through role-structured prompting, requiring no training, access to model internals, or symmetrically strong agents. FOR-Prompting therefore enables scalable study of objection-driven reasoning and offers a practical mechanism for automated iterative refinement across both hosted and local LLMs.

---

### A Locally Executable AI System for Improving Preoperative Patient Communication: A Multi-Domain Clinical Evaluation

Authors: Motoki Sato, Yuki Matsushita, Hidekazu Takahashi, Tomoaki Kakazu, Sou Nagata, Mizuho Ohnuma, Atsushi Yoshikawa, Masayuki Yamamura
Published: 2025-10-02
Categories: cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2510.01671v1

Patients awaiting invasive procedures often have unanswered pre-procedural questions; however, time-pressured workflows and privacy constraints limit personalized counseling. We present LENOHA (Low Energy, No Hallucination, Leave No One Behind Architecture), a safety-first, local-first system that routes inputs with a high-precision sentence-transformer classifier and returns verbatim answers from a clinician-curated FAQ for clinical queries, eliminating free-text generation in the clinical path. We evaluated two domains (tooth extraction and gastroscopy) using expert-reviewed validation sets (n=400/domain) for thresholding and independent test sets (n=200/domain). Among the four encoders, E5-large-instruct (560M) achieved an overall accuracy of 0.983 (95% CI 0.964-0.991), AUC 0.996, and seven total errors, which were statistically indistinguishable from GPT-4o on this task; Gemini made no errors on this test set. Energy logging shows that the non-generative clinical path consumes ~1.0 mWh per input versus ~168 mWh per small-talk reply from a local 8B SLM, a ~170x difference, while maintaining ~0.10 s latency on a single on-prem GPU. These results indicate that near-frontier discrimination and generation-induced errors are structurally avoided in the clinical path by returning vetted FAQ answers verbatim, supporting privacy, sustainability, and equitable deployment in bandwidth-limited environments.

---

### Just Do It!? Computer-Use Agents Exhibit Blind Goal-Directedness

Authors: Erfan Shayegani, Keegan Hines, Yue Dong, Nael Abu-Ghazaleh, Roman Lutz, Spencer Whitehead, Vidhisha Balachandran, Besmira Nushi, Vibhav Vineet
Published: 2025-10-02
Categories: cs.AI, cs.CL, cs.CR, cs.CY, cs.LG
arXiv: https://arxiv.org/abs/2510.01670v1

Computer-Use Agents (CUAs) are an increasingly deployed class of agents that take actions on GUIs to accomplish user goals. In this paper, we show that CUAs consistently exhibit Blind Goal-Directedness (BGD): a bias to pursue goals regardless of feasibility, safety, reliability, or context. We characterize three prevalent patterns of BGD: (i) lack of contextual reasoning, (ii) assumptions and decisions under ambiguity, and (iii) contradictory or infeasible goals. We develop BLIND-ACT, a benchmark of 90 tasks capturing these three patterns. Built on OSWorld, BLIND-ACT provides realistic environments and employs LLM-based judges to evaluate agent behavior, achieving 93.75% agreement with human annotations. We use BLIND-ACT to evaluate nine frontier models, including Claude Sonnet and Opus 4, Computer-Use-Preview, and GPT-5, observing high average BGD rates (80.8%) across them. We show that BGD exposes subtle risks that arise even when inputs are not directly harmful. While prompting-based interventions lower BGD levels, substantial risk persists, highlighting the need for stronger training- or inference-time interventions. Qualitative analysis reveals observed failure modes: execution-first bias (focusing on how to act over whether to act), thought-action disconnect (execution diverging from reasoning), and request-primacy (justifying actions due to user request). Identifying BGD and introducing BLIND-ACT establishes a foundation for future research on studying and mitigating this fundamental risk and ensuring safe CUA deployment.

---

### UniVerse: Unleashing the Scene Prior of Video Diffusion Models for Robust Radiance Field Reconstruction

Authors: Jin Cao, Hongrui Wu, Ziyong Feng, Hujun Bao, Xiaowei Zhou, Sida Peng
Published: 2025-10-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.01669v2

This paper tackles the challenge of robust reconstruction, i.e., the task of reconstructing a 3D scene from a set of inconsistent multi-view images. Some recent works have attempted to simultaneously remove image inconsistencies and perform reconstruction by integrating image degradation modeling into neural 3D scene representations. However, these methods rely heavily on dense observations for robustly optimizing model parameters. To address this issue, we propose to decouple robust reconstruction into two subtasks: restoration and reconstruction, which naturally simplifies the optimization process. To this end, we introduce UniVerse, a unified framework for robust reconstruction based on a video diffusion model. Specifically, UniVerse first converts inconsistent images into initial videos, then uses a specially designed video diffusion model to restore them into consistent images, and finally reconstructs the 3D scenes from these restored images. Compared with case-by-case per-view degradation modeling, the diffusion model learns a general scene prior from large-scale data, making it applicable to diverse image inconsistencies. Extensive experiments on both synthetic and real-world datasets demonstrate the strong generalization capability and superior performance of our method in robust reconstruction. Moreover, UniVerse can control the style of the reconstructed 3D scene. Project page: https://jin-cao-tma.github.io/UniVerse.github.io/

---

### Median2Median: Zero-shot Suppression of Structured Noise in Images

Authors: Jianxu Wang, Ge Wang
Published: 2025-10-02
Categories: eess.IV, cs.CV, q-bio.QM, stat.ML
arXiv: https://arxiv.org/abs/2510.01666v1

Image denoising is a fundamental problem in computer vision and medical imaging. However, real-world images are often degraded by structured noise with strong anisotropic correlations that existing methods struggle to remove. Most data-driven approaches rely on large datasets with high-quality labels and still suffer from limited generalizability, whereas existing zero-shot methods avoid this limitation but remain effective only for independent and identically distributed (i.i.d.) noise. To address this gap, we propose Median2Median (M2M), a zero-shot denoising framework designed for structured noise. M2M introduces a novel sampling strategy that generates pseudo-independent sub-image pairs from a single noisy input. This strategy leverages directional interpolation and generalized median filtering to adaptively exclude values distorted by structured artifacts. To further enlarge the effective sampling space and eliminate systematic bias, a randomized assignment strategy is employed, ensuring that the sampled sub-image pairs are suitable for Noise2Noise training. In our realistic simulation studies, M2M performs on par with state-of-the-art zero-shot methods under i.i.d. noise, while consistently outperforming them under correlated noise. These findings establish M2M as an efficient, data-free solution for structured noise suppression and mark the first step toward effective zero-shot denoising beyond the strict i.i.d. assumption.

---

### Non-Rigid Structure-from-Motion via Differential Geometry with Recoverable Conformal Scale

Authors: Yongbo Chen, Yanhao Zhang, Shaifali Parashar, Liang Zhao, Shoudong Huang
Published: 2025-10-02
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2510.01665v1

Non-rigid structure-from-motion (NRSfM), a promising technique for addressing the mapping challenges in monocular visual deformable simultaneous localization and mapping (SLAM), has attracted growing attention. We introduce a novel method, called Con-NRSfM, for NRSfM under conformal deformations, encompassing isometric deformations as a subset. Our approach performs point-wise reconstruction using 2D selected image warps optimized through a graph-based framework. Unlike existing methods that rely on strict assumptions, such as locally planar surfaces or locally linear deformations, and fail to recover the conformal scale, our method eliminates these constraints and accurately computes the local conformal scale. Additionally, our framework decouples constraints on depth and conformal scale, which are inseparable in other approaches, enabling more precise depth estimation. To address the sensitivity of the formulated problem, we employ a parallel separable iterative optimization strategy. Furthermore, a self-supervised learning framework, utilizing an encoder-decoder network, is incorporated to generate dense 3D point clouds with texture. Simulation and experimental results using both synthetic and real datasets demonstrate that our method surpasses existing approaches in terms of reconstruction accuracy and robustness. The code for the proposed method will be made publicly available on the project website: https://sites.google.com/view/con-nrsfm.

---

### GuruAgents: Emulating Wise Investors with Prompt-Guided LLM Agents

Authors: Yejin Kim, Youngbin Lee, Juhyeong Kim, Yongjae Lee
Published: 2025-10-02
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.01664v1

This study demonstrates that GuruAgents, prompt-guided AI agents, can systematically operationalize the strategies of legendary investment gurus. We develop five distinct GuruAgents, each designed to emulate an iconic investor, by encoding their distinct philosophies into LLM prompts that integrate financial tools and a deterministic reasoning pipeline. In a backtest on NASDAQ-100 constituents from Q4 2023 to Q2 2025, the GuruAgents exhibit unique behaviors driven by their prompted personas. The Buffett GuruAgent achieves the highest performance, delivering a 42.2\% CAGR that significantly outperforms benchmarks, while other agents show varied results. These findings confirm that prompt engineering can successfully translate the qualitative philosophies of investment gurus into reproducible, quantitative strategies, highlighting a novel direction for automated systematic investing. The source code and data are available at https://github.com/yejining99/GuruAgents.

---

### Shift-Invariant Attribute Scoring for Kolmogorov-Arnold Networks via Shapley Value

Authors: Wangxuan Fan, Ching Wang, Siqi Li, Nan Liu
Published: 2025-10-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.01663v2

For many real-world applications, understanding feature-outcome relationships is as crucial as achieving high predictive accuracy. While traditional neural networks excel at prediction, their black-box nature obscures underlying functional relationships. Kolmogorov--Arnold Networks (KANs) address this by employing learnable spline-based activation functions on edges, enabling recovery of symbolic representations while maintaining competitive performance. However, KAN's architecture presents unique challenges for network pruning. Conventional magnitude-based methods become unreliable due to sensitivity to input coordinate shifts. We propose \textbf{ShapKAN}, a pruning framework using Shapley value attribution to assess node importance in a shift-invariant manner. Unlike magnitude-based approaches, ShapKAN quantifies each node's actual contribution, ensuring consistent importance rankings regardless of input parameterization. Extensive experiments on synthetic and real-world datasets demonstrate that ShapKAN preserves true node importance while enabling effective network compression. Our approach improves KAN's interpretability advantages, facilitating deployment in resource-constrained environments.

---