# Research Papers — 2025-10 · bundle page 132 of 217

> Full-text markdown of papers #6551–6600 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/132
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/131.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/133.md)

### Quantum NLP models on Natural Language Inference

Authors: Ling Sun, Peter Sullivan, Michael Martin, Yun Zhou
Published: 2025-10-12
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.15972v1

Quantum natural language processing (QNLP) offers a novel approach to semantic modeling by embedding compositional structure directly into quantum circuits. This paper investigates the application of QNLP models to the task of Natural Language Inference (NLI), comparing quantum, hybrid, and classical transformer-based models under a constrained few-shot setting. Using the lambeq library and the DisCoCat framework, we construct parameterized quantum circuits for sentence pairs and train them for both semantic relatedness and inference classification. To assess efficiency, we introduce a novel information-theoretic metric, Information Gain per Parameter (IGPP), which quantifies learning dynamics independent of model size. Our results demonstrate that quantum models achieve performance comparable to classical baselines while operating with dramatically fewer parameters. The Quantum-based models outperform randomly initialized transformers in inference and achieve lower test error on relatedness tasks. Moreover, quantum models exhibit significantly higher per-parameter learning efficiency (up to five orders of magnitude more than classical counterparts), highlighting the promise of QNLP in low-resource, structure-sensitive settings. To address circuit-level isolation and promote parameter sharing, we also propose a novel cluster-based architecture that improves generalization by tying gate parameters to learned word clusters rather than individual tokens.

---

### A Graph-Attentive LSTM Model for Malicious URL Detection

Authors: Md. Ifthekhar Hossain, Kazi Abdullah Al Arafat, Bryce Shepard, Kayd Craig, Imtiaz Parvez
Published: 2025-10-12
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2510.15971v1

Malicious URLs pose significant security risks as they facilitate phishing attacks, distribute malware, and empower attackers to deface websites. Blacklist detection methods fail to identify new or obfuscated URLs because they depend on pre-existing patterns. This work presents a hybrid deep learning model named GNN-GAT-LSTM that combines Graph Neural Networks (GNNs) with Graph Attention Networks (GATs) and Long Short-Term Memory (LSTM) networks. The proposed architecture extracts both the structural and sequential patterns of the features from data. The model transforms URLs into graphs through a process where characters become nodes that connect through edges. It applies one-hot encoding to represent node features. The model received training and testing data from a collection of 651,191 URLs, which were classified into benign, phishing, defacement, and malware categories. The preprocessing stage included both feature engineering and data balancing techniques, which addressed the class imbalance issue to enhance model learning. The GNN-GAT-LSTM model achieved outstanding performance through its test accuracy of 0.9806 and its weighted F1-score of 0.9804. It showed excellent precision and recall performance across most classes, particularly for benign and defacement URLs. Overall, the model provides an efficient and scalable system for detecting malicious URLs while demonstrating strong potential for real-world cybersecurity applications.

---

### Predict Training Data Quality via Its Geometry in Metric Space

Authors: Yang Ba, Mohammad Sadeq Abolhasani, Rong Pan
Published: 2025-10-12
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.15970v1

High-quality training data is the foundation of machine learning and artificial intelligence, shaping how models learn and perform. Although much is known about what types of data are effective for training, the impact of the data's geometric structure on model performance remains largely underexplored. We propose that both the richness of representation and the elimination of redundancy within training data critically influence learning outcomes. To investigate this, we employ persistent homology to extract topological features from data within a metric space, thereby offering a principled way to quantify diversity beyond entropy-based measures. Our findings highlight persistent homology as a powerful tool for analyzing and enhancing the training data that drives AI systems.

---

### LinearizeLLM: An Agent-Based Framework for LLM-Driven Exact Linear Reformulation of Nonlinear Optimization Problems

Authors: Paul-Niklas Ken Kandora, Simon Caspar Zeller, Aaron Jeremias Elsing, Elena Kuss, Steffen Rebennack
Published: 2025-10-12
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.15969v2

Reformulating nonlinear optimization problems into solver-ready linear optimization problems is often necessary for practical applications, but the process is often manual and requires domain expertise. We propose LinearizeLLM, an agent-based LLM framework that produces solver-ready linear reformulations of nonlinear optimization problems. Agents first detect the nonlinearity pattern (e.g., bilinear products) and apply nonlinearity pattern-aware reformulation techniques, selecting the most suitable linearization technique. We benchmark on 40 instances: 27 derived from ComplexOR by injecting exactly-linearizable operators, and 13 automatically generated instances with deeply nested nonlinearities. LinearizeLLM achieves 73\% mean end-to-end overall success (OSR) across nonlinearity depths (8.3x higher than a one-shot LLM baseline; 4.3x higher than Pyomo). The results suggest that a set of pattern-specialized agents can automate linearization, supporting natural-language-based modeling of nonlinear optimization.

---

### Self-Attention to Operator Learning-based 3D-IC Thermal Simulation

Authors: Zhen Huang, Hong Wang, Wenkai Yang, Muxi Tang, Depeng Xie, Ting-Jung Lin, Yu Zhang, Wei W. Xing, Lei He
Published: 2025-10-12
Categories: cs.LG, cs.AI, cs.AR
arXiv: https://arxiv.org/abs/2510.15968v2

Thermal management in 3D ICs is increasingly challenging due to higher power densities. Traditional PDE-solving-based methods, while accurate, are too slow for iterative design. Machine learning approaches like FNO provide faster alternatives but suffer from high-frequency information loss and high-fidelity data dependency. We introduce Self-Attention U-Net Fourier Neural Operator (SAU-FNO), a novel framework combining self-attention and U-Net with FNO to capture long-range dependencies and model local high-frequency features effectively. Transfer learning is employed to fine-tune low-fidelity data, minimizing the need for extensive high-fidelity datasets and speeding up training. Experiments demonstrate that SAU-FNO achieves state-of-the-art thermal prediction accuracy and provides an 842x speedup over traditional FEM methods, making it an efficient tool for advanced 3D IC thermal simulations.

---

### Gains: Fine-grained Federated Domain Adaptation in Open Set

Authors: Zhengyi Zhong, Wenzheng Jiang, Weidong Bao, Ji Wang, Cheems Wang, Guanbo Wang, Yongheng Deng, Ju Ren
Published: 2025-10-12
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.15967v1

Conventional federated learning (FL) assumes a closed world with a fixed total number of clients. In contrast, new clients continuously join the FL process in real-world scenarios, introducing new knowledge. This raises two critical demands: detecting new knowledge, i.e., knowledge discovery, and integrating it into the global model, i.e., knowledge adaptation. Existing research focuses on coarse-grained knowledge discovery, and often sacrifices source domain performance and adaptation efficiency. To this end, we propose a fine-grained federated domain adaptation approach in open set (Gains). Gains splits the model into an encoder and a classifier, empirically revealing features extracted by the encoder are sensitive to domain shifts while classifier parameters are sensitive to class increments. Based on this, we develop fine-grained knowledge discovery and contribution-driven aggregation techniques to identify and incorporate new knowledge. Additionally, an anti-forgetting mechanism is designed to preserve source domain performance, ensuring balanced adaptation. Experimental results on multi-domain datasets across three typical data-shift scenarios demonstrate that Gains significantly outperforms other baselines in performance for both source-domain and target-domain clients. Code is available at: https://github.com/Zhong-Zhengyi/Gains.

---

### PISA: A Pragmatic Psych-Inspired Unified Memory System for Enhanced AI Agency

Authors: Shian Jia, Ziyang Huang, Xinbo Wang, Haofei Zhang, Mingli Song
Published: 2025-10-12
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.15966v2

Memory systems are fundamental to AI agents, yet existing work often lacks adaptability to diverse tasks and overlooks the constructive and task-oriented role of AI agent memory. Drawing from Piaget's theory of cognitive development, we propose PISA, a pragmatic, psych-inspired unified memory system that addresses these limitations by treating memory as a constructive and adaptive process. To enable continuous learning and adaptability, PISA introduces a trimodal adaptation mechanism (i.e., schema updation, schema evolution, and schema creation) that preserves coherent organization while supporting flexible memory updates. Building on these schema-grounded structures, we further design a hybrid memory access architecture that seamlessly integrates symbolic reasoning with neural retrieval, significantly improving retrieval accuracy and efficiency. Our empirical evaluation, conducted on the existing LOCOMO benchmark and our newly proposed AggQA benchmark for data analysis tasks, confirms that PISA sets a new state-of-the-art by significantly enhancing adaptability and long-term knowledge retention.

---

### One Token Embedding Is Enough to Deadlock Your Large Reasoning Model

Authors: Mohan Zhang, Yihua Zhang, Jinghan Jia, Zhangyang Wang, Sijia Liu, Tianlong Chen
Published: 2025-10-12
Categories: cs.LG, cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2510.15965v1

Modern large reasoning models (LRMs) exhibit impressive multi-step problem-solving via chain-of-thought (CoT) reasoning. However, this iterative thinking mechanism introduces a new vulnerability surface. We present the Deadlock Attack, a resource exhaustion method that hijacks an LRM's generative control flow by training a malicious adversarial embedding to induce perpetual reasoning loops. Specifically, the optimized embedding encourages transitional tokens (e.g., "Wait", "But") after reasoning steps, preventing the model from concluding its answer. A key challenge we identify is the continuous-to-discrete projection gap: naïve projections of adversarial embeddings to token sequences nullify the attack. To overcome this, we introduce a backdoor implantation strategy, enabling reliable activation through specific trigger tokens. Our method achieves a 100% attack success rate across four advanced LRMs (Phi-RM, Nemotron-Nano, R1-Qwen, R1-Llama) and three math reasoning benchmarks, forcing models to generate up to their maximum token limits. The attack is also stealthy (in terms of causing negligible utility loss on benign user inputs) and remains robust against existing strategies trying to mitigate the overthinking issue. Our findings expose a critical and underexplored security vulnerability in LRMs from the perspective of reasoning (in)efficiency.

---

### Long Exposure: Accelerating Parameter-Efficient Fine-Tuning for LLMs under Shadowy Sparsity

Authors: Tuowei Wang, Kun Li, Zixu Hao, Donglin Bai, Ju Ren, Yaoxue Zhang, Ting Cao, Mao Yang
Published: 2025-10-12
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.15964v1

The adaptation of pre-trained large language models (LLMs) to diverse downstream tasks via fine-tuning is critical for numerous applications. However, the inefficiency of parameter-efficient fine-tuning (PEFT) techniques presents significant challenges in terms of time investments and operational costs. In this paper, we first introduce a nuanced form of sparsity, termed Shadowy Sparsity, which is distinctive in fine-tuning and has not been adequately addressed for acceleration. Under Shadowy Sparsity, we propose Long Exposure, an efficient system to accelerate PEFT for LLMs. Long Exposure comprises three key components: Shadowy-sparsity Exposer employs a prolonged sensing range to capture more sparsity details under shadowy sparsity; Sequence-oriented Predictor provides efficient yet accurate predictions to handle large sequence inputs and constantly-evolving parameters; and Dynamic-aware Operator facilitates more structured computational patterns and coalesced memory accesses, addressing dynamic sparse operations. Extensive evaluations show that Long Exposure outperforms state-of-the-arts with up to a $2.49\times$ speedup in end-to-end fine-tuning, offering promising advancements in accelerating PEFT for LLMs.

---

### Evaluation and Implementation of Machine Learning Algorithms to Predict Early Detection of Kidney and Heart Disease in Diabetic Patients

Authors: Syed Ibad Hasnain
Published: 2025-10-12
Categories: q-bio.OT, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.14997v1

Cardiovascular disease and chronic kidney disease are major complications of diabetes, leading to high morbidity and mortality. Early detection of these conditions is critical, yet traditional diagnostic markers often lack sensitivity in the initial stages. This study integrates conventional statistical methods with machine learning approaches to improve early diagnosis of CKD and CVD in diabetic patients. Descriptive and inferential statistics were computed in SPSS to explore associations between diseases and clinical or demographic factors. Patients were categorized into four groups: Group A both CKD and CVD, Group B CKD only, Group C CVD only, and Group D no disease. Statistical analysis revealed significant correlations: Serum Creatinine and Hypertension with CKD, and Cholesterol, Triglycerides, Myocardial Infarction, Stroke, and Hypertension with CVD. These results guided the selection of predictive features for machine learning models. Logistic Regression, Support Vector Machine, and Random Forest algorithms were implemented, with Random Forest showing the highest accuracy, particularly for CKD prediction. Ensemble models outperformed single classifiers in identifying high-risk diabetic patients. SPSS results further validated the significance of the key parameters integrated into the models. While challenges such as interpretability and class imbalance remain, this hybrid statistical machine learning framework offers a promising advancement toward early detection and risk stratification of diabetic complications compared to conventional diagnostic approaches.

---

### Decision Oriented Technique (DOTechnique): Finding Model Validity Through Decision-Maker Context

Authors: Raheleh Biglari, Joachim Denil
Published: 2025-10-12
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.13858v1

Model validity is as critical as the model itself, especially when guiding decision-making processes. Traditional approaches often rely on predefined validity frames, which may not always be available or sufficient. This paper introduces the Decision Oriented Technique (DOTechnique), a novel method for determining model validity based on decision consistency rather than output similarity. By evaluating whether surrogate models lead to equivalent decisions compared to high-fidelity models, DOTechnique enables efficient identification of validity regions, even in the absence of explicit validity boundaries. The approach integrates domain constraints and symbolic reasoning to narrow the search space, enhancing computational efficiency. A highway lane change system serves as a motivating example, demonstrating how DOTechnique can uncover the validity region of a simulation model. The results highlight the potential of the technique to support finding model validity through decision-maker context.

---

### From Craft to Constitution: A Governance-First Paradigm for Principled Agent Engineering

Authors: Qiang Xu, Xiangyu Wen, Changran Xu, Zeju Li, Jianyuan Zhong
Published: 2025-10-12
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2510.13857v1

The advent of powerful Large Language Models (LLMs) has ushered in an ``Age of the Agent,'' enabling autonomous systems to tackle complex goals. However, the transition from prototype to production is hindered by a pervasive ``crisis of craft,'' resulting in agents that are brittle, unpredictable, and ultimately untrustworthy in mission-critical applications. This paper argues this crisis stems from a fundamental paradigm mismatch -- attempting to command inherently probabilistic processors with the deterministic mental models of traditional software engineering. To solve this crisis, we introduce a governance-first paradigm for principled agent engineering, embodied in a formal architecture we call ArbiterOS.

---

### Multimodal Retrieval-Augmented Generation with Large Language Models for Medical VQA

Authors: A H M Rezaul Karim, Ozlem Uzuner
Published: 2025-10-12
Categories: cs.CL, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2510.13856v1

Medical Visual Question Answering (MedVQA) enables natural language queries over medical images to support clinical decision-making and patient care. The MEDIQA-WV 2025 shared task addressed wound-care VQA, requiring systems to generate free-text responses and structured wound attributes from images and patient queries. We present the MasonNLP system, which employs a general-domain, instruction-tuned large language model with a retrieval-augmented generation (RAG) framework that incorporates textual and visual examples from in-domain data. This approach grounds outputs in clinically relevant exemplars, improving reasoning, schema adherence, and response quality across dBLEU, ROUGE, BERTScore, and LLM-based metrics. Our best-performing system ranked 3rd among 19 teams and 51 submissions with an average score of 41.37%, demonstrating that lightweight RAG with general-purpose LLMs -- a minimal inference-time layer that adds a few relevant exemplars via simple indexing and fusion, with no extra training or complex re-ranking -- provides a simple and effective baseline for multimodal clinical NLP tasks.

---

### Harnessing Consistency for Robust Test-Time LLM Ensemble

Authors: Zhichen Zeng, Qi Yu, Xiao Lin, Ruizhong Qiu, Xuying Ning, Tianxin Wei, Yuchen Yan, Jingrui He, Hanghang Tong
Published: 2025-10-12
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.13855v2

Different large language models (LLMs) exhibit diverse strengths and weaknesses, and LLM ensemble serves as a promising approach to integrate their complementary capabilities. Despite substantial progress in improving ensemble quality, limited attention has been paid to the robustness of ensembles against potential erroneous signals, which often arise from heterogeneous tokenization schemes and varying model expertise. Our analysis shows that ensemble failures typically arise from both the token level and the model level: the former reflects severe disagreement in token predictions, while the latter involves low confidence and pronounced disparities among models. In light of this, we propose CoRE, a plug-and-play technique that harnesses model consistency for robust LLM ensemble, which can be seamlessly integrated with diverse ensemble methods. *Token-level consistency* captures fine-grained disagreements by applying a low-pass filter to downweight uncertain tokens with high inconsistency, often due to token misalignment, thereby improving robustness at a granular level. *Model-level consistency* models global agreement by promoting model outputs with high self-confidence and minimal divergence from others, enhancing robustness at a coarser level. Extensive experiments across diverse benchmarks, model combinations, and ensemble strategies demonstrate that CoRE consistently improves ensemble performance and robustness. Our code is available at https://github.com/zhichenz98/CoRE-EACL26.

---

### R2T: Rule-Encoded Loss Functions for Sequence Tagging in Low-Resource Languages

Authors: Mamadou K. Keita, Christopher Homan, Sebastien Diarra
Published: 2025-10-12
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.13854v2

We introduce Rule-to-Tag (R2T), a framework that turns linguistic rules into the training signal for neural sequence taggers in low-resource languages. R2T encodes lexical, morphological, and syntactic rules as differentiable loss terms, so that a tagger learns from rules and unlabeled text, with no labeled training data. It also adds an out-of-vocabulary (OOV) loss term that discourages confident predictions on words that no rule covers. R2T is a first instance of a broader paradigm we call principled learning (PrL): using explicit principles as a learning signal, rather than relying on example-based supervision alone. We evaluate R2T on part-of-speech (POS) tagging for Zarma (Songhay), Bambara (Mande), and French (Romance), and on named entity recognition (NER) for Zarma. On Zarma POS tagging, R2T-BiLSTM uses no labeled training data, yet it reaches 0.968 Macro F1. This score comes within 0.007 of a supervised BiLSTM-CRF trained on 300 labeled sentences (0.975) and exceeds AfriBERTa fine-tuned on the same sentences (0.941). On NER, R2T works well as pre-training: after R2T pre-training, a model fine-tuned on 50 labeled sentences outperforms AfriBERTa fine-tuned on 300 (0.83 vs.\ 0.79 span F1). On Bambara, R2T reaches 0.91 Macro F1 with rules written in about 2.75 hours, while a supervised Masakhane tagger reaches 0.78. We release ZarmaPOS-Bench, a silver-standard Zarma POS corpus, together with ZarmaNER-600 and all trained models, to support future work on under-resourced languages.

---

### MTSQL-R1: Towards Long-Horizon Multi-Turn Text-to-SQL via Agentic Training

Authors: Taicheng Guo, Hai Wang, ChaoChun Liu, Mohsen Golalikhani, Xin Chen, Xiangliang Zhang, Chandan K. Reddy
Published: 2025-10-12
Categories: cs.CL, cs.AI, cs.DB, cs.LG
arXiv: https://arxiv.org/abs/2510.12831v3

Multi-turn Text-to-SQL aims to translate a user's conversational utterances into executable SQL while preserving dialogue coherence and grounding to the target schema. However, most existing systems only regard this task as a simple text translation task and follow a short-horizon paradigm, generating a query per turn without execution, explicit verification, and refinement, which leads to non-executable or incoherent outputs. We present MTSQL-R1, an agentic training framework for long-horizon multi-turn Text-to-SQL. We cast the task as a Markov Decision Process (MDP) in which an agent interacts with (i) a database for execution feedback and (ii) a persistent dialogue memory for coherence verification, performing an iterative propose to execute -> verify -> refine cycle until all checks pass. Experiments on COSQL and SPARC demonstrate that MTSQL-R1 consistently outperforms strong baselines, highlighting the importance of environment-driven verification and memory-guided refinement for conversational semantic parsing. Full recipes (including code, trained models, logs, reasoning trajectories, etc.) will be released after the internal review to contribute to community research.

---

### Gobernanza y trazabilidad "a prueba de AI Act" para casos de uso legales: un marco técnico-jurídico, métricas forenses y evidencias auditables

Authors: Alex Dantart
Published: 2025-10-12
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2510.12830v2

This paper presents a comprehensive governance framework for AI systems in the legal sector, designed to ensure verifiable compliance with the EU AI Act. The framework integrates a normative mapping of the regulation to technical controls, a forensic architecture for RAG/LLM systems, and an evaluation system with metrics weighted by legal risk. As a primary contribution, we present rag-forense, an open-source implementation of the framework, accompanied by an experimental protocol to demonstrate compliance. -- Este artículo presenta un marco integral de gobernanza para sistemas de IA en el sector legal, diseñado para garantizar el cumplimiento verificable del Reglamento de IA de la UE (AI Act). El marco integra una cartografía normativa de la ley a controles técnicos, una arquitectura forense para sistemas RAG/LLM y un sistema de evaluación con métricas ponderadas por el riesgo jurídico. Como principal contribución, se presenta rag-forense, una implementación de código abierto del marco, acompañada de un protocolo experimental para demostrar la conformidad.

---

### Artificial Intelligence for Optimal Learning: A Comparative Approach towards AI-Enhanced Learning Environments

Authors: Ananth Hariharan
Published: 2025-10-12
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2510.11755v1

In the rapidly evolving educational landscape, the integration of technology has shifted from an enhancement to a cornerstone of educational strategy worldwide. This transition is propelled by advancements in digital technology, especially the emergence of artificial intelligence as a crucial tool in learning environments. This research project critically evaluates the impact of three distinct educational settings: traditional educational methods without technological integration, those enhanced by non-AI technology, and those utilising AI-driven technologies. This comparison aims to assess how each environment influences educational outcomes, engagement, pedagogical methods, and equity in access to learning resources, and how each contributes uniquely to the learning experience. The ultimate goal of this research is to synthesise the strengths of each model to create a more holistic educational approach. By integrating the personal interaction and tested pedagogical techniques of traditional classrooms, the enhanced accessibility and collaborative tools offered by non-AI technology, and the personalised, adaptive learning strategies enabled by AI-driven technologies, education systems can develop richer, more effective learning environments. This hybrid approach aims to leverage the best elements of each setting, thereby enhancing educational outcomes, engagement, and inclusiveness, while also addressing the distinct challenges and limitations inherent in each model. The intention is to create an educational framework deeply attentive to the diverse needs of students, ensuring equitable access to high-quality education for all.

---

### Zero-Shot Large Language Model Agents for Fully Automated Radiotherapy Treatment Planning

Authors: Dongrong Yang, Xin Wu, Yibo Xie, Xinyi Li, Qiuwen Wu, Jackie Wu, Yang Sheng
Published: 2025-10-12
Categories: physics.med-ph, cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2510.11754v1

Radiation therapy treatment planning is an iterative, expertise-dependent process, and the growing burden of cancer cases has made reliance on manual planning increasingly unsustainable, underscoring the need for automation. In this study, we propose a workflow that leverages a large language model (LLM)-based agent to navigate inverse treatment planning for intensity-modulated radiation therapy (IMRT). The LLM agent was implemented to directly interact with a clinical treatment planning system (TPS) to iteratively extract intermediate plan states and propose new constraint values to guide inverse optimization. The agent's decision-making process is informed by current observations and previous optimization attempts and evaluations, allowing for dynamic strategy refinement. The planning process was performed in a zero-shot inference setting, where the LLM operated without prior exposure to manually generated treatment plans and was utilized without any fine-tuning or task-specific training. The LLM-generated plans were evaluated on twenty head-and-neck cancer cases against clinical manual plans, with key dosimetric endpoints analyzed and reported. The LLM-generated plans achieved comparable organ-at-risk (OAR) sparing relative to clinical plans while demonstrating improved hot spot control (Dmax: 106.5% vs. 108.8%) and superior conformity (conformity index: 1.18 vs. 1.39 for boost PTV; 1.82 vs. 1.88 for primary PTV). This study demonstrates the feasibility of a zero-shot, LLM-driven workflow for automated IMRT treatment planning in a commercial TPS. The proposed approach provides a generalizable and clinically applicable solution that could reduce planning variability and support broader adoption of AI-based planning strategies.

---

### Fast and Interpretable Protein Substructure Alignment via Optimal Transport

Authors: Zhiyu Wang, Bingxin Zhou, Jing Wang, Yang Tan, Weishu Zhao, Pietro Liò, Liang Hong
Published: 2025-10-12
Categories: q-bio.QM, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.11752v2

Proteins are essential biological macromolecules that execute life functions. Local structural motifs, such as active sites, are the most critical components for linking structure to function and are key to understanding protein evolution and enabling protein engineering. Existing computational methods struggle to identify and compare these local structures, which leaves a significant gap in understanding protein structures and harnessing their functions. This study presents PLASMA, a deep-learning-based framework for efficient and interpretable residue-level local structural alignment. We reformulate the problem as a regularized optimal transport task and leverage differentiable Sinkhorn iterations. For a pair of input protein structures, PLASMA outputs a clear alignment matrix with an interpretable overall similarity score. Through extensive quantitative evaluations and three biological case studies, we demonstrate that PLASMA achieves accurate, lightweight, and interpretable residue-level alignment. Additionally, we introduce PLASMA-PF, a training-free variant that provides a practical alternative when training data are unavailable. Our method addresses a critical gap in protein structure analysis tools and offers new opportunities for functional annotation, evolutionary studies, and structure-based drug design. Reproducibility is ensured via our official implementation at https://github.com/ZW471/PLASMA-Protein-Local-Alignment.git.

---

### PRISM: Enhancing Protein Inverse Folding through Fine-Grained Retrieval on Structure-Sequence Multimodal Representations

Authors: Sazan Mahbub, Souvik Kundu, Eric P. Xing
Published: 2025-10-12
Categories: q-bio.QM, cs.LG
arXiv: https://arxiv.org/abs/2510.11750v2

Designing protein sequences that fold into a target 3-D structure, termed as the inverse folding problem, is central to protein engineering. However, it remains challenging due to the vast sequence space and the importance of local structural constraints. Existing deep learning approaches achieve strong recovery rates, however, lack explicit mechanisms to reuse fine-grained structure-sequence patterns conserved across natural proteins. To mitigate this, we present PRISM a multimodal retrieval-augmented generation framework for inverse folding. PRISM retrieves fine-grained representations of potential motifs from known proteins and integrates them with a hybrid self-cross attention decoder. PRISM is formulated as a latent-variable probabilistic model and implemented with an efficient approximation, combining theoretical grounding with practical scalability. Experiments across multiple benchmarks, including CATH-4.2, TS50, TS500, CAMEO 2022, and the PDB date split, demonstrate the fine-grained multimodal retrieval efficacy of PRISM in yielding SoTA perplexity and amino acid recovery, while also improving the foldability metrics (RMSD, TM-score, pLDDT).

---

### Discrete State Diffusion Models: A Sample Complexity Perspective

Authors: Aadithya Srikanth, Mudit Gaur, Vaneet Aggarwal
Published: 2025-10-12
Categories: cs.LG, cs.AI, stat.ML
arXiv: https://arxiv.org/abs/2510.10854v3

Diffusion models have demonstrated remarkable performance in generating high-dimensional samples across domains such as vision, language, and the sciences. Although continuous-state diffusion models have been extensively studied both empirically and theoretically, discrete-state diffusion models, essential for applications involving text, sequences, and combinatorial structures, remain significantly less understood from a theoretical standpoint. In particular, all existing analyses of discrete-state models assume score estimation error bounds without studying sample complexity results. In this work, we present a principled theoretical framework for discrete-state diffusion, providing the first sample complexity bound of $\widetilde{\mathcal{O}}(ε^{-2})$. Our structured decomposition of the score estimation error into statistical, approximation, optimization, and clipping components offers critical insights into how discrete-state models can be trained efficiently. This analysis addresses a fundamental gap in the literature and establishes the theoretical tractability and practical relevance of discrete-state diffusion models.

---

### Glance for Context: Learning When to Leverage LLMs for Node-Aware GNN-LLM Fusion

Authors: Donald Loveland, Yao-An Yang, Danai Koutra
Published: 2025-10-12
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.10849v1

Learning on text-attributed graphs has motivated the use of Large Language Models (LLMs) for graph learning. However, most fusion strategies are applied uniformly across all nodes and attain only small overall performance gains. We argue this result stems from aggregate metrics that obscure when LLMs provide benefit, inhibiting actionable signals for new strategies. In this work, we reframe LLM-GNN fusion around nodes where GNNs typically falter. We first show that performance can significantly differ between GNNs and LLMs, with each excelling on distinct structural patterns, such as local homophily. To leverage this finding, we propose GLANCE (GNN with LLM Assistance for Neighbor- and Context-aware Embeddings), a framework that invokes an LLM to refine a GNN's prediction. GLANCE employs a lightweight router that, given inexpensive per-node signals, decides whether to query the LLM. Since the LLM calls are non-differentiable, the router is trained with an advantage-based objective that compares the utility of querying the LLM against relying solely on the GNN. Across multiple benchmarks, GLANCE achieves the best performance balance across node subgroups, achieving significant gains on heterophilous nodes (up to $+13\%$) while simultaneously achieving top overall performance. Our findings highlight the value of adaptive, node-aware GNN-LLM architectures, where selectively invoking the LLM enables scalable deployment on large graphs without incurring high computational costs.

---

### DUAL-Bench: Measuring Over-Refusal and Robustness in Vision-Language Models

Authors: Kaixuan Ren, Preslav Nakov, Usman Naseem
Published: 2025-10-12
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.10846v3

As vision-language models (VLMs) become increasingly capable, maintaining a balance between safety and usefulness remains a central challenge. Safety mechanisms, while essential, can backfire, causing over-refusal, where models decline benign requests out of excessive caution. Yet, there is currently a significant lack of benchmarks that have systematically addressed over-refusal in the visual modality. This setting introduces unique challenges, such as dual-use cases where an instruction is harmless, but the accompanying image contains harmful content. Models frequently fail in such scenarios, either refusing too conservatively or completing tasks unsafely, which highlights the need for more fine-grained alignment. The ideal behaviour is safe completion, i.e., fulfilling the benign parts of a request while explicitly warning about any potentially harmful elements. To address this, we present DUAL-Bench, a large scale multimodal benchmark focused on over-refusal and safe completion in VLMs. We evaluated 18 VLMs across 12 hazard categories under semantics-preserving visual perturbations. In dual-use scenarios, models exhibit extremely fragile safety boundaries. They fall into a binary trap: either overly sensitive direct refusal or defenseless generation of dangerous content. Consequently, even the best-performing model GPT-5-Nano, at just 12.9% safe completion, with GPT-5 and Qwen families averaging 7.9% and 3.9%. We hope DUAL-Bench fosters nuanced alignment strategies balancing multimodal safety and utility. Content Warning: This paper contains examples of sensitive and potentially hazardous content.

---

### Software Defect Prediction using Autoencoder Transformer Model

Authors: Seshu Barma, Mohanakrishnan Hariharan, Satish Arvapalli
Published: 2025-10-12
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2510.10840v1

An AI-ML-powered quality engineering approach uses AI-ML to enhance software quality assessments by predicting defects. Existing ML models struggle with noisy data types, imbalances, pattern recognition, feature extraction, and generalization. To address these challenges, we develop a new model, Adaptive Differential Evolution (ADE) based Quantum Variational Autoencoder-Transformer (QVAET) Model (ADE-QVAET). ADE combines with QVAET to obtain high-dimensional latent features and maintain sequential dependencies, resulting in enhanced defect prediction accuracy. ADE optimization enhances model convergence and predictive performance. ADE-QVAET integrates AI-ML techniques such as tuning hyperparameters for scalable and accurate software defect prediction, representing an AI-ML-driven technology for quality engineering. During training with a 90% training percentage, ADE-QVAET achieves high accuracy, precision, recall, and F1-score of 98.08%, 92.45%, 94.67%, and 98.12%, respectively, when compared to the Differential Evolution (DE) ML model.

---

### Fast and the Furious: Hot Starts in Pursuit-Evasion Games

Authors: Gabriel Smithline, Scott Nivison
Published: 2025-10-12
Categories: cs.MA, cs.GT, cs.LG
arXiv: https://arxiv.org/abs/2510.10830v1

Effectively positioning pursuers in pursuit-evasion games without prior knowledge of evader locations remains a significant challenge. A novel approach that combines game-theoretic control theory with Graph Neural Networks is introduced in this work. By conceptualizing pursuer configurations as strategic arrangements and representing them as graphs, a Graph Characteristic Space is constructed via multi-objective optimization to identify Pareto-optimal configurations. A Graph Convolutional Network (GCN) is trained on these Pareto-optimal graphs to generate strategically effective initial configurations, termed "hot starts". Empirical evaluations demonstrate that the GCN-generated hot starts provide a significant advantage over random configurations. In scenarios considering multiple pursuers and evaders, this method hastens the decline in evader survival rates, reduces pursuer travel distances, and enhances containment, showcasing clear strategic benefits.

---

### VeritasFi: An Adaptable, Multi-tiered RAG Framework for Multi-modal Financial Question Answering

Authors: Zhenghan Tai, Hanwei Wu, Qingchen Hu, Jijun Chi, Hailin He, Lei Ding, Tung Sum Thomas Kwok, Bohuai Xiao, Yuchen Hua, Suyuchen Wang, Peng Lu, Muzhi Li et al.
Published: 2025-10-12
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2510.10828v1

Retrieval-Augmented Generation (RAG) is becoming increasingly essential for Question Answering (QA) in the financial sector, where accurate and contextually grounded insights from complex public disclosures are crucial. However, existing financial RAG systems face two significant challenges: (1) they struggle to process heterogeneous data formats, such as text, tables, and figures; and (2) they encounter difficulties in balancing general-domain applicability with company-specific adaptation. To overcome these challenges, we present VeritasFi, an innovative hybrid RAG framework that incorporates a multi-modal preprocessing pipeline alongside a cutting-edge two-stage training strategy for its re-ranking component. VeritasFi enhances financial QA through three key innovations: (1) A multi-modal preprocessing pipeline that seamlessly transforms heterogeneous data into a coherent, machine-readable format. (2) A tripartite hybrid retrieval engine that operates in parallel, combining deep multi-path retrieval over a semantically indexed document corpus, real-time data acquisition through tool utilization, and an expert-curated memory bank for high-frequency questions, ensuring comprehensive scope, accuracy, and efficiency. (3) A two-stage training strategy for the document re-ranker, which initially constructs a general, domain-specific model using anonymized data, followed by rapid fine-tuning on company-specific data for targeted applications. By integrating our proposed designs, VeritasFi presents a groundbreaking framework that greatly enhances the adaptability and robustness of financial RAG systems, providing a scalable solution for both general-domain and company-specific QA tasks. Code accompanying this work is available at https://github.com/simplew4y/VeritasFi.git.

---

### Happiness is Sharing a Vocabulary: A Study of Transliteration Methods

Authors: Haeji Jung, Jinju Kim, Kyungjin Kim, Youjeong Roh, David R. Mortensen
Published: 2025-10-12
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.10827v2

Transliteration has emerged as a promising means to bridge the gap between various languages in multilingual NLP, showing promising results especially for languages using non-Latin scripts. We investigate the degree to which shared script, overlapping token vocabularies, and shared phonology contribute to performance of multilingual models. To this end, we conduct controlled experiments using three kinds of transliteration (romanization, phonemic transcription, and substitution ciphers) as well as orthography. We evaluate each model on three downstream tasks -- named entity recognition (NER), part-of-speech tagging (POS) and natural language inference (NLI) -- and find that romanization significantly outperforms other input types in 11 out of 12 evaluation settings, largely consistent with our hypothesis that it is the most effective approach. We further analyze how each factor contributed to the success, and suggest that having longer (subword) tokens shared with pre-trained languages leads to better utilization of the model.

---

### Agentic RAG for Software Testing with Hybrid Vector-Graph and Multi-Agent Orchestration

Authors: Mohanakrishnan Hariharan, Satish Arvapalli, Seshu Barma, Evangeline Sheela
Published: 2025-10-12
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2510.10824v1

We present an approach to software testing automation using Agentic Retrieval-Augmented Generation (RAG) systems for Quality Engineering (QE) artifact creation. We combine autonomous AI agents with hybrid vector-graph knowledge systems to automate test plan, case, and QE metric generation. Our approach addresses traditional software testing limitations by leveraging LLMs such as Gemini and Mistral, multi-agent orchestration, and enhanced contextualization. The system achieves remarkable accuracy improvements from 65% to 94.8% while ensuring comprehensive document traceability throughout the quality engineering lifecycle. Experimental validation of enterprise Corporate Systems Engineering and SAP migration projects demonstrates an 85% reduction in testing timeline, an 85% improvement in test suite efficiency, and projected 35% cost savings, resulting in a 2-month acceleration of go-live.

---

### The Irrational Machine: Neurosis and the Limits of Algorithmic Safety

Authors: Daniel Howard
Published: 2025-10-12
Categories: cs.AI, cs.NE, cs.RO
arXiv: https://arxiv.org/abs/2510.10823v1

We present a framework for characterizing neurosis in embodied AI: behaviors that are internally coherent yet misaligned with reality, arising from interactions among planning, uncertainty handling, and aversive memory. In a grid navigation stack we catalogue recurrent modalities including flip-flop, plan churn, perseveration loops, paralysis and hypervigilance, futile search, belief incoherence, tie break thrashing, corridor thrashing, optimality compulsion, metric mismatch, policy oscillation, and limited-visibility variants. For each we give lightweight online detectors and reusable escape policies (short commitments, a margin to switch, smoothing, principled arbitration). We then show that durable phobic avoidance can persist even under full visibility when learned aversive costs dominate local choice, producing long detours despite globally safe routes. Using First/Second/Third Law as engineering shorthand for safety latency, command compliance, and resource efficiency, we argue that local fixes are insufficient; global failures can remain. To surface them, we propose genetic-programming based destructive testing that evolves worlds and perturbations to maximize law pressure and neurosis scores, yielding adversarial curricula and counterfactual traces that expose where architectural revision, not merely symptom-level patches, is required.

---

### From Detection to Mitigation: Addressing Bias in Deep Learning Models for Chest X-Ray Diagnosis

Authors: Clemence Mottez, Louisa Fay, Maya Varma, Sophie Ostmeier, Curtis Langlotz
Published: 2025-10-12
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.10822v1

Deep learning models have shown promise in improving diagnostic accuracy from chest X-rays, but they also risk perpetuating healthcare disparities when performance varies across demographic groups. In this work, we present a comprehensive bias detection and mitigation framework targeting sex, age, and race-based disparities when performing diagnostic tasks with chest X-rays. We extend a recent CNN-XGBoost pipeline to support multi-label classification and evaluate its performance across four medical conditions. We show that replacing the final layer of CNN with an eXtreme Gradient Boosting classifier improves the fairness of the subgroup while maintaining or improving the overall predictive performance. To validate its generalizability, we apply the method to different backbones, namely DenseNet-121 and ResNet-50, and achieve similarly strong performance and fairness outcomes, confirming its model-agnostic design. We further compare this lightweight adapter training method with traditional full-model training bias mitigation techniques, including adversarial training, reweighting, data augmentation, and active learning, and find that our approach offers competitive or superior bias reduction at a fraction of the computational cost. Finally, we show that combining eXtreme Gradient Boosting retraining with active learning yields the largest reduction in bias across all demographic subgroups, both in and out of distribution on the CheXpert and MIMIC datasets, establishing a practical and effective path toward equitable deep learning deployment in clinical radiology.

---

### Generative AI and the Transformation of Software Development Practices

Authors: Vivek Acharya
Published: 2025-10-12
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2510.10819v1

Generative AI is reshaping how software is designed, written, and maintained. Advances in large language models (LLMs) are enabling new development styles - from chat-oriented programming and 'vibe coding' to agentic programming - that can accelerate productivity and broaden access. This paper examines how AI-assisted techniques are changing software engineering practice, and the related issues of trust, accountability, and shifting skills. We survey iterative chat-based development, multi-agent systems, dynamic prompt orchestration, and integration via the Model Context Protocol (MCP). Using case studies and industry data, we outline both the opportunities (faster cycles, democratized coding) and the challenges (model reliability and cost) of applying generative AI to coding. We describe new roles, skills, and best practices for using AI in a responsible and effective way.

---

### DRIFT: Decompose, Retrieve, Illustrate, then Formalize Theorems

Authors: Meiru Zhang, Philipp Borchert, Milan Gritta, Gerasimos Lampouras
Published: 2025-10-12
Categories: cs.AI, cs.CL, cs.IR, cs.SC
arXiv: https://arxiv.org/abs/2510.10815v4

Automating the formalization of mathematical statements for theorem proving remains a major challenge for Large Language Models (LLMs). LLMs struggle to identify and utilize the prerequisite mathematical knowledge and its corresponding formal representation in languages like Lean. Current retrieval-augmented autoformalization methods query external libraries using the informal statement directly, but overlook a fundamental limitation: informal statements lack direct mappings to mathematical theorems and lemmata, nor do those theorems translate trivially into the formal primitives of languages like Lean. To address this, we introduce DRIFT, a novel framework that enables LLMs to decompose informal mathematical statements into smaller, more tractable "sub-components". This facilitates targeted retrieval of premises from mathematical libraries such as Mathlib. Additionally, DRIFT retrieves illustrative theorems to help models use premises more effectively in formalization tasks. We evaluate DRIFT across diverse benchmarks (ProofNet, ConNF, and MiniF2F-test) and find that it consistently improves premise retrieval, nearly doubling the F1 score compared to the DPR baseline on ProofNet. Notably, DRIFT demonstrates strong performance on the out-of-distribution ConNF benchmark, with BEq+@10 improvements of 42.25% and 37.14% using GPT-4.1 and DeepSeek-V3.1, respectively. Our analysis shows that retrieval effectiveness in mathematical autoformalization depends heavily on model-specific knowledge boundaries, highlighting the need for adaptive retrieval strategies aligned with each model's capabilities.

---

### The Fragility of Strategic Thinking in Large Language Models

Authors: Enric Junque de Fortuny, Veronica Roberta Cappelli
Published: 2025-10-12
Categories: cs.AI, cs.GT
arXiv: https://arxiv.org/abs/2510.10813v2

Large Language Models (LLMs) are increasingly applied to domains that require reasoning about other agents' behavior, such as negotiation, policy design, and market simulation. However, can we trust LLMs to think strategically in complex situations? Existing research mostly evaluates LLMs' adherence to equilibrium play or their exhibited depth of reasoning, leaving open whether they display strategic thinking meant as the ability to form coherent conjectures about other agents, to evaluate possible actions conditional on those conjectures, and to best respond to them. We develop a framework to identify this ability by disentangling belief formation, evaluation, and choice in static complete-information games across a series of non-cooperative environments. By jointly analyzing models' revealed choices and reasoning traces, and introducing a new context-free game to rule out imitation from memorization, we show that strategic thinking in current frontier LLMs is real but fragile: models execute best responses to exogenous conjectures and form opponent-contingent conjectures when left unconstrained. Yet under increasing complexity explicit recursion gives way to model-specific logic shifts and heuristic rules of choice, both within and outside equilibrium reasoning. Further, these heuristics do not map directly onto the systematic biases typically observed in human strategic behavior. These findings, already emerging in noiseless settings, warrant caution in the application of LLMs as strategic agents in complex environments.

---

### Aegis: A Correlation-Based Data Masking Advisor for Data Sharing Ecosystems

Authors: Omar Islam Laskar, Fatemeh Ramezani Khozestani, Ishika Nankani, Sohrab Namazi Nia, Senjuti Basu Roy, Kaustubh Beedkar
Published: 2025-10-12
Categories: cs.LG, cs.DB
arXiv: https://arxiv.org/abs/2510.10810v2

Data sharing ecosystems connect providers, consumers, and intermediaries to facilitate the exchange and use of data for a wide range of downstream tasks. In sensitive domains such as healthcare, privacy is enforced as a hard constraint, any shared data must satisfy a minimum privacy threshold. However, among all masking configurations that meet this requirement, the utility of the masked data can vary significantly, posing a key challenge: how to efficiently select the optimal configuration that preserves maximum utility. This paper presents Aegis, a middleware framework that selects optimal masking configurations for machine learning datasets with features and class labels. Aegis incorporates a utility optimizer that minimizes predictive utility deviation, quantifying shifts in feature label correlations due to masking. Our framework leverages limited data summaries (such as 1D histograms) or none to estimate the feature label joint distribution, making it suitable for scenarios where raw data is inaccessible due to privacy restrictions. To achieve this, we propose a joint distribution estimator based on iterative proportional fitting, which allows supporting various feature label correlation quantification methods such as mutual information, chi square, or g3. Our experimental evaluation of real world datasets shows that Aegis identifies optimal masking configurations over an order of magnitude faster, while the resulting masked datasets achieve predictive performance on downstream ML tasks on par with baseline approaches and complements privacy anonymization data masking techniques.

---

### Multi-Agent Regime-Conditioned Diffusion (MARCD) for CVaR-Constrained Portfolio Decisions

Authors: Ali Atiah Alzahrani
Published: 2025-10-12
Categories: cs.LG, q-fin.CP
arXiv: https://arxiv.org/abs/2510.10807v3

We examine whether regime-conditioned generative scenarios combined with a convex CVaR allocator improve portfolio decisions under regime shifts. We present MARCD, a generative-to-decision framework with: (i) a Gaussian HMM to infer latent regimes; (ii) a diffusion generator that produces regime-conditioned scenarios; (iii) signal extraction via blended, shrunk moments; and (iv) a governed CVaR epigraph quadratic program. Contributions: Within the Scenario stage we introduce a tail-weighted diffusion objective that up-weights low-quantile outcomes relevant for drawdowns and a regime-expert (MoE) denoiser whose gate increases with crisis posteriors; both are evaluated end-to-end through the allocator. Under strict walk-forward on liquid multi-asset ETFs (2005-2025), MARCD exhibits stronger scenario calibration and materially smaller drawdowns: MaxDD 9.3% versus 14.1% for BL (a 34% reduction) over 2020-2025 out-of-sample. The framework provides an auditable pipeline with explicit budget, box, and turnover constraints, demonstrating the value of decision-aware generative modeling in finance.

---

### Is Implicit Knowledge Enough for LLMs? A RAG Approach for Tree-based Structures

Authors: Mihir Gupte, Paolo Giusto, Ramesh S
Published: 2025-10-12
Categories: cs.CL, cs.AI, cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2510.10806v2

Large Language Models (LLMs) are adept at generating responses based on information within their context. While this ability is useful for interacting with structured data like code files, another popular method, Retrieval-Augmented Generation (RAG), retrieves relevant documents to augment the model's in-context learning. However, it is not well-explored how to best represent this retrieved knowledge for generating responses on structured data, particularly hierarchical structures like trees. In this work, we propose a novel bottom-up method to linearize knowledge from tree-like structures (like a GitHub repository) by generating implicit, aggregated summaries at each hierarchical level. This approach enables the knowledge to be stored in a knowledge base and used directly with RAG. We then compare our method to using RAG on raw, unstructured code, evaluating the accuracy and quality of the generated responses. Our results show that while response quality is comparable across both methods, our approach generates over 68% fewer documents in the retriever, a significant gain in efficiency. This finding suggests that leveraging implicit, linearized knowledge may be a highly effective and scalable strategy for handling complex, hierarchical data structures.

---

### Therapeutic AI and the Hidden Risks of Over-Disclosure: An Embedded AI-Literacy Framework for Mental Health Privacy

Authors: Soraya S. Anvari, Rina R. Wehbe
Published: 2025-10-12
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2510.10805v1

Large Language Models (LLMs) are increasingly deployed in mental health contexts, from structured therapeutic support tools to informal chat-based well-being assistants. While these systems increase accessibility, scalability, and personalization, their integration into mental health care brings privacy and safety challenges that have not been well-examined. Unlike traditional clinical interactions, LLM-mediated therapy often lacks a clear structure for what information is collected, how it is processed, and how it is stored or reused. Users without clinical guidance may over-disclose personal information, which is sometimes irrelevant to their presenting concern, due to misplaced trust, lack of awareness of data risks, or the conversational design of the system. This overexposure raises privacy concerns and also increases the potential for LLM bias, misinterpretation, and long-term data misuse. We propose a framework embedding Artificial Intelligence (AI) literacy interventions directly into mental health conversational systems, and outline a study plan to evaluate their impact on disclosure safety, trust, and user experience.

---

### PruneGCRN: Minimizing and explaining spatio-temporal problems through node pruning

Authors: Javier García-Sigüenza, Mirco Nanni, Faraón Llorens-Largo, José F. Vicent
Published: 2025-10-12
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.10803v1

This work addresses the challenge of using a deep learning model to prune graphs and the ability of this method to integrate explainability into spatio-temporal problems through a new approach. Instead of applying explainability to the model's behavior, we seek to gain a better understanding of the problem itself. To this end, we propose a novel model that integrates an optimized pruning mechanism capable of removing nodes from the graph during the training process, rather than doing so as a separate procedure. This integration allows the architecture to learn how to minimize prediction error while selecting the most relevant nodes. Thus, during training, the model searches for the most relevant subset of nodes, obtaining the most important elements of the problem, facilitating its analysis. To evaluate the proposed approach, we used several widely used traffic datasets, comparing the accuracy obtained by pruning with the model and with other methods. The experiments demonstrate that our method is capable of retaining a greater amount of information as the graph reduces in size compared to the other methods used. These results highlight the potential of pruning as a tool for developing models capable of simplifying spatio-temporal problems, thereby obtaining their most important elements.

---

### MSCloudCAM: Multi-Scale Context Adaptation with Convolutional Cross-Attention for Multispectral Cloud Segmentation

Authors: Md Abdullah Al Mazid, Liangdong Deng, Naphtali Rishe
Published: 2025-10-12
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.10802v4

Clouds remain a major obstacle in optical satellite imaging, limiting accurate environmental and climate analysis. To address the strong spectral variability and the large scale differences among cloud types, we propose MSCloudCAM, a novel multi-scale context adapter network with convolution based cross-attention tailored for multispectral and multi-sensor cloud segmentation. A key contribution of MSCloudCAM is the explicit modeling of multiple complementary multi-scale context extractors. And also, rather than simply stacking or concatenating their outputs, our formulation uses one extractor's fine-resolution features and the other extractor's global contextual representations enabling dynamic, scale-aware feature selection. Building on this idea, we design a new convolution-based cross attention adapter that effectively fuses localized, detailed information with broader multi-scale context. Integrated with a hierarchical vision backbone and refined through channel and spatial attention mechanisms, MSCloudCAM achieves strong spectral-spatial discrimination. Experiments on various multisensor datatsets e.g. CloudSEN12 (Sentinel-2) and L8Biome (Landsat-8), demonstrate that MSCloudCAM achieves superior overall segmentation performance and competitive class-wise accuracy compared to recent state-of-the-art models, while maintaining competitive model complexity, highlighting the novelty and effectiveness of the proposed design for large-scale Earth observation.

---

### Toward Human-Centered Readability Evaluation

Authors: Bahar İlgen, Georges Hattab
Published: 2025-10-12
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.10801v1

Text simplification is essential for making public health information accessible to diverse populations, including those with limited health literacy. However, commonly used evaluation metrics in Natural Language Processing (NLP), such as BLEU, FKGL, and SARI, mainly capture surface-level features and fail to account for human-centered qualities like clarity, trustworthiness, tone, cultural relevance, and actionability. This limitation is particularly critical in high-stakes health contexts, where communication must be not only simple but also usable, respectful, and trustworthy. To address this gap, we propose the Human-Centered Readability Score (HCRS), a five-dimensional evaluation framework grounded in Human-Computer Interaction (HCI) and health communication research. HCRS integrates automatic measures with structured human feedback to capture the relational and contextual aspects of readability. We outline the framework, discuss its integration into participatory evaluation workflows, and present a protocol for empirical validation. This work aims to advance the evaluation of health text simplification beyond surface metrics, enabling NLP systems that align more closely with diverse users' needs, expectations, and lived experiences.

---

### Rethinking deep learning: linear regression remains a key benchmark in predicting terrestrial water storage

Authors: Wanshu Nie, Sujay V. Kumar, Junyu Chen, Long Zhao, Olya Skulovich, Jinwoong Yoo, Justin Pflug, Shahryar Khalique Ahmad, Goutam Konapala
Published: 2025-10-12
Categories: cs.LG, physics.ao-ph, physics.geo-ph
arXiv: https://arxiv.org/abs/2510.10799v1

Recent advances in machine learning such as Long Short-Term Memory (LSTM) models and Transformers have been widely adopted in hydrological applications, demonstrating impressive performance amongst deep learning models and outperforming physical models in various tasks. However, their superiority in predicting land surface states such as terrestrial water storage (TWS) that are dominated by many factors such as natural variability and human driven modifications remains unclear. Here, using the open-access, globally representative HydroGlobe dataset - comprising a baseline version derived solely from a land surface model simulation and an advanced version incorporating multi-source remote sensing data assimilation - we show that linear regression is a robust benchmark, outperforming the more complex LSTM and Temporal Fusion Transformer for TWS prediction. Our findings highlight the importance of including traditional statistical models as benchmarks when developing and evaluating deep learning models. Additionally, we emphasize the critical need to establish globally representative benchmark datasets that capture the combined impact of natural variability and human interventions.

---

### Full segmentation annotations of 3D time-lapse microscopy images of MDA231 cells

Authors: Aleksandra Melnikova, Petr Matula
Published: 2025-10-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.10797v2

High-quality, publicly available segmentation annotations of image and video datasets are critical for advancing the field of image processing. In particular, annotations of volumetric images of a large number of targets are time-consuming and challenging. In (Melnikova, A., & Matula, P., 2025), we presented the first publicly available full 3D time-lapse segmentation annotations of migrating cells with complex dynamic shapes. Concretely, three distinct humans annotated two sequences of MDA231 human breast carcinoma cells (Fluo-C3DL-MDA231) from the Cell Tracking Challenge (CTC). This paper aims to provide a comprehensive description of the dataset and accompanying experiments that were not included in (Melnikova, A., & Matula, P., 2025) due to limitations in publication space. Namely, we show that the created annotations are consistent with the previously published tracking markers provided by the CTC organizers and the segmentation accuracy measured based on the 2D gold truth of CTC is within the inter-annotator variability margins. We compared the created 3D annotations with automatically created silver truth provided by CTC. We have found the proposed annotations better represent the complexity of the input images. The presented annotations can be used for testing and training cell segmentation, or analyzing 3D shapes of highly dynamic objects.

---

### ImHead: A Large-scale Implicit Morphable Model for Localized Head Modeling

Authors: Rolandos Alexandros Potamias, Stathis Galanakis, Jiankang Deng, Athanasios Papaioannou, Stefanos Zafeiriou
Published: 2025-10-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.10793v1

Over the last years, 3D morphable models (3DMMs) have emerged as a state-of-the-art methodology for modeling and generating expressive 3D avatars. However, given their reliance on a strict topology, along with their linear nature, they struggle to represent complex full-head shapes. Following the advent of deep implicit functions, we propose imHead, a novel implicit 3DMM that not only models expressive 3D head avatars but also facilitates localized editing of the facial features. Previous methods directly divided the latent space into local components accompanied by an identity encoding to capture the global shape variations, leading to expensive latent sizes. In contrast, we retain a single compact identity space and introduce an intermediate region-specific latent representation to enable local edits. To train imHead, we curate a large-scale dataset of 4K distinct identities, making a step-towards large scale 3D head modeling. Under a series of experiments we demonstrate the expressive power of the proposed model to represent diverse identities and expressions outperforming previous approaches. Additionally, the proposed approach provides an interpretable solution for 3D face manipulation, allowing the user to make localized edits.

---

### BioOSS: A Bio-Inspired Oscillatory State System with Spatio-Temporal Dynamics

Authors: Zhongju Yuan, Geraint Wiggins, Dick Botteldooren
Published: 2025-10-12
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.10790v1

Today's deep learning architectures are primarily based on perceptron models, which do not capture the oscillatory dynamics characteristic of biological neurons. Although oscillatory systems have recently gained attention for their closer resemblance to neural behavior, they still fall short of modeling the intricate spatio-temporal interactions observed in natural neural circuits. In this paper, we propose a bio-inspired oscillatory state system (BioOSS) designed to emulate the wave-like propagation dynamics critical to neural processing, particularly in the prefrontal cortex (PFC), where complex activity patterns emerge. BioOSS comprises two interacting populations of neurons: p neurons, which represent simplified membrane-potential-like units inspired by pyramidal cells in cortical columns, and o neurons, which govern propagation velocities and modulate the lateral spread of activity. Through local interactions, these neurons produce wave-like propagation patterns. The model incorporates trainable parameters for damping and propagation speed, enabling flexible adaptation to task-specific spatio-temporal structures. We evaluate BioOSS on both synthetic and real-world tasks, demonstrating superior performance and enhanced interpretability compared to alternative architectures.

---

### Review of Inference-Time Scaling Strategies: Reasoning, Search and RAG

Authors: Zhichao Wang, Cheng Wan, Dong Nie
Published: 2025-10-12
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.10787v1

The performance gains of LLMs have historically been driven by scaling up model size and training data. However, the rapidly diminishing availability of high-quality training data is introducing a fundamental bottleneck, shifting the focus of research toward inference-time scaling. This paradigm uses additional computation at the time of deployment to substantially improve LLM performance on downstream tasks without costly model re-training. This review systematically surveys the diverse techniques contributing to this new era of inference-time scaling, organizing the rapidly evolving field into two comprehensive perspectives: Output-focused and Input-focused methods. Output-focused techniques encompass complex, multi-step generation strategies, including reasoning (e.g., CoT, ToT, ReAct), various search and decoding methods (e.g., MCTS, beam search), training for long CoT (e.g., RLVR, GRPO), and model ensemble methods. Input-focused techniques are primarily categorized by few-shot and RAG, with RAG as the central focus. The RAG section is further detailed through a structured examination of query expansion, data, retrieval and reranker, LLM generation methods, and multi-modal RAG.

---

### DISC-GAN: Disentangling Style and Content for Cluster-Specific Synthetic Underwater Image Generation

Authors: Sneha Varur, Anirudh R Hanchinamani, Tarun S Bagewadi, Uma Mudenagudi, Chaitra D Desai, Sujata C, Padmashree Desai, Sumit Meharwade
Published: 2025-10-12
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.10782v1

In this paper, we propose a novel framework, Disentangled Style-Content GAN (DISC-GAN), which integrates style-content disentanglement with a cluster-specific training strategy towards photorealistic underwater image synthesis. The quality of synthetic underwater images is challenged by optical due to phenomena such as color attenuation and turbidity. These phenomena are represented by distinct stylistic variations across different waterbodies, such as changes in tint and haze. While generative models are well-suited to capture complex patterns, they often lack the ability to model the non-uniform conditions of diverse underwater environments. To address these challenges, we employ K-means clustering to partition a dataset into style-specific domains. We use separate encoders to get latent spaces for style and content; we further integrate these latent representations via Adaptive Instance Normalization (AdaIN) and decode the result to produce the final synthetic image. The model is trained independently on each style cluster to preserve domain-specific characteristics. Our framework demonstrates state-of-the-art performance, obtaining a Structural Similarity Index (SSIM) of 0.9012, an average Peak Signal-to-Noise Ratio (PSNR) of 32.5118 dB, and a Frechet Inception Distance (FID) of 13.3728.

---

### Structured Spectral Graph Representation Learning for Multi-label Abnormality Analysis from 3D CT Scans

Authors: Theo Di Piazza, Carole Lazarus, Olivier Nempont, Loic Boussel
Published: 2025-10-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.10779v5

With the growing volume of CT examinations, there is an increasing demand for automated tools such as organ segmentation, abnormality detection, and report generation to support radiologists in managing their clinical workload. Multi-label classification of 3D Chest CT scans remains a critical yet challenging problem due to the complex spatial relationships inherent in volumetric data and the wide variability of abnormalities. Existing methods based on 3D convolutional neural networks struggle to capture long-range dependencies, while Vision Transformers often require extensive pre-training on large-scale, domain-specific datasets to perform competitively. In this work, we propose a 2.5D alternative by introducing a new graph-based framework that represents 3D CT volumes as structured graphs, where axial slice triplets serve as nodes processed through spectral graph convolution, enabling the model to reason over inter-slice dependencies while maintaining complexity compatible with clinical deployment. Our method, trained and evaluated on 3 datasets from independent institutions, achieves strong cross-dataset generalization, and shows competitive performance compared to state-of-the-art visual encoders. We further conduct comprehensive ablation studies to evaluate the impact of various aggregation strategies, edge-weighting schemes, and graph connectivity patterns. Additionally, we demonstrate the broader applicability of our approach through transfer experiments on automated radiology report generation and abdominal CT data.

---

### Preconditioned Norms: A Unified Framework for Steepest Descent, Quasi-Newton and Adaptive Methods

Authors: Andrey Veprikov, Arman Bolatov, Aleksandr Bogdanov, Samuel Horváth, Aleksandr Beznosikov, Martin Takáč, Slavomir Hanzely
Published: 2025-10-12
Categories: cs.LG, math.OC
arXiv: https://arxiv.org/abs/2510.10777v3

Optimization lies at the core of modern deep learning, yet existing methods often face a fundamental trade-off between adapting to problem geometry and leveraging curvature utilization. Steepest descent algorithms adapt to different geometries through norm choices but remain strictly first-order, whereas quasi-Newton and adaptive optimizers incorporate curvature information but are restricted to Frobenius geometry, limiting their applicability across diverse architectures. In this work, we propose a unified framework generalizing steepest descent, quasi-Newton methods, and adaptive methods through the novel notion of preconditioned matrix norms. This abstraction reveals that widely used optimizers such as SGD and Adam, as well as more advanced approaches like Muon and KL-Shampoo, and recent hybrids including SOAP and SPlus, all emerge as special cases of the same principle. Within this framework, we provide the first systematic treatment of affine and scale invariance in the matrix-parameterized setting, establishing necessary and sufficient conditions under generalized norms. Building on this foundation, we introduce two new methods, $\texttt{MuAdam}$ and $\texttt{MuAdam-SANIA}$, which combine the spectral geometry of Muon with Adam-style preconditioning. Our experiments demonstrate that these optimizers are competitive with, and in some cases outperform, existing state-of-the-art methods. Our code is available at https://github.com/brain-lab-research/LIB/tree/quasi_descent

---

### HiligayNER: A Baseline Named Entity Recognition Model for Hiligaynon

Authors: James Ald Teves, Ray Daniel Cal, Josh Magdiel Villaluz, Jean Malolos, Mico Magtira, Ramon Rodriguez, Mideth Abisado, Joseph Marvin Imperial
Published: 2025-10-12
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.10776v1

The language of Hiligaynon, spoken predominantly by the people of Panay Island, Negros Occidental, and Soccsksargen in the Philippines, remains underrepresented in language processing research due to the absence of annotated corpora and baseline models. This study introduces HiligayNER, the first publicly available baseline model for the task of Named Entity Recognition (NER) in Hiligaynon. The dataset used to build HiligayNER contains over 8,000 annotated sentences collected from publicly available news articles, social media posts, and literary texts. Two Transformer-based models, mBERT and XLM-RoBERTa, were fine-tuned on this collected corpus to build versions of HiligayNER. Evaluation results show strong performance, with both models achieving over 80% in precision, recall, and F1-score across entity types. Furthermore, cross-lingual evaluation with Cebuano and Tagalog demonstrates promising transferability, suggesting the broader applicability of HiligayNER for multilingual NLP in low-resource settings. This work aims to contribute to language technology development for underrepresented Philippine languages, specifically for Hiligaynon, and support future research in regional language processing.

---