# Research Papers — 2025-10 · bundle page 164 of 217

> Full-text markdown of papers #8151–8200 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/164
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/163.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/165.md)

### Quantifying Data Contamination in Psychometric Evaluations of LLMs

Authors: Jongwook Han, Woojung Song, Jonggeun Lee, Yohan Jo
Published: 2025-10-08
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.07175v2

Recent studies apply psychometric questionnaires to Large Language Models (LLMs) to assess high-level psychological constructs such as values, personality, moral foundations, and dark traits. Although prior work has raised concerns about possible data contamination from psychometric inventories, which may threaten the reliability of such evaluations, there has been no systematic attempt to quantify the extent of this contamination. To address this gap, we propose a framework to systematically measure data contamination in psychometric evaluations of LLMs, evaluating three aspects: (1) item memorization, (2) evaluation memorization, and (3) target score matching. Applying this framework to 21 models from major families and four widely used psychometric inventories, we provide evidence that popular inventories such as the Big Five Inventory (BFI-44) and Portrait Values Questionnaire (PVQ-40) exhibit strong contamination, where models not only memorize items but can also adjust their responses to achieve specific target scores.

---

### NurseLLM: The First Specialized Language Model for Nursing

Authors: Md Tawkat Islam Khondaker, Julia Harrington, Shady Shehata
Published: 2025-10-08
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.07173v1

Recent advancements in large language models (LLMs) have significantly transformed medical systems. However, their potential within specialized domains such as nursing remains largely underexplored. In this work, we introduce NurseLLM, the first nursing-specialized LLM tailored for multiple choice question-answering (MCQ) tasks. We develop a multi-stage data generation pipeline to build the first large scale nursing MCQ dataset to train LLMs on a broad spectrum of nursing topics. We further introduce multiple nursing benchmarks to enable rigorous evaluation. Our extensive experiments demonstrate that NurseLLM outperforms SoTA general-purpose and medical-specialized LLMs of comparable size on different benchmarks, underscoring the importance of a specialized LLM for the nursing domain. Finally, we explore the role of reasoning and multi-agent collaboration systems in nursing, highlighting their promise for future research and applications.

---

### NewtonBench: Benchmarking Generalizable Scientific Law Discovery in LLM Agents

Authors: Tianshi Zheng, Kelvin Kiu-Wai Tam, Newt Hue-Nam K. Nguyen, Baixuan Xu, Zhaowei Wang, Jiayang Cheng, Hong Ting Tsang, Weiqi Wang, Jiaxin Bai, Tianqing Fang, Yangqiu Song, Ginny Y. Wong et al.
Published: 2025-10-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.07172v3

Large language models are emerging as powerful tools for scientific law discovery, a foundational challenge in AI-driven science. However, existing benchmarks for this task suffer from a fundamental methodological trilemma, forcing a trade-off between scientific relevance, scalability, and resistance to memorization. Furthermore, they oversimplify discovery as static function fitting, failing to capture the authentic scientific process of uncovering embedded laws through the interactive exploration of complex model systems. To address these critical gaps, we introduce NewtonBench, a benchmark comprising 324 scientific law discovery tasks across 12 physics domains. Our design mitigates the evaluation trilemma by using counterfactual law shifts - systematic alterations of canonical laws - to generate a vast suite of problems that are scalable, scientifically relevant, and memorization-resistant. Moreover, we elevate the evaluation from static function fitting to interactive model discovery, requiring agents to experimentally probe simulated complex systems to uncover hidden principles. Our extensive experiment reveals a clear but fragile capability for discovery in frontier LLMs: this ability degrades precipitously with increasing system complexity and exhibits extreme sensitivity to observational noise. Notably, we uncover a paradoxical effect of tool assistance: providing a code interpreter can hinder more capable models by inducing a premature shift from exploration to exploitation, causing them to satisfice on suboptimal solutions. These results demonstrate that robust, generalizable discovery in complex, interactive environments remains the core challenge. By providing a scalable, robust, and scientifically authentic testbed, NewtonBench offers a crucial tool for measuring true progress and guiding the development of next-generation AI agents capable of genuine scientific discovery.

---

### More Data or Better Data? A Critical Analysis of Data Selection and Synthesis for Mathematical Reasoning

Authors: Yike Zhao, Simin Guo, Ziqing Yang, Shifan Han, Dahua Lin, Fei Tan
Published: 2025-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.07169v1

The reasoning capabilities of Large Language Models (LLMs) play a critical role in many downstream tasks, yet depend strongly on the quality of training data. Despite various proposed data construction methods, their practical utility in real-world pipelines remains underexplored. In this work, we conduct a comprehensive analysis of open-source datasets and data synthesis techniques for mathematical reasoning, evaluating them under a unified pipeline designed to mirror training and deployment scenarios. We further distill effective data selection strategies and identify practical methods suitable for industrial applications. Our findings highlight that structuring data in more interpretable formats, or distilling from stronger models often outweighs simply scaling up data volume. This study provides actionable guidance for integrating training data to enhance LLM capabilities, supporting both cost-effective data curation and scalable model enhancement. We hope this work will inspire further research on how to balance "more data" versus "better data" for real-world reasoning tasks.

---

### Reasoning for Hierarchical Text Classification: The Case of Patents

Authors: Lekang Jiang, Wenjun Sun, Stephan Goetz
Published: 2025-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.07167v1

Hierarchical text classification (HTC) assigns documents to multiple levels of a pre-defined taxonomy. Automated patent subject classification represents one of the hardest HTC scenarios because of domain knowledge difficulty and a huge number of labels. Prior approaches only output a flat label set, which offers little insight into the reason behind predictions. Therefore, we propose Reasoning for Hierarchical Classification (RHC), a novel framework that reformulates HTC as a step-by-step reasoning task to sequentially deduce hierarchical labels. RHC trains large language models (LLMs) in two stages: a cold-start stage that aligns outputs with chain-of-thought (CoT) reasoning format and a reinforcement learning (RL) stage to enhance multi-step reasoning ability. RHC demonstrates four advantages in our experiments. (1) Effectiveness: RHC surpasses previous baselines and outperforms the supervised fine-tuning counterparts by approximately 3% in accuracy and macro F1. (2) Explainability: RHC produces natural-language justifications before prediction to facilitate human inspection. (3) Scalability: RHC scales favorably with model size with larger gains compared to standard fine-tuning. (4) Applicability: Beyond patents, we further demonstrate that RHC achieves state-of-the-art performance on other widely used HTC benchmarks, which highlights its broad applicability.

---

### Integrating Domain Knowledge into Process Discovery Using Large Language Models

Authors: Ali Norouzifar, Humam Kourani, Marcus Dees, Wil van der Aalst
Published: 2025-10-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.07161v1

Process discovery aims to derive process models from event logs, providing insights into operational behavior and forming a foundation for conformance checking and process improvement. However, models derived solely from event data may not accurately reflect the real process, as event logs are often incomplete or affected by noise, and domain knowledge, an important complementary resource, is typically disregarded. As a result, the discovered models may lack reliability for downstream tasks. We propose an interactive framework that incorporates domain knowledge, expressed in natural language, into the process discovery pipeline using Large Language Models (LLMs). Our approach leverages LLMs to extract declarative rules from textual descriptions provided by domain experts. These rules are used to guide the IMr discovery algorithm, which recursively constructs process models by combining insights from both the event log and the extracted rules, helping to avoid problematic process structures that contradict domain knowledge. The framework coordinates interactions among the LLM, domain experts, and a set of backend services. We present a fully implemented tool that supports this workflow and conduct an extensive evaluation of multiple LLMs and prompt engineering strategies. Our empirical study includes a case study based on a real-life event log with the involvement of domain experts, who assessed the usability and effectiveness of the framework.

---

### ELMUR: External Layer Memory with Update/Rewrite for Long-Horizon RL Problems

Authors: Egor Cherepanov, Alexey K. Kovalev, Aleksandr I. Panov
Published: 2025-10-08
Categories: cs.LG, cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2510.07151v2

Real-world robotic agents must act under partial observability and long horizons, where key cues may appear long before they affect decision making. However, most modern approaches rely solely on instantaneous information, without incorporating insights from the past. Standard recurrent or transformer models struggle with retaining and leveraging long-term dependencies: context windows truncate history, while naive memory extensions fail under scale and sparsity. We propose ELMUR (External Layer Memory with Update/Rewrite), a transformer architecture with structured external memory. Each layer maintains memory embeddings, interacts with them via bidirectional cross-attention, and updates them through an Least Recently Used (LRU) memory module using replacement or convex blending. ELMUR extends effective horizons up to 100,000 times beyond the attention window and achieves a 100% success rate on a synthetic T-Maze task with corridors up to one million steps. In POPGym, it outperforms baselines on more than half of the tasks. On MIKASA-Robo sparse-reward manipulation tasks with visual observations, it nearly doubles the performance of strong baselines, achieving the best success rate on 21 out of 23 tasks and improving the aggregate success rate across all tasks by about 70% over the previous best baseline. These results demonstrate that structured, layer-local external memory offers a simple and scalable approach to decision making under partial observability. Code and project page: https://elmur-paper.github.io/.

---

### A Multi-Agent Framework for Stateful Inference-Time Search

Authors: Arshika Lalan, Rajat Ghosh, Aditya Kolsur, Debojyoti Dutta
Published: 2025-10-08
Categories: cs.LG, cs.AI, cs.CL, cs.MA, cs.SE
arXiv: https://arxiv.org/abs/2510.07147v1

Recent work explores agentic inference-time techniques to perform structured, multi-step reasoning. However, stateless inference often struggles on multi-step tasks due to the absence of persistent state. Moreover, task-specific fine-tuning or instruction-tuning often achieve surface-level code generation but remain brittle on tasks requiring deeper reasoning and long-horizon dependencies. To address these limitations, we propose stateful multi-agent evolutionary search, a training-free framework that departs from prior stateless approaches by combining (i) persistent inference-time state, (ii) adversarial mutation, and (iii) evolutionary preservation. We demonstrate its effectiveness in automated unit test generation through the generation of edge cases. We generate robust edge cases using an evolutionary search process, where specialized agents sequentially propose, mutate, and score candidates. A controller maintains persistent state across generations, while evolutionary preservation ensures diversity and exploration across all possible cases. This yields a generalist agent capable of discovering robust, high-coverage edge cases across unseen codebases. Experiments show our stateful multi-agent inference framework achieves substantial gains in coverage over stateless single-step baselines, evaluated on prevalent unit-testing benchmarks such as HumanEval and TestGenEvalMini and using three diverse LLM families - Llama, Gemma, and GPT. These results indicate that combining persistent inference-time state with evolutionary search materially improves unit-test generation.

---

### Are We Using the Right Benchmark: An Evaluation Framework for Visual Token Compression Methods

Authors: Chenfei Liao, Wensong Wang, Zichen Wen, Xu Zheng, Yiyu Wang, Haocong He, Yuanhuiyi Lyu, Lutao Jiang, Xin Zou, Yuqian Fu, Bin Ren, Linfeng Zhang et al.
Published: 2025-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.07143v3

Recent efforts to accelerate inference in Multimodal Large Language Models (MLLMs) have largely focused on visual token compression. The effectiveness of these methods is commonly evaluated by measuring the accuracy drop on existing MLLM benchmarks before and after compression. However, these benchmarks are originally designed to assess general perception and reasoning abilities, rather than the specific challenges posed by visual token compression, leading to a fundamental task mismatch. In this work, we uncover a counterintuitive yet consistent phenomenon: simple image downsampling outperforms many advanced visual token compression methods across multiple widely used benchmarks. Through a comprehensive empirical study spanning eight popular benchmarks and multiple state-of-the-art compression techniques, we show that (i) current benchmarks contain substantial noise (task-irrelevant samples) for evaluating visual token compression, and (ii) downsampling can act as an effective data filter that distinguishes between simple and difficult samples with respect to compression sensitivity. Motivated by these findings, we propose VTC-Bench, an evaluation framework that explicitly leverages downsampling as a discriminator to denoise existing benchmarks, enabling a fairer and more meaningful additional assessment of visual token compression methods.

---

### Comparing Human and Language Models Sentence Processing Difficulties on Complex Structures

Authors: Samuel Joseph Amouyal, Aya Meltzer-Asscher, Jonathan Berant
Published: 2025-10-08
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.07141v2

Large language models (LLMs) that fluently converse with humans are a reality - but do LLMs experience human-like processing difficulties? We systematically compare human and LLM sentence comprehension across seven challenging linguistic structures. We collect sentence comprehension data from humans and five families of state-of-the-art LLMs, varying in size and training procedure in a unified experimental framework. Our results show LLMs overall struggle on the target structures, but especially on garden path (GP) sentences. Indeed, while the strongest models achieve near perfect accuracy on non-GP structures (93.7% for GPT-5), they struggle on GP structures (46.8% for GPT-5). Additionally, when ranking structures based on average performance, rank correlation between humans and models increases with parameter count. For each target structure, we also collect data for their matched baseline without the difficult structure. Comparing performance on the target vs. baseline sentences, the performance gap observed in humans holds for LLMs, with two exceptions: for models that are too weak performance is uniformly low across both sentence types, and for models that are too strong the performance is uniformly high. Together, these reveal convergence and divergence in human and LLM sentence comprehension, offering new insights into the similarity of humans and LLMs.

---

### Differentially Private Spectral Graph Clustering: Balancing Privacy, Accuracy, and Efficiency

Authors: Antti Koskela, Mohamed Seif, H. Vincent Poor, Andrea J. Goldsmith
Published: 2025-10-08
Categories: cs.IT, cs.CR, cs.LG, cs.SI
arXiv: https://arxiv.org/abs/2510.07136v2

We study spectral graph clustering under edge differential privacy. We propose a matrix shuffling mechanism that combines randomized edge flipping with a random permutation of the adjacency matrix. While edge flipping alone provides only a constant $\varepsilon$ guarantee as the graph grows, shuffling amplifies privacy so that the effective $\varepsilon$ tends to zero with the number of nodes. We develop a unified error analysis framework -- based on Davis--Kahan perturbation theory and a classification-margin bound -- that gives explicit misclassification rates for all the mechanisms considered as a function of the privacy budget, eigengap, and number of communities. Applying this framework, we show that the matrix shuffling mechanism achieves an error rate scaling of $\tilde{O}(1/n)$, a clear improvement over two canonical DP baselines from the private PCA literature: the Gaussian mechanism applied directly to the adjacency matrix (Analyze Gauss) and the noisy power method, both of which scale as $\tilde{O}(1)$ in $n$. We further propose a private spectral gap detection algorithm for estimating the number of communities. Experiments on synthetic and real-world networks validate our theoretical findings.

---

### Few-Shot Adaptation Benchmark for Remote Sensing Vision-Language Models

Authors: Karim El Khoury, Maxime Zanella, Christophe De Vleeschouwer, Benoit Macq
Published: 2025-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.07135v1

Remote Sensing Vision-Language Models (RSVLMs) have shown remarkable potential thanks to large-scale pretraining, achieving strong zero-shot performance on various tasks. However, their ability to generalize in low-data regimes, such as few-shot learning, remains insufficiently explored. In this work, we present the first structured benchmark for evaluating few-shot adaptation methods on RSVLMs. We conduct comprehensive experiments across ten remote sensing scene classification datasets, applying five widely used few-shot adaptation strategies to three state-of-the-art RSVLMs with varying backbones. Our findings reveal that models with similar zero-shot performance can exhibit markedly different behavior under few-shot adaptation, with some RSVLMs being inherently more amenable to such adaptation than others. The variability of performance and the absence of a clear winner among existing methods highlight the need for the development of more robust methods for few-shot adaptation tailored to RS. To facilitate future research, we provide a reproducible benchmarking framework and open-source code to systematically evaluate RSVLMs under few-shot conditions. The source code is publicly available on Github: https://github.com/elkhouryk/fewshot_RSVLMs

---

### TrackVLA++: Unleashing Reasoning and Memory Capabilities in VLA Models for Embodied Visual Tracking

Authors: Jiahang Liu, Yunpeng Qi, Jiazhao Zhang, Minghan Li, Shaoan Wang, Kui Wu, Hanjing Ye, Hong Zhang, Zhibo Chen, Fangwei Zhong, Zhizheng Zhang, He Wang
Published: 2025-10-08
Categories: cs.RO, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2510.07134v1

Embodied Visual Tracking (EVT) is a fundamental ability that underpins practical applications, such as companion robots, guidance robots and service assistants, where continuously following moving targets is essential. Recent advances have enabled language-guided tracking in complex and unstructured scenes. However, existing approaches lack explicit spatial reasoning and effective temporal memory, causing failures under severe occlusions or in the presence of similar-looking distractors. To address these challenges, we present TrackVLA++, a novel Vision-Language-Action (VLA) model that enhances embodied visual tracking with two key modules, a spatial reasoning mechanism and a Target Identification Memory (TIM). The reasoning module introduces a Chain-of-Thought paradigm, termed Polar-CoT, which infers the target's relative position and encodes it as a compact polar-coordinate token for action prediction. Guided by these spatial priors, the TIM employs a gated update strategy to preserve long-horizon target memory, ensuring spatiotemporal consistency and mitigating target loss during extended occlusions. Extensive experiments show that TrackVLA++ achieves state-of-the-art performance on public benchmarks across both egocentric and multi-camera settings. On the challenging EVT-Bench DT split, TrackVLA++ surpasses the previous leading approach by 5.1 and 12, respectively. Furthermore, TrackVLA++ exhibits strong zero-shot generalization, enabling robust real-world tracking in dynamic and occluded scenarios.

---

### A Digital Twin Framework for Metamorphic Testing of Autonomous Driving Systems Using Generative Model

Authors: Tony Zhang, Burak Kantarci, Umair Siddique
Published: 2025-10-08
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2510.07133v1

Ensuring the safety of self-driving cars remains a major challenge due to the complexity and unpredictability of real-world driving environments. Traditional testing methods face significant limitations, such as the oracle problem, which makes it difficult to determine whether a system's behavior is correct, and the inability to cover the full range of scenarios an autonomous vehicle may encounter. In this paper, we introduce a digital twin-driven metamorphic testing framework that addresses these challenges by creating a virtual replica of the self-driving system and its operating environment. By combining digital twin technology with AI-based image generative models such as Stable Diffusion, our approach enables the systematic generation of realistic and diverse driving scenes. This includes variations in weather, road topology, and environmental features, all while maintaining the core semantics of the original scenario. The digital twin provides a synchronized simulation environment where changes can be tested in a controlled and repeatable manner. Within this environment, we define three metamorphic relations inspired by real-world traffic rules and vehicle behavior. We validate our framework in the Udacity self-driving simulator and demonstrate that it significantly enhances test coverage and effectiveness. Our method achieves the highest true positive rate (0.719), F1 score (0.689), and precision (0.662) compared to baseline approaches. This paper highlights the value of integrating digital twins with AI-powered scenario generation to create a scalable, automated, and high-fidelity testing solution for autonomous vehicle safety.

---

### DPMM-CFL: Clustered Federated Learning via Dirichlet Process Mixture Model Nonparametric Clustering

Authors: Mariona Jaramillo-Civill, Peng Wu, Pau Closas
Published: 2025-10-08
Categories: cs.LG, cs.DC, stat.ML
arXiv: https://arxiv.org/abs/2510.07132v2

Clustered Federated Learning (CFL) improves performance under non-IID client heterogeneity by clustering clients and training one model per cluster, thereby balancing between a global model and fully personalized models. However, most CFL methods require the number of clusters K to be fixed a priori, which is impractical when the latent structure is unknown. We propose DPMM-CFL, a CFL algorithm that places a Dirichlet Process (DP) prior over the distribution of cluster parameters. This enables nonparametric Bayesian inference to jointly infer both the number of clusters and client assignments, while optimizing per-cluster federated objectives. This results in a method where, at each round, federated updates and cluster inferences are coupled, as presented in this paper. The algorithm is validated on benchmark datasets under Dirichlet and class-split non-IID partitions.

---

### Graph Conditioned Diffusion for Controllable Histopathology Image Generation

Authors: Sarah Cechnicka, Matthew Baugh, Weitong Zhang, Mischa Dombrowski, Zhe Li, Johannes C. Paetzold, Candice Roufosse, Bernhard Kainz
Published: 2025-10-08
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.07129v1

Recent advances in Diffusion Probabilistic Models (DPMs) have set new standards in high-quality image synthesis. Yet, controlled generation remains challenging, particularly in sensitive areas such as medical imaging. Medical images feature inherent structure such as consistent spatial arrangement, shape or texture, all of which are critical for diagnosis. However, existing DPMs operate in noisy latent spaces that lack semantic structure and strong priors, making it difficult to ensure meaningful control over generated content. To address this, we propose graph-based object-level representations for Graph-Conditioned-Diffusion. Our approach generates graph nodes corresponding to each major structure in the image, encapsulating their individual features and relationships. These graph representations are processed by a transformer module and integrated into a diffusion model via the text-conditioning mechanism, enabling fine-grained control over generation. We evaluate this approach using a real-world histopathology use case, demonstrating that our generated data can reliably substitute for annotated patient data in downstream segmentation tasks. The code is available here.

---

### A General Framework for Joint Multi-State Models

Authors: Félix Laplante, Christophe Ambroise
Published: 2025-10-08
Categories: stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2510.07128v5

Conventional joint modeling approaches generally characterize the relationship between longitudinal biomarkers and discrete event occurrences within terminal, recurring or competing risk settings, thereby offering a limited representation of complex, multi-state trajectories. We propose a general multi-state joint modeling framework that unifies longitudinal biomarker dynamics with multi-state time-to-event processes defined on arbitrary directed graphs. The proposed framework also accomodates nonlinear longitudinal submodels and scalable inference via stochastic gradient descent. This formulation encompasses both Markovian and semi-Markovian transition structures, allowing recurrent cycles and terminal absorptions to be naturally represented. The longitudinal and event processes are linked through shared latent structures within nonlinear mixed-effects models, extending classical joint modeling formulations. We derive the complete likelihood, model selection criteria, and develop scalable inference procedures based on stochastic gradient descent to enable high-dimensional and large-scale applications. In addition, we formulate a dynamic prediction framework that provides individualized state-transition probabilities and personalized risk assessments along complex event trajectories. Through simulation and application to the PAQUID cohort, we demonstrate accurate parameter recovery and individualized prediction.

---

### Validation of Various Normalization Methods for Brain Tumor Segmentation: Can Federated Learning Overcome This Heterogeneity?

Authors: Jan Fiszer, Dominika Ciupek, Maciej Malawski
Published: 2025-10-08
Categories: cs.CV, cs.DC
arXiv: https://arxiv.org/abs/2510.07126v1

Deep learning (DL) has been increasingly applied in medical imaging, however, it requires large amounts of data, which raises many challenges related to data privacy, storage, and transfer. Federated learning (FL) is a training paradigm that overcomes these issues, though its effectiveness may be reduced when dealing with non-independent and identically distributed (non-IID) data. This study simulates non-IID conditions by applying different MRI intensity normalization techniques to separate data subsets, reflecting a common cause of heterogeneity. These subsets are then used for training and testing models for brain tumor segmentation. The findings provide insights into the influence of the MRI intensity normalization methods on segmentation models, both training and inference. Notably, the FL methods demonstrated resilience to inconsistently normalized data across clients, achieving the 3D Dice score of 92%, which is comparable to a centralized model (trained using all data). These results indicate that FL is a solution to effectively train high-performing models without violating data privacy, a crucial concern in medical applications. The code is available at: https://github.com/SanoScience/fl-varying-normalization.

---

### MoRe: Monocular Geometry Refinement via Graph Optimization for Cross-View Consistency

Authors: Dongki Jung, Jaehoon Choi, Yonghan Lee, Sungmin Eum, Heesung Kwon, Dinesh Manocha
Published: 2025-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.07119v2

Monocular 3D foundation models offer an extensible solution for perception tasks, making them attractive for broader 3D vision applications. In this paper, we propose MoRe, a training-free Monocular Geometry Refinement method designed to improve cross-view consistency and achieve scale alignment. To induce inter-frame relationships, our method employs feature matching between frames to establish correspondences. Rather than applying simple least squares optimization on these matched points, we formulate a graph-based optimization framework that performs local planar approximation using the estimated 3D points and surface normals estimated by monocular foundation models. This formulation addresses the scale ambiguity inherent in monocular geometric priors while preserving the underlying 3D structure. We further demonstrate that MoRe not only enhances 3D reconstruction but also improves novel view synthesis, particularly in sparse view rendering scenarios.

---

### TRIM: Token-wise Attention-Derived Saliency for Data-Efficient Instruction Tuning

Authors: Manish Nagaraj, Sakshi Choudhary, Utkarsh Saxena, Deepak Ravikumar, Kaushik Roy
Published: 2025-10-08
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.07118v3

Instruction tuning is essential for aligning large language models (LLMs) to downstream tasks and commonly relies on large, diverse corpora. However, small, high-quality subsets, known as coresets, can deliver comparable or superior results, though curating them remains challenging. Existing methods often rely on coarse, sample-level signals like gradients, an approach that is computationally expensive and overlooks fine-grained features. To address this, we introduce TRIM (Token Relevance via Interpretable Multi-layer Attention), a forward-only, token-centric framework. Instead of using gradients, TRIM operates by matching underlying representational patterns identified via attention-based "fingerprints" from a handful of target samples. Such an approach makes TRIM highly efficient and uniquely sensitive to the structural features that define a task. Coresets selected by our method consistently outperform state-of-the-art baselines by up to 9% on downstream tasks and even surpass the performance of full-data fine-tuning in some settings. By avoiding expensive backward passes, TRIM achieves this at a fraction of the computational cost. These findings establish TRIM as a scalable and efficient alternative for building high-quality instruction-tuning datasets.

---

### The Conditions of Physical Embodiment Enable Generalization and Care

Authors: Leonardo Christov-Moore, Arthur Juliani, Alex Kiefer, Joel Lehman, Nicco Reggente, B. Scot Rousse, Adam Safron, Nicolás Hinrichs, Daniel Polani, Antonio Damasio
Published: 2025-10-08
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.07117v3

As artificial agents enter open-ended physical environments -- eldercare, disaster response, and space missions -- they must persist under uncertainty while providing reliable care. Yet current systems struggle to generalize across distribution shifts and lack intrinsic motivation to preserve the well-being of others. Vulnerability and mortality are often seen as constraints to be avoided, yet organisms survive and provide care in an open-ended world with relative ease and efficiency. We argue that generalization and care arise from conditions of physical embodiment: being-in-the-world (the agent is a part of the environment) and being-towards-death (unless counteracted, the agent drifts toward terminal states). These conditions necessitate a homeostatic drive to maintain oneself and maximize the future capacity to continue doing so. Fulfilling this drive over long time horizons in multi-agent environments necessitates robust causal modeling of self and others' embodiment and jointly achievable future states. Because embodied agents are part of the environment, with the self delimited by reliable control, empowering others can expand self-boundaries, enabling other-regard. This provides a path from embodiment toward generalization and care based in shared constraints. We outline a reinforcement-learning framework for examining these questions. Homeostatic mortal agents continually learning in open-ended environments may offer efficient robustness and trustworthy alignment.

---

### Enhancing Concept Localization in CLIP-based Concept Bottleneck Models

Authors: Rémi Kazmierczak, Steve Azzolin, Eloïse Berthier, Goran Frehse, Gianni Franchi
Published: 2025-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.07115v1

This paper addresses explainable AI (XAI) through the lens of Concept Bottleneck Models (CBMs) that do not require explicit concept annotations, relying instead on concepts extracted using CLIP in a zero-shot manner. We show that CLIP, which is central in these techniques, is prone to concept hallucination, incorrectly predicting the presence or absence of concepts within an image in scenarios used in numerous CBMs, hence undermining the faithfulness of explanations. To mitigate this issue, we introduce Concept Hallucination Inhibition via Localized Interpretability (CHILI), a technique that disentangles image embeddings and localizes pixels corresponding to target concepts. Furthermore, our approach supports the generation of saliency-based explanations that are more interpretable.

---

### GNN-enhanced Traffic Anomaly Detection for Next-Generation SDN-Enabled Consumer Electronics

Authors: Guan-Yan Yang, Farn Wang, Kuo-Hui Yeh
Published: 2025-10-08
Categories: cs.CR, cs.LG, cs.NI
arXiv: https://arxiv.org/abs/2510.07109v1

Consumer electronics (CE) connected to the Internet of Things are susceptible to various attacks, including DDoS and web-based threats, which can compromise their functionality and facilitate remote hijacking. These vulnerabilities allow attackers to exploit CE for broader system attacks while enabling the propagation of malicious code across the CE network, resulting in device failures. Existing deep learning-based traffic anomaly detection systems exhibit high accuracy in traditional network environments but are often overly complex and reliant on static infrastructure, necessitating manual configuration and management. To address these limitations, we propose a scalable network model that integrates Software-defined Networking (SDN) and Compute First Networking (CFN) for next-generation CE networks. In this network model, we propose a Graph Neural Networks-based Network Anomaly Detection framework (GNN-NAD) that integrates SDN-based CE networks and enables the CFN architecture. GNN-NAD uniquely fuses a static, vulnerability-aware attack graph with dynamic traffic features, providing a holistic view of network security. The core of the framework is a GNN model (GSAGE) for graph representation learning, followed by a Random Forest (RF) classifier. This design (GSAGE+RF) demonstrates superior performance compared to existing feature selection methods. Experimental evaluations on CE environment reveal that GNN-NAD achieves superior metrics in accuracy, recall, precision, and F1 score, even with small sample sizes, exceeding the performance of current network anomaly detection methods. This work advances the security and efficiency of next-generation intelligent CE networks.

---

### Active Control of Turbulent Airfoil Flows Using Adjoint-based Deep Learning

Authors: Xuemin Liu, Tom Hickling, Jonathan F. MacArt
Published: 2025-10-08
Categories: physics.flu-dyn, cs.LG
arXiv: https://arxiv.org/abs/2510.07106v1

We train active neural-network flow controllers using a deep learning PDE augmentation method to optimize lift-to-drag ratios in turbulent airfoil flows at Reynolds number $5\times10^4$ and Mach number 0.4. Direct numerical simulation and large eddy simulation are employed to model compressible, unconfined flow over two- and three-dimensional semi-infinite NACA 0012 airfoils at angles of attack $α= 5^\circ$, $10^\circ$, and $15^\circ$. Control actions, implemented through a blowing/suction jet at a fixed location and geometry on the upper surface, are adaptively determined by a neural network that maps local pressure measurements to optimal jet total pressure, enabling a sensor-informed control policy that responds spatially and temporally to unsteady flow conditions. The sensitivities of the flow to the neural network parameters are computed using the adjoint Navier-Stokes equations, which we construct using automatic differentiation applied to the flow solver. The trained flow controllers significantly improve the lift-to-drag ratios and reduce flow separation for both two- and three-dimensional airfoil flows, especially at $α= 5^\circ$ and $10^\circ$. The 2D-trained models remain effective when applied out-of-sample to 3D flows, which demonstrates the robustness of the adjoint-trained control approach. The 3D-trained models capture the flow dynamics even more effectively, which leads to better energy efficiency and comparable performance for both adaptive (neural network) and offline (simplified, constant-pressure) controllers. These results underscore the effectiveness of this learning-based approach in improving aerodynamic performance.

---

### Opt-ICL at LeWiDi-2025: Maximizing In-Context Signal from Rater Examples via Meta-Learning

Authors: Taylor Sorensen, Yejin Choi
Published: 2025-10-08
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.07105v1

Many natural language processing (NLP) tasks involve subjectivity, ambiguity, or legitimate disagreement between annotators. In this paper, we outline our system for modeling human variation. Our system leverages language models' (LLMs) in-context learning abilities, along with a two-step meta-learning training procedure for 1) post-training on many datasets requiring in-context learning and 2) specializing the model via in-context meta-learning to the particular data distribution of interest. We also evaluate the performance of our system submission to the Learning With Disagreements (LeWiDi) competition, where it was the overall winner on both tasks. Additionally, we perform an ablation study to measure the importance of each system component. We find that including rater examples in-context is crucial for our system's performance, dataset-specific fine-tuning is helpful on the larger datasets, post-training on other in-context datasets is helpful on one of the competition datasets, and that performance improves with model scale.

---

### Diffusion-Augmented Reinforcement Learning for Robust Portfolio Optimization under Stress Scenarios

Authors: Himanshu Choudhary, Arishi Orra, Manoj Thakur
Published: 2025-10-08
Categories: stat.ML, cs.CE, cs.LG, q-fin.CP
arXiv: https://arxiv.org/abs/2510.07099v1

In the ever-changing and intricate landscape of financial markets, portfolio optimisation remains a formidable challenge for investors and asset managers. Conventional methods often struggle to capture the complex dynamics of market behaviour and align with diverse investor preferences. To address this, we propose an innovative framework, termed Diffusion-Augmented Reinforcement Learning (DARL), which synergistically integrates Denoising Diffusion Probabilistic Models (DDPMs) with Deep Reinforcement Learning (DRL) for portfolio management. By leveraging DDPMs to generate synthetic market crash scenarios conditioned on varying stress intensities, our approach significantly enhances the robustness of training data. Empirical evaluations demonstrate that DARL outperforms traditional baselines, delivering superior risk-adjusted returns and resilience against unforeseen crises, such as the 2025 Tariff Crisis. This work offers a robust and practical methodology to bolster stress resilience in DRL-driven financial applications.

---

### TALENT: Table VQA via Augmented Language-Enhanced Natural-text Transcription

Authors: Guo Yutong, Wanying Wang, Yue Wu, Zichen Miao, Haoyu Wang
Published: 2025-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.07098v1

Table Visual Question Answering (Table VQA) is typically addressed by large vision-language models (VLMs). While such models can answer directly from images, they often miss fine-grained details unless scaled to very large sizes, which are computationally prohibitive, especially for mobile deployment. A lighter alternative is to have a small VLM perform OCR and then use a large language model (LLM) to reason over structured outputs such as Markdown tables. However, these representations are not naturally optimized for LLMs and still introduce substantial errors. We propose TALENT (Table VQA via Augmented Language-Enhanced Natural-text Transcription), a lightweight framework that leverages dual representations of tables. TALENT prompts a small VLM to produce both OCR text and natural language narration, then combines them with the question for reasoning by an LLM. This reframes Table VQA as an LLM-centric multimodal reasoning task, where the VLM serves as a perception-narration module rather than a monolithic solver. Additionally, we construct ReTabVQA, a more challenging Table VQA dataset requiring multi-step quantitative reasoning over table images. Experiments show that TALENT enables a small VLM-LLM combination to match or surpass a single large VLM at significantly lower computational cost on both public datasets and ReTabVQA.

---

### Modeling Sarcastic Speech: Semantic and Prosodic Cues in a Speech Synthesis Framework

Authors: Zhu Li, Yuqing Zhang, Xiyuan Gao, Shekhar Nayak, Matt Coler
Published: 2025-10-08
Categories: cs.CL, cs.SD, eess.AS
arXiv: https://arxiv.org/abs/2510.07096v3

Sarcasm is a pragmatic phenomenon in which speakers convey meanings that diverge from literal content, relying on an interaction between semantics and prosodic expression. However, how these cues jointly contribute to the recognition of sarcasm remains poorly understood. We propose a computational framework that models sarcasm as the integration of semantic interpretation and prosodic realization. Semantic cues are derived from an LLaMA 3 model fine-tuned to capture discourse-level markers of sarcastic intent, while prosodic cues are extracted through semantically aligned utterances drawn from a database of sarcastic speech, providing prosodic exemplars of sarcastic delivery. Using a speech synthesis testbed, perceptual evaluations show that semantic and prosodic cues enhance perceived sarcasm, with the combined system achieving the best downstream F1 while maintaining high subjective sarcasm ratings. These findings highlight the complementary roles of semantics and prosody in pragmatic interpretation and illustrate how modeling can shed light on the mechanisms underlying sarcastic communication.

---

### Non-Asymptotic Analysis of Efficiency in Conformalized Regression

Authors: Yunzhen Yao, Lie He, Michael Gastpar
Published: 2025-10-08
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.07093v3

Conformal prediction provides prediction sets with coverage guarantees. The informativeness of conformal prediction depends on its efficiency, typically quantified by the expected size of the prediction set. Prior work on the efficiency of conformalized regression commonly treats the miscoverage level $α$ as a fixed constant. In this work, we establish non-asymptotic bounds on the deviation of the prediction set length from the oracle interval length for conformalized quantile and median regression trained via SGD, under mild assumptions on the data distribution. Our bounds of order $\mathcal{O}(1/\sqrt{n} + 1/(α^2 n) + 1/\sqrt{m} + \exp(-α^2 m))$ capture the joint dependence of efficiency on the proper training set size $n$, the calibration set size $m$, and the miscoverage level $α$. The results identify phase transitions in convergence rates across different regimes of $α$, offering guidance for allocating data to control excess prediction set length. Empirical results are consistent with our theoretical findings.

---

### Generative World Modelling for Humanoids: 1X World Model Challenge Technical Report

Authors: Riccardo Mereu, Aidan Scannell, Yuxin Hou, Yi Zhao, Aditya Jitta, Antonio Dominguez, Luigi Acerbi, Amos Storkey, Paul Chang
Published: 2025-10-08
Categories: cs.LG, cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2510.07092v1

World models are a powerful paradigm in AI and robotics, enabling agents to reason about the future by predicting visual observations or compact latent states. The 1X World Model Challenge introduces an open-source benchmark of real-world humanoid interaction, with two complementary tracks: sampling, focused on forecasting future image frames, and compression, focused on predicting future discrete latent codes. For the sampling track, we adapt the video generation foundation model Wan-2.2 TI2V-5B to video-state-conditioned future frame prediction. We condition the video generation on robot states using AdaLN-Zero, and further post-train the model using LoRA. For the compression track, we train a Spatio-Temporal Transformer model from scratch. Our models achieve 23.0 dB PSNR in the sampling task and a Top-500 CE of 6.6386 in the compression task, securing 1st place in both challenges.

---

### The Cognitive Bandwidth Bottleneck: Shifting Long-Horizon Agent from Planning with Actions to Planning with Schemas

Authors: Baixuan Xu, Tianshi Zheng, Zhaowei Wang, Hong Ting Tsang, Weiqi Wang, Tianqing Fang, Yangqiu Song
Published: 2025-10-08
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.07091v1

Enabling LLMs to effectively operate long-horizon task which requires long-term planning and multiple interactions is essential for open-world autonomy. Conventional methods adopt planning with actions where a executable action list would be provided as reference. However, this action representation choice would be impractical when the environment action space is combinatorial exploded (e.g., open-ended real world). This naturally leads to a question: As environmental action space scales, what is the optimal action representation for long-horizon agents? In this paper, we systematically study the effectiveness of two different action representations. The first one is conventional planning with actions (PwA) which is predominantly adopted for its effectiveness on existing benchmarks. The other one is planning with schemas (PwS) which instantiate an action schema into action lists (e.g., "move (OBJ) to (OBJ)" -> "move apple to desk") to ensure concise action space and reliable scalability. This alternative is motivated by its alignment with human cognition and its compliance with environment-imposed action format restriction. We propose cognitive bandwidth perspective as a conceptual framework to qualitatively understand the differences between these two action representations and empirically observe a representation-choice inflection point between ALFWorld (~35 actions) and SciWorld (~500 actions), which serve as evidence of the need for scalable representations. We further conduct controlled experiments to study how the location of this inflection point interacts with different model capacities: stronger planning proficiency shifts the inflection rightward, whereas better schema instantiation shifts it leftward. Finally, noting the suboptimal performance of PwS agents, we provide an actionable guide for building more capable PwS agents for better scalable autonomy.

---

### DADO: A Depth-Attention framework for Object Discovery

Authors: Federico Gonzalez, Estefania Talavera, Petia Radeva
Published: 2025-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.07089v1

Unsupervised object discovery, the task of identifying and localizing objects in images without human-annotated labels, remains a significant challenge and a growing focus in computer vision. In this work, we introduce a novel model, DADO (Depth-Attention self-supervised technique for Discovering unseen Objects), which combines an attention mechanism and a depth model to identify potential objects in images. To address challenges such as noisy attention maps or complex scenes with varying depth planes, DADO employs dynamic weighting to adaptively emphasize attention or depth features based on the global characteristics of each image. We evaluated DADO on standard benchmarks, where it outperforms state-of-the-art methods in object discovery accuracy and robustness without the need for fine-tuning.

---

### Fourier Analysis on the Boolean Hypercube via Hoeffding Functional Decomposition

Authors: Baptiste Ferrere, Nicolas Bousquet, Fabrice Gamboa, Jean-Michel Loubes, Joseph Muré
Published: 2025-10-08
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.07088v4

Fourier analysis on the Boolean hypercube is fundamentally defined as the orthogonal decomposition of the space of pseudo-Boolean functions with respect to the uniform probability measure. In this work, we propose an ANOVA-based generalization of the Fourier decomposition on the Boolean hypercube endowed with any arbitrary probability measure. We provide an \emph{explicit} decomposition basis which generalizes the Walsh-Hadamard (or parity functions) basis under any \emph{arbitrary} probability measure on the Boolean hypercube. We formulate the computation of the entire functional decomposition as a least squares problem and also provide a method to address the classical \emph{curse of dimensionality} challenge. We provide a comprehensive generalization of Fourier analysis on the Boolean hypercube, enabling the handling of non-uniform configuration spaces inherent to real-world machine learning tasks, \textit{e.g.} when dealing with \emph{one-hot encoded} features. Finally, we demonstrate its practical impact in the field of explainable AI, by conducting comparative studies with feature attribution methods such as SHAP or TreeHFD.

---

### Non-Stationary Online Structured Prediction with Surrogate Losses

Authors: Shinsaku Sakaue, Han Bao, Yuzhou Cao
Published: 2025-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.07086v2

Online structured prediction, including online classification as a special case, is the task of sequentially predicting labels from input features. In this setting, the surrogate regret -- the cumulative excess of the actual target loss (e.g., the 0-1 loss) over the surrogate loss (e.g., the logistic loss) incurred by the best fixed estimator -- has gained attention because it admits a finite bound independent of the time horizon $T$. However, such guarantees break down in non-stationary environments, where every fixed estimator may incur surrogate loss that grows linearly with $T$. To address this limitation, we obtain an upper bound of $F_T + O(1 + P_T)$ on the cumulative target loss, where $F_T$ is the cumulative surrogate loss of any comparator sequence and $P_T$ is its path length. This bound depends on $T$ only through $F_T$ and $P_T$, thus offering stronger guarantees under non-stationarity. Our core idea is to combine the dynamic regret analysis of online gradient descent (OGD) with the exploit-the-surrogate-gap technique. This viewpoint sheds light on the usefulness of a Polyak-style learning rate for OGD, which systematically yields target-loss bounds and performs well empirically. We then extend our approach to broader settings beyond prior work via the convolutional Fenchel--Young loss. Finally, a lower bound shows that the dependence on $F_T$ and $P_T$ is tight.

---

### HTMformer: Hybrid Time and Multivariate Transformer for Time Series Forecasting

Authors: Tan Wang, Yun Wei Dong, Qi Wang
Published: 2025-10-08
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.07084v3

Transformer-based methods have achieved impressive results in time series forecasting. However, existing Transformers still exhibit limitations in sequence modeling as they tend to overemphasize temporal dependencies. This incurs additional computational overhead without yielding corresponding performance gains. We find that the performance of Transformers is highly dependent on the embedding method used to learn effective representations. To address this issue, we extract multivariate features to augment the effective information captured in the embedding layer, yielding multidimensional embeddings that convey richer and more meaningful sequence representations. These representations enable Transformer-based forecasters to better understand the series. Specifically, we introduce Hybrid Temporal and Multivariate Embeddings (HTME). The HTME extractor integrates a lightweight temporal feature extraction module with a carefully designed multivariate feature extraction module to provide complementary features, thereby achieving a balance between model complexity and performance. By combining HTME with the Transformer architecture, we present HTMformer, leveraging the enhanced feature extraction capability of the HTME extractor to build a lightweight forecaster. Experiments conducted on eight real-world datasets demonstrate that our approach outperforms existing baselines in both accuracy and efficiency.

---

### All Claims Are Equal, but Some Claims Are More Equal Than Others: Importance-Sensitive Factuality Evaluation of LLM Generations

Authors: Miriam Wanner, Leif Azzopardi, Paul Thomas, Soham Dan, Benjamin Van Durme, Nick Craswell
Published: 2025-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.07083v1

Existing methods for evaluating the factuality of large language model (LLM) responses treat all claims as equally important. This results in misleading evaluations when vital information is missing or incorrect as it receives the same weight as peripheral details, raising the question: how can we reliably detect such differences when there are errors in key information? Current approaches that measure factuality tend to be insensitive to omitted or false key information. To investigate this lack of sensitivity, we construct VITALERRORS, a benchmark of 6,733 queries with minimally altered LLM responses designed to omit or falsify key information. Using this dataset, we demonstrate the insensitivities of existing evaluation metrics to key information errors. To address this gap, we introduce VITAL, a set of metrics that provide greater sensitivity in measuring the factuality of responses by incorporating the relevance and importance of claims with respect to the query. Our analysis demonstrates that VITAL metrics more reliably detect errors in key information than previous methods. Our dataset, metrics, and analysis provide a foundation for more accurate and robust assessment of LLM factuality.

---

### Accelerating Diffusion LLM Inference via Local Determinism Propagation

Authors: Fanheng Kong, Jingyuan Zhang, Yahui Liu, Zirui Wu, Yu Tian, Victoria W., Guorui Zhou
Published: 2025-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.07081v1

Diffusion large language models (dLLMs) represent a significant advancement in text generation, offering parallel token decoding capabilities. However, existing open-source implementations suffer from quality-speed trade-offs that impede their practical deployment. Conservative sampling strategies typically decode only the most confident token per step to ensure quality (i.e., greedy decoding), at the cost of inference efficiency due to repeated redundant refinement iterations--a phenomenon we term delayed decoding. Through systematic analysis of dLLM decoding dynamics, we characterize this delayed decoding behavior and propose a training-free adaptive parallel decoding strategy, named LocalLeap, to address these inefficiencies. LocalLeap is built on two fundamental empirical principles: local determinism propagation centered on high-confidence anchors and progressive spatial consistency decay. By applying these principles, LocalLeap identifies anchors and performs localized relaxed parallel decoding within bounded neighborhoods, achieving substantial inference step reduction through early commitment of already-determined tokens without compromising output quality. Comprehensive evaluation on various benchmarks demonstrates that LocalLeap achieves 6.94$\times$ throughput improvements and reduces decoding steps to just 14.2\% of the original requirement, achieving these gains with negligible performance impact. The source codes are available at: https://github.com/friedrichor/LocalLeap.

---

### Pseudo-MDPs: A Novel Framework for Efficiently Optimizing Last Revealer Seed Manipulations in Blockchains

Authors: Maxime Reynouard
Published: 2025-10-08
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2510.07080v1

This study tackles the computational challenges of solving Markov Decision Processes (MDPs) for a restricted class of problems. It is motivated by the Last Revealer Attack (LRA), which undermines fairness in some Proof-of-Stake (PoS) blockchains such as Ethereum (\$400B market capitalization). We introduce pseudo-MDPs (pMDPs) a framework that naturally models such problems and propose two distinct problem reductions to standard MDPs. One problem reduction provides a novel, counter-intuitive perspective, and combining the two problem reductions enables significant improvements in dynamic programming algorithms such as value iteration. In the case of the LRA which size is parameterized by $κ$ (in Ethereum's case $κ$= 325), we reduce the computational complexity from $O(2^κκ^{2^{κ+2}})$ to $O(κ^4)$ (per iteration). This solution also provide the usual benefits from Dynamic Programming solutions: exponentially fast convergence toward the optimal solution is guaranteed. The dual perspective also simplifies policy extraction, making the approach well-suited for resource-constrained agents who can operate with very limited memory and computation once the problem has been solved. Furthermore, we generalize those results to a broader class of MDPs, enhancing their applicability. The framework is validated through two case studies: a fictional card game and the LRA on the Ethereum random seed consensus protocol. These applications demonstrate the framework's ability to solve large-scale problems effectively while offering actionable insights into optimal strategies. This work advances the study of MDPs and contributes to understanding security vulnerabilities in blockchain systems.

---

### Vision-Language-Action Models for Robotics: A Review Towards Real-World Applications

Authors: Kento Kawaharazuka, Jihoon Oh, Jun Yamada, Ingmar Posner, Yuke Zhu
Published: 2025-10-08
Categories: cs.RO, cs.AI, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.07077v1

Amid growing efforts to leverage advances in large language models (LLMs) and vision-language models (VLMs) for robotics, Vision-Language-Action (VLA) models have recently gained significant attention. By unifying vision, language, and action data at scale, which have traditionally been studied separately, VLA models aim to learn policies that generalise across diverse tasks, objects, embodiments, and environments. This generalisation capability is expected to enable robots to solve novel downstream tasks with minimal or no additional task-specific data, facilitating more flexible and scalable real-world deployment. Unlike previous surveys that focus narrowly on action representations or high-level model architectures, this work offers a comprehensive, full-stack review, integrating both software and hardware components of VLA systems. In particular, this paper provides a systematic review of VLAs, covering their strategy and architectural transition, architectures and building blocks, modality-specific processing techniques, and learning paradigms. In addition, to support the deployment of VLAs in real-world robotic applications, we also review commonly used robot platforms, data collection strategies, publicly available datasets, data augmentation methods, and evaluation benchmarks. Throughout this comprehensive survey, this paper aims to offer practical guidance for the robotics community in applying VLAs to real-world robotic systems. All references categorized by training approach, evaluation method, modality, and dataset are available in the table on our project website: https://vla-survey.github.io .

---

### LuxInstruct: A Cross-Lingual Instruction Tuning Dataset For Luxembourgish

Authors: Fred Philippy, Laura Bernardy, Siwen Guo, Jacques Klein, Tegawendé F. Bissyandé
Published: 2025-10-08
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.07074v2

Instruction tuning has become a key technique for enhancing the performance of large language models, enabling them to better follow human prompts. However, low-resource languages such as Luxembourgish face severe limitations due to the lack of high-quality instruction datasets. Traditional reliance on machine translation often introduces semantic misalignment and cultural inaccuracies. In this work, we address these challenges by creating a cross-lingual instruction tuning dataset for Luxembourgish, without resorting to machine-generated translations into it. Instead, by leveraging aligned data from English, French, and German, we build a high-quality dataset that preserves linguistic and cultural nuances. We provide evidence that cross-lingual instruction tuning not only improves representational alignment across languages but also the model's generative capabilities in Luxembourgish. This highlights how cross-lingual data curation can avoid the common pitfalls of machine-translated data and directly benefit low-resource language development.

---

### VRPAgent: LLM-Driven Discovery of Heuristic Operators for Vehicle Routing Problems

Authors: André Hottung, Federico Berto, Chuanbo Hua, Nayeli Gast Zepeda, Daniel Wetzel, Michael Römer, Haoran Ye, Davide Zago, Michael Poli, Stefano Massaroli, Jinkyoo Park, Kevin Tierney
Published: 2025-10-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.07073v1

Designing high-performing heuristics for vehicle routing problems (VRPs) is a complex task that requires both intuition and deep domain knowledge. Large language model (LLM)-based code generation has recently shown promise across many domains, but it still falls short of producing heuristics that rival those crafted by human experts. In this paper, we propose VRPAgent, a framework that integrates LLM-generated components into a metaheuristic and refines them through a novel genetic search. By using the LLM to generate problem-specific operators, embedded within a generic metaheuristic framework, VRPAgent keeps tasks manageable, guarantees correctness, and still enables the discovery of novel and powerful strategies. Across multiple problems, including the capacitated VRP, the VRP with time windows, and the prize-collecting VRP, our method discovers heuristic operators that outperform handcrafted methods and recent learning-based approaches while requiring only a single CPU core. To our knowledge, \VRPAgent is the first LLM-based paradigm to advance the state-of-the-art in VRPs, highlighting a promising future for automated heuristics discovery.

---

### Blind Construction of Angular Power Maps in Massive MIMO Networks

Authors: Zheng Xing, Junting Chen
Published: 2025-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.07071v1

Channel state information (CSI) acquisition is a challenging problem in massive multiple-input multiple-output (MIMO) networks. Radio maps provide a promising solution for radio resource management by reducing online CSI acquisition. However, conventional approaches for radio map construction require location-labeled CSI data, which is challenging in practice. This paper investigates unsupervised angular power map construction based on large timescale CSI data collected in a massive MIMO network without location labels. A hidden Markov model (HMM) is built to connect the hidden trajectory of a mobile with the CSI evolution of a massive MIMO channel. As a result, the mobile location can be estimated, enabling the construction of an angular power map. We show that under uniform rectilinear mobility with Poisson-distributed base stations (BSs), the Cramer-Rao Lower Bound (CRLB) for localization error can vanish at any signal-to-noise ratios (SNRs), whereas when BSs are confined to a limited region, the error remains nonzero even with infinite independent measurements. Based on reference signal received power (RSRP) data collected in a real multi-cell massive MIMO network, an average localization error of 18 meters can be achieved although measurements are mainly obtained from a single serving cell.

---

### Inductive Learning for Possibilistic Logic Programs Under Stable Models

Authors: Hongbo Hu, Yisong Wang, Yi Huang, Kewen Wang
Published: 2025-10-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.07069v1

Possibilistic logic programs (poss-programs) under stable models are a major variant of answer set programming (ASP). While its semantics (possibilistic stable models) and properties have been well investigated, the problem of inductive reasoning has not been investigated yet. This paper presents an approach to extracting poss-programs from a background program and examples (parts of intended possibilistic stable models). To this end, the notion of induction tasks is first formally defined, its properties are investigated and two algorithms ilpsm and ilpsmmin for computing induction solutions are presented. An implementation of ilpsmmin is also provided and experimental results show that when inputs are ordinary logic programs, the prototype outperforms a major inductive learning system for normal logic programs from stable models on the datasets that are randomly generated.

---

### Prompt Optimization Across Multiple Agents for Representing Diverse Human Populations

Authors: Manh Hung Nguyen, Sebastian Tschiatschek, Adish Singla
Published: 2025-10-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.07064v1

The difficulty and expense of obtaining large-scale human responses make Large Language Models (LLMs) an attractive alternative and a promising proxy for human behavior. However, prior work shows that LLMs often produce homogeneous outputs that fail to capture the rich diversity of human perspectives and behaviors. Thus, rather than trying to capture this diversity with a single LLM agent, we propose a novel framework to construct a set of agents that collectively capture the diversity of a given human population. Each agent is an LLM whose behavior is steered by conditioning on a small set of human demonstrations (task-response pairs) through in-context learning. The central challenge is therefore to select a representative set of LLM agents from the exponentially large space of possible agents. We tackle this selection problem from the lens of submodular optimization. In particular, we develop methods that offer different trade-offs regarding time complexity and performance guarantees. Extensive experiments in crowdsourcing and educational domains demonstrate that our approach constructs agents that more effectively represent human populations compared to baselines. Moreover, behavioral analyses on new tasks show that these agents reproduce the behavior patterns and perspectives of the students and annotators they are designed to represent.

---

### Revisiting Metric Reliability for Fine-grained Evaluation of Machine Translation and Summarization in Indian Languages

Authors: Amir Hossein Yari, Kalmit Kulkarni, Ahmad Raza Khan, Fajri Koto
Published: 2025-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.07061v2

While automatic metrics drive progress in Machine Translation (MT) and Text Summarization (TS), existing metrics have been developed and validated almost exclusively for English and other high-resource languages. This narrow focus leaves Indian languages, spoken by over 1.5 billion people, largely overlooked, casting doubt on the universality of current evaluation practices. To address this gap, we introduce ITEM, a large-scale benchmark that systematically evaluates the alignment of 29 automatic metrics with human judgments across six major Indian languages, enriched with fine-grained annotations. Our extensive evaluation, covering agreement with human judgments, sensitivity to outliers, language-specific reliability, inter-metric correlations, and resilience to controlled perturbations reveals four central findings: (1) LLM-based evaluators show the strongest alignment with human judgments at both segment and system levels; (2) outliers exert a significant impact on metric-human agreement; (3) In TS, metrics are more effective at capturing content fidelity, whereas in MT, they better reflect fluency; and (4) Metrics differ in their robustness and sensitivity when subjected to diverse perturbations. Collectively, these findings offer critical guidance for advancing metric design and evaluation in Indian languages.

---

### Does Local News Stay Local?: Online Content Shifts in Sinclair-Acquired Stations

Authors: Miriam Wanner, Sophia Hager, Anjalie Field
Published: 2025-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.07060v2

Local news stations are often considered to be reliable sources of non-politicized information, particularly local concerns that residents care about. Because these stations are trusted news sources, viewers are particularly susceptible to the information they report. The Sinclair Broadcast group is a broadcasting company that has acquired many local news stations in the last decade. We investigate the effects of local news stations being acquired by Sinclair: how does coverage change? We use computational methods to investigate changes in internet content put out by local news stations before and after being acquired by Sinclair and in comparison to national news outlets. We find that there is clear evidence that local news stations report more frequently on national news at the expense of local topics, and that their coverage of polarizing national topics increases.

---

### Concept Retrieval -- What and How?

Authors: Ori Nizan, Oren Shrout, Ayellet Tal
Published: 2025-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.07058v3

A concept may reflect either a concrete or abstract idea. Given an input image, this paper seeks to retrieve other images that share its central concepts, capturing aspects of the underlying narrative. This goes beyond conventional retrieval or clustering methods, which emphasize visual or semantic similarity. We formally define the problem, outline key requirements, and introduce appropriate evaluation metrics. We propose a novel approach grounded in two key observations: (1) While each neighbor in the embedding space typically shares at least one concept with the query, not all neighbors necessarily share the same concept with one another. (2) Modeling this neighborhood with a bimodal Gaussian distribution uncovers meaningful structure that facilitates concept identification. Qualitative, quantitative, and human evaluations confirm the effectiveness of our approach. See the package on PyPI: https://pypi.org/project/coret/

---

### Introspection in Learned Semantic Scene Graph Localisation

Authors: Manshika Charvi Bissessur, Efimia Panagiotaki, Daniele De Martini
Published: 2025-10-08
Categories: cs.LG, cs.AI, cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2510.07053v1

This work investigates how semantics influence localisation performance and robustness in a learned self-supervised, contrastive semantic localisation framework. After training a localisation network on both original and perturbed maps, we conduct a thorough post-hoc introspection analysis to probe whether the model filters environmental noise and prioritises distinctive landmarks over routine clutter. We validate various interpretability methods and present a comparative reliability analysis. Integrated gradients and Attention Weights consistently emerge as the most reliable probes of learned behaviour. A semantic class ablation further reveals an implicit weighting in which frequent objects are often down-weighted. Overall, the results indicate that the model learns noise-robust, semantically salient relations about place definition, thereby enabling explainable registration under challenging visual and structural variations.

---

### Enhancing Speech Emotion Recognition via Fine-Tuning Pre-Trained Models and Hyper-Parameter Optimisation

Authors: Aryan Golbaghi, Shuo Zhou
Published: 2025-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.07052v1

We propose a workflow for speech emotion recognition (SER) that combines pre-trained representations with automated hyperparameter optimisation (HPO). Using SpeechBrain wav2vec2-base model fine-tuned on IEMOCAP as the encoder, we compare two HPO strategies, Gaussian Process Bayesian Optimisation (GP-BO) and Tree-structured Parzen Estimators (TPE), under an identical four-dimensional search space and 15-trial budget, with balanced class accuracy (BCA) on the German EmoDB corpus as the objective. All experiments run on 8 CPU cores with 32 GB RAM. GP-BO achieves 0.96 BCA in 11 minutes, and TPE (Hyperopt implementation) attains 0.97 in 15 minutes. In contrast, grid search requires 143 trials and 1,680 minutes to exceed 0.9 BCA, and the best AutoSpeech 2020 baseline reports only 0.85 in 30 minutes on GPU. For cross-lingual generalisation, an EmoDB-trained HPO-tuned model improves zero-shot accuracy by 0.25 on CREMA-D and 0.26 on RAVDESS. Results show that efficient HPO with pre-trained encoders delivers competitive SER on commodity CPUs. Source code to this work is available at: https://github.com/youngaryan/speechbrain-emotion-hpo.

---

### Search-R3: Unifying Reasoning and Embedding in Large Language Models

Authors: Yuntao Gui, James Cheng
Published: 2025-10-08
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.07048v2

Despite their remarkable natural language understanding capabilities, Large Language Models (LLMs) have been underutilized for retrieval tasks. We present Search-R3, a novel framework that addresses this limitation by adapting LLMs to generate search embeddings as a direct output of their reasoning process. Our approach exploits LLMs' chain-of-thought capabilities, allowing them to produce more effective embeddings by reasoning step-by-step through complex semantic analyses. We implement this through three complementary mechanisms. (1) a supervised learning stage enables the model's ability to produce quality embeddings, (2) a reinforcement learning (RL) methodology that optimizes embedding generation alongside reasoning, and (3) a specialized RL environment that efficiently handles evolving embedding representations without requiring complete corpus re-encoding at each training iteration. Our extensive evaluations on diverse benchmarks demonstrate that Search-R3 significantly outperforms prior methods by unifying the reasoning and embedding generation processes. This integrated post-training approach represents a substantial advancement in handling complex knowledge-intensive tasks that require both sophisticated reasoning and effective information retrieval. Project page: https://github.com/ytgui/Search-R3

---