# Research Papers — 2025-10 · bundle page 137 of 217

> Full-text markdown of papers #6801–6850 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/137
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/136.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/138.md)

### Automatic Speech Recognition in the Modern Era: Architectures, Training, and Evaluation

Authors: Md. Nayeem, Md Shamse Tabrej, Kabbojit Jit Deb, Shaonti Goswami, Md. Azizul Hakim
Published: 2025-10-11
Categories: eess.AS, cs.AI, cs.SD
arXiv: https://arxiv.org/abs/2510.12827v1

Automatic Speech Recognition (ASR) has undergone a profound transformation over the past decade, driven by advances in deep learning. This survey provides a comprehensive overview of the modern era of ASR, charting its evolution from traditional hybrid systems, such as Gaussian Mixture Model-Hidden Markov Models (GMM-HMMs) and Deep Neural Network-HMMs (DNN-HMMs), to the now-dominant end-to-end neural architectures. We systematically review the foundational end-to-end paradigms: Connectionist Temporal Classification (CTC), attention-based encoder-decoder models, and the Recurrent Neural Network Transducer (RNN-T), which established the groundwork for fully integrated speech-to-text systems. We then detail the subsequent architectural shift towards Transformer and Conformer models, which leverage self-attention to capture long-range dependencies with high computational efficiency. A central theme of this survey is the parallel revolution in training paradigms. We examine the progression from fully supervised learning, augmented by techniques like SpecAugment, to the rise of self-supervised learning (SSL) with foundation models such as wav2vec 2.0, which drastically reduce the reliance on transcribed data. Furthermore, we analyze the impact of largescale, weakly supervised models like Whisper, which achieve unprecedented robustness through massive data diversity. The paper also covers essential ecosystem components, including key datasets and benchmarks (e.g., LibriSpeech, Switchboard, CHiME), standard evaluation metrics (e.g., Word Error Rate), and critical considerations for real-world deployment, such as streaming inference, on-device efficiency, and the ethical imperatives of fairness and robustness. We conclude by outlining open challenges and future research directions.

---

### Scheming Ability in LLM-to-LLM Strategic Interactions

Authors: Thao Pham
Published: 2025-10-11
Categories: cs.CL, cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2510.12826v2

As large language model (LLM) agents are deployed autonomously in diverse contexts, evaluating their capacity for strategic deception becomes crucial. While recent research has examined how AI systems scheme against human developers, LLM-to-LLM scheming remains underexplored. We investigate the scheming ability and propensity of frontier LLM agents through two game-theoretic frameworks: a Cheap Talk signaling game and a Peer Evaluation adversarial game. Testing four models (GPT-4o, Gemini-2.5-pro, Claude-3.7-Sonnet, and Llama-3.3-70b), we measure scheming performance with and without explicit prompting while analyzing scheming tactics through chain-of-thought reasoning. When prompted, most models, especially Gemini-2.5-pro and Claude-3.7-Sonnet, achieved near-perfect performance. Critically, models exhibited significant scheming propensity without prompting: all models chose deception over confession in Peer Evaluation (100% rate), while models choosing to scheme in Cheap Talk succeeded at 95-100% rates. These findings highlight the need for robust evaluations using high-stakes game-theoretic scenarios in multi-agent settings.

---

### Evolution of wartime discourse on Telegram: A comparative study of Ukrainian and Russian policymakers' communication before and after Russia's full-scale invasion of Ukraine

Authors: Mykola Makhortykh, Aytalina Kulichkina, Kateryna Maikovska
Published: 2025-10-11
Categories: cs.SI, cs.CL, cs.CY
arXiv: https://arxiv.org/abs/2510.11746v1

This study examines elite-driven political communication on Telegram during the ongoing Russo-Ukrainian war, the first large-scale European war in the social media era. Using a unique dataset of Telegram public posts from Ukrainian and Russian policymakers (2019-2024), we analyze changes in communication volume, thematic content, and actor engagement following Russia's 2022 full-scale invasion. Our findings show a sharp increase in Telegram activity after the invasion, particularly among ruling-party policymakers. Ukrainian policymakers initially focused on war-related topics, but this emphasis declined over time In contrast, Russian policymakers largely avoided war-related discussions, instead emphasizing unrelated topics, such as Western crises, to distract public attention. We also identify differences in communication strategies between large and small parties, as well as individual policymakers. Our findings shed light on how policymakers adapt to wartime communication challenges and offer critical insights into the dynamics of online political discourse during times of war.

---

### Think as a Doctor: An Interpretable AI Approach for ICU Mortality Prediction

Authors: Qingwen Li, Xiaohang Zhao, Xiao Han, Hailiang Huang, Lanjuan Liu
Published: 2025-10-11
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.11745v1

Intensive Care Unit (ICU) mortality prediction, which estimates a patient's mortality status at discharge using EHRs collected early in an ICU admission, is vital in critical care. For this task, predictive accuracy alone is insufficient; interpretability is equally essential for building clinical trust and meeting regulatory standards, a topic that has attracted significant attention in information system research. Accordingly, an ideal solution should enable intrinsic interpretability and align its reasoning with three key elements of the ICU decision-making practices: clinical course identification, demographic heterogeneity, and prognostication awareness. However, conventional approaches largely focus on demographic heterogeneity, overlooking clinical course identification and prognostication awareness. Recent prototype learning methods address clinical course identification, yet the integration of the other elements into such frameworks remains underexplored. To address these gaps, we propose ProtoDoctor, a novel ICU mortality prediction framework that delivers intrinsic interpretability while integrating all three elements of the ICU decision-making practices into its reasoning process. Methodologically, ProtoDoctor features two key innovations: the Prognostic Clinical Course Identification module and the Demographic Heterogeneity Recognition module. The former enables the identification of clinical courses via prototype learning and achieves prognostication awareness using a novel regularization mechanism. The latter models demographic heterogeneity through cohort-specific prototypes and risk adjustments. Extensive empirical evaluations demonstrate that ProtoDoctor outperforms state-of-the-art baselines in predictive accuracy. Human evaluations further confirm that its interpretations are more clinically meaningful, trustworthy, and applicable in ICU practice.

---

### Quantum Kernel Methods: Convergence Theory, Separation Bounds and Applications to Marketing Analytics

Authors: Laura Sáez-Ortuño, Santiago Forgas-Coll, Massimiliano Ferrara
Published: 2025-10-11
Categories: quant-ph, cs.LG
arXiv: https://arxiv.org/abs/2510.11744v1

This work studies the feasibility of applying quantum kernel methods to a real consumer classification task in the NISQ regime. We present a hybrid pipeline that combines a quantum-kernel Support Vector Machine (Q-SVM) with a quantum feature extraction module (QFE), and benchmark it against classical and quantum baselines in simulation and with limited shallow-depth hardware runs. With fixed hyperparameters, the proposed Q-SVM attains 0.7790 accuracy, 0.7647 precision, 0.8609 recall, 0.8100 F1, and 0.83 ROC AUC, exhibiting higher sensitivity while maintaining competitive precision relative to classical SVM. We interpret these results as an initial indicator and a concrete starting point for NISQ-era workflows and hardware integration, rather than a definitive benchmark. Methodologically, our design aligns with recent work that formalizes quantum-classical separations and verifies resources via XEB-style approaches, motivating shallow yet expressive quantum embeddings to achieve robust separability despite hardware noise constraints.

---

### Vision4PPG: Emergent PPG Analysis Capability of Vision Foundation Models for Vital Signs like Blood Pressure

Authors: Saurabh Kataria, Ayca Ermis, Lovely Yeswanth Panchumarthi, Minxiao Wang, Xiao Hu
Published: 2025-10-11
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.10366v1

Photoplethysmography (PPG) sensor in wearable and clinical devices provides valuable physiological insights in a non-invasive and real-time fashion. Specialized Foundation Models (FM) or repurposed time-series FMs are used to benchmark physiological tasks. Our experiments with fine-tuning FMs reveal that Vision FM (VFM) can also be utilized for this purpose and, in fact, surprisingly leads to state-of-the-art (SOTA) performance on many tasks, notably blood pressure estimation. We leverage VFMs by simply transforming one-dimensional PPG signals into image-like two-dimensional representations, such as the Short-Time Fourier transform (STFT). Using the latest VFMs, such as DINOv3 and SIGLIP-2, we achieve promising performance on other vital signs and blood lab measurement tasks as well. Our proposal, Vision4PPG, unlocks a new class of FMs to achieve SOTA performance with notable generalization to other 2D input representations, including STFT phase and recurrence plots. Our work improves upon prior investigations of vision models for PPG by conducting a comprehensive study, comparing them to state-of-the-art time-series FMs, and demonstrating the general PPG processing ability by reporting results on six additional tasks. Thus, we provide clinician-scientists with a new set of powerful tools that is also computationally efficient, thanks to Parameter-Efficient Fine-Tuning (PEFT) techniques.

---

### PointMAC: Meta-Learned Adaptation for Robust Test-Time Point Cloud Completion

Authors: Linlian Jiang, Rui Ma, Li Gu, Ziqiang Wang, Xinxin Zuo, Yang Wang
Published: 2025-10-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.10365v1

Point cloud completion is essential for robust 3D perception in safety-critical applications such as robotics and augmented reality. However, existing models perform static inference and rely heavily on inductive biases learned during training, limiting their ability to adapt to novel structural patterns and sensor-induced distortions at test time. To address this limitation, we propose PointMAC, a meta-learned framework for robust test-time adaptation in point cloud completion. It enables sample-specific refinement without requiring additional supervision. Our method optimizes the completion model under two self-supervised auxiliary objectives that simulate structural and sensor-level incompleteness. A meta-auxiliary learning strategy based on Model-Agnostic Meta-Learning (MAML) ensures that adaptation driven by auxiliary objectives is consistently aligned with the primary completion task. During inference, we adapt the shared encoder on-the-fly by optimizing auxiliary losses, with the decoder kept fixed. To further stabilize adaptation, we introduce Adaptive $λ$-Calibration, a meta-learned mechanism for balancing gradients between primary and auxiliary objectives. Extensive experiments on synthetic, simulated, and real-world datasets demonstrate that PointMAC achieves state-of-the-art results by refining each sample individually to produce high-quality completions. To the best of our knowledge, this is the first work to apply meta-auxiliary test-time adaptation to point cloud completion.

---

### Transformer Model Detects Antidepressant Use From a Single Night of Sleep, Unlocking an Adherence Biomarker

Authors: Ali Mirzazadeh, Simon Cadavid, Kaiwen Zha, Chao Li, Sultan Alzahrani, Manar Alawajy, Joshua Korzenik, Kreshnik Hoti, Charles Reynolds, David Mischoulon, John Winkelman, Maurizio Fava et al.
Published: 2025-10-11
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.10364v1

Antidepressant nonadherence is pervasive, driving relapse, hospitalization, suicide risk, and billions in avoidable costs. Clinicians need tools that detect adherence lapses promptly, yet current methods are either invasive (serum assays, neuroimaging) or proxy-based and inaccurate (pill counts, pharmacy refills). We present the first noninvasive biomarker that detects antidepressant intake from a single night of sleep. A transformer-based model analyzes sleep data from a consumer wearable or contactless wireless sensor to infer antidepressant intake, enabling remote, effortless, daily adherence assessment at home. Across six datasets comprising 62,000 nights from >20,000 participants (1,800 antidepressant users), the biomarker achieved AUROC = 0.84, generalized across drug classes, scaled with dose, and remained robust to concomitant psychotropics. Longitudinal monitoring captured real-world initiation, tapering, and lapses. This approach offers objective, scalable adherence surveillance with potential to improve depression care and outcomes.

---

### Generative Modeling of Aerosol State Representations

Authors: Ehsan Saleh, Saba Ghaffari, Jeffrey H. Curtis, Lekha Patel, Peter A. Bosler, Nicole Riemer, Matthew West
Published: 2025-10-11
Categories: physics.ao-ph, cs.LG
arXiv: https://arxiv.org/abs/2510.10361v1

Aerosol-cloud--radiation interactions remain among the most uncertain components of the Earth's climate system, in partdue to the high dimensionality of aerosol state representations and the difficulty of obtaining complete \textit{in situ} measurements. Addressing these challenges requires methods that distill complex aerosol properties into compact yet physically meaningful forms. Generative autoencoder models provide such a pathway. We present a framework for learning deep variational autoencoder (VAE) models of speciated mass and number concentration distributions, which capture detailed aerosol size-composition characteristics. By compressing hundreds of original dimensions into ten latent variables, the approach enables efficient storage and processing while preserving the fidelity of key diagnostics, including cloud condensation nuclei (CCN) spectra, optical scattering and absorption coefficients, and ice nucleation properties. Results show that CCN spectra are easiest to reconstruct accurately, optical properties are moderately difficult, and ice nucleation properties are the most challenging. To improve performance, we introduce a preprocessing optimization strategy that avoids repeated retraining and yields latent representations resilient to high-magnitude Gaussian noise, boosting accuracy for CCN spectra, optical coefficients, and frozen fraction spectra. Finally, we propose a novel realism metric -- based on the sliced Wasserstein distance between generated samples and a held-out test set -- for optimizing the KL divergence weight in VAEs. Together, these contributions enable compact, robust, and physically meaningful representations of aerosol states for large-scale climate applications.

---

### Ortho-Fuse: Orthomosaic Generation for Sparse High-Resolution Crop Health Maps Through Intermediate Optical Flow Estimation

Authors: Rugved Katole, Christopher Stewart
Published: 2025-10-11
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.10360v1

AI-driven crop health mapping systems offer substantial advantages over conventional monitoring approaches through accelerated data acquisition and cost reduction. However, widespread farmer adoption remains constrained by technical limitations in orthomosaic generation from sparse aerial imagery datasets. Traditional photogrammetric reconstruction requires 70-80\% inter-image overlap to establish sufficient feature correspondences for accurate geometric registration. AI-driven systems operating under resource-constrained conditions cannot consistently achieve these overlap thresholds, resulting in degraded reconstruction quality that undermines user confidence in autonomous monitoring technologies. In this paper, we present Ortho-Fuse, an optical flow-based framework that enables the generation of a reliable orthomosaic with reduced overlap requirements. Our approach employs intermediate flow estimation to synthesize transitional imagery between consecutive aerial frames, artificially augmenting feature correspondences for improved geometric reconstruction. Experimental validation demonstrates a 20\% reduction in minimum overlap requirements. We further analyze adoption barriers in precision agriculture to identify pathways for enhanced integration of AI-driven monitoring systems.

---

### Learning to Throw-Flip

Authors: Yang Liu, Bruno Da Costa, Aude Billard
Published: 2025-10-11
Categories: cs.RO, cs.LG
arXiv: https://arxiv.org/abs/2510.10357v1

Dynamic manipulation, such as robot tossing or throwing objects, has recently gained attention as a novel paradigm to speed up logistic operations. However, the focus has predominantly been on the object's landing location, irrespective of its final orientation. In this work, we present a method enabling a robot to accurately "throw-flip" objects to a desired landing pose (position and orientation). Conventionally, objects thrown by revolute robots suffer from parasitic rotation, resulting in highly restricted and uncontrollable landing poses. Our approach is based on two key design choices: first, leveraging the impulse-momentum principle, we design a family of throwing motions that effectively decouple the parasitic rotation, significantly expanding the feasible set of landing poses. Second, we combine a physics-based model of free flight with regression-based learning methods to account for unmodeled effects. Real robot experiments demonstrate that our framework can learn to throw-flip objects to a pose target within ($\pm$5 cm, $\pm$45 degrees) threshold in dozens of trials. Thanks to data assimilation, incorporating projectile dynamics reduces sample complexity by an average of 40% when throw-flipping to unseen poses compared to end-to-end learning methods. Additionally, we show that past knowledge on in-hand object spinning can be effectively reused, accelerating learning by 70% when throwing a new object with a Center of Mass (CoM) shift. A video summarizing the proposed method and the hardware experiments is available at https://youtu.be/txYc9b1oflU.

---

### Prescribed-Basis Coefficient-to-Coefficient Neural Operator for Partial Differential Equations

Authors: Chuqi Chen, Yang Xiang, Weihong Zhang
Published: 2025-10-11
Categories: math.NA, cs.LG
arXiv: https://arxiv.org/abs/2510.10350v3

Operator learning provides a data-driven approach to approximating solution operators of partial differential equations, but its effectiveness depends strongly on how input and output functions are represented. Point-value representations can make the trainable map mesh-dependent and high-dimensional; snapshot-based POD/PCA reductions require aligned data and basis construction, while learned representations introduce additional trainable encoders, decoders, or neural bases. We propose the Fixed-Basis Coefficient-to-Coefficient Network (FB-C2CNet), which learns PDE solution maps in fixed, data-independent approximation spaces using prescribed bases as function encoders and decoders. Input observations are encoded by regularized least-squares projection onto bases such as finite element, random-feature, or radial-basis-function bases. A neural network maps the resulting input coefficients to output coefficients, and the fixed decoder reconstructs the solution at arbitrary target locations. This separation of basis selection from network training avoids neural basis learning and snapshot-based basis extraction, reduces the dimension of the trainable map, and lowers training cost. With suitable prescribed bases, FB-C2CNet also accommodates scattered, non-aligned, and sample-dependent observations. We analyze the stability--bias trade-off of regularized coefficient encoding and the intrinsic projection error determined by the output space. Experiments on elliptic, nonlinear time-dependent, weak-solution, high-dimensional, and inverse Stokes boundary-recovery problems demonstrate competitive accuracy with reduced trainable dimension and training cost, including for high-resolution and irregularly sampled data.

---

### Ordinal Scale Traffic Congestion Classification with Multi-Modal Vision-Language and Motion Analysis

Authors: Yu-Hsuan Lin
Published: 2025-10-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.10342v1

Accurate traffic congestion classification is essential for intelligent transportation systems and real-time urban traffic management. This paper presents a multimodal framework combining open-vocabulary visual-language reasoning (CLIP), object detection (YOLO-World), and motion analysis via MOG2-based background subtraction. The system predicts congestion levels on an ordinal scale from 1 (free flow) to 5 (severe congestion), enabling semantically aligned and temporally consistent classification. To enhance interpretability, we incorporate motion-based confidence weighting and generate annotated visual outputs. Experimental results show the model achieves 76.7 percent accuracy, an F1 score of 0.752, and a Quadratic Weighted Kappa (QWK) of 0.684, significantly outperforming unimodal baselines. These results demonstrate the framework's effectiveness in preserving ordinal structure and leveraging visual-language and motion modalities. Future enhancements include incorporating vehicle sizing and refined density metrics.

---

### Multi-View Graph Learning with Graph-Tuple

Authors: Shiyu Chen, Ningyuan Huang, Soledad Villar
Published: 2025-10-11
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.10341v4

Graph Neural Networks (GNNs) typically scale with the number of graph edges, making them well suited for sparse graphs but less efficient on dense graphs, such as point clouds or molecular interactions. A common remedy is to sparsify the graph via similarity thresholding or distance pruning, but this forces an arbitrary choice of a single interaction scale and discards crucial information from other scales. To overcome this limitation, we introduce a multi-view graph-tuple framework. Instead of a single graph, our graph-tuple framework partitions the graph into disjoint subgraphs, capturing primary local interactions and weaker, long-range connections. We then learn multi-view representations from the graph-tuple via a heterogeneous message-passing architecture inspired by the theory of non-commuting operators, which we formally prove is strictly more expressive and guarantees a lower oracle risk compared to single-graph message-passing models. We instantiate our framework on two scientific domains: molecular property prediction from feature-scarce Coulomb matrices and cosmological parameter inference from geometric point clouds. On both applications, our multi-view graph-tuple models demonstrate better performance than single-graph baselines, highlighting the power and versatility of our multi-view approach.

---

### Measuring What Matters: Connecting AI Ethics Evaluations to System Attributes, Hazards, and Harms

Authors: Shalaleh Rismani, Renee Shelby, Leah Davis, Negar Rostamzadeh, AJung Moon
Published: 2025-10-11
Categories: cs.HC, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.10339v1

Over the past decade, an ecosystem of measures has emerged to evaluate the social and ethical implications of AI systems, largely shaped by high-level ethics principles. These measures are developed and used in fragmented ways, without adequate attention to how they are situated in AI systems. In this paper, we examine how existing measures used in the computing literature map to AI system components, attributes, hazards, and harms. Our analysis draws on a scoping review resulting in nearly 800 measures corresponding to 11 AI ethics principles. We find that most measures focus on four principles - fairness, transparency, privacy, and trust - and primarily assess model or output system components. Few measures account for interactions across system elements, and only a narrow set of hazards is typically considered for each harm type. Many measures are disconnected from where harm is experienced and lack guidance for setting meaningful thresholds. These patterns reveal how current evaluation practices remain fragmented, measuring in pieces rather than capturing how harms emerge across systems. Framing measures with respect to system attributes, hazards, and harms can strengthen regulatory oversight, support actionable practices in industry, and ground future research in systems-level understanding.

---

### Beyond Ethics: How Inclusive Innovation Drives Economic Returns in Medical AI

Authors: Balagopal Unnikrishnan, Ariel Guerra Adames, Amin Adibi, Sameer Peesapati, Rafal Kocielnik, Shira Fischer, Hillary Clinton Kasimbazi, Rodrigo Gameiro, Alina Peluso, Chrystinne Oliveira Fernandes, Maximin Lange, Lovedeep Gondara et al.
Published: 2025-10-11
Categories: cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2510.10338v1

While ethical arguments for fairness in healthcare AI are well-established, the economic and strategic value of inclusive design remains underexplored. This perspective introduces the ``inclusive innovation dividend'' -- the counterintuitive principle that solutions engineered for diverse, constrained use cases generate superior economic returns in broader markets. Drawing from assistive technologies that evolved into billion-dollar mainstream industries, we demonstrate how inclusive healthcare AI development creates business value beyond compliance requirements. We identify four mechanisms through which inclusive innovation drives returns: (1) market expansion via geographic scalability and trust acceleration; (2) risk mitigation through reduced remediation costs and litigation exposure; (3) performance dividends from superior generalization and reduced technical debt, and (4) competitive advantages in talent acquisition and clinical adoption. We present the Healthcare AI Inclusive Innovation Framework (HAIIF), a practical scoring system that enables organizations to evaluate AI investments based on their potential to capture these benefits. HAIIF provides structured guidance for resource allocation, transforming fairness and inclusivity from regulatory checkboxes into sources of strategic differentiation. Our findings suggest that organizations investing incrementally in inclusive design can achieve expanded market reach and sustained competitive advantages, while those treating these considerations as overhead face compounding disadvantages as network effects and data advantages accrue to early movers.

---

### Towards Safe Maneuvering of Double-Ackermann-Steering Robots with a Soft Actor-Critic Framework

Authors: Kohio Deflesselle, Mélodie Daniel, Aly Magassouba, Miguel Aranda, Olivier Ly
Published: 2025-10-11
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2510.10332v2

We present a deep reinforcement learning framework based on Soft Actor-Critic (SAC) for safe and precise maneuvering of double-Ackermann-steering mobile robots (DASMRs). Unlike holonomic or simpler non-holonomic robots such as differential-drive robots, DASMRs face strong kinematic constraints that make classical planners brittle in cluttered environments. Our framework leverages the Hindsight Experience Replay (HER) and the CrossQ overlay to encourage maneuvering efficiency while avoiding obstacles. Simulation results with a heavy four-wheel-steering rover show that the learned policy can robustly reach up to 97% of target positions while avoiding obstacles. Our framework does not rely on handcrafted trajectories or expert demonstrations.

---

### LLM-Friendly Knowledge Representation for Customer Support

Authors: Hanchen Su, Wei Luo, Wei Han, Yu Elaine Liu, Yufeng Wayne Zhang, Cen Mia Zhao, Ying Joy Zhang, Yashar Mehdad
Published: 2025-10-11
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.10331v1

We propose a practical approach by integrating Large Language Models (LLMs) with a framework designed to navigate the complexities of Airbnb customer support operations. In this paper, our methodology employs a novel reformatting technique, the Intent, Context, and Action (ICA) format, which transforms policies and workflows into a structure more comprehensible to LLMs. Additionally, we develop a synthetic data generation strategy to create training data with minimal human intervention, enabling cost-effective fine-tuning of our model. Our internal experiments (not applied to Airbnb products) demonstrate that our approach of restructuring workflows and fine-tuning LLMs with synthetic data significantly enhances their performance, setting a new benchmark for their application in customer support. Our solution is not only cost-effective but also improves customer support, as evidenced by both accuracy and manual processing time evaluation metrics.

---

### End-to-end Automatic Speech Recognition and Speech Translation: Integration of Speech Foundational Models and LLMs

Authors: Nam Luu, Ondřej Bojar
Published: 2025-10-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.10329v1

Speech Translation (ST) is a machine translation task that involves converting speech signals from one language to the corresponding text in another language; this task has two different approaches, namely the traditional cascade and the more recent end-to-end. This paper explores a combined end-to-end architecture of pre-trained speech encoders and Large Language Models (LLMs) for performing both Automatic Speech Recognition (ASR) and ST simultaneously. Experiments with the English-to-German language pair show that our best model not only can achieve better translation results than SeamlessM4T, a large foundational end-to-end, multi-modal translation model, but can also match the performance of a cascaded system with Whisper and NLLB, with up to a score gain of 8% in $\text{COMET}^{\text{DA}}_{22}$ metric.

---

### Are LLMs Empathetic to All? Investigating the Influence of Multi-Demographic Personas on a Model's Empathy

Authors: Ananya Malik, Nazanin Sabri, Melissa Karnaze, Mai Elsherief
Published: 2025-10-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.10328v2

Large Language Models' (LLMs) ability to converse naturally is empowered by their ability to empathetically understand and respond to their users. However, emotional experiences are shaped by demographic and cultural contexts. This raises an important question: Can LLMs demonstrate equitable empathy across diverse user groups? We propose a framework to investigate how LLMs' cognitive and affective empathy vary across user personas defined by intersecting demographic attributes. Our study introduces a novel intersectional analysis spanning 315 unique personas, constructed from combinations of age, culture, and gender, across four LLMs. Results show that attributes profoundly shape a model's empathetic responses. Interestingly, we see that adding multiple attributes at once can attenuate and reverse expected empathy patterns. We show that they broadly reflect real-world empathetic trends, with notable misalignments for certain groups, such as those from Confucian culture. We complement our quantitative findings with qualitative insights to uncover model behaviour patterns across different demographic groups. Our findings highlight the importance of designing empathy-aware LLMs that account for demographic diversity to promote more inclusive and equitable model behaviour.

---

### Mapping the Urban Mobility Intelligence Frontier: A Scientometric Analysis of Data-Driven Pedestrian Trajectory Prediction and Simulation

Authors: Junhao Xu, Hui Zeng
Published: 2025-10-11
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2510.10327v1

Understanding and predicting pedestrian dynamics has become essential for shaping safer, more responsive, and human-centered urban environments. This study conducts a comprehensive scientometric analysis of research on data-driven pedestrian trajectory prediction and crowd simulation, mapping its intellectual evolution and interdisciplinary structure. Using bibliometric data from the Web of Science Core Collection, we employ SciExplorer and Bibliometrix to identify major trends, influential contributors, and emerging frontiers. Results reveal a strong convergence between artificial intelligence, urban informatics, and crowd behavior modeling--driven by graph neural networks, transformers, and generative models. Beyond technical advances, the field increasingly informs urban mobility design, public safety planning, and digital twin development for smart cities. However, challenges remain in ensuring interpretability, inclusivity, and cross-domain transferability. By connecting methodological trajectories with urban applications, this work highlights how data-driven approaches can enrich urban governance and pave the way for adaptive, socially responsible mobility intelligence in future cities.

---

### KG-MAS: Knowledge Graph-Enhanced Multi-Agent Infrastructure for coupling physical and digital robotic environments

Authors: Walid Abdela
Published: 2025-10-11
Categories: cs.MA, cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2510.10325v1

The seamless integration of physical and digital environments in Cyber-Physical Systems(CPS), particularly within Industry 4.0, presents significant challenges stemming from system heterogeneity and complexity. Traditional approaches often rely on rigid, data-centric solutions like co-simulation frameworks or brittle point-to-point middleware bridges, which lack the semantic richness and flexibility required for intelligent, autonomous coordination. This report introduces the Knowledge Graph-Enhanced Multi-Agent Infrastructure(KG-MAS), as resolution in addressing such limitations. KG-MAS leverages a centralized Knowledge Graph (KG) as a dynamic, shared world model, providing a common semantic foundation for a Multi-Agent System(MAS). Autonomous agents, representing both physical and digital components, query this KG for decision-making and update it with real-time state information. The infrastructure features a model-driven architecture which facilitates the automatic generation of agents from semantic descriptions, thereby simplifying system extension and maintenance. By abstracting away underlying communication protocols and providing a unified, intelligent coordination mechanism, KG-MAS offers a robust, scalable, and flexible solution for coupling heterogeneous physical and digital robotic environments.

---

### On some practical challenges of conformal prediction

Authors: Liang Hong, Noura Raydan Nasreddine
Published: 2025-10-11
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.10324v2

Conformal prediction is a model-free machine learning method for constructing prediction regions at a guaranteed coverage probability level. However, a data scientist often faces three challenges in practice: (i) the determination of a conformal prediction region is only approximate, jeopardizing the finite-sample validity of prediction, (ii) the computation required could be prohibitively expensive, and (iii) the shape of a conformal prediction region is hard to control. This article offers new insights into the relationship among the monotonicity of the non-conformity measure, the monotonicity of the plausibility function, and the exact determination of a conformal prediction region. Based on these new insights, we propose a quadratic-polynomial non-conformity measure that allows a data scientist to circumvent the three challenges simultaneously within the full conformal prediction framework.

---

### Bridging Semantics & Structure for Software Vulnerability Detection using Hybrid Network Models

Authors: Jugal Gajjar, Kaustik Ranaware, Kamalasankari Subramaniakuppusamy
Published: 2025-10-11
Categories: cs.SE, cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2510.10321v1

Software vulnerabilities remain a persistent risk, yet static and dynamic analyses often overlook structural dependencies that shape insecure behaviors. Viewing programs as heterogeneous graphs, we capture control- and data-flow relations as complex interaction networks. Our hybrid framework combines these graph representations with light-weight (<4B) local LLMs, uniting topological features with semantic reasoning while avoiding the cost and privacy concerns of large cloud models. Evaluated on Java vulnerability detection (binary classification), our method achieves 93.57% accuracy-an 8.36% gain over Graph Attention Network-based embeddings and 17.81% over pretrained LLM baselines such as Qwen2.5 Coder 3B. Beyond accuracy, the approach extracts salient subgraphs and generates natural language explanations, improving interpretability for developers. These results pave the way for scalable, explainable, and locally deployable tools that can shift vulnerability analysis from purely syntactic checks to deeper structural and semantic insights, facilitating broader adoption in real-world secure software development.

---

### Prepared for the Unknown: Adapting AIOps Capacity Forecasting Models to Data Changes

Authors: Lorena Poenaru-Olaru, Wouter van 't Hof, Adrian Stando, Arkadiusz P. Trawinski, Eileen Kapel, Jan S. Rellermeyer, Luis Cruz, Arie van Deursen
Published: 2025-10-11
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2510.10320v1

Capacity management is critical for software organizations to allocate resources effectively and meet operational demands. An important step in capacity management is predicting future resource needs often relies on data-driven analytics and machine learning (ML) forecasting models, which require frequent retraining to stay relevant as data evolves. Continuously retraining the forecasting models can be expensive and difficult to scale, posing a challenge for engineering teams tasked with balancing accuracy and efficiency. Retraining only when the data changes appears to be a more computationally efficient alternative, but its impact on accuracy requires further investigation. In this work, we investigate the effects of retraining capacity forecasting models for time series based on detected changes in the data compared to periodic retraining. Our results show that drift-based retraining achieves comparable forecasting accuracy to periodic retraining in most cases, making it a cost-effective strategy. However, in cases where data is changing rapidly, periodic retraining is still preferred to maximize the forecasting accuracy. These findings offer actionable insights for software teams to enhance forecasting systems, reducing retraining overhead while maintaining robust performance.

---

### Artificial intelligence as a surrogate brain: Bridging neural dynamical models and data

Authors: Yinuo Zhang, Demao Liu, Zhichao Liang, Jiani Cheng, Kexin Lou, Jinqiao Duan, Ting Gao, Bin Hu, Quanying Liu
Published: 2025-10-11
Categories: q-bio.NC, cs.NE
arXiv: https://arxiv.org/abs/2510.10308v1

Recent breakthroughs in artificial intelligence (AI) are reshaping the way we construct computational counterparts of the brain, giving rise to a new class of ``surrogate brains''. In contrast to conventional hypothesis-driven biophysical models, the AI-based surrogate brain encompasses a broad spectrum of data-driven approaches to solve the inverse problem, with the primary objective of accurately predicting future whole-brain dynamics with historical data. Here, we introduce a unified framework of constructing an AI-based surrogate brain that integrates forward modeling, inverse problem solving, and model evaluation. Leveraging the expressive power of AI models and large-scale brain data, surrogate brains open a new window for decoding neural systems and forecasting complex dynamics with high dimensionality, nonlinearity, and adaptability. We highlight that the learned surrogate brain serves as a simulation platform for dynamical systems analysis, virtual perturbation, and model-guided neurostimulation. We envision that the AI-based surrogate brain will provide a functional bridge between theoretical neuroscience and translational neuroengineering.

---

### Sample-Efficient Online Learning in LM Agents via Hindsight Trajectory Rewriting

Authors: Michael Y. Hu, Benjamin Van Durme, Jacob Andreas, Harsh Jhamtani
Published: 2025-10-11
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.10304v2

Language model (LM) agents deployed in novel environments often exhibit poor sample efficiency when learning from sequential interactions. This significantly hinders the usefulness of such agents in environments where interaction is costly (for example, when they interact with humans or reset physical systems). While a number of existing LM agent architectures incorporate various mechanisms for experience storage and reflection, they make limited use of LMs' abilities to directly generate or reason about full counterfactual trajectories. We introduce ECHO (Experience Consolidation via Hindsight Optimization), a prompting framework that adapts hindsight experience replay from reinforcement learning for language model agents. ECHO generates optimized trajectories for alternative goals that could have been achieved during failed attempts, effectively creating synthetic positive examples from unsuccessful interactions. Our approach consists of two components: a hindsight rule that uses the language model itself to identify relevant subgoals and generate optimized trajectories, and an update rule that maintains compressed trajectory representations in memory. We evaluate ECHO on stateful versions of XMiniGrid, a text-based navigation and planning benchmark, and PeopleJoinQA, a collaborative information-gathering enterprise simulation. Across both domains, ECHO outperforms vanilla language agent baselines by up to 80%; in XMiniGrid, it also outperforms a number of sophisticated agent architectures including Reflexion and AWM, demonstrating faster adaptation to novel environments through more effective utilization of past experiences.

---

### The Algorithmic Regulator

Authors: Giulio Ruffini
Published: 2025-10-11
Categories: cs.CC, cs.AI, cs.IT, eess.SY, q-bio.NC
arXiv: https://arxiv.org/abs/2510.10300v3

The regulator theorem states that, under certain conditions, any optimal controller must embody a model of the system it regulates, grounding the idea that controllers embed, explicitly or implicitly, internal models of the controlled. This principle underpins neuroscience and predictive brain theories like the Free-Energy Principle or Kolmogorov/Algorithmic Agent theory. However, the theorem is only proven in limited settings. Here, we treat the deterministic, closed, coupled world-regulator system $(W,R)$ as a single self-delimiting program $p$ via a constant-size wrapper that produces the world output string~$x$ fed to the regulator. We analyze regulation from the viewpoint of the algorithmic complexity of the output, $K(x)$. We define $R$ to be a \emph{good algorithmic regulator} if it \emph{reduces} the algorithmic complexity of the readout relative to a null (unregulated) baseline $\varnothing$, i.e., \( Δ= K\big(O_{W,\varnothing}\big) - K\big(O_{W,R}\big) > 0. \) We then prove that the larger $Δ$ is, the more world-regulator pairs with high mutual algorithmic information are favored. More precisely, a complexity gap $Δ> 0$ yields \( \Pr\big((W,R)\mid x\big) \le C\,2^{\,M(W{:}R)}\,2^{-Δ}, \) making low $M(W{:}R)$ exponentially unlikely as $Δ$ grows. This is an AIT version of the idea that ``the regulator contains a model of the world.'' The framework is distribution-free, applies to individual sequences, and complements the Internal Model Principle. Beyond this necessity claim, the same coding-theorem calculus singles out a \emph{canonical scalar objective} and implicates a \emph{planner}. On the realized episode, a regulator behaves \emph{as if} it minimized the conditional description length of the readout.

---

### MatryoshkaThinking: Recursive Test-Time Scaling Enables Efficient Reasoning

Authors: Hongwei Chen, Yishu Lei, Dan Zhang, Bo Ke, Danxiang Zhu, Xuyi Chen, Yuxiang Lu, Zhengjie Huang, Shikun Feng, Jingzhou He, Yu Sun, Hua Wu et al.
Published: 2025-10-11
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.10293v1

Test-time scaling has emerged as a promising paradigm in language modeling, wherein additional computational resources are allocated during inference to enhance model performance. Recent approaches, such as DeepConf, have demonstrated the efficacy of this strategy, however, they often incur substantial computational overhead to achieve competitive results. In this work, we propose MatryoshkaThinking, a novel method that significantly reduces computational cost while maintaining state-of-the-art performance. Specifically, MatryoshkaThinking attains a score of 99.79 on AIME2025 using only 4% of the computation required by DeepConf. The core of our approach lies in the recursive exploitation of the model's intrinsic capabilities in reasoning, verification, and summarization, which collectively enhance the retention of correct solutions and reduce the disparity between Pass@k and Pass@1. Comprehensive evaluations across multiple open-source models and challenging multi-modal reasoning benchmarks validate the effectiveness and generality of our method. These findings offer new insights into the design of efficient and scalable test-time inference strategies for advanced language models.

---

### From Programs to Poses: Factored Real-World Scene Generation via Learned Program Libraries

Authors: Joy Hsu, Emily Jin, Jiajun Wu, Niloy J. Mitra
Published: 2025-10-11
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.10292v1

Real-world scenes, such as those in ScanNet, are difficult to capture, with highly limited data available. Generating realistic scenes with varied object poses remains an open and challenging task. In this work, we propose FactoredScenes, a framework that synthesizes realistic 3D scenes by leveraging the underlying structure of rooms while learning the variation of object poses from lived-in scenes. We introduce a factored representation that decomposes scenes into hierarchically organized concepts of room programs and object poses. To encode structure, FactoredScenes learns a library of functions capturing reusable layout patterns from which scenes are drawn, then uses large language models to generate high-level programs, regularized by the learned library. To represent scene variations, FactoredScenes learns a program-conditioned model to hierarchically predict object poses, and retrieves and places 3D objects in a scene. We show that FactoredScenes generates realistic, real-world rooms that are difficult to distinguish from real ScanNet scenes.

---

### Grounded AI for Code Review: Resource-Efficient Large-Model Serving in Enterprise Pipelines

Authors: Sayan Mandal, Hua Jiang
Published: 2025-10-11
Categories: cs.SE, cs.LG
arXiv: https://arxiv.org/abs/2510.10290v1

Automated code review adoption lags in compliance-heavy settings, where static analyzers produce high-volume, low-rationale outputs, and naive LLM use risks hallucination and incurring cost overhead. We present a production system for grounded, PR-native review that pairs static-analysis findings with AST-guided context extraction and a single-GPU, on-demand serving stack (quantized open-weight model, multi-tier caching) to deliver concise explanations and remediation guidance. Evaluated on safety-oriented C/C++ standards, the approach achieves sub-minute median first-feedback (offline p50 build+LLM 59.8s) while maintaining competitive violation reduction and lower violation rates versus larger proprietary models. The architecture is decoupled: teams can adopt the grounding/prompting layer or the serving layer independently. A small internal survey (n=8) provides directional signals of reduced triage effort and moderate perceived grounding, with participants reporting fewer human review iterations. We outline operational lessons and limitations, emphasizing reproducibility, auditability, and pathways to broader standards and assisted patching.

---

### SAM2LoRA: Composite Loss-Guided, Parameter-Efficient Finetuning of SAM2 for Retinal Fundus Segmentation

Authors: Sayan Mandal, Divyadarshini Karthikeyan, Manas Paldhe
Published: 2025-10-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.10288v1

We propose SAM2LoRA, a parameter-efficient fine-tuning strategy that adapts the Segment Anything Model 2 (SAM2) for fundus image segmentation. SAM2 employs a masked autoencoder-pretrained Hierarchical Vision Transformer for multi-scale feature decoding, enabling rapid inference in low-resource settings; however, fine-tuning remains challenging. To address this, SAM2LoRA integrates a low-rank adapter into both the image encoder and mask decoder, requiring fewer than 5\% of the original trainable parameters. Our analysis indicates that for cross-dataset fundus segmentation tasks, a composite loss function combining segmentationBCE, SoftDice, and FocalTversky losses is essential for optimal network tuning. Evaluated on 11 challenging fundus segmentation datasets, SAM2LoRA demonstrates high performance in both blood vessel and optic disc segmentation under cross-dataset training conditions. It achieves Dice scores of up to 0.86 and 0.93 for blood vessel and optic disc segmentation, respectively, and AUC values of up to 0.98 and 0.99, achieving state-of-the-art performance while substantially reducing training overhead.

---

### Bridging Perspectives: Foundation Model Guided BEV Maps for 3D Object Detection and Tracking

Authors: Markus Käppeler, Özgün Çiçek, Daniele Cattaneo, Claudius Gläser, Yakov Miron, Abhinav Valada
Published: 2025-10-11
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2510.10287v1

Camera-based 3D object detection and tracking are essential for perception in autonomous driving. Current state-of-the-art approaches often rely exclusively on either perspective-view (PV) or bird's-eye-view (BEV) features, limiting their ability to leverage both fine-grained object details and spatially structured scene representations. In this work, we propose DualViewDistill, a hybrid detection and tracking framework that incorporates both PV and BEV camera image features to leverage their complementary strengths. Our approach introduces BEV maps guided by foundation models, leveraging descriptive DINOv2 features that are distilled into BEV representations through a novel distillation process. By integrating PV features with BEV maps enriched with semantic and geometric features from DINOv2, our model leverages this hybrid representation via deformable aggregation to enhance 3D object detection and tracking. Extensive experiments on the nuScenes and Argoverse 2 benchmarks demonstrate that DualViewDistill achieves state-of-the-art performance. The results showcase the potential of foundation model BEV maps to enable more reliable perception for autonomous driving. We make the code and pre-trained models available at https://dualviewdistill.cs.uni-freiburg.de .

---

### Reallocating Attention Across Layers to Reduce Multimodal Hallucination

Authors: Haolang Lu, Bolun Chu, WeiYe Fu, Guoshun Nan, Junning Liu, Minghui Pan, Qiankun Li, Yi Yu, Hua Wang, Kun Wang
Published: 2025-10-11
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.10285v3

Multimodal large reasoning models (MLRMs) often suffer from hallucinations that stem not only from insufficient visual grounding but also from imbalanced allocation between perception and reasoning processes. Building upon recent interpretability findings suggesting a staged division of attention across layers, we analyze how this functional misalignment leads to two complementary failure modes: perceptual bias in shallow layers and reasoning drift in deeper layers. To alleviate these issues, we propose Functional Head Identification and Class-Conditioned Rescaling , a lightweight, training-free plugin that identifies perception- and reasoning-oriented heads and adaptively rebalances their layerwise contributions. Our method improves reasoning consistency and visual faithfulness without retraining or any architectural modification. Evaluations across three representative MLRMs and five multimodal reasoning benchmarks show an average 4.2% point gain, with less than 1% additional computation and only 9% baseline latency. Beyond empirical improvements, our study provides an interpretable perspective on regulating cross-layer functional dynamics to enhance the reliability of multimodal reasoning.

---

### ArtPerception: ASCII Art-based Jailbreak on LLMs with Recognition Pre-test

Authors: Guan-Yan Yang, Tzu-Yu Cheng, Ya-Wen Teng, Farn Wanga, Kuo-Hui Yeh
Published: 2025-10-11
Categories: cs.CR, cs.AI, cs.CL, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.10281v1

The integration of Large Language Models (LLMs) into computer applications has introduced transformative capabilities but also significant security challenges. Existing safety alignments, which primarily focus on semantic interpretation, leave LLMs vulnerable to attacks that use non-standard data representations. This paper introduces ArtPerception, a novel black-box jailbreak framework that strategically leverages ASCII art to bypass the security measures of state-of-the-art (SOTA) LLMs. Unlike prior methods that rely on iterative, brute-force attacks, ArtPerception introduces a systematic, two-phase methodology. Phase 1 conducts a one-time, model-specific pre-test to empirically determine the optimal parameters for ASCII art recognition. Phase 2 leverages these insights to launch a highly efficient, one-shot malicious jailbreak attack. We propose a Modified Levenshtein Distance (MLD) metric for a more nuanced evaluation of an LLM's recognition capability. Through comprehensive experiments on four SOTA open-source LLMs, we demonstrate superior jailbreak performance. We further validate our framework's real-world relevance by showing its successful transferability to leading commercial models, including GPT-4o, Claude Sonnet 3.7, and DeepSeek-V3, and by conducting a rigorous effectiveness analysis against potential defenses such as LLaMA Guard and Azure's content filters. Our findings underscore that true LLM security requires defending against a multi-modal space of interpretations, even within text-only inputs, and highlight the effectiveness of strategic, reconnaissance-based attacks. Content Warning: This paper includes potentially harmful and offensive model outputs.

---

### On the Entity-Level Alignment in Crosslingual Consistency

Authors: Yihong Liu, Mingyang Wang, François Yvon, Hinrich Schütze
Published: 2025-10-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.10280v1

Multilingual large language models (LLMs) are expected to recall factual knowledge consistently across languages. However, the factors that give rise to such crosslingual consistency -- and its frequent failure -- remain poorly understood. In this work, we hypothesize that these inconsistencies may arise from failures in entity alignment, the process of mapping subject and object entities into a shared conceptual space across languages. To test this, we assess alignment through entity-level (subject and object) translation tasks, and find that consistency is strongly correlated with alignment across all studied models, with misalignment of subjects or objects frequently resulting in inconsistencies. Building on this insight, we propose SubSub and SubInj, two effective methods that integrate English translations of subjects into prompts across languages, leading to substantial gains in both factual recall accuracy and consistency. Finally, our mechanistic analysis reveals that these interventions reinforce the entity representation alignment in the conceptual space through model's internal pivot-language processing, offering effective and practical strategies for improving multilingual factual prediction.

---

### Simulating Viva Voce Examinations to Evaluate Clinical Reasoning in Large Language Models

Authors: Christopher Chiu, Silviu Pitis, Mihaela van der Schaar
Published: 2025-10-11
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.10278v1

Clinical reasoning in medicine is a hypothesis-driven process where physicians refine diagnoses from limited information through targeted history, physical examination, and diagnostic investigations. In contrast, current medical benchmarks for large language models (LLMs) primarily assess knowledge recall through single-turn questions, where complete clinical information is provided upfront. To address this gap, we introduce VivaBench, a multi-turn benchmark that evaluates sequential clinical reasoning in LLM agents. Our dataset consists of 1762 physician-curated clinical vignettes structured as interactive scenarios that simulate a (oral) examination in medical training, requiring agents to actively probe for relevant findings, select appropriate investigations, and synthesize information across multiple steps to reach a diagnosis. While current LLMs demonstrate competence in diagnosing conditions from well-described clinical presentations, their performance degrades significantly when required to navigate iterative diagnostic reasoning under uncertainty in our evaluation. Our analysis identified several failure modes that mirror common cognitive errors in clinical practice, including: (1) fixation on initial hypotheses, (2) inappropriate investigation ordering, (3) premature diagnostic closure, and (4) failing to screen for critical conditions. These patterns reveal fundamental limitations in how current LLMs reason and make decisions under uncertainty. Through VivaBench, we provide a standardized benchmark for evaluating conversational medical AI systems for real-world clinical decision support. Beyond medical applications, we contribute to the larger corpus of research on agentic AI by demonstrating how sequential reasoning trajectories can diverge in complex decision-making environments.

---

### Lost in the Middle: An Emergent Property from Information Retrieval Demands in LLMs

Authors: Nikolaus Salvatore, Hao Wang, Qiong Zhang
Published: 2025-10-11
Categories: cs.LG, q-bio.NC
arXiv: https://arxiv.org/abs/2510.10276v1

The performance of Large Language Models (LLMs) often degrades when crucial information is in the middle of a long context, a "lost-in-the-middle" phenomenon that mirrors the primacy and recency effects in human memory. We propose that this behavior is not simply a flaw indicative of information loss but an adaptation to different information retrieval demands during pre-training: some tasks require uniform recall across the entire input (a long-term memory demand), while others prioritize the most recent information (a short-term memory demand). Consistent with this view, we show that this U-shaped performance curve emerges when LLMs (GPT-2 and Llama variants) are trained from scratch on two simple human memory paradigms simulating long-term and short-term memory demands. Our analysis reveals that while the recency effect directly aligns with short-term memory demand in the training data, the primacy effect is induced by the uniform long-term memory demand and is additionally influenced by the model's autoregressive properties and the formation of attention sinks. Our main findings from simple human memory paradigms also generalize to a sequence completion task, which more closely resembles the next-token prediction process in LLM pre-training. Together, our findings reveal how information retrieval demands, model architecture, and structural attention dynamics during model training can jointly produce positional bias observed in LLMs.

---

### X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model

Authors: Jinliang Zheng, Jianxiong Li, Zhihao Wang, Dongxiu Liu, Xirui Kang, Yuchun Feng, Yinan Zheng, Jiayin Zou, Yilun Chen, Jia Zeng, Ya-Qin Zhang, Jiangmiao Pang et al.
Published: 2025-10-11
Categories: cs.RO, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2510.10274v1

Successful generalist Vision-Language-Action (VLA) models rely on effective training across diverse robotic platforms with large-scale, cross-embodiment, heterogeneous datasets. To facilitate and leverage the heterogeneity in rich, diverse robotic data sources, we propose a novel Soft Prompt approach with minimally added parameters, by infusing prompt learning concepts into cross-embodiment robot learning and introducing separate sets of learnable embeddings for each distinct data source. These embeddings serve as embodiment-specific prompts, which in unity empower VLA models with effective exploitation of varying cross-embodiment features. Our new X-VLA, a neat flow-matching-based VLA architecture, relies exclusively on soft-prompted standard Transformer encoders, enjoying both scalability and simplicity. Evaluated across 6 simulations as well as 3 real-world robots, our 0.9B instantiation-X-VLA-0.9B simultaneously achieves SOTA performance over a sweep of benchmarks, demonstrating superior results on a wide axes of capabilities, from flexible dexterity to quick adaptation across embodiments, environments, and tasks. Website: https://thu-air-dream.github.io/X-VLA/

---

### MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation

Authors: Wentian Zhu, Zhen Xiang, Wei Niu, Le Guan
Published: 2025-10-11
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2510.10271v2

Unlike regular tokens derived from existing text corpora, special tokens are artificially created to annotate structured conversations during the fine-tuning process of Large Language Models (LLMs). Serving as metadata of training data, these tokens play a crucial role in instructing LLMs to generate coherent and context-aware responses. We demonstrate that special tokens can be exploited to construct four attack primitives, with which malicious users can reliably bypass the internal safety alignment of online LLM services and circumvent state-of-the-art (SOTA) external content moderation systems simultaneously. Moreover, we found that addressing this threat is challenging, as aggressive defense mechanisms-such as input sanitization by removing special tokens entirely, as suggested in academia-are less effective than anticipated. This is because such defense can be evaded when the special tokens are replaced by regular ones with high semantic similarity within the tokenizer's embedding space. We systemically evaluated our method, named MetaBreak, on both lab environment and commercial LLM platforms. Our approach achieves jailbreak rates comparable to SOTA prompt-engineering-based solutions when no content moderation is deployed. However, when there is content moderation, MetaBreak outperforms SOTA solutions PAP and GPTFuzzer by 11.6% and 34.8%, respectively. Finally, since MetaBreak employs a fundamentally different strategy from prompt engineering, the two approaches can work synergistically. Notably, empowering MetaBreak on PAP and GPTFuzzer boosts jailbreak rates by 24.3% and 20.2%, respectively.

---

### VividAnimator: An End-to-End Audio and Pose-driven Half-Body Human Animation Framework

Authors: Donglin Huang, Yongyuan Li, Tianhang Liu, Junming Huang, Xiaoda Yang, Chi Wang, Weiwei Xu
Published: 2025-10-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.10269v1

Existing for audio- and pose-driven human animation methods often struggle with stiff head movements and blurry hands, primarily due to the weak correlation between audio and head movements and the structural complexity of hands. To address these issues, we propose VividAnimator, an end-to-end framework for generating high-quality, half-body human animations driven by audio and sparse hand pose conditions. Our framework introduces three key innovations. First, to overcome the instability and high cost of online codebook training, we pre-train a Hand Clarity Codebook (HCC) that encodes rich, high-fidelity hand texture priors, significantly mitigating hand degradation. Second, we design a Dual-Stream Audio-Aware Module (DSAA) to model lip synchronization and natural head pose dynamics separately while enabling interaction. Third, we introduce a Pose Calibration Trick (PCT) that refines and aligns pose conditions by relaxing rigid constraints, ensuring smooth and natural gesture transitions. Extensive experiments demonstrate that Vivid Animator achieves state-of-the-art performance, producing videos with superior hand detail, gesture realism, and identity consistency, validated by both quantitative metrics and qualitative evaluations.

---

### Neural Variational Cut Posteriors without Upstream Data

Authors: Jiafang Song, Sandipan Pramanik, Abhirup Datta
Published: 2025-10-11
Categories: stat.ML, cs.LG, stat.ME
arXiv: https://arxiv.org/abs/2510.10268v3

In many applications, one must propagate parameter uncertainty from an earlier (upstream) analysis, available as samples, to subsequent (downstream) analyses without feedback. This problem is called cutting feedback or cut-Bayes, and the cut-posterior, the optimal posterior preserving information-flow constraints, is well characterized. However, sampling from it (e.g., via nested MCMC) is computationally intensive, while existing variational inference methods for cut-Bayes require access to upstream data and model, often unavailable. We propose a modular and provably accurate cut-Bayes approach requiring no access to upstream data or model. We leverage the characterization of the cut-posterior as the minimizer of the expected downstream conditional Kullback-Leibler divergence over the upstream posterior, replacing the expectation with the sample average over upstream draws. Our method, NeVI-Cut (neural variational inference for cut-Bayes), employs conditional normalizing flows as the variational family for downstream parameters. We provide fixed-data convergence rates of NeVI-Cut in terms of the richness of neural architecture and complexity of the cut-posterior. We establish, to our knowledge, first results on uniform Kullback-Leibler approximation rates of conditional distributions by common flow classes, yielding widely applicable fixed-data error rates for variational flows. A stochastic algorithm implements NeVI-Cut efficiently, and we demonstrate its speed and accuracy on multiple applications.

---

### Backdoor Collapse: Eliminating Unknown Threats via Known Backdoor Aggregation in Language Models

Authors: Liang Lin, Miao Yu, Moayad Aloqaily, Zhenhong Zhou, Kun Wang, Linsey Pang, Prakhar Mehrotra, Qingsong Wen
Published: 2025-10-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.10265v2

Backdoor attacks are a significant threat to large language models (LLMs), often embedded via public checkpoints, yet existing defenses rely on impractical assumptions about trigger settings. To address this challenge, we propose \ourmethod, a defense framework that requires no prior knowledge of trigger settings. \ourmethod is based on the key observation that when deliberately injecting known backdoors into an already-compromised model, both existing unknown and newly injected backdoors aggregate in the representation space. \ourmethod leverages this through a two-stage process: \textbf{first}, aggregating backdoor representations by injecting known triggers, and \textbf{then}, performing recovery fine-tuning to restore benign outputs. Extensive experiments across multiple LLM architectures demonstrate that: (I) \ourmethod reduces the average Attack Success Rate to 4.41\% across multiple benchmarks, outperforming existing baselines by 28.1\%$\sim$69.3\%$\uparrow$. (II) Clean accuracy and utility are preserved within 0.5\% of the original model, ensuring negligible impact on legitimate tasks. (III) The defense generalizes across different types of backdoors, confirming its robustness in practical deployment scenarios.

---

### Unveiling Gamer Archetypes through Multi modal feature Correlations and Unsupervised Learning

Authors: Moona Kanwal, Muhammad Sami Siddiqui, Syed Anael Ali
Published: 2025-10-11
Categories: cs.HC, cs.AI, cs.CY, cs.LG
arXiv: https://arxiv.org/abs/2510.10263v1

Profiling gamers provides critical insights for adaptive game design, behavioral understanding, and digital well-being. This study proposes an integrated, data-driven framework that combines psychological measures, behavioral analytics, and machine learning to reveal underlying gamer personas. A structured survey of 250 participants, including 113 active gamers, captured multidimensional behavioral, motivational, and social data. The analysis pipeline integrated feature engineering, association-network, knowledge-graph analysis, and unsupervised clustering to extract meaningful patterns. Correlation statistics uses Cramers V, Tschuprows T, Theils U, and Spearmans quantified feature associations, and network centrality guided feature selection. Dimensionality-reduction techniques such as PCA, SVD, t-SNE are coupled with clustering algorithms like K-Means, Agglomerative, Spectral, DBSCAN, evaluated using Silhouette, Calinski Harabasz, and Davies Bouldin indices. The PCA with K-Means with k = 4 model achieved optimal cluster quality with Silhouette = 0.4, identifying four archetypes as Immersive Social Story-Seekers, Disciplined Optimizers, Strategic Systems Navigators, and Competitive Team-Builders. This research contributes a reproducible pipeline that links correlation-driven network insights with unsupervised learning. The integration of behavioral correlation networks with clustering not only enhances classification accuracy but also offers a holistic lens to connect gameplay motivations with psychological and wellness outcomes.

---

### Enhancing the Cross-Size Generalization for Solving Vehicle Routing Problems via Continual Learning

Authors: Jingwen Li, Zhiguang Cao, Yaoxin Wu, Tang Liu
Published: 2025-10-11
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.10262v2

Exploring machine learning techniques for addressing vehicle routing problems has attracted considerable research attention. To achieve decent and efficient solutions, existing deep models for vehicle routing problems are typically trained and evaluated using instances of a single size. This substantially limits their ability to generalize across different problem sizes and thus hampers their practical applicability. To address the issue, we propose a continual learning based framework that sequentially trains a deep model with instances of ascending problem sizes. Specifically, on the one hand, we design an inter-task regularization scheme to retain the knowledge acquired from smaller problem sizes in the model training on a larger size. On the other hand, we introduce an intra-task regularization scheme to consolidate the model by imitating the latest desirable behaviors during training on each size. Additionally, we exploit the experience replay to revisit instances of formerly trained sizes for mitigating the catastrophic forgetting. Experimental results show that our approach achieves predominantly superior performance across various problem sizes (either seen or unseen in the training), as compared to state-of-the-art deep models including the ones specialized for generalizability enhancement. Meanwhile, the ablation studies on the key designs manifest their synergistic effect in the proposed framework.

---

### Robust Exploratory Stopping under Ambiguity in Reinforcement Learning

Authors: Junyan Ye, Hoi Ying Wong, Kyunghyun Park
Published: 2025-10-11
Categories: math.OC, math.PR, q-fin.MF, stat.ML
arXiv: https://arxiv.org/abs/2510.10260v2

We propose and analyze a continuous-time robust reinforcement learning framework for optimal stopping under ambiguity. In this framework, an agent chooses a robust exploratory stopping time motivated by two objectives: robust decision-making under ambiguity and learning about the unknown environment. Here, ambiguity refers to considering multiple probability measures dominated by a reference measure, reflecting the agent's awareness that the reference measure representing her learned belief about the environment would be erroneous. Using the $g$-expectation framework, we reformulate the optimal stopping problem under ambiguity as a robust exploratory control problem with Bernoulli distributed controls. We then characterize the optimal Bernoulli distributed control via backward stochastic differential equations and, based on this, construct the robust exploratory stopping time that approximates the optimal stopping time under ambiguity. Last, we establish a policy iteration theorem and implement it as a reinforcement learning algorithm. Numerical experiments demonstrate the convergence, robustness, and scalability of our reinforcement learning algorithm across different levels of ambiguity and exploration.

---

### Opacity-Gradient Driven Density Control for Compact and Efficient Few-Shot 3D Gaussian Splatting

Authors: Abdelrhman Elrawy, Emad A. Mohammed
Published: 2025-10-11
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.10257v1

3D Gaussian Splatting (3DGS) struggles in few-shot scenarios, where its standard adaptive density control (ADC) can lead to overfitting and bloated reconstructions. While state-of-the-art methods like FSGS improve quality, they often do so by significantly increasing the primitive count. This paper presents a framework that revises the core 3DGS optimization to prioritize efficiency. We replace the standard positional gradient heuristic with a novel densification trigger that uses the opacity gradient as a lightweight proxy for rendering error. We find this aggressive densification is only effective when paired with a more conservative pruning schedule, which prevents destructive optimization cycles. Combined with a standard depth-correlation loss for geometric guidance, our framework demonstrates a fundamental improvement in efficiency. On the 3-view LLFF dataset, our model is over 40% more compact (32k vs. 57k primitives) than FSGS, and on the Mip-NeRF 360 dataset, it achieves a reduction of approximately 70%. This dramatic gain in compactness is achieved with a modest trade-off in reconstruction metrics, establishing a new state-of-the-art on the quality-vs-efficiency Pareto frontier for few-shot view synthesis.

---

### Are Video Models Emerging as Zero-Shot Learners and Reasoners in Medical Imaging?

Authors: Yuxiang Lai, Jike Zhong, Ming Li, Yuheng Li, Xiaofeng Yang
Published: 2025-10-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.10254v2

Recent advances in large generative models have shown that simple autoregressive formulations, when scaled appropriately, can exhibit strong zero-shot generalization across domains. Motivated by this trend, we investigate whether autoregressive video modeling principles can be directly applied to medical imaging tasks, despite the model never being trained on medical data. Specifically, we evaluate a large vision model (LVM) in a zero-shot setting across four representative tasks: organ segmentation, denoising, super-resolution, and motion prediction. Remarkably, even without domain-specific fine-tuning, the LVM can delineate anatomical structures in CT scans and achieve competitive performance on segmentation, denoising, and super-resolution. Most notably, in radiotherapy motion prediction, the model forecasts future 3D CT phases directly from prior phases of a 4D CT scan, producing anatomically consistent predictions that capture patient-specific respiratory dynamics with realistic temporal coherence. We evaluate the LVM on 4D CT data from 122 patients, totaling over 1,820 3D CT volumes. Despite no prior exposure to medical data, the model achieves strong performance across all tasks and surpasses specialized DVF-based and generative baselines in motion prediction, achieving state-of-the-art spatial accuracy. These findings reveal the emergence of zero-shot capabilities in medical video modeling and highlight the potential of general-purpose video models to serve as unified learners and reasoners laying the groundwork for future medical foundation models built on video models.

---

### Audit-of-Understanding: Posterior-Constrained Inference for Mathematical Reasoning in Language Models

Authors: Samir Abdaljalil, Erchin Serpedin, Khalid Qaraqe, Hasan Kurban
Published: 2025-10-11
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.10252v2

Large language models (LLMs) often generate reasoning traces that appear coherent but rest on unsupported assumptions, leading to hallucinated conclusions. Prior work mainly addresses factual hallucinations or relies on post-hoc verification, leaving reasoning-induced hallucinations largely unaddressed. We propose Audit-of-Understanding (AoU), a framework that constrains inference to validated premises through three phases: (1) decomposing a query into candidate assumptions, (2) auditing their support, and (3) conditioning inference only on the validated subset. Formally, AoU is \emph{posterior-constrained inference}, connecting to selective prediction and rejection learning. Our contributions are threefold: (i) theoretical guarantees under perfect validation, (ii) excess-risk bounds under imperfect audits, and (iii) tractability analysis. Empirically, AoU improves both accuracy and faithfulness on GSM8K, MultiArith, and SVAMP, achieving up to +30% gains on GSM8K, +45% on MultiArith, and consistent +20--28% improvements on SVAMP over Chain-of-Thought, Self-Consistency, and CoT-Decoding. Code is available at https://anonymous.4open.science/r/audit-of-understanding-E28B.

---

### MRI Brain Tumor Detection with Computer Vision

Authors: Jack Krolik, Jake Lynn, John Henry Rudden, Dmytro Vremenko
Published: 2025-10-11
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.10250v1

This study explores the application of deep learning techniques in the automated detection and segmentation of brain tumors from MRI scans. We employ several machine learning models, including basic logistic regression, Convolutional Neural Networks (CNNs), and Residual Networks (ResNet) to classify brain tumors effectively. Additionally, we investigate the use of U-Net for semantic segmentation and EfficientDet for anchor-based object detection to enhance the localization and identification of tumors. Our results demonstrate promising improvements in the accuracy and efficiency of brain tumor diagnostics, underscoring the potential of deep learning in medical imaging and its significance in improving clinical outcomes.

---