# Research Papers — 2025-10 · bundle page 57 of 217

> Full-text markdown of papers #2801–2850 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/57
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/56.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/58.md)

### From Masks to Worlds: A Hitchhiker's Guide to World Models

Authors: Jinbin Bai, Yu Lei, Hecong Wu, Yuchen Zhu, Shufan Li, Yi Xin, Xiangtai Li, Molei Tao, Aditya Grover, Ming-Hsuan Yang
Published: 2025-10-23
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.20668v1

This is not a typical survey of world models; it is a guide for those who want to build worlds. We do not aim to catalog every paper that has ever mentioned a ``world model". Instead, we follow one clear road: from early masked models that unified representation learning across modalities, to unified architectures that share a single paradigm, then to interactive generative models that close the action-perception loop, and finally to memory-augmented systems that sustain consistent worlds over time. We bypass loosely related branches to focus on the core: the generative heart, the interactive loop, and the memory system. We show that this is the most promising path towards true world models.

---

### Bayesian Jammer Localization with a Hybrid CNN and Path-Loss Mixture of Experts

Authors: Mariona Jaramillo-Civill, Luis González-Gudiño, Tales Imbiriba, Pau Closas
Published: 2025-10-23
Categories: cs.LG, eess.SP
arXiv: https://arxiv.org/abs/2510.20666v1

Global Navigation Satellite System (GNSS) signals are vulnerable to jamming, particularly in urban areas where multipath and shadowing distort received power. Previous data-driven approaches achieved reasonable localization but poorly reconstructed the received signal strength (RSS) field due to limited spatial context. We propose a hybrid Bayesian mixture-of-experts framework that fuses a physical path-loss (PL) model and a convolutional neural network (CNN) through log-linear pooling. The PL expert ensures physical consistency, while the CNN leverages building-height maps to capture urban propagation effects. Bayesian inference with Laplace approximation provides posterior uncertainty over both the jammer position and RSS field. Experiments on urban ray-tracing data show that localization accuracy improves and uncertainty decreases with more training points, while uncertainty concentrates near the jammer and along urban canyons where propagation is most sensitive.

---

### The Shape of Reasoning: Topological Analysis of Reasoning Traces in Large Language Models

Authors: Xue Wen Tan, Nathaniel Tan, Galen Lee, Stanley Kok
Published: 2025-10-23
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.20665v3

Evaluating the quality of reasoning traces from large language models remains understudied, labor-intensive, and unreliable: current practice relies on expert rubrics, manual annotation, and slow pairwise judgments. Automated efforts are dominated by graph-based proxies that quantify structural connectivity but do not clarify what constitutes high-quality reasoning; such abstractions can be overly simplistic for inherently complex processes. We introduce a topological data analysis (TDA)-based evaluation framework that captures the geometry of reasoning traces and enables label-efficient, automated assessment. In our empirical study, topological features yield substantially higher predictive power for assessing reasoning quality than standard graph metrics, suggesting that effective reasoning is better captured by higher-dimensional geometric structures rather than purely relational graphs. We further show that a compact, stable set of topological features reliably indicates trace quality, offering a practical signal for future reinforcement learning algorithms.

---

### The Shape of Reasoning: Topological Analysis of Reasoning Traces in Large Language Models

Authors: Xue Wen Tan, Nathaniel Tan, Galen Lee, Stanley Kok
Published: 2025-10-23
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.20665v1

Evaluating the quality of reasoning traces from large language models remains understudied, labor-intensive, and unreliable: current practice relies on expert rubrics, manual annotation, and slow pairwise judgments. Automated efforts are dominated by graph-based proxies that quantify structural connectivity but do not clarify what constitutes high-quality reasoning; such abstractions can be overly simplistic for inherently complex processes. We introduce a topological data analysis (TDA)-based evaluation framework that captures the geometry of reasoning traces and enables label-efficient, automated assessment. In our empirical study, topological features yield substantially higher predictive power for assessing reasoning quality than standard graph metrics, suggesting that effective reasoning is better captured by higher-dimensional geometric structures rather than purely relational graphs. We further show that a compact, stable set of topological features reliably indicates trace quality, offering a practical signal for future reinforcement learning algorithms.

---

### UltraHR-100K: Enhancing UHR Image Synthesis with A Large-Scale High-Quality Dataset

Authors: Chen Zhao, En Ci, Yunzhe Xu, Tiehan Fan, Shanyan Guan, Yanhao Ge, Jian Yang, Ying Tai
Published: 2025-10-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.20661v1

Ultra-high-resolution (UHR) text-to-image (T2I) generation has seen notable progress. However, two key challenges remain : 1) the absence of a large-scale high-quality UHR T2I dataset, and (2) the neglect of tailored training strategies for fine-grained detail synthesis in UHR scenarios. To tackle the first challenge, we introduce \textbf{UltraHR-100K}, a high-quality dataset of 100K UHR images with rich captions, offering diverse content and strong visual fidelity. Each image exceeds 3K resolution and is rigorously curated based on detail richness, content complexity, and aesthetic quality. To tackle the second challenge, we propose a frequency-aware post-training method that enhances fine-detail generation in T2I diffusion models. Specifically, we design (i) \textit{Detail-Oriented Timestep Sampling (DOTS)} to focus learning on detail-critical denoising steps, and (ii) \textit{Soft-Weighting Frequency Regularization (SWFR)}, which leverages Discrete Fourier Transform (DFT) to softly constrain frequency components, encouraging high-frequency detail preservation. Extensive experiments on our proposed UltraHR-eval4K benchmarks demonstrate that our approach significantly improves the fine-grained detail quality and overall fidelity of UHR image generation. The code is available at \href{https://github.com/NJU-PCALab/UltraHR-100k}{here}.

---

### Finding the Sweet Spot: Trading Quality, Cost, and Speed During Inference-Time LLM Reflection

Authors: Jack Butler, Nikita Kozodoi, Zainab Afolabi, Brian Tyacke, Gaiar Baimuratov
Published: 2025-10-23
Categories: stat.ML, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.20653v1

As Large Language Models (LLMs) continue to evolve, practitioners face increasing options for enhancing inference-time performance without model retraining, including budget tuning and multi-step techniques like self-reflection. While these methods improve output quality, they create complex trade-offs among accuracy, cost, and latency that remain poorly understood across different domains. This paper systematically compares self-reflection and budget tuning across mathematical reasoning and translation tasks. We evaluate prominent LLMs, including Anthropic Claude, Amazon Nova, and Mistral families, along with other models under varying reflection depths and compute budgets to derive Pareto optimal performance frontiers. Our analysis reveals substantial domain dependent variation in self-reflection effectiveness, with performance gains up to 220\% in mathematical reasoning. We further investigate how reflection round depth and feedback mechanism quality influence performance across model families. To validate our findings in a real-world setting, we deploy a self-reflection enhanced marketing content localisation system at Lounge by Zalando, where it shows market-dependent effectiveness, reinforcing the importance of domain specific evaluation when deploying these techniques. Our results provide actionable guidance for selecting optimal inference strategies given specific domains and resource constraints. We open source our self-reflection implementation for reproducibility at https://github.com/aws-samples/sample-genai-reflection-for-bedrock.

---

### xTime: Extreme Event Prediction with Hierarchical Knowledge Distillation and Expert Fusion

Authors: Quan Li, Wenchao Yu, Suhang Wang, Minhua Lin, Lingwei Chen, Wei Cheng, Haifeng Chen
Published: 2025-10-23
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.20651v1

Extreme events frequently occur in real-world time series and often carry significant practical implications. In domains such as climate and healthcare, these events, such as floods, heatwaves, or acute medical episodes, can lead to serious consequences. Accurate forecasting of such events is therefore of substantial importance. Most existing time series forecasting models are optimized for overall performance within the prediction window, but often struggle to accurately predict extreme events, such as high temperatures or heart rate spikes. The main challenges are data imbalance and the neglect of valuable information contained in intermediate events that precede extreme events. In this paper, we propose xTime, a novel framework for extreme event forecasting in time series. xTime leverages knowledge distillation to transfer information from models trained on lower-rarity events, thereby improving prediction performance on rarer ones. In addition, we introduce a mixture of experts (MoE) mechanism that dynamically selects and fuses outputs from expert models across different rarity levels, which further improves the forecasting performance for extreme events. Experiments on multiple datasets show that xTime achieves consistent improvements, with forecasting accuracy on extreme events improving from 3% to 78%.

---

### The Reasoning Lingua Franca: A Double-Edged Sword for Multilingual AI

Authors: Alan Saji, Raj Dabre, Anoop Kunchukuttan, Ratish Puduppully
Published: 2025-10-23
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.20647v3

Large Reasoning Models (LRMs) achieve strong performance on mathematical, scientific, and other question-answering tasks, but their multilingual reasoning abilities remain underexplored. When presented with non-English questions, LRMs often default to reasoning in English, raising concerns about interpretability and the handling of linguistic and cultural nuances. We systematically compare an LRM's reasoning in English versus the language of the question. Our evaluation spans two tasks: MGSM and GPQA Diamond. Beyond measuring answer accuracy, we also analyze cognitive attributes in the reasoning traces. We find that English reasoning traces exhibit a substantially higher presence of these cognitive behaviors, and that reasoning in English generally yields higher final-answer accuracy, with the performance gap increasing as tasks become more complex. However, this English-centric strategy is susceptible to a key failure mode - getting "Lost in Translation," where translation steps lead to errors that would have been avoided by reasoning in the language of the question.

---

### The Reasoning Lingua Franca: A Double-Edged Sword for Multilingual AI

Authors: Alan Saji, Raj Dabre, Anoop Kunchukuttan, Ratish Puduppully
Published: 2025-10-23
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.20647v1

Large Reasoning Models (LRMs) achieve strong performance on mathematical, scientific, and other question-answering tasks, but their multilingual reasoning abilities remain underexplored. When presented with non-English questions, LRMs often default to reasoning in English, raising concerns about interpretability and the handling of linguistic and cultural nuances. We systematically compare an LRM's reasoning in English versus the language of the question. Our evaluation spans two tasks: MGSM and GPQA Diamond. Beyond measuring answer accuracy, we also analyze cognitive attributes in the reasoning traces. We find that English reasoning traces exhibit a substantially higher presence of these cognitive behaviors, and that reasoning in English generally yields higher final-answer accuracy, with the performance gap increasing as tasks become more complex. However, this English-centric strategy is susceptible to a key failure mode - getting "Lost in Translation," where translation steps lead to errors that would have been avoided by question's language reasoning.

---

### Connecting Jensen-Shannon and Kullback-Leibler Divergences: A New Bound for Representation Learning

Authors: Reuben Dorent, Polina Golland, William Wells
Published: 2025-10-23
Categories: cs.LG, cs.IT
arXiv: https://arxiv.org/abs/2510.20644v2

Mutual Information (MI) is a fundamental measure of statistical dependence widely used in representation learning. While direct optimization of MI via its definition as a Kullback-Leibler divergence (KLD) is often intractable, many recent methods have instead maximized alternative dependence measures, most notably, the Jensen-Shannon divergence (JSD) between joint and product of marginal distributions via discriminative losses. However, the connection between these surrogate objectives and MI remains poorly understood. In this work, we bridge this gap by deriving a new, tight, and tractable lower bound on KLD as a function of JSD in the general case. By specializing this bound to joint and marginal distributions, we demonstrate that maximizing the JSD-based information increases a guaranteed lower bound on mutual information. Furthermore, we revisit the practical implementation of JSD-based objectives and observe that minimizing the cross-entropy loss of a binary classifier trained to distinguish joint from marginal pairs recovers a known variational lower bound on the JSD. Extensive experiments demonstrate that our lower bound is tight when applied to MI estimation. We compared our lower bound to state-of-the-art neural estimators of variational lower bound across a range of established reference scenarios. Our lower bound estimator consistently provides a stable, low-variance estimate of a tight lower bound on MI. We also demonstrate its practical usefulness in the context of the Information Bottleneck framework. Taken together, our results provide new theoretical justifications and strong empirical evidence for using discriminative learning in MI-based representation learning.

---

### Connecting Jensen-Shannon and Kullback-Leibler Divergences: A New Bound for Representation Learning

Authors: Reuben Dorent, Polina Golland, William Wells III
Published: 2025-10-23
Categories: cs.LG, cs.IT, math.IT
arXiv: https://arxiv.org/abs/2510.20644v1

Mutual Information (MI) is a fundamental measure of statistical dependence widely used in representation learning. While direct optimization of MI via its definition as a Kullback-Leibler divergence (KLD) is often intractable, many recent methods have instead maximized alternative dependence measures, most notably, the Jensen-Shannon divergence (JSD) between joint and product of marginal distributions via discriminative losses. However, the connection between these surrogate objectives and MI remains poorly understood. In this work, we bridge this gap by deriving a new, tight, and tractable lower bound on KLD as a function of JSD in the general case. By specializing this bound to joint and marginal distributions, we demonstrate that maximizing the JSD-based information increases a guaranteed lower bound on mutual information. Furthermore, we revisit the practical implementation of JSD-based objectives and observe that minimizing the cross-entropy loss of a binary classifier trained to distinguish joint from marginal pairs recovers a known variational lower bound on the JSD. Extensive experiments demonstrate that our lower bound is tight when applied to MI estimation. We compared our lower bound to state-of-the-art neural estimators of variational lower bound across a range of established reference scenarios. Our lower bound estimator consistently provides a stable, low-variance estimate of a tight lower bound on MI. We also demonstrate its practical usefulness in the context of the Information Bottleneck framework. Taken together, our results provide new theoretical justifications and strong empirical evidence for using discriminative learning in MI-based representation learning.

---

### Integrating Machine Learning into Belief-Desire-Intention Agents: Current Advances and Open Challenges

Authors: Andrea Agiollo, Andrea Omicini
Published: 2025-10-23
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.20641v1

Thanks to the remarkable human-like capabilities of machine learning (ML) models in perceptual and cognitive tasks, frameworks integrating ML within rational agent architectures are gaining traction. Yet, the landscape remains fragmented and incoherent, often focusing on embedding ML into generic agent containers while overlooking the expressive power of rational architectures--such as Belief-Desire-Intention (BDI) agents. This paper presents a fine-grained systematisation of existing approaches, using the BDI paradigm as a reference. Our analysis illustrates the fast-evolving literature on rational agents enhanced by ML, and identifies key research opportunities and open challenges for designing effective rational ML agents.

---

### Attention Enhanced Entity Recommendation for Intelligent Monitoring in Cloud Systems

Authors: Fiza Husain, Anson Bastos, Anjaly Parayil, Ayush Choure, Chetan Bansal, Rujia Wang, Saravan Rajmohan
Published: 2025-10-23
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.20640v2

In this paper, we present DiRecGNN, an attention-enhanced entity recommendation framework for monitoring cloud services at Microsoft. We provide insights on the usefulness of this feature as perceived by the cloud service owners and lessons learned from deployment. Specifically, we introduce the problem of recommending the optimal subset of attributes (dimensions) that should be tracked by an automated watchdog (monitor) for cloud services. To begin, we construct the monitor heterogeneous graph at production-scale. The interaction dynamics of these entities are often characterized by limited structural and engagement information, resulting in inferior performance of state-of-the-art approaches. Moreover, traditional methods fail to capture the dependencies between entities spanning a long range due to their homophilic nature. Therefore, we propose an attention-enhanced entity ranking model inspired by transformer architectures. Our model utilizes a multi-head attention mechanism to focus on heterogeneous neighbors and their attributes, and further attends to paths sampled using random walks to capture long-range dependencies. We also employ multi-faceted loss functions to optimize for relevant recommendations while respecting the inherent sparsity of the data. Empirical evaluations demonstrate significant improvements over existing methods, with our model achieving a 43.1% increase in MRR. Furthermore, product teams who consumed these features perceive the feature as useful and rated it 4.5 out of 5.

---

### Attention Enhanced Entity Recommendation for Intelligent Monitoring in Cloud Systems

Authors: Fiza Hussain, Anson Bastos, Anjaly Parayil, Ayush Choure, Chetan Bansal, Rujia Wang, Saravan Rajmohan
Published: 2025-10-23
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.20640v1

In this paper, we present DiRecGNN, an attention-enhanced entity recommendation framework for monitoring cloud services at Microsoft. We provide insights on the usefulness of this feature as perceived by the cloud service owners and lessons learned from deployment. Specifically, we introduce the problem of recommending the optimal subset of attributes (dimensions) that should be tracked by an automated watchdog (monitor) for cloud services. To begin, we construct the monitor heterogeneous graph at production-scale. The interaction dynamics of these entities are often characterized by limited structural and engagement information, resulting in inferior performance of state-of-the-art approaches. Moreover, traditional methods fail to capture the dependencies between entities spanning a long range due to their homophilic nature. Therefore, we propose an attention-enhanced entity ranking model inspired by transformer architectures. Our model utilizes a multi-head attention mechanism to focus on heterogeneous neighbors and their attributes, and further attends to paths sampled using random walks to capture long-range dependencies. We also employ multi-faceted loss functions to optimize for relevant recommendations while respecting the inherent sparsity of the data. Empirical evaluations demonstrate significant improvements over existing methods, with our model achieving a 43.1% increase in MRR. Furthermore, product teams who consumed these features perceive the feature as useful and rated it 4.5 out of 5.

---

### Better Tokens for Better 3D: Advancing Vision-Language Modeling in 3D Medical Imaging

Authors: Ibrahim Ethem Hamamci, Sezgin Er, Suprosanna Shit, Hadrien Reynaud, Dong Yang, Pengfei Guo, Marc Edgar, Daguang Xu, Bernhard Kainz, Bjoern Menze
Published: 2025-10-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.20639v1

Recent progress in vision-language modeling for 3D medical imaging has been fueled by large-scale computed tomography (CT) corpora with paired free-text reports, stronger architectures, and powerful pretrained models. This has enabled applications such as automated report generation and text-conditioned 3D image synthesis. Yet, current approaches struggle with high-resolution, long-sequence volumes: contrastive pretraining often yields vision encoders that are misaligned with clinical language, and slice-wise tokenization blurs fine anatomy, reducing diagnostic performance on downstream tasks. We introduce BTB3D (Better Tokens for Better 3D), a causal convolutional encoder-decoder that unifies 2D and 3D training and inference while producing compact, frequency-aware volumetric tokens. A three-stage training curriculum enables (i) local reconstruction, (ii) overlapping-window tiling, and (iii) long-context decoder refinement, during which the model learns from short slice excerpts yet generalizes to scans exceeding 300 slices without additional memory overhead. BTB3D sets a new state-of-the-art on two key tasks: it improves BLEU scores and increases clinical F1 by 40% over CT2Rep, CT-CHAT, and Merlin for report generation; and it reduces FID by 75% and halves FVD compared to GenerateCT and MedSyn for text-to-CT synthesis, producing anatomically consistent 512*512*241 volumes. These results confirm that precise three-dimensional tokenization, rather than larger language backbones alone, is essential for scalable vision-language modeling in 3D medical imaging. The codebase is available at: https://github.com/ibrahimethemhamamci/BTB3D

---

### Large Multimodal Models-Empowered Task-Oriented Autonomous Communications: Design Methodology and Implementation Challenges

Authors: Hyun Jong Yang, Hyunsoo Kim, Hyeonho Noh, Seungnyun Kim, Byonghyo Shim
Published: 2025-10-23
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.20637v1

Large language models (LLMs) and large multimodal models (LMMs) have achieved unprecedented breakthrough, showcasing remarkable capabilities in natural language understanding, generation, and complex reasoning. This transformative potential has positioned them as key enablers for 6G autonomous communications among machines, vehicles, and humanoids. In this article, we provide an overview of task-oriented autonomous communications with LLMs/LMMs, focusing on multimodal sensing integration, adaptive reconfiguration, and prompt/fine-tuning strategies for wireless tasks. We demonstrate the framework through three case studies: LMM-based traffic control, LLM-based robot scheduling, and LMM-based environment-aware channel estimation. From experimental results, we show that the proposed LLM/LMM-aided autonomous systems significantly outperform conventional and discriminative deep learning (DL) model-based techniques, maintaining robustness under dynamic objectives, varying input parameters, and heterogeneous multimodal conditions where conventional static optimization degrades.

---

### Fluidity Index: Next-Generation Super-intelligence Benchmarks

Authors: Eric Ngoiya, Tianshu Bao
Published: 2025-10-23
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.20636v1

This paper introduces the Fluidity Index (FI) to quantify model adaptability in dynamic, scaling environments. The benchmark evaluates response accuracy based on deviations in initial, current, and future environment states, assessing context switching and continuity. We distinguish between closed-ended and open-ended benchmarks, prioritizing closed-loop open-ended real-world benchmarks to test adaptability. The approach measures a model's ability to understand, predict, and adjust to state changes in scaling environments. A truly super-intelligent model should exhibit at least second-order adaptability, enabling self-sustained computation through digital replenishment for optimal fluidity.

---

### Why Did Apple Fall: Evaluating Curiosity in Large Language Models

Authors: Haoyu Wang, Sihang Jiang, Yuyan Chen, Xiaojun Meng, Jiansheng Wei, Yitong Wang, Yanghua Xiao
Published: 2025-10-23
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.20635v2

Curiosity serves as a pivotal conduit for human beings to discover and learn new knowledge. Recent advancements of large language models (LLMs) in natural language processing have sparked discussions regarding whether these models possess capability of curiosity-driven learning akin to humans. In this paper, starting from the human curiosity assessment questionnaire Five-Dimensional Curiosity scale Revised (5DCR), we design a comprehensive evaluation framework that covers dimensions such as Information Seeking, Thrill Seeking, and Social Curiosity to assess the extent of curiosity exhibited by LLMs. The results demonstrate that LLMs exhibit a stronger thirst for knowledge than humans but still tend to make conservative choices when faced with uncertain environments. We further investigated the relationship between curiosity and thinking of LLMs, confirming that curious behaviors can enhance the model's reasoning and active learning abilities. These findings suggest that LLMs have the potential to exhibit curiosity similar to that of humans, providing experimental support for the future development of learning capabilities and innovative research in LLMs.

---

### Why Did Apple Fall To The Ground: Evaluating Curiosity In Large Language Model

Authors: Haoyu Wang, Sihang Jiang, Yuyan Chen, Yitong Wang, Yanghua Xiao
Published: 2025-10-23
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.20635v1

Curiosity serves as a pivotal conduit for human beings to discover and learn new knowledge. Recent advancements of large language models (LLMs) in natural language processing have sparked discussions regarding whether these models possess capability of curiosity-driven learning akin to humans. In this paper, starting from the human curiosity assessment questionnaire Five-Dimensional Curiosity scale Revised (5DCR), we design a comprehensive evaluation framework that covers dimensions such as Information Seeking, Thrill Seeking, and Social Curiosity to assess the extent of curiosity exhibited by LLMs. The results demonstrate that LLMs exhibit a stronger thirst for knowledge than humans but still tend to make conservative choices when faced with uncertain environments. We further investigated the relationship between curiosity and thinking of LLMs, confirming that curious behaviors can enhance the model's reasoning and active learning abilities. These findings suggest that LLMs have the potential to exhibit curiosity similar to that of humans, providing experimental support for the future development of learning capabilities and innovative research in LLMs.

---

### Deep Learning in Dental Image Analysis: A Systematic Review of Datasets, Methodologies, and Emerging Challenges

Authors: Zhenhuan Zhou, Jingbo Zhu, Yuchen Zhang, Xiaohang Guan, Peng Wang, Tao Li
Published: 2025-10-23
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.20634v1

Efficient analysis and processing of dental images are crucial for dentists to achieve accurate diagnosis and optimal treatment planning. However, dental imaging inherently poses several challenges, such as low contrast, metallic artifacts, and variations in projection angles. Combined with the subjectivity arising from differences in clinicians' expertise, manual interpretation often proves time-consuming and prone to inconsistency. Artificial intelligence (AI)-based automated dental image analysis (DIA) offers a promising solution to these issues and has become an integral part of computer-aided dental diagnosis and treatment. Among various AI technologies, deep learning (DL) stands out as the most widely applied and influential approach due to its superior feature extraction and representation capabilities. To comprehensively summarize recent progress in this field, we focus on the two fundamental aspects of DL research-datasets and models. In this paper, we systematically review 260 studies on DL applications in DIA, including 49 papers on publicly available dental datasets and 211 papers on DL-based algorithms. We first introduce the basic concepts of dental imaging and summarize the characteristics and acquisition methods of existing datasets. Then, we present the foundational techniques of DL and categorize relevant models and algorithms according to different DIA tasks, analyzing their network architectures, optimization strategies, training methods, and performance. Furthermore, we summarize commonly used training and evaluation metrics in the DIA domain. Finally, we discuss the current challenges of existing research and outline potential future directions. We hope that this work provides a valuable and systematic reference for researchers in this field. All supplementary materials and detailed comparison tables will be made publicly available on GitHub.

---

### Towards Reliable Evaluation of Large Language Models for Multilingual and Multimodal E-Commerce Applications

Authors: Shuyi Xie, Ziqin Liew, Hailing Zhang, Haibo Zhang, Ling Hu, Zhiqiang Zhou, Shuman Liu, Anxiang Zeng
Published: 2025-10-23
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.20632v1

Large Language Models (LLMs) excel on general-purpose NLP benchmarks, yet their capabilities in specialized domains remain underexplored. In e-commerce, existing evaluations-such as EcomInstruct, ChineseEcomQA, eCeLLM, and Shopping MMLU-suffer from limited task diversity (e.g., lacking product guidance and after-sales issues), limited task modalities (e.g., absence of multimodal data), synthetic or curated data, and a narrow focus on English and Chinese, leaving practitioners without reliable tools to assess models on complex, real-world shopping scenarios. We introduce EcomEval, a comprehensive multilingual and multimodal benchmark for evaluating LLMs in e-commerce. EcomEval covers six categories and 37 tasks (including 8 multimodal tasks), sourced primarily from authentic customer queries and transaction logs, reflecting the noisy and heterogeneous nature of real business interactions. To ensure both quality and scalability of reference answers, we adopt a semi-automatic pipeline in which large models draft candidate responses subsequently reviewed and modified by over 50 expert annotators with strong e-commerce and multilingual expertise. We define difficulty levels for each question and task category by averaging evaluation scores across models with different sizes and capabilities, enabling challenge-oriented and fine-grained assessment. EcomEval also spans seven languages-including five low-resource Southeast Asian languages-offering a multilingual perspective absent from prior work.

---

### Quantum Processing Unit (QPU) processing time Prediction with Machine Learning

Authors: Lucy Xing, Sanjay Vishwakarma, David Kremer, Francisco Martin-Fernandez, Ismael Faro, Juan Cruz-Benito
Published: 2025-10-23
Categories: quant-ph, cs.AI
arXiv: https://arxiv.org/abs/2510.20630v1

This paper explores the application of machine learning (ML) techniques in predicting the QPU processing time of quantum jobs. By leveraging ML algorithms, this study introduces predictive models that are designed to enhance operational efficiency in quantum computing systems. Using a dataset of about 150,000 jobs that follow the IBM Quantum schema, we employ ML methods based on Gradient-Boosting (LightGBM) to predict the QPU processing times, incorporating data preprocessing methods to improve model accuracy. The results demonstrate the effectiveness of ML in forecasting quantum jobs. This improvement can have implications on improving resource management and scheduling within quantum computing frameworks. This research not only highlights the potential of ML in refining quantum job predictions but also sets a foundation for integrating AI-driven tools in advanced quantum computing operations.

---

### Equitable Survival Prediction: A Fairness-Aware Survival Modeling (FASM) Approach

Authors: Mingxuan Liu, Yilin Ning, Haoyuan Wang, Chuan Hong, Matthew Engelhard, Danielle S. Bitterman, William G. La Cava, Nan Liu
Published: 2025-10-23
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.20629v1

As machine learning models become increasingly integrated into healthcare, structural inequities and social biases embedded in clinical data can be perpetuated or even amplified by data-driven models. In survival analysis, censoring and time dynamics can further add complexity to fair model development. Additionally, algorithmic fairness approaches often overlook disparities in cross-group rankings, e.g., high-risk Black patients may be ranked below lower-risk White patients who do not experience the event of mortality. Such misranking can reinforce biological essentialism and undermine equitable care. We propose a Fairness-Aware Survival Modeling (FASM), designed to mitigate algorithmic bias regarding both intra-group and cross-group risk rankings over time. Using breast cancer prognosis as a representative case and applying FASM to SEER breast cancer data, we show that FASM substantially improves fairness while preserving discrimination performance comparable to fairness-unaware survival models. Time-stratified evaluations show that FASM maintains stable fairness over a 10-year horizon, with the greatest improvements observed during the mid-term of follow-up. Our approach enables the development of survival models that prioritize both accuracy and equity in clinical decision-making, advancing fairness as a core principle in clinical care.

---

### H-SPLID: HSIC-based Saliency Preserving Latent Information Decomposition

Authors: Lukas Miklautz, Chengzhi Shi, Andrii Shkabrii, Theodoros Thirimachos Davarakis, Prudence Lam, Claudia Plant, Jennifer Dy, Stratis Ioannidis
Published: 2025-10-23
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.20627v2

We introduce H-SPLID, a novel algorithm for learning salient feature representations through the explicit decomposition of salient and non-salient features into separate spaces. We show that H-SPLID promotes learning low-dimensional, task-relevant features. We prove that the expected prediction deviation under input perturbations is upper-bounded by the dimension of the salient subspace and the Hilbert-Schmidt Independence Criterion (HSIC) between inputs and representations. This establishes a link between robustness and latent representation compression in terms of the dimensionality and information preserved. Empirical evaluations on image classification tasks show that models trained with H-SPLID primarily rely on salient input components, as indicated by reduced sensitivity to perturbations affecting non-salient features, such as image backgrounds. Our code is available at https://github.com/neu-spiral/H-SPLID.

---

### H-SPLID: HSIC-based Saliency Preserving Latent Information Decomposition

Authors: Lukas Miklautz, Chengzhi Shi, Andrii Shkabrii, Theodoros Thirimachos Davarakis, Prudence Lam, Claudia Plant, Jennifer Dy, Stratis Ioannidis
Published: 2025-10-23
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.20627v1

We introduce H-SPLID, a novel algorithm for learning salient feature representations through the explicit decomposition of salient and non-salient features into separate spaces. We show that H-SPLID promotes learning low-dimensional, task-relevant features. We prove that the expected prediction deviation under input perturbations is upper-bounded by the dimension of the salient subspace and the Hilbert-Schmidt Independence Criterion (HSIC) between inputs and representations. This establishes a link between robustness and latent representation compression in terms of the dimensionality and information preserved. Empirical evaluations on image classification tasks show that models trained with H-SPLID primarily rely on salient input components, as indicated by reduced sensitivity to perturbations affecting non-salient features, such as image backgrounds. Our code is available at https://github.com/neu-spiral/H-SPLID.

---

### SeViCES: Unifying Semantic-Visual Evidence Consensus for Long Video Understanding

Authors: Yuan Sheng, Yanbin Hao, Chenxu Li, Shuo Wang, Xiangnan He
Published: 2025-10-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.20622v1

Long video understanding remains challenging due to its complex, diverse, and temporally scattered content. Although video large language models (Video-LLMs) can process videos lasting tens of minutes, applying them to truly long sequences is computationally prohibitive and often leads to unfocused or inconsistent reasoning. A promising solution is to select only the most informative frames, yet existing approaches typically ignore temporal dependencies or rely on unimodal evidence, limiting their ability to provide complete and query-relevant context. We propose a Semantic-Visual Consensus Evidence Selection (SeViCES) framework for effective and reliable long video understanding. SeViCES is training-free and model-agnostic, and introduces two key components. The Semantic-Visual Consensus Frame Selection (SVCFS) module selects frames through (1) a temporal-aware semantic branch that leverages LLM reasoning over captions, and (2) a cluster-guided visual branch that aligns embeddings with semantic scores via mutual information. The Answer Consensus Refinement (ACR) module further resolves inconsistencies between semantic- and visual-based predictions by fusing evidence and constraining the answer space. Extensive experiments on long video understanding benchmarks show that SeViCES consistently outperforms state-of-the-art methods in both accuracy and robustness, demonstrating the importance of consensus-driven evidence selection for Video-LLMs.

---

### Towards the Formalization of a Trustworthy AI for Mining Interpretable Models explOiting Sophisticated Algorithms

Authors: Riccardo Guidotti, Martina Cinquini, Marta Marchiori Manerba, Mattia Setzu, Francesco Spinnato
Published: 2025-10-23
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.20621v2

Interpretable-by-design models are crucial for fostering trust, accountability, and safe adoption of automated decision-making models in real-world applications. In this paper we formalize the ground for the MIMOSA (Mining Interpretable Models explOiting Sophisticated Algorithms) framework, a comprehensive methodology for generating predictive models that balance interpretability with performance while embedding key ethical properties. We formally define here the supervised learning setting across diverse decision-making tasks and data types, including tabular data, time series, images, text, transactions, and trajectories. We characterize three major families of interpretable models: feature importance, rule, and instance based models. For each family, we analyze their interpretability dimensions, reasoning mechanisms, and complexity. Beyond interpretability, we formalize three critical ethical properties, namely causality, fairness, and privacy, providing formal definitions, evaluation metrics, and verification procedures for each. We then examine the inherent trade-offs between these properties and discuss how privacy requirements, fairness constraints, and causal reasoning can be embedded within interpretable pipelines. By evaluating ethical measures during model generation, this framework establishes the theoretical foundations for developing AI systems that are not only accurate and interpretable but also fair, privacy-preserving, and causally aware, i.e., trustworthy.

---

### Towards the Formalization of a Trustworthy AI for Mining Interpretable Models explOiting Sophisticated Algorithms

Authors: Riccardo Guidotti, Martina Cinquini, Marta Marchiori Manerba, Mattia Setzu, Francesco Spinnato
Published: 2025-10-23
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.20621v1

Interpretable-by-design models are crucial for fostering trust, accountability, and safe adoption of automated decision-making models in real-world applications. In this paper we formalize the ground for the MIMOSA (Mining Interpretable Models explOiting Sophisticated Algorithms) framework, a comprehensive methodology for generating predictive models that balance interpretability with performance while embedding key ethical properties. We formally define here the supervised learning setting across diverse decision-making tasks and data types, including tabular data, time series, images, text, transactions, and trajectories. We characterize three major families of interpretable models: feature importance, rule, and instance based models. For each family, we analyze their interpretability dimensions, reasoning mechanisms, and complexity. Beyond interpretability, we formalize three critical ethical properties, namely causality, fairness, and privacy, providing formal definitions, evaluation metrics, and verification procedures for each. We then examine the inherent trade-offs between these properties and discuss how privacy requirements, fairness constraints, and causal reasoning can be embedded within interpretable pipelines. By evaluating ethical measures during model generation, this framework establishes the theoretical foundations for developing AI systems that are not only accurate and interpretable but also fair, privacy-preserving, and causally aware, i.e., trustworthy.

---

### On Optimal Hyperparameters for Differentially Private Deep Transfer Learning

Authors: Aki Rehn, Linzh Zhao, Mikko A. Heikkilä, Antti Honkela
Published: 2025-10-23
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.20616v2

Differentially private (DP) transfer learning, i.e., fine-tuning a pretrained model on private data, is the current state-of-the-art approach for training large models under privacy constraints. We focus on two key hyperparameters in this setting: the clipping bound $C$ and batch size $B$. We show a clear mismatch between the current theoretical understanding of how to choose an optimal $C$ (stronger privacy requires smaller $C$) and empirical outcomes (larger $C$ performs better under strong privacy), caused by changes in the gradient distributions. Assuming a limited compute budget (fixed epochs), we demonstrate that the existing heuristics for tuning $B$ do not work, while cumulative DP noise better explains whether smaller or larger batches perform better. We also highlight how the common practice of using a single $(C,B)$ setting across tasks can lead to suboptimal performance. We find that performance drops especially when moving between loose and tight privacy and between plentiful and limited compute, which we explain by analyzing clipping as a form of gradient re-weighting and examining cumulative DP noise.

---

### On Optimal Hyperparameters for Differentially Private Deep Transfer Learning

Authors: Aki Rehn, Linzh Zhao, Mikko A. Heikkilä, Antti Honkela
Published: 2025-10-23
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.20616v1

Differentially private (DP) transfer learning, i.e., fine-tuning a pretrained model on private data, is the current state-of-the-art approach for training large models under privacy constraints. We focus on two key hyperparameters in this setting: the clipping bound $C$ and batch size $B$. We show a clear mismatch between the current theoretical understanding of how to choose an optimal $C$ (stronger privacy requires smaller $C$) and empirical outcomes (larger $C$ performs better under strong privacy), caused by changes in the gradient distributions. Assuming a limited compute budget (fixed epochs), we demonstrate that the existing heuristics for tuning $B$ do not work, while cumulative DP noise better explains whether smaller or larger batches perform better. We also highlight how the common practice of using a single $(C,B)$ setting across tasks can lead to suboptimal performance. We find that performance drops especially when moving between loose and tight privacy and between plentiful and limited compute, which we explain by analyzing clipping as a form of gradient re-weighting and examining cumulative DP noise.

---

### MS-BART: Unified Modeling of Mass Spectra and Molecules for Structure Elucidation

Authors: Yang Han, Pengyu Wang, Kai Yu, Xin Chen, Lu Chen
Published: 2025-10-23
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.20615v1

Mass spectrometry (MS) plays a critical role in molecular identification, significantly advancing scientific discovery. However, structure elucidation from MS data remains challenging due to the scarcity of annotated spectra. While large-scale pretraining has proven effective in addressing data scarcity in other domains, applying this paradigm to mass spectrometry is hindered by the complexity and heterogeneity of raw spectral signals. To address this, we propose MS-BART, a unified modeling framework that maps mass spectra and molecular structures into a shared token vocabulary, enabling cross-modal learning through large-scale pretraining on reliably computed fingerprint-molecule datasets. Multi-task pretraining objectives further enhance MS-BART's generalization by jointly optimizing denoising and translation task. The pretrained model is subsequently transferred to experimental spectra through finetuning on fingerprint predictions generated with MIST, a pre-trained spectral inference model, thereby enhancing robustness to real-world spectral variability. While finetuning alleviates the distributional difference, MS-BART still suffers molecular hallucination and requires further alignment. We therefore introduce a chemical feedback mechanism that guides the model toward generating molecules closer to the reference structure. Extensive evaluations demonstrate that MS-BART achieves SOTA performance across 5/12 key metrics on MassSpecGym and NPLIB1 and is faster by one order of magnitude than competing diffusion-based methods, while comprehensive ablation studies systematically validate the model's effectiveness and robustness.

---

### Black Box Absorption: LLMs Undermining Innovative Ideas

Authors: Wenjun Cao
Published: 2025-10-23
Categories: cs.CY, cs.AI, cs.CR, cs.LG, econ.GN
arXiv: https://arxiv.org/abs/2510.20612v1

Large Language Models are increasingly adopted as critical tools for accelerating innovation. This paper identifies and formalizes a systemic risk inherent in this paradigm: \textbf{Black Box Absorption}. We define this as the process by which the opaque internal architectures of LLM platforms, often operated by large-scale service providers, can internalize, generalize, and repurpose novel concepts contributed by users during interaction. This mechanism threatens to undermine the foundational principles of innovation economics by creating severe informational and structural asymmetries between individual creators and platform operators, thereby jeopardizing the long-term sustainability of the innovation ecosystem. To analyze this challenge, we introduce two core concepts: the idea unit, representing the transportable functional logic of an innovation, and idea safety, a multidimensional standard for its protection. This paper analyzes the mechanisms of absorption and proposes a concrete governance and engineering agenda to mitigate these risks, ensuring that creator contributions remain traceable, controllable, and equitable.

---

### PSO-XAI: A PSO-Enhanced Explainable AI Framework for Reliable Breast Cancer Detection

Authors: Mirza Raquib, Niloy Das, Farida Siddiqi Prity, Arafath Al Fahim, Saydul Akbar Murad, Mohammad Amzad Hossain, MD Jiabul Hoque, Mohammad Ali Moni
Published: 2025-10-23
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.20611v1

Breast cancer is considered the most critical and frequently diagnosed cancer in women worldwide, leading to an increase in cancer-related mortality. Early and accurate detection is crucial as it can help mitigate possible threats while improving survival rates. In terms of prediction, conventional diagnostic methods are often limited by variability, cost, and, most importantly, risk of misdiagnosis. To address these challenges, machine learning (ML) has emerged as a powerful tool for computer-aided diagnosis, with feature selection playing a vital role in improving model performance and interpretability. This research study proposes an integrated framework that incorporates customized Particle Swarm Optimization (PSO) for feature selection. This framework has been evaluated on a comprehensive set of 29 different models, spanning classical classifiers, ensemble techniques, neural networks, probabilistic algorithms, and instance-based algorithms. To ensure interpretability and clinical relevance, the study uses cross-validation in conjunction with explainable AI methods. Experimental evaluation showed that the proposed approach achieved a superior score of 99.1\% across all performance metrics, including accuracy and precision, while effectively reducing dimensionality and providing transparent, model-agnostic explanations. The results highlight the potential of combining swarm intelligence with explainable ML for robust, trustworthy, and clinically meaningful breast cancer diagnosis.

---

### BUSTED at AraGenEval Shared Task: A Comparative Study of Transformer-Based Models for Arabic AI-Generated Text Detection

Authors: Ali Zain, Sareem Farooqui, Muhammad Rafi
Published: 2025-10-23
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.20610v2

This paper details our submission to the AraGenEval Shared Task on Arabic AI-generated text detection, where our team, BUSTED, secured 5th place. We investigated the effectiveness of three pre-trained transformer models: AraELECTRA, CAMeLBERT, and XLM-RoBERTa. Our approach involved fine-tuning each model on the provided dataset for a binary classification task. Our findings revealed a surprising result: the multilingual XLM-RoBERTa model achieved the highest performance with an F1 score of 0.7701, outperforming the specialized Arabic models. This work underscores the complexities of AI-generated text detection and highlights the strong generalization capabilities of multilingual models.

---

### BUSTED at AraGenEval Shared Task: A Comparative Study of Transformer-Based Models for Arabic AI-Generated Text Detection

Authors: Ali Zain, Sareem Farooqui, Muhammad Rafi
Published: 2025-10-23
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.20610v1

This paper details our submission to the Ara- GenEval Shared Task on Arabic AI-generated text detection, where our team, BUSTED, se- cured 5th place. We investigated the effec- tiveness of three pre-trained transformer mod- els: AraELECTRA, CAMeLBERT, and XLM- RoBERTa. Our approach involved fine-tuning each model on the provided dataset for a binary classification task. Our findings revealed a sur- prising result: the multilingual XLM-RoBERTa model achieved the highest performance with an F1 score of 0.7701, outperforming the spe- cialized Arabic models. This work underscores the complexities of AI-generated text detection and highlights the strong generalization capa- bilities of multilingual models.

---

### Practical Code RAG at Scale: Task-Aware Retrieval Design Choices under Compute Budgets

Authors: Timur Galimzyanov, Olga Kolomyttseva, Egor Bogomolov
Published: 2025-10-23
Categories: cs.LG, cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2510.20609v1

We study retrieval design for code-focused generation tasks under realistic compute budgets. Using two complementary tasks from Long Code Arena -- code completion and bug localization -- we systematically compare retrieval configurations across various context window sizes along three axes: (i) chunking strategy, (ii) similarity scoring, and (iii) splitting granularity. (1) For PL-PL, sparse BM25 with word-level splitting is the most effective and practical, significantly outperforming dense alternatives while being an order of magnitude faster. (2) For NL-PL, proprietary dense encoders (Voyager-3 family) consistently beat sparse retrievers, however requiring 100x larger latency. (3) Optimal chunk size scales with available context: 32-64 line chunks work best at small budgets, and whole-file retrieval becomes competitive at 16000 tokens. (4) Simple line-based chunking matches syntax-aware splitting across budgets. (5) Retrieval latency varies by up to 200x across configurations; BPE-based splitting is needlessly slow, and BM25 + word splitting offers the best quality-latency trade-off. Thus, we provide evidence-based recommendations for implementing effective code-oriented RAG systems based on task requirements, model constraints, and computational efficiency.

---

### Convergence Analysis of SGD under Expected Smoothness

Authors: Yuta Kawamoto, Hideaki Iiduka
Published: 2025-10-23
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.20608v2

Stochastic gradient descent (SGD) is the workhorse of large-scale learning, yet classical analyses rely on assumptions that can be either too strong (bounded variance) or too coarse (uniform noise). The expected smoothness (ES) condition has emerged as a flexible alternative that ties the second moment of stochastic gradients to the objective value and the full gradient. This paper presents a self-contained convergence analysis of SGD under ES. We (i) refine ES with interpretations and sampling-dependent constants; (ii) derive bounds of the expectation of squared full gradient norm; and (iii) prove $O(1/K)$ rates with explicit residual errors for various step-size schedules. All proofs are given in full detail in the appendix. Our treatment unifies and extends recent threads (Khaled and Richtárik, 2020; Umeda and Iiduka, 2025).

---

### Convergence Analysis of SGD under Expected Smoothness

Authors: Yuta Kawamoto, Hideaki Iiduka
Published: 2025-10-23
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.20608v1

Stochastic gradient descent (SGD) is the workhorse of large-scale learning, yet classical analyses rely on assumptions that can be either too strong (bounded variance) or too coarse (uniform noise). The expected smoothness (ES) condition has emerged as a flexible alternative that ties the second moment of stochastic gradients to the objective value and the full gradient. This paper presents a self-contained convergence analysis of SGD under ES. We (i) refine ES with interpretations and sampling-dependent constants; (ii) derive bounds of the expectation of squared full gradient norm; and (iii) prove $O(1/K)$ rates with explicit residual errors for various step-size schedules. All proofs are given in full detail in the appendix. Our treatment unifies and extends recent threads (Khaled and Richt\'arik, 2020; Umeda and Iiduka, 2025).

---

### Generalizable Reasoning through Compositional Energy Minimization

Authors: Alexandru Oarga, Yilun Du
Published: 2025-10-23
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.20607v1

Generalization is a key challenge in machine learning, specifically in reasoning tasks, where models are expected to solve problems more complex than those encountered during training. Existing approaches typically train reasoning models in an end-to-end fashion, directly mapping input instances to solutions. While this allows models to learn useful heuristics from data, it often results in limited generalization beyond the training distribution. In this work, we propose a novel approach to reasoning generalization by learning energy landscapes over the solution spaces of smaller, more tractable subproblems. At test time, we construct a global energy landscape for a given problem by combining the energy functions of multiple subproblems. This compositional approach enables the incorporation of additional constraints during inference, allowing the construction of energy landscapes for problems of increasing difficulty. To improve the sample quality from this newly constructed energy landscape, we introduce Parallel Energy Minimization (PEM). We evaluate our approach on a wide set of reasoning problems. Our method outperforms existing state-of-the-art methods, demonstrating its ability to generalize to larger and more complex problems. Project website can be found at: https://alexoarga.github.io/compositional_reasoning/

---

### Strategic Costs of Perceived Bias in Fair Selection

Authors: L. Elisa Celis, Lingxiao Huang, Milind Sohoni, Nisheeth K. Vishnoi
Published: 2025-10-23
Categories: cs.GT, cs.CY, cs.LG, econ.TH
arXiv: https://arxiv.org/abs/2510.20606v2

Meritocratic systems, from admissions to hiring, aim to impartially reward skill and effort. Yet persistent disparities across race, gender, and class challenge this ideal. Some attribute these gaps to structural inequality; others to individual choice. We develop a game-theoretic model in which candidates from different socioeconomic groups differ in their perceived post-selection value--shaped by social context and, increasingly, by AI-powered tools offering personalized career or salary guidance. Each candidate strategically chooses effort, balancing its cost against expected reward; effort translates into observable merit, and selection is based solely on merit. We characterize the unique Nash equilibrium in the large-agent limit and derive explicit formulas showing how valuation disparities and institutional selectivity jointly determine effort, representation, social welfare, and utility. We further propose a cost-sensitive optimization framework that quantifies how modifying selectivity or perceived value can reduce disparities without compromising institutional goals. Our analysis reveals a perception-driven bias: when perceptions of post-selection value differ across groups, these differences translate into rational differences in effort, propagating disparities backward through otherwise "fair" selection processes. While the model is static, it captures one stage of a broader feedback cycle linking perceptions, incentives, and outcome--bridging rational-choice and structural explanations of inequality by showing how techno-social environments shape individual incentives in meritocratic systems.

---

### Strategic Costs of Perceived Bias in Fair Selection

Authors: L. Elisa Celis, Lingxiao Huang, Milind Sohoni, Nisheeth K. Vishnoi
Published: 2025-10-23
Categories: cs.GT, cs.CY, cs.LG, econ.TH
arXiv: https://arxiv.org/abs/2510.20606v1

Meritocratic systems, from admissions to hiring, aim to impartially reward skill and effort. Yet persistent disparities across race, gender, and class challenge this ideal. Some attribute these gaps to structural inequality; others to individual choice. We develop a game-theoretic model in which candidates from different socioeconomic groups differ in their perceived post-selection value--shaped by social context and, increasingly, by AI-powered tools offering personalized career or salary guidance. Each candidate strategically chooses effort, balancing its cost against expected reward; effort translates into observable merit, and selection is based solely on merit. We characterize the unique Nash equilibrium in the large-agent limit and derive explicit formulas showing how valuation disparities and institutional selectivity jointly determine effort, representation, social welfare, and utility. We further propose a cost-sensitive optimization framework that quantifies how modifying selectivity or perceived value can reduce disparities without compromising institutional goals. Our analysis reveals a perception-driven bias: when perceptions of post-selection value differ across groups, these differences translate into rational differences in effort, propagating disparities backward through otherwise "fair" selection processes. While the model is static, it captures one stage of a broader feedback cycle linking perceptions, incentives, and outcome--bridging rational-choice and structural explanations of inequality by showing how techno-social environments shape individual incentives in meritocratic systems.

---

### OnlineSplatter: Pose-Free Online 3D Reconstruction for Free-Moving Objects

Authors: Mark He Huang, Lin Geng Foo, Christian Theobalt, Ying Sun, De Wen Soh
Published: 2025-10-23
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.20605v1

Free-moving object reconstruction from monocular video remains challenging, particularly without reliable pose or depth cues and under arbitrary object motion. We introduce OnlineSplatter, a novel online feed-forward framework generating high-quality, object-centric 3D Gaussians directly from RGB frames without requiring camera pose, depth priors, or bundle optimization. Our approach anchors reconstruction using the first frame and progressively refines the object representation through a dense Gaussian primitive field, maintaining constant computational cost regardless of video sequence length. Our core contribution is a dual-key memory module combining latent appearance-geometry keys with explicit directional keys, robustly fusing current frame features with temporally aggregated object states. This design enables effective handling of free-moving objects via spatial-guided memory readout and an efficient sparsification mechanism, ensuring comprehensive yet compact object coverage. Evaluations on real-world datasets demonstrate that OnlineSplatter significantly outperforms state-of-the-art pose-free reconstruction baselines, consistently improving with more observations while maintaining constant memory and runtime.

---

### Efficient Algorithms for Computing Random Walk Centrality

Authors: Changan Liu, Zixuan Xie, Ahad N. Zehmakan, Zhongzhi Zhang
Published: 2025-10-23
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.20604v1

Random walk centrality is a fundamental metric in graph mining for quantifying node importance and influence, defined as the weighted average of hitting times to a node from all other nodes. Despite its ability to capture rich graph structural information and its wide range of applications, computing this measure for large networks remains impractical due to the computational demands of existing methods. In this paper, we present a novel formulation of random walk centrality, underpinning two scalable algorithms: one leveraging approximate Cholesky factorization and sparse inverse estimation, while the other sampling rooted spanning trees. Both algorithms operate in near-linear time and provide strong approximation guarantees. Extensive experiments on large real-world networks, including one with over 10 million nodes, demonstrate the efficiency and approximation quality of the proposed algorithms.

---

### What Defines Good Reasoning in LLMs? Dissecting Reasoning Steps with Multi-Aspect Evaluation

Authors: Heejin Do, Jaehui Hwang, Dongyoon Han, Seong Joon Oh, Sangdoo Yun
Published: 2025-10-23
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.20603v1

Evaluating large language models (LLMs) on final-answer correctness is the dominant paradigm. This approach, however, provides a coarse signal for model improvement and overlooks the quality of the underlying reasoning process. We argue that a more granular evaluation of reasoning offers a more effective path to building robust models. We decompose reasoning quality into two dimensions: relevance and coherence. Relevance measures if a step is grounded in the problem; coherence measures if it follows logically from prior steps. To measure these aspects reliably, we introduce causal stepwise evaluation (CaSE). This method assesses each reasoning step using only its preceding context, which avoids hindsight bias. We validate CaSE against human judgments on our new expert-annotated benchmarks, MRa-GSM8K and MRa-MATH. More importantly, we show that curating training data with CaSE-evaluated relevance and coherence directly improves final task performance. Our work provides a scalable framework for analyzing, debugging, and improving LLM reasoning, demonstrating the practical value of moving beyond validity checks.

---

### Resounding Acoustic Fields with Reciprocity

Authors: Zitong Lan, Yiduo Hao, Mingmin Zhao
Published: 2025-10-23
Categories: cs.SD, cs.AI, eess.AS, eess.SP
arXiv: https://arxiv.org/abs/2510.20602v1

Achieving immersive auditory experiences in virtual environments requires flexible sound modeling that supports dynamic source positions. In this paper, we introduce a task called resounding, which aims to estimate room impulse responses at arbitrary emitter location from a sparse set of measured emitter positions, analogous to the relighting problem in vision. We leverage the reciprocity property and introduce Versa, a physics-inspired approach to facilitating acoustic field learning. Our method creates physically valid samples with dense virtual emitter positions by exchanging emitter and listener poses. We also identify challenges in deploying reciprocity due to emitter/listener gain patterns and propose a self-supervised learning approach to address them. Results show that Versa substantially improve the performance of acoustic field learning on both simulated and real-world datasets across different metrics. Perceptual user studies show that Versa can greatly improve the immersive spatial sound experience. Code, dataset and demo videos are available on the project website: https://waves.seas.upenn.edu/projects/versa.

---

### Unsupervised Domain Adaptation via Similarity-based Prototypes for Cross-Modality Segmentation

Authors: Ziyu Ye, Chen Ju, Chaofan Ma, Xiaoyun Zhang
Published: 2025-10-23
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.20596v1

Deep learning models have achieved great success on various vision challenges, but a well-trained model would face drastic performance degradation when applied to unseen data. Since the model is sensitive to domain shift, unsupervised domain adaptation attempts to reduce the domain gap and avoid costly annotation of unseen domains. This paper proposes a novel framework for cross-modality segmentation via similarity-based prototypes. In specific, we learn class-wise prototypes within an embedding space, then introduce a similarity constraint to make these prototypes representative for each semantic class while separable from different classes. Moreover, we use dictionaries to store prototypes extracted from different images, which prevents the class-missing problem and enables the contrastive learning of prototypes, and further improves performance. Extensive experiments show that our method achieves better results than other state-of-the-art methods.

---

### Diffusion Autoencoders with Perceivers for Long, Irregular and Multimodal Astronomical Sequences

Authors: Yunyi Shen, Alexander Gagliano
Published: 2025-10-23
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.20595v1

Self-supervised learning has become a central strategy for representation learning, but the majority of architectures used for encoding data have only been validated on regularly-sampled inputs such as images, audios. and videos. In many scientific domains, data instead arrive as long, irregular, and multimodal sequences. To extract semantic information from these data, we introduce the Diffusion Autoencoder with Perceivers (daep). daep tokenizes heterogeneous measurements, compresses them with a Perceiver encoder, and reconstructs them with a Perceiver-IO diffusion decoder, enabling scalable learning in diverse data settings. To benchmark the daep architecture, we adapt the masked autoencoder to a Perceiver encoder/decoder design, and establish a strong baseline (maep) in the same architectural family as daep. Across diverse spectroscopic and photometric astronomical datasets, daep achieves lower reconstruction errors, produces more discriminative latent spaces, and better preserves fine-scale structure than both VAE and maep baselines. These results establish daep as an effective framework for scientific domains where data arrives as irregular, heterogeneous sequences.

---

### Transferable Graph Learning for Transmission Congestion Management via Busbar Splitting

Authors: Ali Rajaei, Peter Palensky, Jochen L. Cremer
Published: 2025-10-23
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.20591v2

Network topology optimization (NTO) via busbar splitting can mitigate transmission grid congestion and reduce redispatch costs. However, solving this mixed-integer nonlinear problem for large-scale systems in near-real-time is currently intractable with existing solvers. Machine learning (ML) approaches have emerged as a promising alternative, but they have limited generalization to unseen topologies, varying operating conditions, and different systems, which limits their practical applicability. This paper formulates NTO for congestion management considering linearized AC power flow, and proposes a graph neural network (GNN)-accelerated approach. We develop a heterogeneous edge-aware message passing GNN to predict effective nodes for busbar splitting actions as candidate NTO solutions. The proposed GNN captures local flow patterns, improves generalization to unseen topology changes, and enhances transferability across systems. Case studies show up to 4 orders-of-magnitude speed-up, delivering AC-feasible solutions within one minute and a 2.3% optimality gap on the GOC 2000-bus system. These results demonstrate a significant step toward near-real-time NTO for large-scale systems with topology and cross-system generalization.

---

### Transferable Graph Learning for Transmission Congestion Management via Busbar Splitting

Authors: Ali Rajaei, Peter Palensky, Jochen L. Cremer
Published: 2025-10-23
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.20591v1

Network topology optimization (NTO) via busbar splitting can mitigate transmission grid congestion and reduce redispatch costs. However, solving this mixed-integer non-linear problem for large-scale systems in near-real-time is currently intractable with existing solvers. Machine learning (ML) approaches have emerged as a promising alternative, but they have limited generalization to unseen topologies, varying operating conditions, and different systems, which limits their practical applicability. This paper formulates NTO for congestion management problem considering linearized AC PF, and proposes a graph neural network (GNN)-accelerated approach. We develop a heterogeneous edge-aware message passing NN to predict effective busbar splitting actions as candidate NTO solutions. The proposed GNN captures local flow patterns, achieves generalization to unseen topology changes, and improves transferability across systems. Case studies show up to 4 orders-of-magnitude speed-up, delivering AC-feasible solutions within one minute and a 2.3% optimality gap on the GOC 2000-bus system. These results demonstrate a significant step toward near-real-time NTO for large-scale systems with topology and cross-system generalization.

---

### Embedding the MLOps Lifecycle into OT Reference Models

Authors: Simon Schindler, Christoph Binder, Lukas Lürzer, Stefan Huber
Published: 2025-10-23
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.20590v1

Machine Learning Operations (MLOps) practices are increas- ingly adopted in industrial settings, yet their integration with Opera- tional Technology (OT) systems presents significant challenges. This pa- per analyzes the fundamental obstacles in combining MLOps with OT en- vironments and proposes a systematic approach to embed MLOps prac- tices into established OT reference models. We evaluate the suitability of the Reference Architectural Model for Industry 4.0 (RAMI 4.0) and the International Society of Automation Standard 95 (ISA-95) for MLOps integration and present a detailed mapping of MLOps lifecycle compo- nents to RAMI 4.0 exemplified by a real-world use case. Our findings demonstrate that while standard MLOps practices cannot be directly transplanted to OT environments, structured adaptation using existing reference models can provide a pathway for successful integration.

---