# Research Papers — 2025-11 · bundle page 194 of 197

> Full-text markdown of papers #9651–9700 of 9830 published in 2025-11, newest first. AI-readable mirrors of the full 9830-paper 2025-11 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2025-11/page/194
[← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/193.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-11/page/195.md)

### Reliable Curation of EHR Dataset via Large Language Models under Environmental Constraints

Authors: Raymond M. Xiong, Panyu Chen, Tianze Dong, Jian Lu, Louis Hu, Nathan Yu, Benjamin Goldstein, Danyang Zhuo, Anru R. Zhang
Published: 2025-11-02
Categories: cs.DB, cs.LG, stat.AP
arXiv: https://arxiv.org/abs/2511.00772v2

Electronic health records (EHRs) are central to modern healthcare delivery and research; yet, many researchers lack the database expertise necessary to write complex SQL queries or generate effective visualizations, limiting efficient data use and scientific discovery. To address this barrier, we introduce CELEC, a large language model (LLM)-powered framework for automated EHR data extraction and analytics. CELEC translates natural language queries into SQL using a prompting strategy that integrates schema information, few-shot demonstrations, and chain-of-thought reasoning, which together improve accuracy and robustness. CELEC also adheres to strict privacy protocols: the LLM accesses only database metadata (e.g., table and column names), while all query execution occurs securely within the institutional environment, ensuring that no patient-level data is ever transmitted to or shared with the LLM. On a subset of the EHRSQL benchmark, CELEC achieves execution accuracy comparable to prior systems while maintaining low latency, cost efficiency, and strict privacy by exposing only database metadata to the LLM. Ablation studies confirm that each component of the SQL generation pipeline, particularly the few-shot demonstrations, plays a critical role in performance. By lowering technical barriers and enabling medical researchers to query EHR databases directly, CELEC streamlines research workflows and accelerates biomedical discovery.

---

### A Framework Based on Graph Cellular Automata for Similarity Evaluation in Urban Spatial Networks

Authors: Peiru Wu, Maojun Zhai, Lingzhu Zhang
Published: 2025-11-02
Categories: cs.SI, cs.LG
arXiv: https://arxiv.org/abs/2511.00768v1

Measuring similarity in urban spatial networks is key to understanding cities as complex systems. Yet most existing methods are not tailored for spatial networks and struggle to differentiate them effectively. We propose GCA-Sim, a similarity-evaluation framework based on graph cellular automata. Each submodel measures similarity by the divergence between value distributions recorded at multiple stages of an information evolution process. We find that some propagation rules magnify differences among network signals; we call this "network resonance." With an improved differentiable logic-gate network, we learn several submodels that induce network resonance. We evaluate similarity through clustering performance on fifty city-level and fifty district-level road networks. The submodels in this framework outperform existing methods, with Silhouette scores above 0.9. Using the best submodel, we further observe that planning-led street networks are less internally homogeneous than organically grown ones; morphological categories from different domains contribute with comparable importance; and degree, as a basic topological signal, becomes increasingly aligned with land value and related variables over iterations.

---

### A Quantitative Study of Sustained Focus in Large Language Models via Repetitive Deterministic Prediction Tasks

Authors: Wanda Hou, Leon Zhou, Hong-Ye Hu, Yubei Chen, Yi-Zhuang You, Xiao-Liang Qi
Published: 2025-11-02
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.00763v3

We investigate the performance of large language models (LLMs) on repetitive deterministic prediction tasks and study how the sequence accuracy rate (SAR) scales with output length. Each such task involves the repetition of the same operation $N$ times. Examples of such tasks include letter replacement in letter strings following a given rule, integer addition, and multiplication of string operators in many-body quantum mechanics. If the LLM performs the task by a simple repetition algorithm, the success rate would follow an exponential decay with sequence length. In contrast, our experiments on leading LLMs reveal a crossover that is sharper than exponential: $-\log\mathrm{SAR}$ grows super-linearly with $N$, and accuracy collapses around a characteristic length $N_*$, the accuracy cliff that separates reliable from unreliable generation. The hypothesis of independent per-step errors is rejected for every model and task we studied. The crossover is well described by a double-exponential accumulation law, $\mathrm{SAR}=\exp(-β_0 Nα^{N-1})$, whose crossover scale $N_*$ does not depend on the functional form chosen to fit it. To interpret this behaviour we introduce a minimal effective model in which step-correctness variables interact through dense random couplings and compete with an external field set by the prompt. Solved by direct enumeration, the model reproduces the super-linear error accumulation and the accuracy cliff qualitatively, and it assigns to each model--task pair two interpretable parameters, an intrinsic error rate and an error-accumulation factor.

---

### Automatic Policy Search using Population-Based Hyper-heuristics for the Integrated Procurement and Perishable Inventory Problem

Authors: Leonardo Kanashiro Felizardo, Edoardo Fadda, Mariá Cristina Vasconcelos Nascimento
Published: 2025-11-02
Categories: cs.NE, math.OC
arXiv: https://arxiv.org/abs/2511.00762v1

This paper addresses the problem of managing perishable inventory under multiple sources of uncertainty, including stochastic demand, unreliable supplier fulfillment, and probabilistic product shelf life. We develop a discrete-event simulation environment to compare two optimization strategies for this multi-item, multi-supplier problem. The first strategy optimizes uniform classic policies (e.g., Constant Order and Base Stock) by tuning their parameters globally, complemented by a direct search to select the best-fitting suppliers for the integrated problem. The second approach is a hyper-heuristic approach, driven by metaheuristics such as a Genetic Algorithm (GA) and Particle Swarm Optimization (PSO). This framework constructs a composite policy by automating the selection of the heuristic type, its parameters, and the sourcing suppliers on an item-by-item basis. Computational results from twelve distinct instances demonstrate that the hyper-heuristic framework consistently identifies superior policies, with GA and EGA exhibiting the best overall performance. Our primary contribution is verifying that this item-level policy construction yields significant performance gains over simpler global policies, thereby justifying the associated computational cost.

---

### Active Thinking Model: A Goal-Directed Self-Improving Framework for Real-World Adaptive Intelligence

Authors: Hong Su
Published: 2025-11-02
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.00758v1

Real-world artificial intelligence (AI) systems are increasingly required to operate autonomously in dynamic, uncertain, and continuously changing environments. However, most existing AI models rely on predefined objectives, static training data, and externally supplied feedback, which restrict their ability to adapt, reflect, and improve independently. In this paper, we propose the Active Thinking Model (ATM)- a unified cognitive framework that integrates goal reasoning, dynamic task generation, and self-reflective learning into an adaptive architecture. Unlike conventional systems that passively execute fixed procedures, ATM actively evaluates its performance through logical reasoning and environmental indicators, reuses effective methods to solve new problems, and generates novel strategies for unseen situations via a continuous self-improvement loop. A mathematically grounded theoretical analysis demonstrates that ATM can autonomously evolve from suboptimal to optimal behavior without external supervision and maintain bounded tracking regret under changing environmental conditions.

---

### Self-Consistency Is Losing Its Edge: Diminishing Returns and Rising Costs in Modern LLMs

Authors: Chiyan Loo
Published: 2025-11-02
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2511.00751v2

Self-consistency -- sampling multiple reasoning paths and selecting the most frequent answer -- was designed for an era when language models made frequent, unpredictable errors. This study argues that the technique has become increasingly wasteful as models grow stronger, and may degrade performance on problems that modern models already solve reliably. Using Gemini 2.5 models on HotpotQA and MATH-500, we show that accuracy gains from increasing the number of sampled reasoning paths are minimal -- 0.4% on HotpotQA across 20 samples, and 1.6% on MATH-500 -- while token costs scale nearly linearly with sample count. Critically, performance plateaued early and in some configurations declined at high sample counts, suggesting that additional paths introduce noise rather than signal when models already solve problems reliably. As inference costs rise with model scale, indiscriminate self-consistency is difficult to justify. We recommend reserving multi-path sampling for problems that demonstrably exceed a model's single-pass reliability.

---

### Trust Region-Based Bayesian Optimisation to Discover Diverse Solutions

Authors: Kokila Kasuni Perera, Frank Neumann, Aneta Neumann
Published: 2025-11-02
Categories: cs.NE, cs.LG
arXiv: https://arxiv.org/abs/2511.00750v1

Bayesian optimisation (BO) is a surrogate-based optimisation technique that efficiently solves expensive black-box functions with small evaluation budgets. Recent studies consider trust regions to improve the scalability of BO approaches when the problem space scales to more dimensions. Motivated by this research, we explore the effectiveness of trust region-based BO algorithms for diversity optimisation in different dimensional black box problems. We propose diversity optimisation approaches extending TuRBO1, which is the first BO method that uses a trust region-based approach for scalability. We extend TuRBO1 as divTuRBO1, which finds an optimal solution while maintaining a given distance threshold relative to a reference solution set. We propose two approaches to find diverse solutions for black-box functions by combining divTuRBO1 runs in a sequential and an interleaving fashion. We conduct experimental investigations on the proposed algorithms and compare their performance with that of the baseline method, ROBOT (rank-ordered Bayesian optimisation with trust regions). We evaluate proposed algorithms on benchmark functions with dimensions 2 to 20. Experimental investigations demonstrate that the proposed methods perform well, particularly in larger dimensions, even with a limited evaluation budget.

---

### Erasing 'Ugly' from the Internet: Propagation of the Beauty Myth in Text-Image Models

Authors: Tanvi Dinkar, Aiqi Jiang, Gavin Abercrombie, Ioannis Konstas
Published: 2025-11-02
Categories: cs.CV, cs.CL
arXiv: https://arxiv.org/abs/2511.00749v2

Social media has exacerbated the promotion of Western beauty norms, leading to negative self-image, particularly in women and girls, and causing harm such as body dysmorphia. Increasingly content on the internet has been artificially generated, leading to concerns that these norms are being exaggerated. The aim of this work is to study how generative AI models may encode 'beauty' and erase 'ugliness', and discuss the implications of this for society. To investigate these aims, we create two image generation pipelines: a text-to-image model and a text-to-language model-to image model. We develop a structured beauty taxonomy which we use to prompt three language models (LMs) and two text-to-image models to cumulatively generate 5984 images using our two pipelines. We then recruit women and non-binary social media users to evaluate 1200 of the images through a Likert-scale within-subjects study. Participants show high agreement in their ratings. Our results show that 86.5% of generated images depicted people with lighter skin tones, 22% contained explicit content despite Safe for Work (SFW) training, and 74% were rated as being in a younger age demographic. In particular, the images of non-binary individuals were rated as both younger and more hypersexualised, indicating troubling intersectional effects. Notably, prompts encoded with 'negative' or 'ugly' beauty traits (such as "a wide nose") consistently produced higher Not SFW (NSFW) ratings regardless of gender. This work sheds light on the pervasive demographic biases related to beauty standards present in generative AI models -- biases that are actively perpetuated by model developers, such as via negative prompting. We conclude by discussing the implications of this on society, which include pollution of the data streams and active erasure of features that do not fall inside the stereotype of what is considered beautiful by developers.

---

### Effective Series Decomposition and Components Learning for Time Series Generation

Authors: Zixuan Ma, Chenfeng Huang
Published: 2025-11-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.00747v1

Time series generation focuses on modeling the underlying data distribution and resampling to produce authentic time series data. Key components, such as trend and seasonality, drive temporal fluctuations, yet many existing approaches fail to employ interpretative decomposition methods, limiting their ability to synthesize meaningful trend and seasonal patterns. To address this gap, we introduce Seasonal-Trend Diffusion (STDiffusion), a novel framework for multivariate time series generation that integrates diffusion probabilistic models with advanced learnable series decomposition techniques, enhancing the interpretability of the generation process. Our approach separates the trend and seasonal learning into distinct blocks: a Multi-Layer Perceptron (MLP) structure captures the trend, while adaptive wavelet distillation facilitates effective multi-resolution learning of seasonal components. This decomposition improves the interpretability of the model on multiple scales. In addition, we designed a comprehensive correction mechanism aimed at ensuring that the generated components exhibit a high degree of internal consistency and preserve meaningful interrelationships with one another. Our empirical studies on eight real-world datasets demonstrate that STDiffusion achieves state-of-the-art performance in time series generation tasks. Furthermore, we extend the model's application to multi-window long-sequence time series generation, which delivered reliable results and highlighted its robustness and versatility.

---

### Correspondence Between Ising Machines and Neural Networks

Authors: Andrew G. Moore
Published: 2025-11-02
Categories: cond-mat.dis-nn, cs.ET, cs.LG, quant-ph
arXiv: https://arxiv.org/abs/2511.00746v1

Computation with the Ising model is central to future computing technologies like quantum annealing, adiabatic quantum computing, and thermodynamic classical computing. Traditionally, computed values have been equated with ground states. This paper generalizes computation with ground states to computation with spin averages, allowing computations to take place at high temperatures. It then introduces a systematic correspondence between Ising devices and neural networks and a simple method to run trained feed-forward neural networks on Ising-type hardware. Finally, a mathematical proof is offered that these implementations are always successful.

---

### Test-time Scaling of LLMs: A Survey from A Subproblem Structure Perspective

Authors: Zhuoyi Yang, Xu Guo, Tong Zhang, Huijuan Xu, Boyang Li
Published: 2025-11-01
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.14772v1

With this paper, we survey techniques for improving the predictive accuracy of pretrained large language models by allocating additional compute at inference time. In categorizing test-time scaling methods, we place special emphasis on how a problem is decomposed into subproblems and on the topological organization of these subproblems whether sequential, parallel, or tree-structured. This perspective allows us to unify diverse approaches such as Chain-of-Thought, Branch-Solve-Merge, and Tree-of-Thought under a common lens. We further synthesize existing analyses of these techniques, highlighting their respective strengths and weaknesses, and conclude by outlining promising directions for future research

---

### Enhancing failure prediction in nuclear industry: Hybridization of knowledge- and data-driven techniques

Authors: Amaratou Mahamadou Saley, Thierry Moyaux, Aïcha Sekhari, Vincent Cheutet, Jean-Baptiste Danielou
Published: 2025-11-01
Categories: cs.LG, cs.CY
arXiv: https://arxiv.org/abs/2511.11604v1

The convergence of the Internet of Things (IoT) and Industry 4.0 has significantly enhanced data-driven methodologies within the nuclear industry, notably enhancing safety and economic efficiency. This advancement challenges the precise prediction of future maintenance needs for assets, which is crucial for reducing downtime and operational costs. However, the effectiveness of data-driven methodologies in the nuclear sector requires extensive domain knowledge due to the complexity of the systems involved. Thus, this paper proposes a novel predictive maintenance methodology that combines data-driven techniques with domain knowledge from a nuclear equipment. The methodological originality of this paper is located on two levels: highlighting the limitations of purely data-driven approaches and demonstrating the importance of knowledge in enhancing the performance of the predictive models. The applicative novelty of this work lies in its use within a domain such as a nuclear industry, which is highly restricted and ultrasensitive due to security, economic and environmental concerns. A detailed real-world case study which compares the current state of equipment monitoring with two scenarios, demonstrate that the methodology significantly outperforms purely data-driven methods in failure prediction. While purely data-driven methods achieve only a modest performance with a prediction horizon limited to 3 h and a F1 score of 56.36%, the hybrid approach increases the prediction horizon to 24 h and achieves a higher F1 score of 93.12%.

---

### Cognitively-Inspired Episodic Memory Architectures for Accurate and Efficient Character AI

Authors: Rafael Arias Gonzalez, Steve DiPaola
Published: 2025-11-01
Categories: cs.CL, cs.AI, cs.HC, cs.LG
arXiv: https://arxiv.org/abs/2511.10652v1

Large language models show promise for embodying historical characters in dialogue systems, but existing approaches face a critical trade-off: simple retrieval-augmented generation produces shallow responses, while multi-stage reflection achieves depth at prohibitive latency. We present an architecture that resolves this tension through offline data augmentation and efficient parallel retrieval from structured episodic memory. Our system transforms biographical data into 1,774 enriched first-person memories with affective-semantic metadata, then employs two-stage retrieval achieving 0.52s prompt generation. Evaluation using LLM-as-judge and RAGAs metrics shows our approach achieves parity with traditional RAG on GPT-4 while significantly outperforming it on smaller models (GPT-3.5, GPT-3), suggesting particular value for resource-constrained deployments. Beyond dialogue, the structured memory enables novel visualization tools: spatiotemporal heatmaps, emotional trajectory analysis, and interactive path tracking, positioning the system as both a dialogue interface and research tool for biographical analysis. We use Van Gogh as a test case, but the architecture is generalizable to any historical figure with substantial textual records, offering a practical framework for educational, museum, and research applications requiring both accuracy and efficiency

---

### Data Analysis and Performance Evaluation of Simulation Deduction Based on LLMs

Authors: Shansi Zhang, Min Li
Published: 2025-11-01
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.10651v1

Data analysis and performance evaluation of simulation deduction plays a pivotal role in modern warfare, which enables military personnel to gain invaluable insights into the potential effectiveness of different strategies, tactics, and operational plans. Traditional manual analysis approach is time-consuming and limited by human errors. To enhance efficiency and accuracy, large language models (LLMs) with strong analytical and inferencing capabilities can be employed. However, high-quality analysis reports with well-structured formatting cannot be obtained through a single instruction input to the LLM. To tackle this issue, we propose a method that first decomposes the complex task into several sub-tasks and designs effective system prompts and user prompts for each sub-task. Multi-round interactions with the LLM incorporating self-check and reflection are then conducted to enable structured data extraction as well as multi-step analysis and evaluation. Furthermore, custom tools are defined and invoked to generate figures and compute metrics. We also design multiple report templates, each tailored to a specific application and input data type, ensuring their adaptability across a variety of scenarios. Extensive evaluation results demonstrate that the reports generated by our method exhibit higher quality, therefore obtaining higher scores than the baseline method.

---

### Retrieval-Augmented Generation of Pediatric Speech-Language Pathology vignettes: A Proof-of-Concept Study

Authors: Yilan Liu
Published: 2025-11-01
Categories: cs.CL, cs.HC
arXiv: https://arxiv.org/abs/2511.08600v1

Clinical vignettes are essential educational tools in speech-language pathology (SLP), but manual creation is time-intensive. While general-purpose large language models (LLMs) can generate text, they lack domain-specific knowledge, leading to hallucinations and requiring extensive expert revision. This study presents a proof-of-concept system integrating retrieval-augmented generation (RAG) with curated knowledge bases to generate pediatric SLP case materials. A multi-model RAG-based system was prototyped integrating curated domain knowledge with engineered prompt templates, supporting five commercial (GPT-4o, Claude 3.5 Sonnet, Gemini 2.5 Pro) and open-source (Llama 3.2, Qwen 2.5-7B) LLMs. Seven test scenarios spanning diverse disorder types and grade levels were systematically designed. Generated cases underwent automated quality assessment using a multi-dimensional rubric evaluating structural completeness, internal consistency, clinical appropriateness, and IEP goal/session note quality. This proof-of-concept demonstrates technical feasibility for RAG-augmented generation of pediatric SLP vignettes. Commercial models showed marginal quality advantages, but open-source alternatives achieved acceptable performance, suggesting potential for privacy-preserving institutional deployment. Integration of curated knowledge bases enabled content generation aligned with professional guidelines. Extensive validation through expert review, student pilot testing, and psychometric evaluation is required before educational or research implementation. Future applications may extend to clinical decision support, automated IEP goal generation, and clinical reflection training.

---

### Agentic Educational Content Generation for African Languages on Edge Devices

Authors: Ravi Gupta, Guneet Bhatia
Published: 2025-11-01
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.07437v1

Addressing educational inequity in Sub-Saharan Africa, this research presents an autonomous agent-orchestrated framework for decentralized, culturally adaptive educational content generation on edge devices. The system leverages four specialized agents that work together to generate contextually appropriate educational content. Experimental validation on platforms including Raspberry Pi 4B and NVIDIA Jetson Nano demonstrates significant performance achievements. InkubaLM on Jetson Nano achieved a Time-To-First-Token (TTFT) of 129 ms, an average inter-token latency of 33 ms, and a throughput of 45.2 tokens per second while consuming 8.4 W. On Raspberry Pi 4B, InkubaLM also led with 326 ms TTFT and 15.9 tokens per second at 5.8 W power consumption. The framework consistently delivered high multilingual quality, averaging a BLEU score of 0.688, cultural relevance of 4.4/5, and fluency of 4.2/5 across tested African languages. Through potential partnerships with active community organizations including African Youth & Community Organization (AYCO) and Florida Africa Foundation, this research aims to establish a practical foundation for accessible, localized, and sustainable AI-driven education in resource-constrained environments. Keeping focus on long-term viability and cultural appropriateness, it contributes to United Nations SDGs 4, 9, and 10. Index Terms - Multi-Agent Systems, Edge AI Computing, Educational Technology, African Languages, Rural Education, Sustainable Development, UN SDG.

---

### Automated Invoice Data Extraction: Using LLM and OCR

Authors: Khushi Khanchandani, Advait Thakur, Akshita Shetty, Chaitravi Reddy, Ritisa Behera
Published: 2025-11-01
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.05547v2

Conventional Optical Character Recognition (OCR) systems are challenged by variant invoice layouts, handwritten text, and low-quality scans, which are often caused by strong template dependencies that restrict their flexibility across different document structures and layouts. Newer solutions utilize advanced deep learning models such as Convolutional Neural Networks (CNN) as well as Transformers, and domain-specific models for better layout analysis and accuracy across various sections over varied document types. Large Language Models (LLMs) have revolutionized extraction pipelines at their core with sophisticated entity recognition and semantic comprehension to support complex contextual relationship mapping without direct programming specification. Visual Named Entity Recognition (NER) capabilities permit extraction from invoice images with greater contextual sensitivity and much higher accuracy rates than older approaches. Existing industry best practices utilize hybrid architectures that blend OCR technology and LLM for maximum scalability and minimal human intervention. This work introduces a holistic Artificial Intelligence (AI) platform combining OCR, deep learning, LLMs, and graph analytics to achieve unprecedented extraction quality and consistency.

---

### Separate the Wheat from the Chaff: Winnowing Down Divergent Views in Retrieval Augmented Generation

Authors: Song Wang, Zihan Chen, Peng Wang, Zhepei Wei, Zhen Tan, Yu Meng, Cong Shen, Jundong Li
Published: 2025-11-01
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.04700v1

Retrieval-augmented generation (RAG) enhances large language models (LLMs) by integrating external knowledge sources to address their limitations in accessing up-to-date or specialized information. A natural strategy to increase the likelihood of retrieving relevant information is to expand the number of retrieved documents. However, involving more documents could introduce significant noise, as many documents may be irrelevant or misleading, thereby reducing the overall accuracy of the generated responses. To overcome the challenge associated with handling a larger number of documents, we propose WinnowRAG, a novel RAG framework designed to systematically filter out noisy documents while preserving valuable content -- a process we refer to as winnowing. WinnowRAG operates in two stages: In Stage I, we perform query-aware clustering to group similar documents and form distinct topic clusters. Each cluster is assigned to an LLM agent for generating a unique answer. In Stage II, we perform winnowing, wherein a critic LLM evaluates the outputs of multiple agents and iteratively separates useful documents from noisy ones. To retain useful documents when discarding agents, we propose two strategic merging techniques to ensure that only relevant knowledge is used for generating the final response. Crucially, WinnowRAG is model-agnostic and does not require any model fine-tuning, making it easily adaptable to various tasks. Extensive experiments on various realistic datasets demonstrate the effectiveness of WinnowRAG over state-of-the-art baselines.

---

### Cross-Lingual SynthDocs: A Large-Scale Synthetic Corpus for Any to Arabic OCR and Document Understanding

Authors: Haneen Al-Homoud, Asma Ibrahim, Murtadha Al-Jubran, Fahad Al-Otaibi, Yazeed Al-Harbi, Daulet Toibazar, Kesen Wang, Pedro J. Moreno
Published: 2025-11-01
Categories: cs.CL, cs.CV
arXiv: https://arxiv.org/abs/2511.04699v1

Cross-Lingual SynthDocs is a large-scale synthetic corpus designed to address the scarcity of Arabic resources for Optical Character Recognition (OCR) and Document Understanding (DU). The dataset comprises over 2.5 million of samples, including 1.5 million textual data, 270K fully annotated tables, and hundred thousands of real data based charts. Our pipeline leverages authentic scanned backgrounds, bilingual layouts, and diacritic aware fonts to capture the typographic and structural complexity of Arabic documents. In addition to text, the corpus includes variety of rendered styles for charts and tables. Finetuning Qwen-2.5-VL on SynthDocs yields consistent improvements in Word Error Rate (WER) and Character Error Rate (CER) in terms of OCR across multiple public Arabic benchmarks, Tree-Edit Distance Similarity (TEDS) and Chart Extraction Score (CharTeX) improved as well in other modalities. SynthDocs provides a scalable, visually realistic resource for advancing research in multilingual document analysis.

---

### multiMentalRoBERTa: A Fine-tuned Multiclass Classifier for Mental Health Disorder

Authors: K M Sajjadul Islam, John Fields, Praveen Madiraju
Published: 2025-11-01
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.04698v2

The early detection of mental health disorders from social media text is critical for enabling timely support, risk assessment, and referral to appropriate resources. This work introduces multiMentalRoBERTa, a fine-tuned RoBERTa model designed for multiclass classification of common mental health conditions, including stress, anxiety, depression, post-traumatic stress disorder (PTSD), suicidal ideation, and neutral discourse. Drawing on multiple curated datasets, data exploration is conducted to analyze class overlaps, revealing strong correlations between depression and suicidal ideation as well as anxiety and PTSD, while stress emerges as a broad, overlapping category. Comparative experiments with traditional machine learning methods, domain-specific transformers, and prompting-based large language models demonstrate that multiMentalRoBERTa achieves superior performance, with macro F1-scores of 0.839 in the six-class setup and 0.870 in the five-class setup (excluding stress), outperforming both fine-tuned MentalBERT and baseline classifiers. Beyond predictive accuracy, explainability methods, including Layer Integrated Gradients and KeyBERT, are applied to identify lexical cues that drive classification, with a particular focus on distinguishing depression from suicidal ideation. The findings emphasize the effectiveness of fine-tuned transformers for reliable and interpretable detection in sensitive contexts, while also underscoring the importance of fairness, bias mitigation, and human-in-the-loop safety protocols. Overall, multiMentalRoBERTa is presented as a lightweight, robust, and deployable solution for enhancing support in mental health platforms.

---

### Fibbinary-Based Compression and Quantization for Efficient Neural Radio Receivers

Authors: Roberta Fiandaca, Manil Dev Gomony
Published: 2025-11-01
Categories: cs.IT, cs.AI
arXiv: https://arxiv.org/abs/2511.01921v1

Neural receivers have shown outstanding performance compared to the conventional ones but this comes with a high network complexity leading to a heavy computational cost. This poses significant challenges in their deployment on hardware-constrained devices. To address the issue, this paper explores two optimization strategies: quantization and compression. We introduce both uniform and non-uniform quantization such as the Fibonacci Code word Quantization (FCQ). A novel fine-grained approach to the Incremental Network Quantization (INQ) strategy is then proposed to compensate for the losses introduced by the above mentioned quantization techniques. Additionally, we introduce two novel lossless compression algorithms that effectively reduce the memory size by compressing sequences of Fibonacci quantized parameters characterized by a huge redundancy. The quantization technique provides a saving of 45\% and 44\% in the multiplier's power and area, respectively, and its combination with the compression determines a 63.4\% reduction in memory footprint, while still providing higher performances than a conventional receiver.

---

### Superpositional Gradient Descent: Harnessing Quantum Principles for Model Training

Authors: Ahmet Erdem Pamuk, Emir Kaan Özdemir, Şuayp Talha Kocabay
Published: 2025-11-01
Categories: cs.LG, quant-ph
arXiv: https://arxiv.org/abs/2511.01918v2

Large language models (LLMs) are increasingly trained with classical optimization techniques like AdamW to improve convergence and generalization. However, the mechanisms by which quantum-inspired methods enhance classical training remain underexplored. We introduce Superpositional Gradient Descent (SGD), a novel optimizer linking gradient updates with quantum superposition by injecting quantum circuit perturbations. We present a mathematical framework and implement hybrid quantum-classical circuits in PyTorch and Qiskit. On synthetic sequence classification and large-scale LLM fine-tuning, SGD converges faster and yields lower final loss than AdamW. Despite promising results, scalability and hardware constraints limit adoption. Overall, this work provides new insights into the intersection of quantum computing and deep learning, suggesting practical pathways for leveraging quantum principles to control and enhance model behavior.

---

### Challenging DINOv3 Foundation Model under Low Inter-Class Variability: A Case Study on Fetal Brain Ultrasound

Authors: Edoardo Conti, Riccardo Rosati, Lorenzo Federici, Adriano Mancini, Maria Chiara Fiorentin
Published: 2025-11-01
Categories: cs.CV, eess.IV
arXiv: https://arxiv.org/abs/2511.01915v1

Purpose: This study provides the first comprehensive evaluation of foundation models in fetal ultrasound (US) imaging under low inter-class variability conditions. While recent vision foundation models such as DINOv3 have shown remarkable transferability across medical domains, their ability to discriminate anatomically similar structures has not been systematically investigated. We address this gap by focusing on fetal brain standard planes--transthalamic (TT), transventricular (TV), and transcerebellar (TC)--which exhibit highly overlapping anatomical features and pose a critical challenge for reliable biometric assessment. Methods: To ensure a fair and reproducible evaluation, all publicly available fetal ultrasound datasets were curated and aggregated into a unified multicenter benchmark, FetalUS-188K, comprising more than 188,000 annotated images from heterogeneous acquisition settings. DINOv3 was pretrained in a self-supervised manner to learn ultrasound-aware representations. The learned features were then evaluated through standardized adaptation protocols, including linear probing with frozen backbone and full fine-tuning, under two initialization schemes: (i) pretraining on FetalUS-188K and (ii) initialization from natural-image DINOv3 weights. Results: Models pretrained on fetal ultrasound data consistently outperformed those initialized on natural images, with weighted F1-score improvements of up to 20 percent. Domain-adaptive pretraining enabled the network to preserve subtle echogenic and structural cues crucial for distinguishing intermediate planes such as TV. Conclusion: Results demonstrate that generic foundation models fail to generalize under low inter-class variability, whereas domain-specific pretraining is essential to achieve robust and clinically reliable representations in fetal brain ultrasound imaging.

---

### iFlyBot-VLA Technical Report

Authors: Yuan Zhang, Chenyu Xue, Wenjie Xu, Chao Ji, Jiajia wu, Jia Pan
Published: 2025-11-01
Categories: cs.CV, cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2511.01914v1

We introduce iFlyBot-VLA, a large-scale Vision-Language-Action (VLA) model trained under a novel framework. The main contributions are listed as follows: (1) a latent action model thoroughly trained on large-scale human and robotic manipulation videos; (2) a dual-level action representation framework that jointly supervises both the Vision-Language Model (VLM) and the action expert during training; (3) a mixed training strategy that combines robot trajectory data with general QA and spatial QA datasets, effectively enhancing the 3D perceptual and reasoning capabilities of the VLM backbone. Specifically, the VLM is trained to predict two complementary forms of actions: latent actions, derived from our latent action model pretrained on cross-embodiment manipulation data, which capture implicit high-level intentions; and structured discrete action tokens, obtained through frequency-domain transformations of continuous control signals, which encode explicit low-level dynamics. This dual supervision aligns the representation spaces of language, vision, and action, enabling the VLM to directly contribute to action generation. Experimental results on the LIBERO Franka benchmark demonstrate the superiority of our frame-work, while real-world evaluations further show that iFlyBot-VLA achieves competitive success rates across diverse and challenging manipulation tasks. Furthermore, we plan to open-source a portion of our self-constructed dataset to support future research in the community

---

### Delta-learned force fields for nonbonded interactions: Addressing the strength mismatch between covalent-nonbonded interaction for global models

Authors: Leonardo Cázares-Trejo, Marco Loreto-Silva, Huziel E. Sauceda
Published: 2025-11-01
Categories: physics.chem-ph, cond-mat.mtrl-sci, cs.LG, physics.comp-ph
arXiv: https://arxiv.org/abs/2511.01913v1

Noncovalent interactions--vdW dispersion, hydrogen/halogen bonding, ion-$π$, and $π$-stacking--govern structure, dynamics, and emergent phenomena in materials and molecular systems, yet accurately learning them alongside covalent forces remains a core challenge for machine-learned force fields (MLFFs). This challenge is acute for global models that use Coulomb-matrix (CM) descriptors compared under Euclidean/Frobenius metrics in multifragment settings. We show that the mismatch between predominantly covalent force labels and the CM's overrepresentation of intermolecular features biases single-model training and degrades force-field fidelity. To address this, we introduce \textit{$Δ$-sGDML}, a scale-aware formulation within the sGDML framework that explicitly decouples intra- and intermolecular physics by training fragment-specific models alongside a dedicated binding model, then composing them at inference. Across benzene dimers, host-guest complexes (C$_{60}$@buckycatcher, NO$_3^-$@i-corona(6)arene), benzene-water, and benzene-Na$^+$, \mbox{$Δ$-sGDML} delivers consistent gains over a single global model, with fragment-resolved force-error reductions up to \textbf{75\%}, without loss of energy accuracy. Furthermore, molecular-dynamics simulations further confirm that the $Δ$-model yields a reliable force field for C$_{60}$@buckycatcher, producing stable trajectories across a wide range of temperatures (10-400~K), unlike the single global model, which loses stability above $\sim$200~K. The method offers a practical route to homogenize per-fragment errors and recover reliable noncovalent physics in global MLFFs.

---

### EvoMem: Improving Multi-Agent Planning with Dual-Evolving Memory

Authors: Wenzhe Fan, Ning Yan, Masood Mortazavi
Published: 2025-11-01
Categories: cs.MA, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.01912v2

Planning has been a cornerstone of artificial intelligence for solving complex problems, and recent progress in LLM-based multi-agent frameworks have begun to extend this capability. However, the role of human-like memory within these frameworks remains largely unexplored. Understanding how agents coordinate through memory is critical for natural language planning, where iterative reasoning, constraint tracking, and error correction drive the success. Inspired by working memory model in cognitive psychology, we present EvoMem, a multi-agent framework built on a dual-evolving memory mechanism. The framework consists of three agents (Constraint Extractor, Verifier, and Actor) and two memory modules: Constraint Memory (CMem), which evolves across queries by storing task-specific rules and constraints while remains fixed within a query, and Query-feedback Memory (QMem), which evolves within a query by accumulating feedback across iterations for solution refinement. Both memory modules are reset at the end of each query session. Evaluations on trip planning, meeting planning, and calendar scheduling show consistent performance improvements, highlighting the effectiveness of EvoMem. This success underscores the importance of memory in enhancing multi-agent planning.

---

### Towards Understanding, Analyzing, and Optimizing Agentic AI Execution: A CPU-Centric Perspective

Authors: Ritik Raj, Souvik Kundu, Ishita Vohra, Hong Wang, Tushar Krishna
Published: 2025-11-01
Categories: cs.AI, cs.LG, cs.MA
arXiv: https://arxiv.org/abs/2511.00739v3

Agentic AI serving converts monolithic LLM-based inference to autonomous problem-solvers that can plan, call tools, perform reasoning, and adapt on the fly. Due to diverse task execution need, such serving heavily rely on heterogeneous CPU-GPU systems with majority of the external tools responsible for agentic capability, either run on or are orchestrated by the CPU. Towards having a deeper understanding of its role, this paper aims to characterize and analyze the system bottlenecks introduced by agentic AI workloads from a largely overlooked CPU-centric perspective. We first present a compile-time characterization of agentic AI execution and choose representative workloads to capture the algorithmic diversity. We then perform runtime characterization of the representative workloads analyzing the end-to-end latency and throughput on two different hardware systems to isolate respective architectural bottlenecks. Based on the insights on the bottlenecks, we finally present two scheduling optimizations, namely, 1. CPU-Aware Overlapped Micro-Batching (COMB) and 2. Mixed Agentic Scheduling (MAS) on homogeneous and heterogeneous agentic workloads, respectively. In specific, these methods optimize for improved CPU-GPU concurrent utilization while reducing skewed resource allocation for heterogeneous execution. Experimental evaluations on the two hardware systems demonstrate the efficacy of COMB in yielding up to 1.7x lower P50 latency in standalone homogeneous workload execution and up to 3.9x/1.8x lower service/total latency under homogeneous open-loop load. Additionally, for heterogeneous open-loop load, MAS can reduce the total latency for minority request-type by up to 2.37x/2.49x at P50/P90 percentile.

---

### Towards classification-based representation learning for place recognition on LiDAR scans

Authors: Maksim Konoplia, Dmitrii Khizbullin
Published: 2025-11-01
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.00738v2

Place recognition is a crucial task in autonomous driving, allowing vehicles to determine their position using sensor data. While most existing methods rely on contrastive learning, we explore an alternative approach by framing place recognition as a multi-class classification problem. Our method assigns discrete location labels to LiDAR scans and trains an encoder-decoder model to classify each scan's position directly. We evaluate this approach on the NuScenes dataset and show that it achieves competitive performance compared to contrastive learning-based methods while offering advantages in training efficiency and stability.

---

### EP-HDC: Hyperdimensional Computing with Encrypted Parameters for High-Throughput Privacy-Preserving Inference

Authors: Jaewoo Park, Chenghao Quan, Jongeun Lee
Published: 2025-11-01
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2511.00737v1

While homomorphic encryption (HE) provides strong privacy protection, its high computational cost has restricted its application to simple tasks. Recently, hyperdimensional computing (HDC) applied to HE has shown promising performance for privacy-preserving machine learning (PPML). However, when applied to more realistic scenarios such as batch inference, the HDC-based HE has still very high compute time as well as high encryption and data transmission overheads. To address this problem, we propose HDC with encrypted parameters (EP-HDC), which is a novel PPML approach featuring client-side HE, i.e., inference is performed on a client using a homomorphically encrypted model. Our EP-HDC can effectively mitigate the encryption and data transmission overhead, as well as providing high scalability with many clients while providing strong protection for user data and model parameters. In addition to application examples for our client-side PPML, we also present design space exploration involving quantization, architecture, and HE-related parameters. Our experimental results using the BFV scheme and the Face/Emotion datasets demonstrate that our method can improve throughput and latency of batch inference by orders of magnitude over previous PPML methods (36.52~1068x and 6.45~733x, respectively) with less than 1% accuracy degradation.

---

### FeNN-DMA: A RISC-V SoC for SNN acceleration

Authors: Zainab Aizaz, James C. Knight, Thomas Nowotny
Published: 2025-11-01
Categories: cs.NE, cs.AI, cs.AR
arXiv: https://arxiv.org/abs/2511.00732v2

Spiking Neural Networks (SNNs) are a promising, energy-efficient alternative to standard Artificial Neural Networks (ANNs) and are particularly well-suited to spatio-temporal tasks such as keyword spotting and video classification. However, SNNs have a much lower arithmetic intensity than ANNs and are therefore not well-matched to standard accelerators like GPUs and TPUs. Field Programmable Gate Arrays (FPGAs) are designed for such memory-bound workloads, and here we present a novel, fully-programmable RISC-V-based system-on-chip (FeNN-DMA), tailored to simulating SNNs on modern UltraScale+ FPGAs. We show that FeNN-DMA has comparable resource usage and energy requirements to state-of-the-art fixed-function SNN accelerators, yet it supports more complex neuron models and network topologies, and can simulate up to 16 thousand neurons and 256 million synapses per core. Using this functionality, we demonstrate state-of-the-art classification accuracy on the Spiking Heidelberg Digits, Neuromorphic MNIST and Braille tactile classification tasks.

---

### Validating Deep Models for Alzheimer's 18F-FDG PET Diagnosis Across Populations: A Study with Latin American Data

Authors: Hugo Massaroli, Hernan Chaves, Pilar Anania, Mauricio Farez, Emmanuel Iarussi, Viviana Siless
Published: 2025-11-01
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.00728v1

Deep learning models have shown strong performance in diagnosing Alzheimer's disease (AD) using neuroimaging data, particularly 18F-FDG PET scans, with training datasets largely composed of North American cohorts such as those in the Alzheimer's Disease Neuroimaging Initiative (ADNI). However, their generalization to underrepresented populations remains underexplored. In this study, we benchmark convolutional and Transformer-based models on the ADNI dataset and assess their generalization performance on a novel Latin American clinical cohort from the FLENI Institute in Buenos Aires, Argentina. We show that while all models achieve high AUCs on ADNI (up to .96, .97), their performance drops substantially on FLENI (down to .82, .80, respectively), revealing a significant domain shift. The tested architectures demonstrated similar performance, calling into question the supposed advantages of transformers for this specific task. Through ablation studies, we identify per-image normalization and a correct sampling selection as key factors for generalization. Occlusion sensitivity analysis further reveals that models trained on ADNI, generally attend to canonical hypometabolic regions for the AD class, but focus becomes unclear for the other classes and for FLENI scans. These findings highlight the need for population-aware validation of diagnostic AI models and motivate future work on domain adaptation and cohort diversification.

---

### Cross-Validated Causal Inference: a Modern Method to Combine Experimental and Observational Data

Authors: Xuelin Yang, Licong Lin, Susan Athey, Michael I. Jordan, Guido W. Imbens
Published: 2025-11-01
Categories: econ.EM, stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2511.00727v1

We develop new methods to integrate experimental and observational data in causal inference. While randomized controlled trials offer strong internal validity, they are often costly and therefore limited in sample size. Observational data, though cheaper and often with larger sample sizes, are prone to biases due to unmeasured confounders. To harness their complementary strengths, we propose a systematic framework that formulates causal estimation as an empirical risk minimization (ERM) problem. A full model containing the causal parameter is obtained by minimizing a weighted combination of experimental and observational losses--capturing the causal parameter's validity and the full model's fit, respectively. The weight is chosen through cross-validation on the causal parameter across experimental folds. Our experiments on real and synthetic data show the efficacy and reliability of our method. We also provide theoretical non-asymptotic error bounds.

---

### Enhancing Heavy Rain Nowcasting with Multimodal Data: Integrating Radar and Satellite Observations

Authors: Rama Kassoumeh, David Rügamer, Henning Oppel
Published: 2025-11-01
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.00716v1

The increasing frequency of heavy rainfall events, which are a major cause of urban flooding, underscores the urgent need for accurate precipitation forecasting - particularly in urban areas where localized events often go undetected by ground-based sensors. In Germany, only 17.3% of hourly heavy rain events between 2001 and 2018 were recorded by rain gauges, highlighting the limitations of traditional monitoring systems. Radar data are another source that effectively tracks ongoing precipitation; however, forecasting the development of heavy rain using radar alone remains challenging due to the brief and unpredictable nature of such events. Our focus is on evaluating the effectiveness of fusing satellite and radar data for nowcasting. We develop a multimodal nowcasting model that combines both radar and satellite imagery for predicting precipitation at lead times of 5, 15, and 30 minutes. We demonstrate that this multimodal strategy significantly outperforms radar-only approaches. Experimental results show that integrating satellite data improves prediction accuracy, particularly for intense precipitation. The proposed model increases the Critical Success Index for heavy rain by 4% and for violent rain by 3% at a 5-minute lead time. Moreover, it maintains higher predictive skill at longer lead times, where radar-only performance declines. A qualitative analysis of the severe flooding event in the state of North Rhine-Westphalia, Germany in 2021 further illustrates the superior performance of the multimodal model. Unlike the radar-only model, which captures general precipitation patterns, the multimodal model yields more detailed and accurate forecasts for regions affected by heavy rain. This improved precision enables timely, reliable, life-saving warnings. Implementation available at https://github.com/RamaKassoumeh/Multimodal_heavy_rain

---

### TRISKELION-1: Unified Descriptive-Predictive-Generative AI

Authors: Nardeep Kumar, Arun Kanwar
Published: 2025-11-01
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.00711v1

TRISKELION-1 is a unified descriptive-predictive-generative architecture that integrates statistical, mechanistic, and generative reasoning within a single encoder-decoder framework. The model demonstrates how descriptive representation learning, predictive inference, and generative synthesis can be jointly optimized using variational objectives. Experiments on MNIST validate that descriptive reconstruction, predictive classification, and generative sampling can coexist stably within one model. The framework provides a blueprint toward universal intelligence architectures that connect interpretability, accuracy, and creativity.

---

### Does RLVR Extend Reasoning Boundaries? Investigating Capability Expansion in Vision-Language Models

Authors: Minghe Shen, Zhuo Zhi, Chonghan Liu, Shuo Xing, Zhengzhong Tu, Che Liu
Published: 2025-11-01
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.00710v4

Recent studies posit that Reinforcement Learning with Verifiable Rewards (RLVR) primarily amplifies behaviors inherent to the pre-training distribution rather than inducing new capabilities, but these insights are predominantly limited to language-only domains, leaving the dynamics of visual-centric spatial reasoning under-explored. To examine the impact of RLVR on the capability boundaries of Vision-Language Models (VLMs), we introduce \textbf{Ariadne}, a controlled framework based on synthetic maze navigation where the reasoning difficulty is precisely regulated by path length and the number of turns. We demonstrate that applying RLVR extends the spatial reasoning boundary, achieving success on problems where the base policy VLM consistently attains $0\%$ accuracy despite increasing pass@k sampling budgets, indicating that the optimized policy successfully navigates search spaces that were effectively unreachable by the base distribution. Furthermore, despite being trained exclusively on synthetic mazes, we evaluate the model on two real-world navigation benchmarks (MapBench and ReasonMap) in a zero-shot setting. The observed improvements in these out-of-domain tasks suggest genuine spatial reasoning capability expansion rather than mere sampling efficiency.

---

### A Voice-Enabled Virtual Patient System for Interactive Training in Standardized Clinical Assessment

Authors: Veronica Bossio Botero, Vijay Yadav, Jacob Ouyang, Anzar Abbas, Michelle Worthington
Published: 2025-11-01
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2511.00709v2

Training mental health clinicians to conduct standardized clinical assessments is challenging due to a lack of scalable, realistic practice opportunities, which can impact data quality in clinical trials. To address this gap, we introduce a voice-enabled virtual patient simulation system powered by a large language model (LLM). This study describes the system's development and validates its ability to generate virtual patients who accurately adhere to pre-defined clinical profiles, maintain coherent narratives, and produce realistic dialogue. We implemented a system using a LLM to simulate patients with specified symptom profiles, demographics, and communication styles. The system was evaluated by 5 experienced clinical raters who conducted 20 simulated structured MADRS interviews across 4 virtual patient personas. The virtual patients demonstrated strong adherence to their clinical profiles, with a mean item difference between rater-assigned MADRS scores and configured scores of 0.52 (SD=0.75). Inter-rater reliability across items was 0.90 (95% CI=0.68-0.99). Expert raters consistently rated the qualitative realism and cohesiveness of the virtual patients favorably, giving average ratings between "Agree" and "Strongly Agree." Our findings suggest that LLM-powered virtual patient simulations are a viable and scalable tool for training clinicians, capable of producing high-fidelity, clinically relevant practice scenarios.

---

### Polynomial Mixing Times of Simulated Tempering for Mixture Targets by Conductance Decomposition

Authors: Quan Zhou
Published: 2025-11-01
Categories: stat.CO, math.PR, stat.ML
arXiv: https://arxiv.org/abs/2511.00708v1

We study the theoretical complexity of simulated tempering for sampling from mixtures of log-concave components differing only by location shifts. The main result establishes the first polynomial-time guarantee for simulated tempering combined with the Metropolis-adjusted Langevin algorithm (MALA) with respect to the problem dimension $d$, maximum mode displacement $D$, and logarithmic accuracy $\log ε^{-1}$. The proof builds on a general state decomposition theorem for $s$-conductance, applied to an auxiliary Markov chain constructed on an augmented space. We also obtain an improved complexity estimate for simulated tempering combined with random-walk Metropolis. Our bounds assume an inverse-temperature ladder with smallest value $β_1 = O(D^{-2})$ and spacing $β_{i+1}/β_i = 1 + O( d^{-1/2} )$, both of which are shown to be asymptotically optimal up to logarithmic factors.

---

### Investigating the Robustness of Knowledge Tracing Models in the Presence of Student Concept Drift

Authors: Morgan Lee, Artem Frenk, Eamon Worden, Karish Gupta, Thinh Pham, Ethan Croteau, Neil Heffernan
Published: 2025-11-01
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2511.00704v2

Knowledge Tracing (KT) has been an established problem in the educational data mining field for decades, and it is commonly assumed that the underlying learning process being modeled remains static. Given the ever-changing landscape of online learning platforms (OLPs), we investigate how concept drift and changing student populations can impact student behavior within an OLP through testing model performance both within a single academic year and across multiple academic years. Four well-studied KT models were applied to five academic years of data to assess how susceptible KT models are to concept drift. Through our analysis, we find that all four families of KT models can exhibit degraded performance, Bayesian Knowledge Tracing (BKT) remains the most stable KT model when applied to newer data, while more complex, attention based models lose predictive power significantly faster.

---

### Applying Medical Imaging Tractography Techniques to Painterly Rendering of Images

Authors: Alberto Di Biase
Published: 2025-11-01
Categories: cs.GR, cs.CV
arXiv: https://arxiv.org/abs/2511.00702v1

Doctors and researchers routinely use diffusion tensor imaging (DTI) and tractography to visualize the fibrous structure of tissues in the human body. This paper explores the connection of these techniques to the painterly rendering of images. Using a tractography algorithm the presented method can place brush strokes that mimic the painting process of human artists, analogously to how fibres are tracked in DTI. The analogue to the diffusion tensor for image orientation is the structural tensor, which can provide better local orientation information than the gradient alone. I demonstrate this technique in portraits and general images, and discuss the parallels between fibre tracking and brush stroke placement, and frame it in the language of tractography. This work presents an exploratory investigation into the cross-domain application of diffusion tensor imaging techniques to painterly rendering of images. All the code is available at https://github.com/tito21/st-python

---

### Privacy-Aware Time Series Synthesis via Public Knowledge Distillation

Authors: Penghang Liu, Haibei Zhu, Eleonora Kreacic, Svitlana Vyetrenko
Published: 2025-11-01
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.00700v1

Sharing sensitive time series data in domains such as finance, healthcare, and energy consumption, such as patient records or investment accounts, is often restricted due to privacy concerns. Privacy-aware synthetic time series generation addresses this challenge by enforcing noise during training, inherently introducing a trade-off between privacy and utility. In many cases, sensitive sequences is correlated with publicly available, non-sensitive contextual metadata (e.g., household electricity consumption may be influenced by weather conditions and electricity prices). However, existing privacy-aware data generation methods often overlook this opportunity, resulting in suboptimal privacy-utility trade-offs. In this paper, we present Pub2Priv, a novel framework for generating private time series data by leveraging heterogeneous public knowledge. Our model employs a self-attention mechanism to encode public data into temporal and feature embeddings, which serve as conditional inputs for a diffusion model to generate synthetic private sequences. Additionally, we introduce a practical metric to assess privacy by evaluating the identifiability of the synthetic data. Experimental results show that Pub2Priv consistently outperforms state-of-the-art benchmarks in improving the privacy-utility trade-off across finance, energy, and commodity trading domains.

---

### Inference-Time Chain-of-Thought Pruning with Latent Informativeness Signals

Authors: Sophie Li, Nicholas Huang, Nayan Saxena, Nina Luo, Vincent Lin, Kevin Zhu, Sunishchal Dev
Published: 2025-11-01
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.00699v2

Large language models (LLMs) improve reasoning accuracy when generating multiple candidate solutions at test time, but standard methods like Best-of-N (BoN) incur high computational cost by fully generating all branches. Self-Truncation Best-of-N (ST-BoN) mitigates this by truncating unpromising paths early, but its reliance on consistency-based heuristics is a limitation as it does not directly evaluate branch quality. We present KL-Adjusted Pruned Path Algorithm (KAPPA), an inference-time method that combines Kullback-Leibler divergence, confidence, and entropy into a principled scoring function to guide progressive pruning. By promoting diversity during exploration and selectively eliminating low-scoring branches, KAPPA maintains accuracy while substantially reducing memory and token usage. Experiments on GSM8K and MATH500 with DeepSeek-R1-Distill-Qwen-1.5B and Qwen2.5-7B-Instruct demonstrate that KAPPA stabilizes performance in smaller models and achieves up to ~60% reduction in peak memory and ~90% reduction in total token generation relative to BoN, with minimal impact on accuracy.

---

### Toward Better Optimization of Low-Dose CT Enhancement: A Critical Analysis of Loss Functions and Image Quality Assessment Metrics

Authors: Taifour Yousra, Beghdadi Azeddine, Marie Luong, Zuheng Ming
Published: 2025-11-01
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.00698v1

Low-dose CT (LDCT) imaging is widely used to reduce radiation exposure to mitigate high exposure side effects, but often suffers from noise and artifacts that affect diagnostic accuracy. To tackle this issue, deep learning models have been developed to enhance LDCT images. Various loss functions have been employed, including classical approaches such as Mean Square Error and adversarial losses, as well as customized loss functions(LFs) designed for specific architectures. Although these models achieve remarkable performance in terms of PSNR and SSIM, these metrics are limited in their ability to reflect perceptual quality, especially for medical images. In this paper, we focus on one of the most critical elements of DL-based architectures, namely the loss function. We conduct an objective analysis of the relevance of different loss functions for LDCT image quality enhancement and their consistency with image quality metrics. Our findings reveal inconsistencies between LFs and quality metrics, and highlight the need of consideration of image quality metrics when developing a new loss function for image quality enhancement.

---

### Do Methods to Jailbreak and Defend LLMs Generalize Across Languages?

Authors: Berk Atil, Rebecca J. Passonneau, Fred Morstatter
Published: 2025-11-01
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.00689v2

Large language models (LLMs) undergo safety alignment after training and tuning, yet recent work shows that safety can be bypassed through jailbreak attacks. While many jailbreaks and defenses exist, their cross-lingual generalization remains underexplored. This paper presents the first systematic multilingual evaluation of jailbreaks and defenses across ten languages -- spanning high-, medium-, and low-resource languages -- using six LLMs on HarmBench and AdvBench. We assess two jailbreak types: logical-expression-based and adversarial-prompt-based. For both types, attack success and defense robustness vary across languages: high-resource languages are safer under standard queries but more vulnerable to adversarial ones. Simple defenses can be effective, but are language- and model-dependent. These findings call for language-aware and cross-lingual safety benchmarks for LLMs.

---

### Evolve to Inspire: Novelty Search for Diverse Image Generation

Authors: Alex Inch, Passawis Chaiyapattanaporn, Yuchen Zhu, Yuan Lu, Ting-Wen Ko, Davide Paglieri
Published: 2025-11-01
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.00686v1

Text-to-image diffusion models, while proficient at generating high-fidelity images, often suffer from limited output diversity, hindering their application in exploratory and ideation tasks. Existing prompt optimization techniques typically target aesthetic fitness or are ill-suited to the creative visual domain. To address this shortcoming, we introduce WANDER, a novelty search-based approach to generating diverse sets of images from a single input prompt. WANDER operates directly on natural language prompts, employing a Large Language Model (LLM) for semantic evolution of diverse sets of images, and using CLIP embeddings to quantify novelty. We additionally apply emitters to guide the search into distinct regions of the prompt space, and demonstrate that they boost the diversity of the generated images. Empirical evaluations using FLUX-DEV for generation and GPT-4o-mini for mutation demonstrate that WANDER significantly outperforms existing evolutionary prompt optimization baselines in diversity metrics. Ablation studies confirm the efficacy of emitters.

---

### SOCRATES: Simulation Optimization with Correlated Replicas and Adaptive Trajectory Evaluations

Authors: Haoting Zhang, Haoxian Chen, Donglin Zhan, Hanyang Zhao, Henry Lam, Wenpin Tang, David Yao, Zeyu Zheng
Published: 2025-11-01
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2511.00685v1

The field of simulation optimization (SO) encompasses various methods developed to optimize complex, expensive-to-sample stochastic systems. Established methods include, but are not limited to, ranking-and-selection for finite alternatives and surrogate-based methods for continuous domains, with broad applications in engineering and operations management. The recent advent of large language models (LLMs) offers a new paradigm for exploiting system structure and automating the strategic selection and composition of these established SO methods into a tailored optimization procedure. This work introduces SOCRATES (Simulation Optimization with Correlated Replicas and Adaptive Trajectory Evaluations), a novel two-stage procedure that leverages LLMs to automate the design of tailored SO algorithms. The first stage constructs an ensemble of digital replicas of the real system. An LLM is employed to implement causal discovery from a textual description of the system, generating a structural `skeleton' that guides the sample-efficient learning of the replicas. In the second stage, this replica ensemble is used as an inexpensive testbed to evaluate a set of baseline SO algorithms. An LLM then acts as a meta-optimizer, analyzing the performance trajectories of these algorithms to iteratively revise and compose a final, hybrid optimization schedule. This schedule is designed to be adaptive, with the ability to be updated during the final execution on the real system when the optimization performance deviates from expectations. By integrating LLM-driven reasoning with LLM-assisted trajectory-aware meta-optimization, SOCRATES creates an effective and sample-efficient solution for complex SO optimization problems.

---

### Outlier-Aware Post-Training Quantization for Image Super-Resolution

Authors: Hailing Wang, jianglin Lu, Yitian Zhang, Yun Fu
Published: 2025-11-01
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.00682v1

Quantization techniques, including quantization-aware training (QAT) and post-training quantization (PTQ), have become essential for inference acceleration of image super-resolution (SR) networks. Compared to QAT, PTQ has garnered significant attention as it eliminates the need for ground truth and model retraining. However, existing PTQ methods for SR often fail to achieve satisfactory performance as they overlook the impact of outliers in activation. Our empirical analysis reveals that these prevalent activation outliers are strongly correlated with image color information, and directly removing them leads to significant performance degradation. Motivated by this, we propose a dual-region quantization strategy that partitions activations into an outlier region and a dense region, applying uniform quantization to each region independently to better balance bit-width allocation. Furthermore, we observe that different network layers exhibit varying sensitivities to quantization, leading to different levels of performance degradation. To address this, we introduce sensitivity-aware finetuning that encourages the model to focus more on highly sensitive layers, further enhancing quantization performance. Extensive experiments demonstrate that our method outperforms existing PTQ approaches across various SR networks and datasets, while achieving performance comparable to QAT methods in most scenarios with at least a 75 speedup.

---

### Metadata-Aligned 3D MRI Representations for Contrast Understanding and Quality Control

Authors: Mehmet Yigit Avci, Pedro Borges, Virginia Fernandez, Paul Wright, Mehmet Yigitsoy, Sebastien Ourselin, Jorge Cardoso
Published: 2025-11-01
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.00681v1

Magnetic Resonance Imaging suffers from substantial data heterogeneity and the absence of standardized contrast labels across scanners, protocols, and institutions, which severely limits large-scale automated analysis. A unified representation of MRI contrast would enable a wide range of downstream utilities, from automatic sequence recognition to harmonization and quality control, without relying on manual annotations. To this end, we introduce MR-CLIP, a metadata-guided framework that learns MRI contrast representations by aligning volumetric images with their DICOM acquisition parameters. The resulting embeddings shows distinct clusters of MRI sequences and outperform supervised 3D baselines under data scarcity in few-shot sequence classification. Moreover, MR-CLIP enables unsupervised data quality control by identifying corrupted or inconsistent metadata through image-metadata embedding distances. By transforming routinely available acquisition metadata into a supervisory signal, MR-CLIP provides a scalable foundation for label-efficient MRI analysis across diverse clinical datasets.

---

### Isotropic Curvature Model for Understanding Deep Learning Optimization: Is Gradient Orthogonalization Optimal?

Authors: Weijie Su
Published: 2025-11-01
Categories: math.OC, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.00674v1

In this paper, we introduce a model for analyzing deep learning optimization over a single iteration by leveraging the matrix structure of the weights. We derive the model by assuming isotropy of curvature, including the second-order Hessian and higher-order terms, of the loss function across all perturbation directions; hence, we call it the isotropic curvature model. This model is a convex optimization program amenable to analysis, which allows us to understand how an update on the weights in the form of a matrix relates to the change in the total loss function. As an application, we use the isotropic curvature model to analyze the recently introduced Muon optimizer and other matrix-gradient methods for training language models. First, we show that under a general growth condition on the curvature, the optimal update matrix is obtained by making the spectrum of the original gradient matrix more homogeneous -- that is, making its singular values closer in ratio -- which in particular improves the conditioning of the update matrix. Next, we show that the orthogonalized gradient becomes optimal for the isotropic curvature model when the curvature exhibits a phase transition in growth. Taken together, these results suggest that the gradient orthogonalization employed in Muon and other related methods is directionally correct but may not be strictly optimal. Finally, we discuss future research on how to leverage the isotropic curvature model for designing new optimization methods for training deep learning and language models.

---

### Lifted Successor Generation in Numeric Planning

Authors: Dominik Drexler
Published: 2025-11-01
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.00673v1

Most planners ground numeric planning tasks, given in a first-order-like language, into a ground task representation. However, this can lead to an exponential blowup in task representation size, which occurs in practice for hard-to-ground tasks. We extend a state-of-the-art lifted successor generator for classical planning to support numeric precondition applicability. The method enumerates maximum cliques in a substitution consistency graph. Each maximum clique represents a substitution for the variables of the action schema, yielding a ground action. We augment this graph with numeric action preconditions and prove the successor generator is exact under formally specified conditions. When the conditions fail, our generator may list inapplicable ground actions; a final applicability check filters these without affecting completeness. However, this cannot happen in 23 of 25 benchmark domains, and it occurs only in 1 domain. To the authors' knowledge, no other lifted successor generator supports numeric action preconditions. This enables future research on lifted planning for a very rich planning fragment.

---

### Filtered Neural Galerkin model reduction schemes for efficient propagation of initial condition uncertainties in digital twins

Authors: Zhiyang Ning, Benjamin Peherstorfer
Published: 2025-11-01
Categories: math.NA, cs.LG
arXiv: https://arxiv.org/abs/2511.00670v1

Uncertainty quantification in digital twins is critical to enable reliable and credible predictions beyond available data. A key challenge is that ensemble-based approaches can become prohibitively expensive when embedded in control and data assimilation loops in digital twins, even when reduced models are used. We introduce a reduced modeling approach that advances in time the mean and covariance of the reduced solution distribution induced by the initial condition uncertainties, which eliminates the need to maintain and propagate a costly ensemble of reduced solutions. The mean and covariance dynamics are obtained as a moment closure from Neural Galerkin schemes on pre-trained neural networks, which can be interpreted as filtered Neural Galerkin dynamics analogous to Gaussian filtering and the extended Kalman filter. Numerical experiments demonstrate that filtered Neural Galerkin schemes achieve more than one order of magnitude speedup compared to ensemble-based uncertainty propagation.

---