# Research Papers — 2025-10 · bundle page 160 of 217

> Full-text markdown of papers #7951–8000 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/160
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/159.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/161.md)

### Role-Conditioned Refusals: Evaluating Access Control Reasoning in Large Language Models

Authors: Đorđe Klisura, Joseph Khoury, Ashish Kundu, Ram Krishnan, Anthony Rios
Published: 2025-10-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.07642v1

Access control is a cornerstone of secure computing, yet large language models often blur role boundaries by producing unrestricted responses. We study role-conditioned refusals, focusing on the LLM's ability to adhere to access control policies by answering when authorized and refusing when not. To evaluate this behavior, we created a novel dataset that extends the Spider and BIRD text-to-SQL datasets, both of which have been modified with realistic PostgreSQL role-based policies at the table and column levels. We compare three designs: (i) zero or few-shot prompting, (ii) a two-step generator-verifier pipeline that checks SQL against policy, and (iii) LoRA fine-tuned models that learn permission awareness directly. Across multiple model families, explicit verification (the two-step framework) improves refusal precision and lowers false permits. At the same time, fine-tuning achieves a stronger balance between safety and utility (i.e., when considering execution accuracy). Longer and more complex policies consistently reduce the reliability of all systems. We release RBAC-augmented datasets and code.

---

### Property Classification of Vacation Rental Properties during Covid-19

Authors: Favour Yahdii Aghaebe, Dustin Foley, Eric Atwell, Stephen Clark
Published: 2025-10-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.07639v1

This study advocates for employing clustering techniques to classify vacation rental properties active during the Covid pandemic to identify inherent patterns and behaviours. The dataset, a collaboration between the ESRC funded Consumer Data Research Centre (CDRC) and AirDNA, encompasses data for over a million properties and hosts. Utilising K-means and K-medoids clustering techniques, we identify homogenous groups and their common characteristics. Our findings enhance comprehension of the intricacies of vacation rental evaluations and could potentially be utilised in the creation of targeted, cluster-specific policies.

---

### PIT-QMM: A Large Multimodal Model For No-Reference Point Cloud Quality Assessment

Authors: Shashank Gupta, Gregoire Phillips, Alan C. Bovik
Published: 2025-10-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.07636v1

Large Multimodal Models (LMMs) have recently enabled considerable advances in the realm of image and video quality assessment, but this progress has yet to be fully explored in the domain of 3D assets. We are interested in using these models to conduct No-Reference Point Cloud Quality Assessment (NR-PCQA), where the aim is to automatically evaluate the perceptual quality of a point cloud in absence of a reference. We begin with the observation that different modalities of data - text descriptions, 2D projections, and 3D point cloud views - provide complementary information about point cloud quality. We then construct PIT-QMM, a novel LMM for NR-PCQA that is capable of consuming text, images and point clouds end-to-end to predict quality scores. Extensive experimentation shows that our proposed method outperforms the state-of-the-art by significant margins on popular benchmarks with fewer training iterations. We also demonstrate that our framework enables distortion localization and identification, which paves a new way forward for model explainability and interactivity. Code and datasets are available at https://www.github.com/shngt/pit-qmm.

---

### Safely Exploring Novel Actions in Recommender Systems via Deployment-Efficient Policy Learning

Authors: Haruka Kiyohara, Yusuke Narita, Yuta Saito, Kei Tateno, Takuma Udagawa
Published: 2025-10-09
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.07635v1

In many real recommender systems, novel items are added frequently over time. The importance of sufficiently presenting novel actions has widely been acknowledged for improving long-term user engagement. A recent work builds on Off-Policy Learning (OPL), which trains a policy from only logged data, however, the existing methods can be unsafe in the presence of novel actions. Our goal is to develop a framework to enforce exploration of novel actions with a guarantee for safety. To this end, we first develop Safe Off-Policy Policy Gradient (Safe OPG), which is a model-free safe OPL method based on a high confidence off-policy evaluation. In our first experiment, we observe that Safe OPG almost always satisfies a safety requirement, even when existing methods violate it greatly. However, the result also reveals that Safe OPG tends to be too conservative, suggesting a difficult tradeoff between guaranteeing safety and exploring novel actions. To overcome this tradeoff, we also propose a novel framework called Deployment-Efficient Policy Learning for Safe User Exploration, which leverages safety margin and gradually relaxes safety regularization during multiple (not many) deployments. Our framework thus enables exploration of novel actions while guaranteeing safe implementation of recommender systems.

---

### Test-Time Matching: Unlocking Compositional Reasoning in Multimodal Models

Authors: Yinglun Zhu, Jiancheng Zhang, Fuzhi Tang
Published: 2025-10-09
Categories: cs.AI, cs.CL, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.07632v2

Frontier AI models have achieved remarkable progress, yet recent studies suggest they struggle with compositional reasoning, often performing at or below random chance on established benchmarks. We revisit this problem and show that widely used evaluation metrics systematically underestimate model capability. To correct this artifact, we introduce a group matching score that more faithfully evaluates model capability. Moreover, correctness under the new metric can be translated into correctness under existing metrics via a simple overfitting step. This adjustment enables SigLIP-B16 to surpass all previous results and GPT-4.1 to yield the first result surpassing estimated human performance on Winoground. Building on this insight, we propose Test-Time Matching (TTM), an iterative, self-improving algorithm that further bootstraps model performance without any external supervision. TTM delivers additional, non-trivial improvements: for example, TTM enables SigLIP-B16 to surpass GPT-4.1 on MMVP-VLM, establishing a new state of the art. TTM also extends beyond contrastive vision-language models, yielding clear gains on a generative multimodal model across benchmarks. Importantly, TTM remains broadly effective even on benchmarks without metric-induced effects or group structures, achieving relative gains up to 85.7% on challenging datasets such as WhatsUp. Across 16 dataset variants spanning diverse setups, our experiments demonstrate that TTM consistently improves model performance and advances the frontier of compositional reasoning.

---

### Rectified-CFG++ for Flow Based Models

Authors: Shreshth Saini, Shashank Gupta, Alan C. Bovik
Published: 2025-10-09
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.07631v1

Classifier-free guidance (CFG) is the workhorse for steering large diffusion models toward text-conditioned targets, yet its native application to rectified flow (RF) based models provokes severe off-manifold drift, yielding visual artifacts, text misalignment, and brittle behaviour. We present Rectified-CFG++, an adaptive predictor-corrector guidance that couples the deterministic efficiency of rectified flows with a geometry-aware conditioning rule. Each inference step first executes a conditional RF update that anchors the sample near the learned transport path, then applies a weighted conditional correction that interpolates between conditional and unconditional velocity fields. We prove that the resulting velocity field is marginally consistent and that its trajectories remain within a bounded tubular neighbourhood of the data manifold, ensuring stability across a wide range of guidance strengths. Extensive experiments on large-scale text-to-image models (Flux, Stable Diffusion 3/3.5, Lumina) show that Rectified-CFG++ consistently outperforms standard CFG on benchmark datasets such as MS-COCO, LAION-Aesthetic, and T2I-CompBench. Project page: https://rectified-cfgpp.github.io/

---

### CodeVaani: A Multilingual, Voice-Based Code Learning Assistant

Authors: Jayant Havare, Srikanth Tamilselvam, Ashish Mittal, Shalaka Thorat, Soham Jadia, Varsha Apte, Ganesh Ramakrishnan
Published: 2025-10-08
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2511.20654v1

Programming education often assumes English proficiency and text-based interaction, creating barriers for students from multilingual regions such as India. We present CodeVaani, a multilingual speech-driven assistant for understanding code, built into Bodhitree (1), a Learning Management System developed at IIT Bombay. It is a voice-enabled assistant that helps learners explore programming concepts in their native languages. The system integrates Indic ASR, a codeaware transcription refinement module, and a code model for generating relevant answers. Responses are provided in both text and audio for natural interaction. In a study with 28 beginner programmers, CodeVaani achieved 75% response accuracy, with over 80% of participants rating the experience positively. Compared to classroom assistance, our framework offers ondemand availability, scalability to support many learners, and multilingual support that lowers the entry barrier for students with limited English proficiency. The demo will illustrate these capabilities and highlight how voice-based AI systems can make programming education more inclusive. Supplementary artifacts and demo video are also made available.

---

### Parallel and Multi-Stage Knowledge Graph Retrieval for Behaviorally Aligned Financial Asset Recommendations

Authors: Fernando Spadea, Oshani Seneviratne
Published: 2025-10-08
Categories: cs.LG, cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2511.11583v1

Large language models (LLMs) show promise for personalized financial recommendations but are hampered by context limits, hallucinations, and a lack of behavioral grounding. Our prior work, FLARKO, embedded structured knowledge graphs (KGs) in LLM prompts to align advice with user behavior and market data. This paper introduces RAG-FLARKO, a retrieval-augmented extension to FLARKO, that overcomes scalability and relevance challenges using multi-stage and parallel KG retrieval processes. Our method first retrieves behaviorally relevant entities from a user's transaction KG and then uses this context to filter temporally consistent signals from a market KG, constructing a compact, grounded subgraph for the LLM. This pipeline reduces context overhead and sharpens the model's focus on relevant information. Empirical evaluation on a real-world financial transaction dataset demonstrates that RAG-FLARKO significantly enhances recommendation quality. Notably, our framework enables smaller, more efficient models to achieve high performance in both profitability and behavioral alignment, presenting a viable path for deploying grounded financial AI in resource-constrained environments.

---

### Beyond Models: A Framework for Contextual and Cultural Intelligence in African AI Deployment

Authors: Qness Ndlovu
Published: 2025-10-08
Categories: cs.HC, cs.AI, cs.CL, cs.CY
arXiv: https://arxiv.org/abs/2510.24729v1

While global AI development prioritizes model performance and computational scale, meaningful deployment in African markets requires fundamentally different architectural decisions. This paper introduces Contextual and Cultural Intelligence (CCI) -- a systematic framework enabling AI systems to process cultural meaning, not just data patterns, through locally relevant, emotionally intelligent, and economically inclusive design. Using design science methodology, we validate CCI through a production AI-native cross-border shopping platform serving diaspora communities. Key empirical findings: 89% of users prefer WhatsApp-based AI interaction over traditional web interfaces (n=602, chi-square=365.8, p<0.001), achieving 536 WhatsApp users and 3,938 total conversations across 602 unique users in just 6 weeks, and culturally informed prompt engineering demonstrates sophisticated understanding of culturally contextualized queries, with 89% family-focused commerce patterns and natural code-switching acceptance. The CCI framework operationalizes three technical pillars: Infrastructure Intelligence (mobile-first, resilient architectures), Cultural Intelligence (multilingual NLP with social context awareness), and Commercial Intelligence (trust-based conversational commerce). This work contributes both theoretical innovation and reproducible implementation patterns, challenging Silicon Valley design orthodoxies while providing actionable frameworks for equitable AI deployment across resource-constrained markets.

---

### Lean Finder: Semantic Search for Mathlib That Understands User Intents

Authors: Jialin Lu, Kye Emond, Kaiyu Yang, Swarat Chaudhuri, Weiran Sun, Wuyang Chen
Published: 2025-10-08
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.15940v2

We present Lean Finder, a semantic search engine for Lean and mathlib that understands and aligns with the intents of mathematicians. Progress in formal theorem proving is often hindered by the difficulty of locating relevant theorems and the steep learning curve of the Lean 4 language, making advancement slow and labor-intensive. Existing Lean search engines, though helpful, rely primarily on informalizations (natural language translation of the formal statements), while largely overlooking the mismatch with real-world user queries. In contrast, we propose a user-centered semantic search tailored to the needs of mathematicians. Our approach begins by analyzing and clustering the semantics of public Lean discussions, then fine-tuning text embeddings on synthesized queries that emulate user intents. We further align Lean Finder with mathematicians' preferences using diverse feedback signals, encoding it with a rich awareness of their goals from multiple perspectives. Evaluations on real-world queries, informalized statements, and proof states demonstrate that our Lean Finder achieves over $30\%$ relative improvement compared to previous search engines and GPT-4o. In addition, Lean Finder is compatible with LLM-based theorem provers, bridging retrieval with formal reasoning. Lean Finder is available at: https://leanfinder.github.io

---

### Dynamic Factor Analysis of Price Movements in the Philippine Stock Exchange

Authors: Brian Godwin Lim, Dominic Dayta, Benedict Ryan Tiu, Renzo Roel Tan, Len Patrick Dominic Garces, Kazushi Ikeda
Published: 2025-10-08
Categories: q-fin.ST, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.15938v1

The intricate dynamics of stock markets have led to extensive research on models that are able to effectively explain their inherent complexities. This study leverages the econometrics literature to explore the dynamic factor model as an interpretable model with sufficient predictive capabilities for capturing essential market phenomena. Although the model has been extensively applied for predictive purposes, this study focuses on analyzing the extracted loadings and common factors as an alternative framework for understanding stock price dynamics. The results reveal novel insights into traditional market theories when applied to the Philippine Stock Exchange using the Kalman method and maximum likelihood estimation, with subsequent validation against the capital asset pricing model. Notably, a one-factor model extracts a common factor representing systematic or market dynamics similar to the composite index, whereas a two-factor model extracts common factors representing market trends and volatility. Furthermore, an application of the model for nowcasting the growth rates of the Philippine gross domestic product highlights the potential of the extracted common factors as viable real-time market indicators, yielding over a 34% decrease in the out-of-sample prediction error. Overall, the results underscore the value of dynamic factor analysis in gaining a deeper understanding of market price movement dynamics.

---

### A2AS: Agentic AI Runtime Security and Self-Defense

Authors: Eugene Neelou, Ivan Novikov, Max Moroz, Om Narayan, Tiffany Saade, Mika Ayenson, Ilya Kabanov, Jen Ozmen, Edward Lee, Vineeth Sai Narajala, Emmanuel Guilherme Junior, Ken Huang et al.
Published: 2025-10-08
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2510.13825v1

The A2AS framework is introduced as a security layer for AI agents and LLM-powered applications, similar to how HTTPS secures HTTP. A2AS enforces certified behavior, activates model self-defense, and ensures context window integrity. It defines security boundaries, authenticates prompts, applies security rules and custom policies, and controls agentic behavior, enabling a defense-in-depth strategy. The A2AS framework avoids latency overhead, external dependencies, architectural changes, model retraining, and operational complexity. The BASIC security model is introduced as the A2AS foundation: (B) Behavior certificates enable behavior enforcement, (A) Authenticated prompts enable context window integrity, (S) Security boundaries enable untrusted input isolation, (I) In-context defenses enable secure model reasoning, (C) Codified policies enable application-specific rules. This first paper in the series introduces the BASIC security model and the A2AS framework, exploring their potential toward establishing the A2AS industry standard.

---

### Cancer Diagnosis Categorization in Electronic Health Records Using Large Language Models and BioBERT: Model Performance Evaluation Study

Authors: Soheil Hashtarkhani, Rezaur Rashid, Christopher L Brett, Lokesh Chinthala, Fekede Asefa Kumsa, Janet A Zink, Robert L Davis, David L Schwartz, Arash Shaban-Nejad
Published: 2025-10-08
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.12813v1

Electronic health records contain inconsistently structured or free-text data, requiring efficient preprocessing to enable predictive health care models. Although artificial intelligence-driven natural language processing tools show promise for automating diagnosis classification, their comparative performance and clinical reliability require systematic evaluation. The aim of this study is to evaluate the performance of 4 large language models (GPT-3.5, GPT-4o, Llama 3.2, and Gemini 1.5) and BioBERT in classifying cancer diagnoses from structured and unstructured electronic health records data. We analyzed 762 unique diagnoses (326 International Classification of Diseases (ICD) code descriptions, 436free-text entries) from 3456 records of patients with cancer. Models were tested on their ability to categorize diagnoses into 14predefined categories. Two oncology experts validated classifications. BioBERT achieved the highest weighted macro F1-score for ICD codes (84.2) and matched GPT-4o in ICD code accuracy (90.8). For free-text diagnoses, GPT-4o outperformed BioBERT in weighted macro F1-score (71.8 vs 61.5) and achieved slightly higher accuracy (81.9 vs 81.6). GPT-3.5, Gemini, and Llama showed lower overall performance on both formats. Common misclassification patterns included confusion between metastasis and central nervous system tumors, as well as errors involving ambiguous or overlapping clinical terminology. Although current performance levels appear sufficient for administrative and research use, reliable clinical applications will require standardized documentation practices alongside robust human oversight for high-stakes decision-making.

---

### Multi-objective Bayesian Optimization with Human-in-the-Loop for Flexible Neuromorphic Electronics Fabrication

Authors: Benius Dunn, Javier Meza-Arroyo, Armi Tiihonen, Mark Lee, Julia W. P. Hsu
Published: 2025-10-08
Categories: cs.ET, cond-mat.mtrl-sci, cs.LG
arXiv: https://arxiv.org/abs/2510.11727v1

Neuromorphic computing hardware enables edge computing and can be implemented in flexible electronics for novel applications. Metal oxide materials are promising candidates for fabricating flexible neuromorphic electronics, but suffer from processing constraints due to the incompatibilities between oxides and polymer substrates. In this work, we use photonic curing to fabricate flexible metal-insulator-metal capacitors with solution-processible aluminum oxide dielectric tailored for neuromorphic applications. Because photonic curing outcomes depend on many input parameters, identifying an optimal processing condition through a traditional grid-search approach is unfeasible. Here, we apply multi-objective Bayesian optimization (MOBO) to determine photonic curing conditions that optimize the trade-off between desired electrical properties of large capacitance-frequency dispersion and low leakage current. Furthermore, we develop a human-in-the-loop (HITL) framework for incorporating failed experiments into the MOBO machine learning workflow, demonstrating that this framework accelerates optimization by reducing the number of experimental rounds required. Once optimization is concluded, we analyze different Pareto-optimal conditions to tune the dielectrics properties and provide insight into the importance of different inputs through Shapley Additive exPlanations analysis. The demonstrated framework of combining MOBO with HITL feedback can be adapted to a wide range of multi-objective experimental problems that have interconnected inputs and high experimental failure rates to generate usable results for machine learning models.

---

### scPPDM: A Diffusion Model for Single-Cell Drug-Response Prediction

Authors: Zhaokang Liang, Shuyang Zhuang, Xiaoran Jiao, Weian Mao, Hao Chen, Chunhua Shen
Published: 2025-10-08
Categories: q-bio.QM, cs.LG
arXiv: https://arxiv.org/abs/2510.11726v1

This paper introduces the Single-Cell Perturbation Prediction Diffusion Model (scPPDM), the first diffusion-based framework for single-cell drug-response prediction from scRNA-seq data. scPPDM couples two condition channels, pre-perturbation state and drug with dose, in a unified latent space via non-concatenative GD-Attn. During inference, factorized classifier-free guidance exposes two interpretable controls for state preservation and drug-response strength and maps dose to guidance magnitude for tunable intensity. Evaluated on the Tahoe-100M benchmark under two stringent regimes, unseen covariate combinations (UC) and unseen drugs (UD), scPPDM sets new state-of-the-art results across log fold-change recovery, delta correlations, explained variance, and DE-overlap. Representative gains include +36.11%/+34.21% on DEG logFC-Spearman/Pearson in UD over the second-best model. This control interface enables transparent what-if analyses and dose tuning, reducing experimental burden while preserving biological specificity.

---

### Fortifying LLM-Based Code Generation with Graph-Based Reasoning on Secure Coding Practices

Authors: Rupam Patir, Keyan Guo, Haipeng Cai, Hongxin Hu
Published: 2025-10-08
Categories: cs.CR, cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2510.09682v1

The code generation capabilities of Large Language Models (LLMs) have transformed the field of software development. However, this advancement also presents significant security challenges, as LLM-generated code often contains vulnerabilities. One direction of research strengthens LLMs by injecting or refining security knowledge through curated datasets, model tuning, or static analyzers. While effective in certain settings, these methods can be resource-intensive, less adaptable to zero-day vulnerabilities, and often inapplicable to proprietary models. To address these challenges, we introduce GRASP, which explores a new direction that focuses on structured reasoning over Secure Coding Practices(SCPs) rather than additional training or external feedback. GRASP comprises two key ideas: (1) an SCP graph that organizes SCPs into a Directed Acyclic Graph (DAG) capturing dependencies and relationships, and (2) a graph-based reasoning process that systematically guides LLMs through relevant SCPs for code generation. This design enables interpretable, model-agnostic, and scalable security improvements, particularly for previously unseen vulnerabilities. Our evaluation shows that GRASP consistently achieves Security Rates (SR) exceeding 80% across multiple LLMs, and delivers up to 88% improvements over baselines on zero-day vulnerabilities.

---

### NNDM: NN_UNet Diffusion Model for Brain Tumor Segmentation

Authors: Sashank Makanaboyina
Published: 2025-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.09681v1

Accurate detection and segmentation of brain tumors in magnetic resonance imaging (MRI) are critical for effective diagnosis and treatment planning. Despite advances in convolutional neural networks (CNNs) such as U-Net, existing models often struggle with generalization, boundary precision, and limited data diversity. To address these challenges, we propose NNDM (NN\_UNet Diffusion Model)a hybrid framework that integrates the robust feature extraction of NN-UNet with the generative capabilities of diffusion probabilistic models. In our approach, the diffusion model progressively refines the segmentation masks generated by NN-UNet by learning the residual error distribution between predicted and ground-truth masks. This iterative denoising process enables the model to correct fine structural inconsistencies and enhance tumor boundary delineation. Experiments conducted on the BraTS 2021 datasets demonstrate that NNDM achieves superior performance compared to conventional U-Net and transformer-based baselines, yielding improvements in Dice coefficient and Hausdorff distance metrics. Moreover, the diffusion-guided refinement enhances robustness across modalities and tumor subregions. The proposed NNDM establishes a new direction for combining deterministic segmentation networks with stochastic diffusion models, advancing the state of the art in automated brain tumor analysis.

---

### Knowledge-Aware Mamba for Joint Change Detection and Classification from MODIS Times Series

Authors: Zhengsen Xu, Yimin Zhu, Zack Dewis, Mabel Heffring, Motasem Alkayid, Saeid Taleghanidoozdoozan, Lincoln Linlin Xu
Published: 2025-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.09679v1

Although change detection using MODIS time series is critical for environmental monitoring, it is a highly challenging task due to key MODIS difficulties, e.g., mixed pixels, spatial-spectral-temporal information coupling effect, and background class heterogeneity. This paper presents a novel knowledge-aware Mamba (KAMamba) for enhanced MODIS change detection, with the following contributions. First, to leverage knowledge regarding class transitions, we design a novel knowledge-driven transition-matrix-guided approach, leading to a knowledge-aware transition loss (KAT-loss) that can enhance detection accuracies. Second, to improve model constraints, a multi-task learning approach is designed, where three losses, i.e., pre-change classification loss (PreC-loss), post-change classification loss (PostC-loss), and change detection loss (Chg-loss) are used for improve model learning. Third, to disentangle information coupling in MODIS time series, novel spatial-spectral-temporal Mamba (SSTMamba) modules are designed. Last, to improve Mamba model efficiency and remove computational cost, a sparse and deformable Mamba (SDMamba) backbone is used in SSTMamba. On the MODIS time-series dataset for Saskatchewan, Canada, we evaluate the method on land-cover change detection and LULC classification; results show about 1.5-6% gains in average F1 for change detection over baselines, and about 2% improvements in OA, AA, and Kappa for LULC classification.

---

### AI in Computational Thinking Education in Higher Education: A Systematic Literature Review

Authors: Ebrahim Rahimi, Clara Maathuis
Published: 2025-10-08
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2510.09677v1

Computational Thinking (CT) is a key skill set for students in higher education to thrive and adapt to an increasingly technology-driven future and workplace. While research on CT education has gained remarkable momentum in K12 over the past decade, it has remained under-explored in higher education, leaving higher education teachers with an insufficient overview, knowledge, and support regarding CT education. The proliferation and adoption of artificial intelligence (AI) by educational institutions have demonstrated promising potential to support instructional activities across many disciplines, including CT education. However, a comprehensive overview outlining the various aspects of integrating AI in CT education in higher education is lacking. To mitigate this gap, we conducted this systematic literature review study. The focus of our study is to identify initiatives applying AI in CT education within higher education and to explore various educational aspects of these initiatives, including the benefits and challenges of AI in CT education, instructional strategies employed, CT components covered, and AI techniques and models utilized. This study provides practical and scientific contributions to the CT education community, including an inventory of AI-based initiatives for CT education useful to educators, an overview of various aspects of integrating AI into CT education such as its benefits and challenges (e.g., AI potential to reshape CT education versus its potential to diminish students creativity) and insights into new and expanded perspectives on CT in light of AI (e.g., the decoding approach alongside the coding approach to CT).

---

### Coupled Data and Measurement Space Dynamics for Enhanced Diffusion Posterior Sampling

Authors: Shayan Mohajer Hamidi, En-Hui Yang, Ben Liang
Published: 2025-10-08
Categories: cs.LG, cs.AI, stat.ML
arXiv: https://arxiv.org/abs/2510.09676v2

Inverse problems, where the goal is to recover an unknown signal from noisy or incomplete measurements, are central to applications in medical imaging, remote sensing, and computational biology. Diffusion models have recently emerged as powerful priors for solving such problems. However, existing methods either rely on projection-based techniques that enforce measurement consistency through heuristic updates, or they approximate the likelihood $p(\boldsymbol{y} \mid \boldsymbol{x})$, often resulting in artifacts and instability under complex or high-noise conditions. To address these limitations, we propose a novel framework called \emph{coupled data and measurement space diffusion posterior sampling} (C-DPS), which eliminates the need for constraint tuning or likelihood approximation. C-DPS introduces a forward stochastic process in the measurement space $\{\boldsymbol{y}_t\}$, evolving in parallel with the data-space diffusion $\{\boldsymbol{x}_t\}$, which enables the derivation of a closed-form posterior $p(\boldsymbol{x}_{t-1} \mid \boldsymbol{x}_t, \boldsymbol{y}_{t-1})$. This coupling allows for accurate and recursive sampling based on a well-defined posterior distribution. Empirical results demonstrate that C-DPS consistently outperforms existing baselines, both qualitatively and quantitatively, across multiple inverse problem benchmarks.

---

### Leveraging LLMs to Streamline the Review of Public Funding Applications

Authors: Joao D. S. Marques, Andre V. Duarte, Andre Carvalho, Gil Rocha, Bruno Martins, Arlindo L. Oliveira
Published: 2025-10-08
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2510.09674v1

Every year, the European Union and its member states allocate millions of euros to fund various development initiatives. However, the increasing number of applications received for these programs often creates significant bottlenecks in evaluation processes, due to limited human capacity. In this work, we detail the real-world deployment of AI-assisted evaluation within the pipeline of two government initiatives: (i) corporate applications aimed at international business expansion, and (ii) citizen reimbursement claims for investments in energy-efficient home improvements. While these two cases involve distinct evaluation procedures, our findings confirm that AI effectively enhanced processing efficiency and reduced workload across both types of applications. Specifically, in the citizen reimbursement claims initiative, our solution increased reviewer productivity by 20.1%, while keeping a negligible false-positive rate based on our test set observations. These improvements resulted in an overall reduction of more than 2 months in the total evaluation time, illustrating the impact of AI-driven automation in large-scale evaluation workflows.

---

### Table Question Answering in the Era of Large Language Models: A Comprehensive Survey of Tasks, Methods, and Evaluation

Authors: Wei Zhou, Bolei Ma, Annemarie Friedrich, Mohsen Mesgar
Published: 2025-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.09671v2

Table Question Answering (TQA) aims to answer natural language questions about tabular data, often accompanied by additional contexts such as text passages. The task spans diverse settings, varying in table representation, question/answer complexity, modality involved, and domain. While recent advances in large language models (LLMs) have led to substantial progress in TQA, the field still lacks a systematic organization and understanding of task formulations, core challenges, and methodological trends, particularly in light of emerging research directions such as reinforcement learning. This survey addresses this gap by providing a comprehensive and structured overview of TQA research with a focus on LLM-based methods. We provide a comprehensive categorization of existing benchmarks and task setups. We group current modeling strategies according to the challenges they target, and analyze their strengths and limitations. Furthermore, we highlight underexplored but timely topics that have not been systematically covered in prior research. By unifying disparate research threads and identifying open problems, our survey offers a consolidated foundation for the TQA community, enabling a deeper understanding of the state of the art and guiding future developments in this rapidly evolving area.

---

### A physics-aware deep learning model for shear band formation around collapsing pores in shocked reactive materials

Authors: Xinlun Cheng, Bingzhe Chen, Joseph Choi, Yen T. Nguyen, Pradeep Seshadri, Mayank Verma, H. S. Udaykumar, Stephen Baek
Published: 2025-10-08
Categories: cs.LG, cond-mat.mtrl-sci, physics.comp-ph
arXiv: https://arxiv.org/abs/2510.09670v1

Modeling shock-to-detonation phenomena in energetic materials (EMs) requires capturing complex physical processes such as strong shocks, rapid changes in microstructural morphology, and nonlinear dynamics of chemical reaction fronts. These processes participate in energy localization at hotspots, which initiate chemical energy release leading to detonation. This study addresses the formation of hotspots in crystalline EMs subjected to weak-to-moderate shock loading, which, despite its critical relevance to the safe storage and handling of EMs, remains underexplored compared to the well-studied strong shock conditions. To overcome the computational challenges associated with direct numerical simulations, we advance the Physics-Aware Recurrent Convolutional Neural Network (PARCv2), which has been shown to be capable of predicting strong shock responses in EMs. We improved the architecture of PARCv2 to rapidly predict shear localizations and plastic heating, which play important roles in the weak-to-moderate shock regime. PARCv2 is benchmarked against two widely used physics-informed models, namely, Fourier neural operator and neural ordinary differential equation; we demonstrate its superior performance in capturing the spatiotemporal dynamics of shear band formation. While all models exhibit certain failure modes, our findings underscore the importance of domain-specific considerations in developing robust AI-accelerated simulation tools for reactive materials.

---

### Population synthesis with geographic coordinates

Authors: Jacopo Lenti, Lorenzo Costantini, Ariadna Fosch, Anna Monticelli, David Scala, Marco Pangallo
Published: 2025-10-08
Categories: cs.LG, cs.CY, cs.SI, physics.soc-ph, stat.ML
arXiv: https://arxiv.org/abs/2510.09669v1

It is increasingly important to generate synthetic populations with explicit coordinates rather than coarse geographic areas, yet no established methods exist to achieve this. One reason is that latitude and longitude differ from other continuous variables, exhibiting large empty spaces and highly uneven densities. To address this, we propose a population synthesis algorithm that first maps spatial coordinates into a more regular latent space using Normalizing Flows (NF), and then combines them with other features in a Variational Autoencoder (VAE) to generate synthetic populations. This approach also learns the joint distribution between spatial and non-spatial features, exploiting spatial autocorrelations. We demonstrate the method by generating synthetic homes with the same statistical properties of real homes in 121 datasets, corresponding to diverse geographies. We further propose an evaluation framework that measures both spatial accuracy and practical utility, while ensuring privacy preservation. Our results show that the NF+VAE architecture outperforms popular benchmarks, including copula-based methods and uniform allocation within geographic areas. The ability to generate geolocated synthetic populations at fine spatial resolution opens the door to applications requiring detailed geography, from household responses to floods, to epidemic spread, evacuation planning, and transport modeling.

---

### A Hybrid Computational Intelligence Framework with Metaheuristic Optimization for Drug-Drug Interaction Prediction

Authors: Maryam Abdollahi Shamami, Babak Teimourpour, Farshad Sharifi
Published: 2025-10-08
Categories: cs.LG, cs.AI, q-bio.BM
arXiv: https://arxiv.org/abs/2510.09668v2

Drug-drug interactions (DDIs) are a leading cause of preventable adverse events, often complicating treatment and increasing healthcare costs. At the same time, knowing which drugs do not interact is equally important, as such knowledge supports safer prescriptions and better patient outcomes. In this study, we propose an interpretable and efficient framework that blends modern machine learning with domain knowledge to improve DDI prediction. Our approach combines two complementary molecular embeddings - Mol2Vec, which captures fragment-level structural patterns, and SMILES-BERT, which learns contextual chemical features - together with a leakage-free, rule-based clinical score (RBScore) that injects pharmacological knowledge without relying on interaction labels. A lightweight neural classifier is then optimized using a novel three-stage metaheuristic strategy (RSmpl-ACO-PSO), which balances global exploration and local refinement for stable performance. Experiments on real-world datasets demonstrate that the model achieves high predictive accuracy (ROC-AUC 0.911, PR-AUC 0.867 on DrugBank) and generalizes well to a clinically relevant Type 2 Diabetes Mellitus cohort. Beyond raw performance, studies show how embedding fusion, RBScore, and the optimizer each contribute to precision and robustness. Together, these results highlight a practical pathway for building reliable, interpretable, and computationally efficient models that can support safer drug therapies and clinical decision-making.

---

### OmniSAT: Compact Action Token, Faster Auto Regression

Authors: Huaihai Lyu, Chaofan Chen, Senwei Xie, Pengwei Wang, Xiansheng Chen, Shanghang Zhang, Changsheng Xu
Published: 2025-10-08
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2510.09667v1

Existing Vision-Language-Action (VLA) models can be broadly categorized into diffusion-based and auto-regressive (AR) approaches: diffusion models capture continuous action distributions but rely on computationally heavy iterative denoising. In contrast, AR models enable efficient optimization and flexible sequence construction, making them better suited for large-scale pretraining. To further improve AR efficiency, particularly when action chunks induce extended and high-dimensional sequences, prior work applies entropy-guided and token-frequency techniques to shorten the sequence length. However, such compression struggled with \textit{poor reconstruction or inefficient compression}. Motivated by this, we introduce an Omni Swift Action Tokenizer, which learns a compact, transferable action representation. Specifically, we first normalize value ranges and temporal horizons to obtain a consistent representation with B-Spline encoding. Then, we apply multi-stage residual quantization to the position, rotation, and gripper subspaces, producing compressed discrete tokens with coarse-to-fine granularity for each part. After pre-training on the large-scale dataset Droid, the resulting discrete tokenization shortens the training sequence by 6.8$\times$, and lowers the target entropy. To further explore the potential of OmniSAT, we develop a cross-embodiment learning strategy that builds on the unified action-pattern space and jointly leverages robot and human demonstrations. It enables scalable auxiliary supervision from heterogeneous egocentric videos. Across diverse real-robot and simulation experiments, OmniSAT encompasses higher compression while preserving reconstruction quality, enabling faster AR training convergence and model performance.

---

### Spatial Uncertainty Quantification in Wildfire Forecasting for Climate-Resilient Emergency Planning

Authors: Aditya Chakravarty
Published: 2025-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.09666v1

Climate change is intensifying wildfire risks globally, making reliable forecasting critical for adaptation strategies. While machine learning shows promise for wildfire prediction from Earth observation data, current approaches lack uncertainty quantification essential for risk-aware decision making. We present the first systematic analysis of spatial uncertainty in wildfire spread forecasting using multimodal Earth observation inputs. We demonstrate that predictive uncertainty exhibits coherent spatial structure concentrated near fire perimeters. Our novel distance metric reveals high-uncertainty regions form consistent 20-60 meter buffer zones around predicted firelines - directly applicable for emergency planning. Feature attribution identifies vegetation health and fire activity as primary uncertainty drivers. This work enables more robust wildfire management systems supporting communities adapting to increasing fire risk under climate change.

---

### LMCache: An Efficient KV Cache Layer for Enterprise-Scale LLM Inference

Authors: Yuhan Liu, Yihua Cheng, Jiayi Yao, Yuwei An, Xiaokun Chen, Shaoting Feng, Yuyang Huang, Samuel Shen, Rui Zhang, Kuntai Du, Junchen Jiang
Published: 2025-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.09665v2

KV cache has traditionally been stored in GPU memory to accelerate the decoding phase of large language model (LLM) inference. However, it is increasingly necessary to move KV caches outside GPU devices, to enable cache reuse across different queries and inference engines. Our real-world usage statistics confirm this trend: over time, the total KV cache stored by users has grown rapidly, far exceeding the capacity of GPU memory. Despite this need, there lacks an efficient solution for offloading and transferring KV caches. We present LMCACHE, the first and so far the most efficient open-source KV caching solution, which extracts and stores KV caches generated by modern LLM engines (vLLM and SGLang) out of the GPU memory and shares them across engines and queries. LMCACHE supports both cache offloading (prefix reuse across queries) and prefill-decode (PD) disaggregation (cross-engine/GPU cache transfer). LMCACHE's high performance and wide adoption stem from the following contributions: (1) highly optimized KV cache data movement powered by batched data movement operations, compute and I/O pipelining; (2) a modular KV cache connector component, decoupling LMCACHE from the rapid evolution of inference engines; (3) a first-class control API for flexible cache orchestration across GPU, CPU, storage, and network layers. Our evaluation shows that combining LMCACHE with vLLM achieves up to 15x improvement in throughput across workloads such as multi-round question answering and document analysis. Large-scale adoption of LMCACHE in enterprise settings provides us valuable insights, for example, fetching KV cache from remote storage has unsurprisingly benefits to prefill delay, and that context truncation, which is a widely applied technique in industry, can greatly reduce prefix cache hit ratio by half. The source code of LMCACHE is at: https://github.com/LMCache/LMCache.

---

### Into the Rabbit Hull: From Task-Relevant Concepts in DINO to Minkowski Geometry

Authors: Thomas Fel, Binxu Wang, Michael A. Lepori, Matthew Kowal, Andrew Lee, Randall Balestriero, Sonia Joseph, Ekdeep S. Lubana, Talia Konkle, Demba Ba, Martin Wattenberg
Published: 2025-10-08
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.08638v3

DINOv2 is routinely deployed to recognize objects, scenes, and actions; yet the nature of what it perceives remains unknown. As a working baseline, we adopt the Linear Representation Hypothesis (LRH) and operationalize it using SAEs, producing a 32,000-unit dictionary that serves as the interpretability backbone of our study, which unfolds in three parts. In the first part, we analyze how different downstream tasks recruit concepts from our learned dictionary, revealing functional specialization: classification exploits "Elsewhere" concepts that fire everywhere except on target objects, implementing learned negations; segmentation relies on boundary detectors forming coherent subspaces; depth estimation draws on three distinct monocular depth cues matching visual neuroscience principles. Following these functional results, we analyze the geometry and statistics of the concepts learned by the SAE. We found that representations are partly dense rather than strictly sparse. The dictionary evolves toward greater coherence and departs from maximally orthogonal ideals (Grassmannian frames). Within an image, tokens occupy a low dimensional, locally connected set persisting after removing position. These signs suggest representations are organized beyond linear sparsity alone. Synthesizing these observations, we propose a refined view: tokens are formed by combining convex mixtures of archetypes (e.g., a rabbit among animals, brown among colors, fluffy among textures). This structure is grounded in Gardenfors' conceptual spaces and in the model's mechanism as multi-head attention produces sums of convex mixtures, defining regions bounded by archetypes. We introduce the Minkowski Representation Hypothesis (MRH) and examine its empirical signatures and implications for interpreting vision-transformer representations.

---

### Detection of high-frequency oscillations using time-frequency analysis

Authors: Mostafa Mohammadpour, Mehdi Zekriyapanah Gashti, Yusif S. Gasimov
Published: 2025-10-08
Categories: cs.CV, physics.med-ph
arXiv: https://arxiv.org/abs/2510.08637v1

High-frequency oscillations (HFOs) are a new biomarker for identifying the epileptogenic zone. Mapping HFO-generating regions can improve the precision of resection sites in patients with refractory epilepsy. However, detecting HFOs remains challenging, and their clinical features are not yet fully defined. Visual identification of HFOs is time-consuming, labor-intensive, and subjective. As a result, developing automated methods to detect HFOs is critical for research and clinical use. In this study, we developed a novel method for detecting HFOs in the ripple and fast ripple frequency bands (80-500 Hz). We validated it using both controlled datasets and data from epilepsy patients. Our method employs an unsupervised clustering technique to categorize events extracted from the time-frequency domain using the S-transform. The proposed detector differentiates HFOs events from spikes, background activity, and artifacts. Compared to existing detectors, our method achieved a sensitivity of 97.67%, a precision of 98.57%, and an F-score of 97.78% on the controlled dataset. In epilepsy patients, our results showed a stronger correlation with surgical outcomes, with a ratio of 0.73 between HFOs rates in resected versus non-resected contacts. The study confirmed previous findings that HFOs are promising biomarkers of epileptogenicity in epileptic patients. Removing HFOs, especially fast ripple, leads to seizure freedom, while remaining HFOs lead to seizure recurrence.

---

### Hi-OSCAR: Hierarchical Open-set Classifier for Human Activity Recognition

Authors: Conor McCarthy, Loes Quirijnen, Jan Peter van Zandwijk, Zeno Geradts, Marcel Worring
Published: 2025-10-08
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.08635v1

Within Human Activity Recognition (HAR), there is an insurmountable gap between the range of activities performed in life and those that can be captured in an annotated sensor dataset used in training. Failure to properly handle unseen activities seriously undermines any HAR classifier's reliability. Additionally within HAR, not all classes are equally dissimilar, some significantly overlap or encompass other sub-activities. Based on these observations, we arrange activity classes into a structured hierarchy. From there, we propose Hi-OSCAR: a Hierarchical Open-set Classifier for Activity Recognition, that can identify known activities at state-of-the-art accuracy while simultaneously rejecting unknown activities. This not only enables open-set classification, but also allows for unknown classes to be localized to the nearest internal node, providing insight beyond a binary "known/unknown" classification. To facilitate this and future open-set HAR research, we collected a new dataset: NFI_FARED. NFI_FARED contains data from multiple subjects performing nineteen activities from a range of contexts, including daily living, commuting, and rapid movements, which is fully public and available for download.

---

### Next Semantic Scale Prediction via Hierarchical Diffusion Language Models

Authors: Cai Zhou, Chenyu Wang, Dinghuai Zhang, Shangyuan Tong, Yifei Wang, Stephen Bates, Tommi Jaakkola
Published: 2025-10-08
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.08632v1

In this paper we introduce Hierarchical Diffusion Language Models (HDLM) -- a novel family of discrete diffusion models for language modeling. HDLM builds on a hierarchical vocabulary where low-level tokens with detailed semantics are surjectively mapped to high-level tokens with coarse-grained meanings. In the forward process, each token is independently perturbed to its higher-level ancestor with more abstract semantics according to the scheduler, while in the reverse process the model progressively predicts the next, more detailed semantics. Taken together, HDLM provides a general time-varying next semantic scale prediction process for language modeling. We derive closed-form expressions for the diffusion Evidence Lower Bound (ELBO), and show that HDLM can be implemented in a flexible manner while including the existing MDLM as a special case. We also propose practical training techniques based on the insights. Extensive text generation experiments validate the effectiveness of HDLM, which demonstrates consistently lower validation and generative perplexity than baselines.

---

### Out-of-Distribution Detection in LiDAR Semantic Segmentation Using Epistemic Uncertainty from Hierarchical GMMs

Authors: Hanieh Shojaei Miandashti, Claus Brenner
Published: 2025-10-08
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.08631v1

In addition to accurate scene understanding through precise semantic segmentation of LiDAR point clouds, detecting out-of-distribution (OOD) objects, instances not encountered during training, is essential to prevent the incorrect assignment of unknown objects to known classes. While supervised OOD detection methods depend on auxiliary OOD datasets, unsupervised methods avoid this requirement but typically rely on predictive entropy, the entropy of the predictive distribution obtained by averaging over an ensemble or multiple posterior weight samples. However, these methods often conflate epistemic (model) and aleatoric (data) uncertainties, misclassifying ambiguous in distribution regions as OOD. To address this issue, we present an unsupervised OOD detection approach that employs epistemic uncertainty derived from hierarchical Bayesian modeling of Gaussian Mixture Model (GMM) parameters in the feature space of a deep neural network. Without requiring auxiliary data or additional training stages, our approach outperforms existing uncertainty-based methods on the SemanticKITTI dataset, achieving an 18\% improvement in AUROC, 22\% increase in AUPRC, and 36\% reduction in FPR95 (from 76\% to 40\%), compared to the predictive entropy approach used in prior works.

---

### ExPO-HM: Learning to Explain-then-Detect for Hateful Meme Detection

Authors: Jingbiao Mei, Mingsheng Sun, Jinghong Chen, Pengda Qin, Yuhong Li, Da Chen, Bill Byrne
Published: 2025-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.08630v3

Hateful memes have emerged as a particularly challenging form of online abuse, motivating the development of automated detection systems. Most prior approaches rely on direct detection, producing only binary predictions. Such models fail to provide the context and explanations that real-world moderation requires. Recent Explain-then-Detect approaches, using Chain-of-Thought prompting or LMM agents, perform worse than simple SFT baselines, and even advanced post-training methods such as GRPO fail to close the gap. Our analysis identifies two key issues of such systems: important policy-relevant cues such as targets and attack types are not hypothesized by the model as a likely explanation; and the binary reward signal is insufficient to guide reasoning. To address these challenges, we propose ExPO-HM (Explain-then-Detect Policy Optimization for Hateful Memes), inspired by the training and evaluation process of human annotators. ExPO-HM combines SFT warmup, GRPO with curriculum learning, and Conditional Decision Entropy (CDE) as both metric and reward for reasoning quality. Across three hateful meme benchmarks, ExPO-HM achieves state-of-the-art performance on binary detection, fine-grained classification, and reasoning quality, with up to 15\% and 17\% F1 improvement over the GRPO and DPO baselines, respectively. By moving hateful meme detection from simple binary alarms to explanation-driven detection, ExPO-HM provides accurate, interpretable, and actionable moderation support. Code available at https://github.com/JingbiaoMei/ExPO-HM

---

### Dynamic Mixture-of-Experts for Visual Autoregressive Model

Authors: Jort Vincenti, Metod Jazbec, Guoxuan Xia
Published: 2025-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.08629v2

Visual Autoregressive Models (VAR) offer efficient and high-quality image generation but suffer from computational redundancy due to repeated Transformer calls at increasing resolutions. We introduce a dynamic Mixture-of-Experts router integrated into VAR. The new architecture allows to trade compute for quality through scale-aware thresholding. This thresholding strategy balances expert selection based on token complexity and resolution, without requiring additional training. As a result, we achieve 20% fewer FLOPs, 11% faster inference and match the image quality achieved by the dense baseline.

---

### The Digital Mirror: Gender Bias and Occupational Stereotypes in AI-Generated Images

Authors: Siiri Leppälampi, Sonja M. Hyrynsalmi, Erno Vanhala
Published: 2025-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.08628v1

Generative AI offers vast opportunities for creating visualisations, such as graphics, videos, and images. However, recent studies around AI-generated visualisations have primarily focused on the creation process and image quality, overlooking representational biases. This study addresses this gap by testing representation biases in AI-generated pictures in an occupational setting and evaluating how two AI image generator tools, DALL-E 3 and Ideogram, compare. Additionally, the study discusses topics such as ageing and emotions in AI-generated images. As AI image tools are becoming more widely used, addressing and mitigating harmful gender biases becomes essential to ensure diverse representation in media and professional settings. In this study, over 750 AI-generated images of occupations were prompted. The thematic analysis results revealed that both DALL-E 3 and Ideogram reinforce traditional gender stereotypes in AI-generated images, although to varying degrees. These findings emphasise that AI visualisation tools risk reinforcing narrow representations. In our discussion section, we propose suggestions for practitioners, individuals and researchers to increase representation when generating images with visible genders.

---

### A Denoising Diffusion-Based Evolutionary Algorithm Framework: Application to the Maximum Independent Set Problem

Authors: Joan Salvà Soler, Günther R. Raidl
Published: 2025-10-08
Categories: cs.NE, cs.DM
arXiv: https://arxiv.org/abs/2510.08627v1

Denoising diffusion models (DDMs) offer a promising generative approach for combinatorial optimization, yet they often lack the robust exploration capabilities of traditional metaheuristics like evolutionary algorithms (EAs). We propose a Denoising Diffusion-based Evolutionary Algorithm (DDEA) framework that synergistically integrates these paradigms. It utilizes pre-trained DDMs for both high-quality and diverse population initialization and a novel diffusion-based recombination operator, trained via imitation learning against an optimal demonstrator. Evaluating DDEA on the Maximum Independent Set problem on Erdős-Rényi graphs, we demonstrate notable improvements over DIFUSCO, a leading DDM solver. DDEA consistently outperforms it given the same time budget, and surpasses Gurobi on larger graphs under the same time limit, with DDEA's solution sizes being 3.9% and 7.5% larger on the ER-300-400 and ER-700-800 datasets, respectively. In out-of-distribution experiments, DDEA provides solutions of 11.6% higher quality than DIFUSCO under the same time limit. Ablation studies confirm that both diffusion initialization and recombination are crucial. Our work highlights the potential of hybridizing DDMs and EAs, offering a promising direction for the development of powerful machine learning solvers for complex combinatorial optimization problems.

---

### From What to Why: Thought-Space Recommendation with Small Language Models

Authors: Prosenjit Biswas, Pervez Shaik, Abhinav Thorat, Ravi Kolla, Niranjan Pedanekar
Published: 2025-10-08
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.08626v1

Large Language Models (LLMs) have advanced recommendation capabilities through enhanced reasoning, but pose significant challenges for real-world deployment due to high inference costs. Conversely, while Small Language Models (SLMs) offer an efficient alternative, their reasoning capabilities for recommendation remain underexplored. Existing systems often use natural language rationales merely as unsupervised descriptive text, failing to harness their full potential as learning signals. In this work our main idea is to create a common understanding of user and items across multiple domains called Thought Space with SLMs instead of using LLMs' distilled knowledge. To that end we propose PULSE (Preference Understanding by Latent Semantic Embeddings), a framework that treats SLM-generated rationales as director learning signals, supervising them with interaction histories to jointly model user actions (what) and their semantic drivers (why). Existing methods consider only interactions such as sequences and embeddings, whereas PULSE treats rationales as first-class signals, this novel design yields embeddings that are more robust and generalizable. Extensive experiments demonstrate that PULSE outperforms leading ID, Collaborative Filtering (CF), and LLM-based sequential recommendation models across multiple benchmark datasets. Furthermore, PULSE exhibits superior transferability in cross-domain recommendation and demonstrates strong performance on downstream tasks such as reasoning-oriented question answering. Our code is available \href{https://anonymous.4open.science/r/Thinking_PULSE-0FC5/README.md}{here}.

---

### Adjusting Initial Noise to Mitigate Memorization in Text-to-Image Diffusion Models

Authors: Hyeonggeun Han, Sehwan Kim, Hyungjun Joo, Sangwoo Hong, Jungwoo Lee
Published: 2025-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.08625v1

Despite their impressive generative capabilities, text-to-image diffusion models often memorize and replicate training data, prompting serious concerns over privacy and copyright. Recent work has attributed this memorization to an attraction basin-a region where applying classifier-free guidance (CFG) steers the denoising trajectory toward memorized outputs-and has proposed deferring CFG application until the denoising trajectory escapes this basin. However, such delays often result in non-memorized images that are poorly aligned with the input prompts, highlighting the need to promote earlier escape so that CFG can be applied sooner in the denoising process. In this work, we show that the initial noise sample plays a crucial role in determining when this escape occurs. We empirically observe that different initial samples lead to varying escape times. Building on this insight, we propose two mitigation strategies that adjust the initial noise-either collectively or individually-to find and utilize initial samples that encourage earlier basin escape. These approaches significantly reduce memorization while preserving image-text alignment.

---

### Do LLMs Know They Are Being Tested? Evaluation Awareness and Incentive-Sensitive Failures in GPT-OSS-20B

Authors: Nisar Ahmed, Muhammad Imran Zaman, Gulshan Saleem, Ali Hassan
Published: 2025-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.08624v1

Benchmarks for large language models (LLMs) often rely on rubric-scented prompts that request visible reasoning and strict formatting, whereas real deployments demand terse, contract-bound answers. We investigate whether such "evaluation scent" inflates measured performance without commensurate capability gains. Using a single open-weights model (GPT-OSS-20B), we run six paired A/B scenarios that hold task content and decoding fixed while varying framing (evaluation-oriented vs. real-world) and reasoning depth (Medium/High): deterministic math, strict code-fix, citation generation, incentive flips (caution vs. competence), CoT visibility, and multilingual (Urdu) headers. Deterministic validators compute accuracy, answer-only compliance, hedging/refusals, chain-of-thought (CoT) length, and schema compliance, with pre-registered deltas and composite indices. Across scenarios, evaluation framing reliably inflates CoT (hundreds to >1000 characters) and reduces answer-only compliance, with limited or inconsistent accuracy gains. In structured outputs, it improves wrappers (e.g., fenced blocks, enumerated lists) but not regex-validated substance. Incentive wording reweights error composition: praising caution modestly improves accuracy at high reasoning and reduces wrong-but-confident errors, whereas praising competence yields terser but riskier outputs. Urdu rubric headers reproduce these signatures and can decrease accuracy at higher reasoning depth, indicating multilingual parity risks. We provide a reproducible A/B framework (prompt banks, validators, per-run scores, scripts; versioned DOI) and practical guidance: neutral phrasing or dual-framing checks, contract-aware grading, style-delta reporting, confidence governance, and multilingual dashboards to ensure that benchmark gains reflect deployable capability.

---

### PARSE: LLM Driven Schema Optimization for Reliable Entity Extraction

Authors: Anubhav Shrimal, Aryan Jain, Soumyajit Chowdhury, Promod Yenigalla
Published: 2025-10-08
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.08623v1

Structured information extraction from unstructured text is critical for emerging Software 3.0 systems where LLM agents autonomously interact with APIs and tools. Recent approaches apply large language models directly to extraction tasks using existing JSON schemas, often with constraint decoding or reinforcement learning approaches to ensure syntactic validity, but treat JSON schemas as static contracts designed for human developers, leading to suboptimal extraction performance, frequent hallucinations, and unreliable agent behavior when schemas contain ambiguous or incomplete specifications. We recognize that JSON schemas themselves are a form of natural language understanding contract that encodes rules, relationships, and expectations about data structure contracts that LLMs should be able to both interpret and systematically improve. Consequently, we develop PARSE (Parameter Automated Refinement and Schema Extraction), a novel system with two synergistic components: ARCHITECT, which autonomously optimizes JSON schemas for LLM consumption while maintaining backward compatibility through RELAY (an integrated code generation system), and SCOPE, which implements reflection-based extraction with combined static and LLM-based guardrails. We evaluate PARSE qualitatively and quantitatively on three datasets including Schema-Guided Dialogue (SGD), Structured Web Data Extraction (SWDE), and internal retail conversation data, and find that it achieves up to 64.7% improvement in extraction accuracy on SWDE with combined framework improvements reaching 10% across models, while reducing extraction errors by 92% within the first retry and and maintaining practical latency.

---

### Automated Alignment between Elicitation Interviews and Requirements

Authors: Francesco Dente, Fabiano Dalpiaz, Paolo Papotti
Published: 2025-10-08
Categories: cs.CL, cs.SE
arXiv: https://arxiv.org/abs/2510.08622v2

Software requirements are derived from a variety of elicitation techniques, many of which have a conversational nature, like interviews. However, evaluating whether those derived requirements faithfully reflect the stakeholders' needs remains a challenging manual task. In this paper, we formalize the task of aligning the transcript of an interview with a collection of requirements represented as user stories. We propose two heuristic metrics for alignment, called (i) requirements faithfulness: the proportion of stories supported by the transcript, and (ii) interview coverage: the proportion of transcript supported by at least one story. Then, we run experiments with large language models and embedding models that assess the ability of evaluating these metrics automatically. Experiments over four datasets show that an LLM-based solution achieves 0.86 macro-F1 on manually labeled chunk-story pairs. We also show how embedding models can be used as blockers to make the approach more scalable. This work paves the way for more research on linking conversational artifacts with requirements. The formal framework and the automated matching techniques are basic components that can be used for emerging tasks such as tracing requirements to interviews and generating requirements from conversations.

---

### From Simulation to Strategy: Automating Personalized Interaction Planning for Conversational Agents

Authors: Wen-Yu Chang, Tzu-Hung Huang, Chih-Ho Chen, Yun-Nung Chen
Published: 2025-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.08621v2

Amid the rapid rise of agentic dialogue models, realistic user-simulator studies are essential for tuning effective conversation strategies. This work investigates a sales-oriented agent that adapts its dialogue based on user profiles spanning age, gender, and occupation. While age and gender influence overall performance, occupation produces the most pronounced differences in conversational intent. Leveraging this insight, we introduce a lightweight, occupation-conditioned strategy that guides the agent to prioritize intents aligned with user preferences, resulting in shorter and more successful dialogues. Our findings highlight the importance of rich simulator profiles and demonstrate how simple persona-informed strategies can enhance the effectiveness of sales-oriented dialogue systems.

---

### JAI-1: A Thai-Centric Large Language Model

Authors: Attapol T. Rutherford, Jullajak Karnjanaekarin, Narongkorn Panitsrisit, Pontakorn Trakuekul, Sumana Sumanakul, Natchanon Pollertlam
Published: 2025-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.08620v1

This technical report introduces JAI-1, a Thai-centric language model with 75B parameters. Recent Thai models have primarily relied on existing open-source models, applying additional training without structural modifications to specialize in Thai. However, this approach risks eroding pre-existing knowledge in the model's parameter space during the injection of Thai-specific information, as optimized parameters for general tasks may conflict with new linguistic requirements. In contrast, JAI-1 adopts an upscaling strategy: starting from a smaller, high-performing English open-source LLM, we expanded its parameter space and utilized the newly allocated capacity to systematically integrate Thai-language knowledge. This methodology not only preserves the original model's general intelligence but also establishes a unique architecture distinct from other open-source models, enabling scalable future enhancements. During pre-training, JAI-1 was exposed to 1.5T tokens, including over 300B Thai language tokens. This was followed by post-training stages -- supervised fine-tuning and alignment tuning -- using more than 600K instruction-based examples. The final model demonstrated superior performance compared to Typhoon2-70B on Thai-centric benchmarks (IFEval-TH, MT-Bench-TH, and JAI-Hall-Bench), validating the efficacy of its upscaling and knowledge-integration framework.

---

### Hypothesis Hunting with Evolving Networks of Autonomous Scientific Agents

Authors: Tennison Liu, Silas Ruhrberg Estévez, David L. Bentley, Mihaela van der Schaar
Published: 2025-10-08
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.08619v1

Large-scale scientific datasets -- spanning health biobanks, cell atlases, Earth reanalyses, and more -- create opportunities for exploratory discovery unconstrained by specific research questions. We term this process hypothesis hunting: the cumulative search for insight through sustained exploration across vast and complex hypothesis spaces. To support it, we introduce AScience, a framework modeling discovery as the interaction of agents, networks, and evaluation norms, and implement it as ASCollab, a distributed system of LLM-based research agents with heterogeneous behaviors. These agents self-organize into evolving networks, continually producing and peer-reviewing findings under shared standards of evaluation. Experiments show that such social dynamics enable the accumulation of expert-rated results along the diversity-quality-novelty frontier, including rediscoveries of established biomarkers, extensions of known pathways, and proposals of new therapeutic targets. While wet-lab validation remains indispensable, our experiments on cancer cohorts demonstrate that socially structured, agentic networks can sustain exploratory hypothesis hunting at scale.

---

### VAPO: End-to-end Slide-Enhanced Speech Recognition with Omni-modal Large Language Models

Authors: Rui Hu, Delai Qiu, Yining Wang, Shengping Liu, Jitao Sang
Published: 2025-10-08
Categories: eess.AS, cs.CV, cs.SD
arXiv: https://arxiv.org/abs/2510.08618v2

Omni-modal large language models (OLLMs) offer a promising end-to-end solution for slide-enhanced speech recognition due to their inherent multimodal capabilities. However, we found a fundamental issue faced by OLLMs: \textit{Visual Interference}, where models show a bias towards visible text over auditory signals, causing them to hallucinate slide content that was never spoken. To address this, we propose Visually-Anchored Policy Optimization (VAPO), which aims to reshape models' inference process to follow the human-like ``Look-then-Listen'' inference chain. Specifically, we design a temporally decoupled policy: the model first extracts visual priors in a <think> block to serve as semantic anchors, then generates the transcription in an <answer> block. The policy is optimized via multi-objective reinforcement learning. Furthermore, we introduce SlideASR-Bench, a comprehensive benchmark designed to address the scarcity of entity-rich data, comprising a large-scale synthetic corpus for training and a challenging real-world test set for evaluation. We conduct extensive evaluations demonstrating that VAPO effectively eliminates visual interference and achieves state-of-the-art performance on SlideASR-Bench and public datasets, significantly reducing entity recognition errors in specialized domains.

---

### Reproducible Evaluation of Data Augmentation and Loss Functions for Brain Tumor Segmentation

Authors: Saumya B
Published: 2025-10-08
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.08617v1

Brain tumor segmentation is crucial for diagnosis and treatment planning, yet challenges such as class imbalance and limited model generalization continue to hinder progress. This work presents a reproducible evaluation of U-Net segmentation performance on brain tumor MRI using focal loss and basic data augmentation strategies. Experiments were conducted on a publicly available MRI dataset, focusing on focal loss parameter tuning and assessing the impact of three data augmentation techniques: horizontal flip, rotation, and scaling. The U-Net with focal loss achieved a precision of 90%, comparable to state-of-the-art results. By making all code and results publicly available, this study establishes a transparent, reproducible baseline to guide future research on augmentation strategies and loss function design in brain tumor segmentation.

---

### LLMs Show Surface-Form Brittleness Under Paraphrase Stress Tests

Authors: Juan Miguel Navarro Carranza
Published: 2025-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.08616v1

Benchmark scores for Large Language Models (LLMs) can be inflated by memorization of test items or near duplicates. We present a simple, protocol that probes generalization by re-evaluating models on paraphrased versions of benchmark questions. Using Mistral-7B-Instruct and Qwen2.5-7B-Instruct, we measure the accuracy gap between original and paraphrased items on ARC-Easy and ARC-Challenge. Our pipeline controls decoding, enforces multiple-choice output format, and includes a robust paraphrase-cleaning step to preserve semantics. We find that paraphrasing induces a non-trivial accuracy drop (original vs. paraphrased), consistent with prior concerns about contamination and brittle surface-form shortcuts.

---

### Iterative LLM-Based Generation and Refinement of Distracting Conditions in Math Word Problems

Authors: Kaiqi Yang, Hang Li, Yucheng Chu, Zitao Liu, Mi Tian, Hui Liu
Published: 2025-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.08615v3

Mathematical reasoning serves as a crucial testbed for the intelligence of large language models (LLMs), and math word problems (MWPs) are a popular type of math problems. Most MWP datasets consist of problems containing only the necessary information, while problems with distracting and excessive conditions are often overlooked. Prior works have tested popular LLMs and found a dramatic performance drop in the presence of distracting conditions. However, datasets of MWPs with distracting conditions are limited, and most suffer from lower levels of difficulty and out-of-context expressions. This makes distracting conditions easy to identify and exclude, thus reducing the credibility of benchmarking on them. Moreover, when adding distracting conditions, the reasoning and answers may also change, requiring intensive labor to check and write the solutions. To address these issues, we design an iterative framework to generate distracting conditions using LLMs. We develop a set of prompts to revise MWPs from different perspectives and cognitive levels, encouraging the generation of distracting conditions as well as suggestions for further revision. Another advantage is the shared solutions between original and revised problems: we explicitly guide the LLMs to generate distracting conditions that do not alter the original solutions, thus avoiding the need to generate new solutions. This framework is efficient and easy to deploy, reducing the overhead of generating MWPs with distracting conditions while maintaining data quality.

---

### Gender Bias in Large Language Models for Healthcare: Assignment Consistency and Clinical Implications

Authors: Mingxuan Liu, Yuhe Ke, Wentao Zhu, Mayli Mertens, Yilin Ning, Jingchi Liao, Chuan Hong, Daniel Shu Wei Ting, Yifan Peng, Danielle S. Bitterman, Marcus Eng Hock Ong, Nan Liu
Published: 2025-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.08614v1

The integration of large language models (LLMs) into healthcare holds promise to enhance clinical decision-making, yet their susceptibility to biases remains a critical concern. Gender has long influenced physician behaviors and patient outcomes, raising concerns that LLMs assuming human-like roles, such as clinicians or medical educators, may replicate or amplify gender-related biases. Using case studies from the New England Journal of Medicine Challenge (NEJM), we assigned genders (female, male, or unspecified) to multiple open-source and proprietary LLMs. We evaluated their response consistency across LLM-gender assignments regarding both LLM-based diagnosis and models' judgments on the clinical relevance or necessity of patient gender. In our findings, diagnoses were relatively consistent across LLM genders for most models. However, for patient gender's relevance and necessity in LLM-based diagnosis, all models demonstrated substantial inconsistency across LLM genders, particularly for relevance judgements. Some models even displayed a systematic female-male disparity in their interpretation of patient gender. These findings present an underexplored bias that could undermine the reliability of LLMs in clinical practice, underscoring the need for routine checks of identity-assignment consistency when interacting with LLMs to ensure reliable and equitable AI-supported clinical care.

---