# Research Papers — 2025-10 · bundle page 56 of 217

> Full-text markdown of papers #2751–2800 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/56
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/55.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/57.md)

### RAGRank: Using PageRank to Counter Poisoning in CTI LLM Pipelines

Authors: Austin Jia, Avaneesh Ramesh, Zain Shamsi, Daniel Zhang, Alex Liu
Published: 2025-10-23
Categories: cs.CR, cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2510.20768v2

Retrieval-Augmented Generation (RAG) has emerged as the dominant architectural pattern to operationalize Large Language Model (LLM) usage in Cyber Threat Intelligence (CTI) systems. However, this design is susceptible to poisoning attacks, and previously proposed defenses can fail for CTI contexts as cyber threat information is often completely new for emerging attacks, and sophisticated threat actors can mimic legitimate formats, terminology, and stylistic conventions. To address this issue, we propose that the robustness of modern RAG defenses can be accelerated by applying source credibility algorithms on corpora, using PageRank as an example. In our experiments, we demonstrate quantitatively that our algorithm applies a lower authority score to malicious documents while promoting trusted content, using the standardized MS MARCO dataset. We also demonstrate proof-of-concept performance of our algorithm on CTI documents and feeds.

---

### RAGRank: Using PageRank to Counter Poisoning in CTI LLM Pipelines

Authors: Austin Jia, Avaneesh Ramesh, Zain Shamsi, Daniel Zhang, Alex Liu
Published: 2025-10-23
Categories: cs.CR, cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2510.20768v1

Retrieval-Augmented Generation (RAG) has emerged as the dominant architectural pattern to operationalize Large Language Model (LLM) usage in Cyber Threat Intelligence (CTI) systems. However, this design is susceptible to poisoning attacks, and previously proposed defenses can fail for CTI contexts as cyber threat information is often completely new for emerging attacks, and sophisticated threat actors can mimic legitimate formats, terminology, and stylistic conventions. To address this issue, we propose that the robustness of modern RAG defenses can be accelerated by applying source credibility algorithms on corpora, using PageRank as an example. In our experiments, we demonstrate quantitatively that our algorithm applies a lower authority score to malicious documents while promoting trusted content, using the standardized MS MARCO dataset. We also demonstrate proof-of-concept performance of our algorithm on CTI documents and feeds.

---

### DyPE: Dynamic Position Extrapolation for Ultra High Resolution Diffusion

Authors: Noam Issachar, Guy Yariv, Sagie Benaim, Yossi Adi, Dani Lischinski, Raanan Fattal
Published: 2025-10-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.20766v2

Diffusion Transformer models can generate images with remarkable fidelity and detail, yet training them at ultra-high resolutions remains extremely costly due to the self-attention mechanism's quadratic scaling with the number of image tokens. In this paper, we introduce Dynamic Position Extrapolation (DyPE), a novel, training-free method that enables pre-trained diffusion transformers to synthesize images at resolutions far beyond their training data, with no additional sampling cost. DyPE takes advantage of the spectral progression inherent to the diffusion process, where low-frequency structures converge early, while high-frequencies take more steps to resolve. Specifically, DyPE dynamically adjusts the model's positional encoding at each diffusion step, matching their frequency spectrum with the current stage of the generative process. This approach allows us to generate images at resolutions that exceed the training resolution dramatically, e.g., 16 million pixels using FLUX. On multiple benchmarks, DyPE consistently improves performance and achieves state-of-the-art fidelity in ultra-high-resolution image generation, with gains becoming even more pronounced at higher resolutions. Project page is available at https://noamissachar.github.io/DyPE/.

---

### DyPE: Dynamic Position Extrapolation for Ultra High Resolution Diffusion

Authors: Noam Issachar, Guy Yariv, Sagie Benaim, Yossi Adi, Dani Lischinski, Raanan Fattal
Published: 2025-10-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.20766v1

Diffusion Transformer models can generate images with remarkable fidelity and detail, yet training them at ultra-high resolutions remains extremely costly due to the self-attention mechanism's quadratic scaling with the number of image tokens. In this paper, we introduce Dynamic Position Extrapolation (DyPE), a novel, training-free method that enables pre-trained diffusion transformers to synthesize images at resolutions far beyond their training data, with no additional sampling cost. DyPE takes advantage of the spectral progression inherent to the diffusion process, where low-frequency structures converge early, while high-frequencies take more steps to resolve. Specifically, DyPE dynamically adjusts the model's positional encoding at each diffusion step, matching their frequency spectrum with the current stage of the generative process. This approach allows us to generate images at resolutions that exceed the training resolution dramatically, e.g., 16 million pixels using FLUX. On multiple benchmarks, DyPE consistently improves performance and achieves state-of-the-art fidelity in ultra-high-resolution image generation, with gains becoming even more pronounced at higher resolutions. Project page is available at https://noamissachar.github.io/DyPE/.

---

### MEIcoder: Decoding Visual Stimuli from Neural Activity by Leveraging Most Exciting Inputs

Authors: Jan Sobotka, Luca Baroni, Ján Antolík
Published: 2025-10-23
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2510.20762v1

Decoding visual stimuli from neural population activity is crucial for understanding the brain and for applications in brain-machine interfaces. However, such biological data is often scarce, particularly in primates or humans, where high-throughput recording techniques, such as two-photon imaging, remain challenging or impossible to apply. This, in turn, poses a challenge for deep learning decoding techniques. To overcome this, we introduce MEIcoder, a biologically informed decoding method that leverages neuron-specific most exciting inputs (MEIs), a structural similarity index measure loss, and adversarial training. MEIcoder achieves state-of-the-art performance in reconstructing visual stimuli from single-cell activity in primary visual cortex (V1), especially excelling on small datasets with fewer recorded neurons. Using ablation studies, we demonstrate that MEIs are the main drivers of the performance, and in scaling experiments, we show that MEIcoder can reconstruct high-fidelity natural-looking images from as few as 1,000-2,500 neurons and less than 1,000 training data points. We also propose a unified benchmark with over 160,000 samples to foster future research. Our results demonstrate the feasibility of reliable decoding in early visual system and provide practical insights for neuroscience and neuroengineering applications.

---

### Incomplete U-Statistics of Equireplicate Designs: Berry-Esseen Bound and Efficient Construction

Authors: Cesare Miglioli, Jordan Awan
Published: 2025-10-23
Categories: math.ST, math.CO, stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2510.20755v4

U-statistics are a fundamental class of estimators that generalize the sample mean and underpin much of nonparametric statistics. Although extensively studied in both statistics and probability, key challenges remain: their high computational cost - addressed partly through incomplete U-statistics - and their non-standard asymptotic behavior in the degenerate case, which typically requires resampling methods for hypothesis testing. This paper presents a novel perspective on U-statistics, grounded in hypergraph theory and combinatorial designs. Our approach bypasses the traditional Hoeffding decomposition, the main analytical tool in this literature but one that is highly sensitive to degeneracy. By characterizing the dependence structure of a U-statistic, we derive a Berry-Esseen bound valid for incomplete U-statistics of deterministic designs, yielding conditions under which Gaussian limiting distributions can be established even in degenerate cases and when the order diverges. We also introduce efficient algorithms to construct incomplete U-statistics based on equireplicate designs, a subclass of deterministic designs that, in certain cases, achieve minimum variance. Beyond its theoretical contributions, our framework provides a systematic way to construct permutation-free counterparts to tests based on degenerate U-statistics, as demonstrated in experiments with kernel-based tests using the Maximum Mean Discrepancy and the Hilbert-Schmidt Independence Criterion.

---

### Incomplete U-Statistics of Equireplicate Designs: Berry-Esseen Bound and Efficient Construction

Authors: Cesare Miglioli, Jordan Awan
Published: 2025-10-23
Categories: math.ST, math.CO, stat.ME, stat.ML, stat.TH
arXiv: https://arxiv.org/abs/2510.20755v1

U-statistics are a fundamental class of estimators that generalize the sample mean and underpin much of nonparametric statistics. Although extensively studied in both statistics and probability, key challenges remain: their high computational cost - addressed partly through incomplete U-statistics - and their non-standard asymptotic behavior in the degenerate case, which typically requires resampling methods for hypothesis testing. This paper presents a novel perspective on U-statistics, grounded in hypergraph theory and combinatorial designs. Our approach bypasses the traditional Hoeffding decomposition, the main analytical tool in this literature but one highly sensitive to degeneracy. By characterizing the dependence structure of a U-statistic, we derive a Berry-Esseen bound that applies to all incomplete U-statistics of deterministic designs, yielding conditions under which Gaussian limiting distributions can be established even in the degenerate case and when the order diverges. We also introduce efficient algorithms to construct incomplete U-statistics of equireplicate designs, a subclass of deterministic designs that, in certain cases, achieve minimum variance. Finally, we apply our framework to kernel-based tests that use Maximum Mean Discrepancy (MMD) and Hilbert-Schmidt Independence Criterion. In a real data example with CIFAR-10, our permutation-free MMD test delivers substantial computational gains while retaining power and type I error control.

---

### ACS-SegNet: An Attention-Based CNN-SegFormer Segmentation Network for Tissue Segmentation in Histopathology

Authors: Nima Torbati, Anastasia Meshcheryakova, Ramona Woitek, Diana Mechtcheriakova, Amirreza Mahbod
Published: 2025-10-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.20754v1

Automated histopathological image analysis plays a vital role in computer-aided diagnosis of various diseases. Among developed algorithms, deep learning-based approaches have demonstrated excellent performance in multiple tasks, including semantic tissue segmentation in histological images. In this study, we propose a novel approach based on attention-driven feature fusion of convolutional neural networks (CNNs) and vision transformers (ViTs) within a unified dual-encoder model to improve semantic segmentation performance. Evaluation on two publicly available datasets showed that our model achieved μIoU/μDice scores of 76.79%/86.87% on the GCPS dataset and 64.93%/76.60% on the PUMA dataset, outperforming state-of-the-art and baseline benchmarks. The implementation of our method is publicly available in a GitHub repository: https://github.com/NimaTorbati/ACS-SegNet

---

### Reinforcement Learning and Consumption-Savings Behavior

Authors: Brandon Gary Kaplowitz
Published: 2025-10-23
Categories: econ.GN, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.20748v3

This paper demonstrates how reinforcement learning can explain two puzzling empirical patterns in household consumption behavior during economic downturns. I develop a model where agents use Q-learning with neural network approximation to make consumption-savings decisions under income uncertainty, departing from standard rational expectations assumptions. The model replicates two key findings from recent literature: (1) unemployed households with previously low liquid assets exhibit substantially higher marginal propensities to consume (MPCs) out of stimulus transfers compared to high-asset households (0.50 vs 0.34), even when neither group faces borrowing constraints, consistent with Ganong et al. (2024); and (2) households with more past unemployment experiences maintain persistently lower consumption levels after controlling for current economic conditions, a "scarring" effect documented by Malmendier and Shen (2024). Unlike existing explanations based on belief updating about income risk or ex-ante heterogeneity, the reinforcement learning mechanism generates both higher MPCs and lower consumption levels simultaneously through value function approximation errors that evolve with experience. Simulation results closely match the empirical estimates, suggesting that adaptive learning through reinforcement learning provides a unifying framework for understanding how past experiences shape current consumption behavior beyond what current economic conditions would predict.

---

### Reinforcement Learning and Consumption-Savings Behavior

Authors: Brandon Kaplowitz
Published: 2025-10-23
Categories: econ.GN, cs.AI, cs.LG, q-fin.EC
arXiv: https://arxiv.org/abs/2510.20748v1

This paper demonstrates how reinforcement learning can explain two puzzling empirical patterns in household consumption behavior during economic downturns. I develop a model where agents use Q-learning with neural network approximation to make consumption-savings decisions under income uncertainty, departing from standard rational expectations assumptions. The model replicates two key findings from recent literature: (1) unemployed households with previously low liquid assets exhibit substantially higher marginal propensities to consume (MPCs) out of stimulus transfers compared to high-asset households (0.50 vs 0.34), even when neither group faces borrowing constraints, consistent with Ganong et al. (2024); and (2) households with more past unemployment experiences maintain persistently lower consumption levels after controlling for current economic conditions, a "scarring" effect documented by Malmendier and Shen (2024). Unlike existing explanations based on belief updating about income risk or ex-ante heterogeneity, the reinforcement learning mechanism generates both higher MPCs and lower consumption levels simultaneously through value function approximation errors that evolve with experience. Simulation results closely match the empirical estimates, suggesting that adaptive learning through reinforcement learning provides a unifying framework for understanding how past experiences shape current consumption behavior beyond what current economic conditions would predict.

---

### Empathic Prompting: Non-Verbal Context Integration for Multimodal LLM Conversations

Authors: Lorenzo Stacchio, Andrea Ubaldi, Alessandro Galdelli, Maurizio Mauri, Emanuele Frontoni, Andrea Gaggioli
Published: 2025-10-23
Categories: cs.HC, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.20743v2

We present Empathic Prompting, a novel framework for multimodal human-AI interaction that enriches Large Language Model (LLM) conversations with implicit non-verbal context. The system integrates a commercial facial expression recognition service to capture users' emotional cues and embeds them as contextual signals during prompting. Unlike traditional multimodal interfaces, empathic prompting requires no explicit user control; instead, it unobtrusively augments textual input with affective information for conversational and smoothness alignment. The architecture is modular and scalable, allowing integration of additional non-verbal modules. We describe the system design, implemented through a locally deployed DeepSeek instance, and report a preliminary service and usability evaluation (N=5). Results show consistent integration of non-verbal input into coherent LLM outputs, with participants highlighting conversational fluidity. Beyond this proof of concept, empathic prompting points to applications in chatbot-mediated communication, particularly in domains like healthcare or education, where users' emotional signals are critical yet often opaque in verbal exchanges.

---

### Empathic Prompting: Non-Verbal Context Integration for Multimodal LLM Conversations

Authors: Lorenzo Stacchio, Andrea Ubaldi, Alessandro Galdelli, Maurizio Mauri, Emanuele Frontoni, Andrea Gaggioli
Published: 2025-10-23
Categories: cs.HC, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.20743v1

We present Empathic Prompting, a novel framework for multimodal human-AI interaction that enriches Large Language Model (LLM) conversations with implicit non-verbal context. The system integrates a commercial facial expression recognition service to capture users' emotional cues and embeds them as contextual signals during prompting. Unlike traditional multimodal interfaces, empathic prompting requires no explicit user control; instead, it unobtrusively augments textual input with affective information for conversational and smoothness alignment. The architecture is modular and scalable, allowing integration of additional non-verbal modules. We describe the system design, implemented through a locally deployed DeepSeek instance, and report a preliminary service and usability evaluation (N=5). Results show consistent integration of non-verbal input into coherent LLM outputs, with participants highlighting conversational fluidity. Beyond this proof of concept, empathic prompting points to applications in chatbot-mediated communication, particularly in domains like healthcare or education, where users' emotional signals are critical yet often opaque in verbal exchanges.

---

### Learning to Triage Vulnerability Reports from Program Analysis: An Empirical Study in Node.js

Authors: Ronghao Ni, Aidan Z. H. Yang, Min-Chien Hsu, Nuno Sabino, Limin Jia, Ruben Martins, Darion Cassel, Kevin Cheang
Published: 2025-10-23
Categories: cs.CR, cs.LG, cs.SE
arXiv: https://arxiv.org/abs/2510.20739v2

Program analysis tools often produce large volumes of candidate vulnerability reports that require costly manual review, creating a practical challenge: how can security analysts prioritize the reports most likely to be true vulnerabilities? This paper investigates whether machine learning can be applied to prioritizing vulnerabilities reported by program analysis tools. We focus on Node$.$js packages and collect a benchmark of 1,883 Node$.$js packages, each containing one reported ACE or ACI vulnerability. We evaluate a variety of machine learning approaches, including classical models, graph neural networks (GNNs), large language models (LLMs), and hybrid models that combine GNNs and LLMs, trained on data derived from program analysis tool outputs (NodeMedic-FINE in our case study). The top LLM achieves $F_{1}{=}0.915$, while the best provenance-graph-based method achieves $F_{1}{=}0.904$. On the reports that the upstream tool flags but cannot automatically confirm, at a target of recovering 90% of the exploitable reports, the leading model eliminates 75% of the benign reports from manual review. If the best model is tuned to operate at a precision level of 0.8 (i.e., allowing 20% false positives among all warnings), our approach can report 99.2% of exploitable taint flows while missing only 0.8%, demonstrating strong potential for real-world vulnerability triage.

---

### Learning to Triage Taint Flows Reported by Dynamic Program Analysis in Node.js Packages

Authors: Ronghao Ni, Aidan Z. H. Yang, Min-Chien Hsu, Nuno Sabino, Limin Jia, Ruben Martins, Darion Cassel, Kevin Cheang
Published: 2025-10-23
Categories: cs.CR, cs.LG, cs.SE
arXiv: https://arxiv.org/abs/2510.20739v1

Program analysis tools often produce large volumes of candidate vulnerability reports that require costly manual review, creating a practical challenge: how can security analysts prioritize the reports most likely to be true vulnerabilities? This paper investigates whether machine learning can be applied to prioritizing vulnerabilities reported by program analysis tools. We focus on Node.js packages and collect a benchmark of 1,883 Node.js packages, each containing one reported ACE or ACI vulnerability. We evaluate a variety of machine learning approaches, including classical models, graph neural networks (GNNs), large language models (LLMs), and hybrid models that combine GNN and LLMs, trained on data based on a dynamic program analysis tool's output. The top LLM achieves $F_{1} {=} 0.915$, while the best GNN and classical ML models reaching $F_{1} {=} 0.904$. At a less than 7% false-negative rate, the leading model eliminates 66.9% of benign packages from manual review, taking around 60 ms per package. If the best model is tuned to operate at a precision level of 0.8 (i.e., allowing 20% false positives amongst all warnings), our approach can detect 99.2% of exploitable taint flows while missing only 0.8%, demonstrating strong potential for real-world vulnerability triage.

---

### Amplifying Prominent Representations in Multimodal Learning via Variational Dirichlet Process

Authors: Tsai Hor Chan, Feng Wu, Yihang Chen, Guosheng Yin, Lequan Yu
Published: 2025-10-23
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.20736v1

Developing effective multimodal fusion approaches has become increasingly essential in many real-world scenarios, such as health care and finance. The key challenge is how to preserve the feature expressiveness in each modality while learning cross-modal interactions. Previous approaches primarily focus on the cross-modal alignment, while over-emphasis on the alignment of marginal distributions of modalities may impose excess regularization and obstruct meaningful representations within each modality. The Dirichlet process (DP) mixture model is a powerful Bayesian non-parametric method that can amplify the most prominent features by its richer-gets-richer property, which allocates increasing weights to them. Inspired by this unique characteristic of DP, we propose a new DP-driven multimodal learning framework that automatically achieves an optimal balance between prominent intra-modal representation learning and cross-modal alignment. Specifically, we assume that each modality follows a mixture of multivariate Gaussian distributions and further adopt DP to calculate the mixture weights for all the components. This paradigm allows DP to dynamically allocate the contributions of features and select the most prominent ones, leveraging its richer-gets-richer property, thus facilitating multimodal feature fusion. Extensive experiments on several multimodal datasets demonstrate the superior performance of our model over other competitors. Ablation analysis further validates the effectiveness of DP in aligning modality distributions and its robustness to changes in key hyperparameters. Code is anonymously available at https://github.com/HKU-MedAI/DPMM.git

---

### Thought Communication in Multiagent Collaboration

Authors: Yujia Zheng, Zhuokai Zhao, Zijian Li, Yaqi Xie, Mingze Gao, Lizhu Zhang, Kun Zhang
Published: 2025-10-23
Categories: cs.LG, cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2510.20733v1

Natural language has long enabled human cooperation, but its lossy, ambiguous, and indirect nature limits the potential of collective intelligence. While machines are not subject to these constraints, most LLM-based multi-agent systems still rely solely on natural language, exchanging tokens or their embeddings. To go beyond language, we introduce a new paradigm, thought communication, which enables agents to interact directly mind-to-mind, akin to telepathy. To uncover these latent thoughts in a principled way, we formalize the process as a general latent variable model, where agent states are generated by an unknown function of underlying thoughts. We prove that, in a nonparametric setting without auxiliary information, both shared and private latent thoughts between any pair of agents can be identified. Moreover, the global structure of thought sharing, including which agents share which thoughts and how these relationships are structured, can also be recovered with theoretical guarantees. Guided by the established theory, we develop a framework that extracts latent thoughts from all agents prior to communication and assigns each agent the relevant thoughts, along with their sharing patterns. This paradigm naturally extends beyond LLMs to all modalities, as most observational data arise from hidden generative processes. Experiments on both synthetic and real-world benchmarks validate the theory and demonstrate the collaborative advantages of thought communication. We hope this work illuminates the potential of leveraging the hidden world, as many challenges remain unsolvable through surface-level observation alone, regardless of compute or data scale.

---

### Co-Designing Quantum Codes with Transversal Diagonal Gates via Multi-Agent Systems

Authors: Xi He, Sirui Lu, Bei Zeng
Published: 2025-10-23
Categories: quant-ph, cs.AI, cs.CL, math-ph
arXiv: https://arxiv.org/abs/2510.20728v3

Exact scientific discovery requires more than heuristic search: candidate constructions must be turned into exact objects and checked independently. We address this gap by extending TeXRA with an independent Lean 4 verification layer, turning it into a human-guided multi-agent platform for exact scientific discovery. The platform couples symbolic synthesis, combinatorial and linear-programming search, exact reconstruction of numerical candidates, and formal verification in Lean. We apply this platform to nonadditive quantum error-correcting codes with prescribed transversal diagonal gates within the subset-sum linear-programming (SSLP) framework. In the distance-2 regime where logical states occupy distinct residue classes, the platform yields a Lean-certified catalogue of 14,116 codes for $K\in\{2,3,4\}$ and up to six physical qubits, realizing cyclic logical orders 2 through 18, from which we extract closed-form infinite families. We also construct a residue-degenerate $((6,4,2))$ code implementing the logical controlled-phase gate $\mathrm{diag}(1,1,1,i)$. At distance 3, we resolve the transversal-$T$ problem for $((7,2,3))$ codes within the complementary binary-dihedral $\mathrm{BD}_{16}$ setting: among the 12 candidates surviving the SSLP filters, 10 admit exact realizations and 2 are excluded by no-go proofs. All accepted constructions, families, and no-go results are formalized and checked in Lean, illustrating how AI-assisted workflows can bridge search, exact reconstruction, and formal proof in the physical sciences.

---

### Co-Designing Quantum Codes with Transversal Diagonal Gates via Multi-Agent Systems

Authors: Xi He, Sirui Lu, Bei Zeng
Published: 2025-10-23
Categories: quant-ph, cs.AI, cs.CL, math-ph, math.MP
arXiv: https://arxiv.org/abs/2510.20728v1

We present a multi-agent, human-in-the-loop workflow that co-designs quantum codes with prescribed transversal diagonal gates. It builds on the Subset-Sum Linear Programming (SSLP) framework (arXiv:2504.20847), which partitions basis strings by modular residues and enforces $Z$-marginal Knill-Laflamme (KL) equalities via small LPs. The workflow is powered by GPT-5 and implemented within TeXRA (https://texra.ai)-a multi-agent research assistant platform that supports an iterative tool-use loop agent and a derivation-then-edit workflow reasoning agent. We work in a LaTeX-Python environment where agents reason, edit documents, execute code, and synchronize their work to Git/Overleaf. Within this workspace, three roles collaborate: a Synthesis Agent formulates the problem; a Search Agent sweeps/screens candidates and exactifies numerics into rationals; and an Audit Agent independently checks all KL equalities and the induced logical action. As a first step we focus on distance $d=2$ with nondegenerate residues. For code dimension $K\in\{2,3,4\}$ and $n\le6$ qubits, systematic sweeps yield certificate-backed tables cataloging attainable cyclic logical groups-all realized by new codes-e.g., for $K=3$ we obtain order $16$ at $n=6$. From verified instances, Synthesis Agent abstracts recurring structures into closed-form families and proves they satisfy the KL equalities for all parameters. It further demonstrates that SSLP accommodates residue degeneracy by exhibiting a new $((6,4,2))$ code implementing the transversal controlled-phase $diag(1,1,1,i)$. Overall, the workflow recasts diagonal-transversal feasibility as an analytical pipeline executed at scale, combining systematic enumeration with exact analytical reconstruction. It yields reproducible code constructions, supports targeted extensions to larger $K$ and higher distances, and leads toward data-driven classification.

---

### Automated Extraction of Fluoropyrimidine Treatment and Treatment-Related Toxicities from Clinical Notes Using Natural Language Processing

Authors: Xizhi Wu, Madeline S. Kreider, Philip E. Empey, Chenyu Li, Yanshan Wang
Published: 2025-10-23
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.20727v1

Objective: Fluoropyrimidines are widely prescribed for colorectal and breast cancers, but are associated with toxicities such as hand-foot syndrome and cardiotoxicity. Since toxicity documentation is often embedded in clinical notes, we aimed to develop and evaluate natural language processing (NLP) methods to extract treatment and toxicity information. Materials and Methods: We constructed a gold-standard dataset of 236 clinical notes from 204,165 adult oncology patients. Domain experts annotated categories related to treatment regimens and toxicities. We developed rule-based, machine learning-based (Random Forest, Support Vector Machine (SVM), Logistic Regression (LR)), deep learning-based (BERT, ClinicalBERT), and large language models (LLM)-based NLP approaches (zero-shot and error-analysis prompting). Models used an 80:20 train-test split. Results: Sufficient data existed to train and evaluate 5 annotated categories. Error-analysis prompting achieved optimal precision, recall, and F1 scores (F1=1.000) for treatment and toxicities extraction, whereas zero-shot prompting reached F1=1.000 for treatment and F1=0.876 for toxicities extraction.LR and SVM ranked second for toxicities (F1=0.937). Deep learning underperformed, with BERT (F1=0.873 treatment; F1= 0.839 toxicities) and ClinicalBERT (F1=0.873 treatment; F1 = 0.886 toxicities). Rule-based methods served as our baseline with F1 scores of 0.857 in treatment and 0.858 in toxicities. Discussion: LMM-based approaches outperformed all others, followed by machine learning methods. Machine and deep learning approaches were limited by small training data and showed limited generalizability, particularly for rare categories. Conclusion: LLM-based NLP most effectively extracted fluoropyrimidine treatment and toxicity information from clinical notes, and has strong potential to support oncology research and pharmacovigilance.

---

### AutoScape: Geometry-Consistent Long-Horizon Scene Generation

Authors: Jiacheng Chen, Ziyu Jiang, Mingfu Liang, Bingbing Zhuang, Jong-Chyi Su, Sparsh Garg, Ying Wu, Manmohan Chandraker
Published: 2025-10-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.20726v1

This paper proposes AutoScape, a long-horizon driving scene generation framework. At its core is a novel RGB-D diffusion model that iteratively generates sparse, geometrically consistent keyframes, serving as reliable anchors for the scene's appearance and geometry. To maintain long-range geometric consistency, the model 1) jointly handles image and depth in a shared latent space, 2) explicitly conditions on the existing scene geometry (i.e., rendered point clouds) from previously generated keyframes, and 3) steers the sampling process with a warp-consistent guidance. Given high-quality RGB-D keyframes, a video diffusion model then interpolates between them to produce dense and coherent video frames. AutoScape generates realistic and geometrically consistent driving videos of over 20 seconds, improving the long-horizon FID and FVD scores over the prior state-of-the-art by 48.6\% and 43.0\%, respectively.

---

### No-Regret Thompson Sampling for Finite-Horizon Markov Decision Processes with Gaussian Processes

Authors: Jasmine Bayrooti, Sattar Vakili, Amanda Prorok, Carl Henrik Ek
Published: 2025-10-23
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.20725v1

Thompson sampling (TS) is a powerful and widely used strategy for sequential decision-making, with applications ranging from Bayesian optimization to reinforcement learning (RL). Despite its success, the theoretical foundations of TS remain limited, particularly in settings with complex temporal structure such as RL. We address this gap by establishing no-regret guarantees for TS using models with Gaussian marginal distributions. Specifically, we consider TS in episodic RL with joint Gaussian process (GP) priors over rewards and transitions. We prove a regret bound of $\mathcal{\tilde{O}}(\sqrt{KHΓ(KH)})$ over $K$ episodes of horizon $H$, where $Γ(\cdot)$ captures the complexity of the GP model. Our analysis addresses several challenges, including the non-Gaussian nature of value functions and the recursive structure of Bellman updates, and extends classical tools such as the elliptical potential lemma to multi-output settings. This work advances the understanding of TS in RL and highlights how structural assumptions and model uncertainty shape its performance in finite-horizon Markov Decision Processes.

---

### User Perceptions vs. Proxy LLM Judges: Privacy and Helpfulness in LLM Responses to Privacy-Sensitive Scenarios

Authors: Xiaoyuan Wu, Roshni Kaushik, Wenkai Li, Lujo Bauer, Koichi Onoue
Published: 2025-10-23
Categories: cs.CL, cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2510.20721v4

Large language models (LLMs) are rapidly being adopted for tasks like drafting emails, summarizing meetings, and answering health questions. In these settings, users may need to share private information (e.g., contact details, health records). To evaluate LLMs' ability to identify and redact such information, prior work introduced real-life, scenario-based benchmarks (e.g., ConfAIde, PrivacyLens) and found that LLMs can leak private information in complex scenarios. However, these evaluations relied on proxy LLMs to judge the helpfulness and privacy-preservation quality of LLM responses, rather than directly measuring users' perceptions. To understand how users perceive the helpfulness and privacy-preservation quality of LLM responses to privacy-sensitive scenarios, we conducted a user study ($n=94$) using 90 PrivacyLens scenarios. We found that users had low agreement with each other when evaluating identical LLM responses. In contrast, five proxy LLMs reached high agreement, yet each proxy LLM had low correlation with users' evaluations. These results indicate that proxy LLMs cannot accurately estimate users' wide range of perceptions of utility and privacy in privacy-sensitive scenarios. We discuss the need for more user-centered studies to measure LLMs' ability to help users while preserving privacy, and for improving alignment between LLMs and users in estimating perceived privacy and utility.

---

### User Perceptions of Privacy and Helpfulness in LLM Responses to Privacy-Sensitive Scenarios

Authors: Xiaoyuan Wu, Roshni Kaushik, Wenkai Li, Lujo Bauer, Koichi Onoue
Published: 2025-10-23
Categories: cs.CL, cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2510.20721v1

Large language models (LLMs) have seen rapid adoption for tasks such as drafting emails, summarizing meetings, and answering health questions. In such uses, users may need to share private information (e.g., health records, contact details). To evaluate LLMs' ability to identify and redact such private information, prior work developed benchmarks (e.g., ConfAIde, PrivacyLens) with real-life scenarios. Using these benchmarks, researchers have found that LLMs sometimes fail to keep secrets private when responding to complex tasks (e.g., leaking employee salaries in meeting summaries). However, these evaluations rely on LLMs (proxy LLMs) to gauge compliance with privacy norms, overlooking real users' perceptions. Moreover, prior work primarily focused on the privacy-preservation quality of responses, without investigating nuanced differences in helpfulness. To understand how users perceive the privacy-preservation quality and helpfulness of LLM responses to privacy-sensitive scenarios, we conducted a user study with 94 participants using 90 scenarios from PrivacyLens. We found that, when evaluating identical responses to the same scenario, users showed low agreement with each other on the privacy-preservation quality and helpfulness of the LLM response. Further, we found high agreement among five proxy LLMs, while each individual LLM had low correlation with users' evaluations. These results indicate that the privacy and helpfulness of LLM responses are often specific to individuals, and proxy LLMs are poor estimates of how real users would perceive these responses in privacy-sensitive scenarios. Our results suggest the need to conduct user-centered studies on measuring LLMs' ability to help users while preserving privacy. Additionally, future research could investigate ways to improve the alignment between proxy LLMs and users for better estimation of users' perceived privacy and utility.

---

### Unsupervised Anomaly Prediction with N-BEATS and Graph Neural Network in Multi-variate Semiconductor Process Time Series

Authors: Daniel Sorensen, Bappaditya Dey, Minjin Hwang, Sandip Halder
Published: 2025-10-23
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.20718v1

Semiconductor manufacturing is an extremely complex and precision-driven process, characterized by thousands of interdependent parameters collected across diverse tools and process steps. Multi-variate time-series analysis has emerged as a critical field for real-time monitoring and fault detection in such environments. However, anomaly prediction in semiconductor fabrication presents several critical challenges, including high dimensionality of sensor data and severe class imbalance due to the rarity of true faults. Furthermore, the complex interdependencies between variables complicate both anomaly prediction and root-cause-analysis. This paper proposes two novel approaches to advance the field from anomaly detection to anomaly prediction, an essential step toward enabling real-time process correction and proactive fault prevention. The proposed anomaly prediction framework contains two main stages: (a) training a forecasting model on a dataset assumed to contain no anomalies, and (b) performing forecast on unseen time series data. The forecast is compared with the forecast of the trained signal. Deviations beyond a predefined threshold are flagged as anomalies. The two approaches differ in the forecasting model employed. The first assumes independence between variables by utilizing the N-BEATS model for univariate time series forecasting. The second lifts this assumption by utilizing a Graph Neural Network (GNN) to capture inter-variable relationships. Both models demonstrate strong forecasting performance up to a horizon of 20 time points and maintain stable anomaly prediction up to 50 time points. The GNN consistently outperforms the N-BEATS model while requiring significantly fewer trainable parameters and lower computational cost. These results position the GNN as promising solution for online anomaly forecasting to be deployed in manufacturing environments.

---

### An interpretable data-driven approach to optimizing clinical fall risk assessment

Authors: Fardin Ganjkhanloo, Emmett Springer, Erik H. Hoyer, Daniel L. Young, Kimia Ghobadi
Published: 2025-10-23
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.20714v2

In this study we aim to better align fall risk prediction from the Johns Hopkins Fall Risk Assessment Tool (JHFRAT) with additional clinically meaningful measures via a data-driven modelling approach. We conducted a retrospective analysis of 54,209 inpatient admissions from three Johns Hopkins Health System hospitals between March 2022 and October 2023. A total of 20,208 admissions were included as high fall risk encounters, and 13,941 were included as low fall risk encounters. To incorporate clinical knowledge and maintain interpretability, we employed constrained score optimization (CSO) models on JHFRAT assessment data and additional electronic health record (EHR) variables. The model demonstrated significant improvements in predictive performance over the current JHFRAT (CSO AUC-ROC=0.91, JHFRAT AUC-ROC=0.86). The constrained score optimization models performed similarly with and without the EHR variables. Although the benchmark black-box model (XGBoost), improves upon the performance metrics of the knowledge-based constrained logistic regression (AUC-ROC=0.94), the CSO demonstrates more robustness to variations in risk labelling. This evidence-based approach provides a robust foundation for health systems to systematically enhance inpatient fall prevention protocols and patient safety using data-driven optimization techniques, contributing to improved risk assessment and resource allocation in healthcare settings.

---

### Optimizing Clinical Fall Risk Prediction: A Data-Driven Integration of EHR Variables with the Johns Hopkins Fall Risk Assessment Tool

Authors: Fardin Ganjkhanloo, Emmett Springer, Erik H. Hoyer, Daniel L. Young, Kimia Ghobadi
Published: 2025-10-23
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.20714v1

In this study we aim to better align fall risk prediction from the Johns Hopkins Fall Risk Assessment Tool (JHFRAT) with additional clinically meaningful measures via a data-driven modelling approach. We conducted a retrospective analysis of 54,209 inpatient admissions from three Johns Hopkins Health System hospitals between March 2022 and October 2023. A total of 20,208 admissions were included as high fall risk encounters, and 13,941 were included as low fall risk encounters. To incorporate clinical knowledge and maintain interpretability, we employed constrained score optimization (CSO) models on JHFRAT assessment data and additional electronic health record (EHR) variables. The model demonstrated significant improvements in predictive performance over the current JHFRAT (CSO AUC-ROC=0.91, JHFRAT AUC-ROC=0.86). The constrained score optimization models performed similarly with and without the EHR variables. Although the benchmark black-box model (XGBoost), improves upon the performance metrics of the knowledge-based constrained logistic regression (AUC-ROC=0.94), the CSO demonstrates more robustness to variations in risk labelling. This evidence-based approach provides a robust foundation for health systems to systematically enhance inpatient fall prevention protocols and patient safety using data-driven optimization techniques, contributing to improved risk assessment and resource allocation in healthcare settings.

---

### Experimental differentiation and extremization with analog quantum circuits

Authors: Evan Philip, Julius de Hond, Vytautas Abramavicius, Kaonan Micadei, Mario Dagrada, Panagiotis Barkoutsos, Mourad Beji, Louis-Paul Henry, Vincent E. Elfving, Antonio A. Gentile, Savvas Varsamopoulos
Published: 2025-10-23
Categories: quant-ph, cs.NE
arXiv: https://arxiv.org/abs/2510.20713v1

Solving and optimizing differential equations (DEs) is ubiquitous in both engineering and fundamental science. The promise of quantum architectures to accelerate scientific computing thus naturally involved interest towards how efficiently quantum algorithms can solve DEs. Differentiable quantum circuits (DQC) offer a viable route to compute DE solutions using a variational approach amenable to existing quantum computers, by producing a machine-learnable surrogate of the solution. Quantum extremal learning (QEL) complements such approach by finding extreme points in the output of learnable models of unknown (implicit) functions, offering a powerful tool to bypass a full DE solution, in cases where the crux consists in retrieving solution extrema. In this work, we provide the results from the first experimental demonstration of both DQC and QEL, displaying their performance on a synthetic usecase. Whilst both DQC and QEL are expected to require digital quantum hardware, we successfully challenge this assumption by running a closed-loop instance on a commercial analog quantum computer, based upon neutral atom technology.

---

### Separating the what and how of compositional computation to enable reuse and continual learning

Authors: Haozhe Shan, Sun Minni, Lea Duncker
Published: 2025-10-23
Categories: cs.LG, q-bio.NC
arXiv: https://arxiv.org/abs/2510.20709v1

The ability to continually learn, retain and deploy skills to accomplish goals is a key feature of intelligent and efficient behavior. However, the neural mechanisms facilitating the continual learning and flexible (re-)composition of skills remain elusive. Here, we study continual learning and the compositional reuse of learned computations in recurrent neural network (RNN) models using a novel two-system approach: one system that infers what computation to perform, and one that implements how to perform it. We focus on a set of compositional cognitive tasks commonly studied in neuroscience. To construct the what system, we first show that a large family of tasks can be systematically described by a probabilistic generative model, where compositionality stems from a shared underlying vocabulary of discrete task epochs. The shared epoch structure makes these tasks inherently compositional. We first show that this compositionality can be systematically described by a probabilistic generative model. Furthermore, We develop an unsupervised online learning approach that can learn this model on a single-trial basis, building its vocabulary incrementally as it is exposed to new tasks, and inferring the latent epoch structure as a time-varying computational context within a trial. We implement the how system as an RNN whose low-rank components are composed according to the context inferred by the what system. Contextual inference facilitates the creation, learning, and reuse of low-rank RNN components as new tasks are introduced sequentially, enabling continual learning without catastrophic forgetting. Using an example task set, we demonstrate the efficacy and competitive performance of this two-system learning framework, its potential for forward and backward transfer, as well as fast compositional generalization to unseen tasks.

---

### ALICE-LRI: A General Method for Lossless Range Image Generation for Spinning LiDAR Sensors without Calibration Metadata

Authors: Samuel Soutullo, Miguel Yermo, David L. Vilariño, Óscar G. Lorenzo, José C. Cabaleiro, Francisco F. Rivera
Published: 2025-10-23
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2510.20708v1

3D LiDAR sensors are essential for autonomous navigation, environmental monitoring, and precision mapping in remote sensing applications. To efficiently process the massive point clouds generated by these sensors, LiDAR data is often projected into 2D range images that organize points by their angular positions and distances. While these range image representations enable efficient processing, conventional projection methods suffer from fundamental geometric inconsistencies that cause irreversible information loss, compromising high-fidelity applications. We present ALICE-LRI (Automatic LiDAR Intrinsic Calibration Estimation for Lossless Range Images), the first general, sensor-agnostic method that achieves lossless range image generation from spinning LiDAR point clouds without requiring manufacturer metadata or calibration files. Our algorithm automatically reverse-engineers the intrinsic geometry of any spinning LiDAR sensor by inferring critical parameters including laser beam configuration, angular distributions, and per-beam calibration corrections, enabling lossless projection and complete point cloud reconstruction with zero point loss. Comprehensive evaluation across the complete KITTI and DurLAR datasets demonstrates that ALICE-LRI achieves perfect point preservation, with zero points lost across all point clouds. Geometric accuracy is maintained well within sensor precision limits, establishing geometric losslessness with real-time performance. We also present a compression case study that validates substantial downstream benefits, demonstrating significant quality improvements in practical applications. This paradigm shift from approximate to lossless LiDAR projections opens new possibilities for high-precision remote sensing applications requiring complete geometric preservation.

---

### Mixing Importance with Diversity: Joint Optimization for KV Cache Compression in Large Vision-Language Models

Authors: Xuyang Liu, Xiyan Gui, Yuchao Zhang, Linfeng Zhang
Published: 2025-10-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.20707v2

Recent large vision-language models (LVLMs) demonstrate remarkable capabilities in processing extended multi-modal sequences, yet the resulting key-value (KV) cache expansion creates a critical memory bottleneck that fundamentally limits deployment scalability. While existing KV cache compression methods focus on retaining high-importance KV pairs to minimize storage, they often overlook the modality-specific semantic redundancy patterns that emerge distinctively in multi-modal KV caches. In this work, we first analyze how, beyond simple importance, the KV cache in LVLMs exhibits varying levels of redundancy across attention heads. We show that relying solely on importance can only cover a subset of the full KV cache information distribution, leading to potential loss of semantic coverage. To address this, we propose MixKV, a novel method that mixes importance with diversity for optimized KV cache compression in LVLMs. MixKV adapts to head-wise semantic redundancy, selectively balancing diversity and importance when compressing KV pairs. Extensive experiments demonstrate that MixKV consistently enhances existing methods across multiple LVLMs. Under extreme compression (budget=64), MixKV improves baseline methods by an average of 5.1% across five multi-modal understanding benchmarks and achieves remarkable gains of 8.0% and 9.0% for SnapKV and AdaKV on GUI grounding tasks, all while maintaining comparable inference efficiency. Furthermore, MixKV extends seamlessly to LLMs with comparable performance gains. Our code is available at https://github.com/xuyang-liu16/MixKV.

---

### Mixing Importance with Diversity: Joint Optimization for KV Cache Compression in Large Vision-Language Models

Authors: Xuyang Liu, Xiyan Gui, Yuchao Zhang, Linfeng Zhang
Published: 2025-10-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.20707v1

Recent large vision-language models (LVLMs) demonstrate remarkable capabilities in processing extended multi-modal sequences, yet the resulting key-value (KV) cache expansion creates a critical memory bottleneck that fundamentally limits deployment scalability. While existing KV cache compression methods focus on retaining high-importance KV pairs to minimize storage, they often overlook the modality-specific semantic redundancy patterns that emerge distinctively in multi-modal KV caches. In this work, we first analyze how, beyond simple importance, the KV cache in LVLMs exhibits varying levels of redundancy across attention heads. We show that relying solely on importance can only cover a subset of the full KV cache information distribution, leading to potential loss of semantic coverage. To address this, we propose \texttt{MixKV}, a novel method that mixes importance with diversity for optimized KV cache compression in LVLMs. \texttt{MixKV} adapts to head-wise semantic redundancy, selectively balancing diversity and importance when compressing KV pairs. Extensive experiments demonstrate that \texttt{MixKV} consistently enhances existing methods across multiple LVLMs. Under extreme compression (budget=64), \texttt{MixKV} improves baseline methods by an average of \textbf{5.1\%} across five multi-modal understanding benchmarks and achieves remarkable gains of \textbf{8.0\%} and \textbf{9.0\%} for SnapKV and AdaKV on GUI grounding tasks, all while maintaining comparable inference efficiency. Furthermore, \texttt{MixKV} extends seamlessly to LLMs with comparable performance gains. Our code is available at \href{https://github.com/xuyang-liu16/MixKV}{\textcolor{citeblue}{https://github.com/xuyang-liu16/MixKV}}.

---

### Real-Time Gait Adaptation for Quadrupeds using Model Predictive Control and Reinforcement Learning

Authors: Prakrut Kotecha, Ganga Nair B, Shishir Kolathaya
Published: 2025-10-23
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2510.20706v2

Model-free reinforcement learning (RL) has enabled adaptable and agile quadruped locomotion; however, policies often converge to a single gait, leading to suboptimal performance. Traditionally, Model Predictive Control (MPC) has been extensively used to obtain task-specific optimal policies but lacks the ability to adapt to varying environments. To address these limitations, we propose an optimization framework for real-time gait adaptation in a continuous gait space, combining the Model Predictive Path Integral (MPPI) algorithm with a Dreamer module to produce adaptive and optimal policies for quadruped locomotion. At each time step, MPPI jointly optimizes the actions and gait variables using a learned Dreamer reward that promotes velocity tracking, energy efficiency, stability, and smooth transitions, while penalizing abrupt gait changes. A learned value function is incorporated as terminal reward, extending the formulation to an infinite-horizon planner. We evaluate our framework in simulation on the Unitree Go1, demonstrating an average reduction of up to 36.48 % in energy consumption across varying target speeds, while maintaining accurate tracking and adaptive, task-appropriate gaits.

---

### Real-Time Gait Adaptation for Quadrupeds using Model Predictive Control and Reinforcement Learning

Authors: Ganga Nair B, Prakrut Kotecha, Shishir Kolathaya
Published: 2025-10-23
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2510.20706v1

Model-free reinforcement learning (RL) has enabled adaptable and agile quadruped locomotion; however, policies often converge to a single gait, leading to suboptimal performance. Traditionally, Model Predictive Control (MPC) has been extensively used to obtain task-specific optimal policies but lacks the ability to adapt to varying environments. To address these limitations, we propose an optimization framework for real-time gait adaptation in a continuous gait space, combining the Model Predictive Path Integral (MPPI) algorithm with a Dreamer module to produce adaptive and optimal policies for quadruped locomotion. At each time step, MPPI jointly optimizes the actions and gait variables using a learned Dreamer reward that promotes velocity tracking, energy efficiency, stability, and smooth transitions, while penalizing abrupt gait changes. A learned value function is incorporated as terminal reward, extending the formulation to an infinite-horizon planner. We evaluate our framework in simulation on the Unitree Go1, demonstrating an average reduction of up to 36.48\% in energy consumption across varying target speeds, while maintaining accurate tracking and adaptive, task-appropriate gaits.

---

### Structure-Conditional Minimum Bayes Risk Decoding

Authors: Bryan Eikema, Anna Rutkiewicz, Mario Giulianelli
Published: 2025-10-23
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.20700v1

Minimum Bayes Risk (MBR) decoding has seen renewed interest as an alternative to traditional generation strategies. While MBR has proven effective in machine translation, where the variability of a language model's outcome space is naturally constrained, it may face challenges in more open-ended tasks such as dialogue or instruction-following. We hypothesise that in such settings, applying MBR with standard similarity-based utility functions may result in selecting responses that are broadly representative of the model's distribution, yet sub-optimal with respect to any particular grouping of generations that share an underlying latent structure. In this work, we introduce three lightweight adaptations to the utility function, designed to make MBR more sensitive to structural variability in the outcome space. To test our hypothesis, we curate a dataset capturing three representative types of latent structure: dialogue act, emotion, and response structure (e.g., a sentence, a paragraph, or a list). We further propose two metrics to evaluate the structural optimality of MBR. Our analysis demonstrates that common similarity-based utility functions fall short by these metrics. In contrast, our proposed adaptations considerably improve structural optimality. Finally, we evaluate our approaches on real-world instruction-following benchmarks, AlpacaEval and MT-Bench, and show that increased structural sensitivity improves generation quality by up to 13.7 percentage points in win rate.

---

### Fusing Narrative Semantics for Financial Volatility Forecasting

Authors: Yaxuan Kong, Yoontae Hwang, Marcus Kaiser, Chris Vryonides, Roel Oomen, Stefan Zohren
Published: 2025-10-23
Categories: q-fin.CP, cs.AI
arXiv: https://arxiv.org/abs/2510.20699v1

We introduce M2VN: Multi-Modal Volatility Network, a novel deep learning-based framework for financial volatility forecasting that unifies time series features with unstructured news data. M2VN leverages the representational power of deep neural networks to address two key challenges in this domain: (i) aligning and fusing heterogeneous data modalities, numerical financial data and textual information, and (ii) mitigating look-ahead bias that can undermine the validity of financial models. To achieve this, M2VN combines open-source market features with news embeddings generated by Time Machine GPT, a recently introduced point-in-time LLM, ensuring temporal integrity. An auxiliary alignment loss is introduced to enhance the integration of structured and unstructured data within the deep learning architecture. Extensive experiments demonstrate that M2VN consistently outperforms existing baselines, underscoring its practical value for risk management and financial decision-making in dynamic markets.

---

### Diagnosing Visual Reasoning: Challenges, Insights, and a Path Forward

Authors: Jing Bi, Guangyu Sun, Ali Vosoughi, Chen Chen, Chenliang Xu
Published: 2025-10-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.20696v1

Multimodal large language models (MLLMs) that integrate visual and textual reasoning leverage chain-of-thought (CoT) prompting to tackle complex visual tasks, yet continue to exhibit visual hallucinations and an over-reliance on textual priors. We present a systematic diagnosis of state-of-the-art vision-language models using a three-stage evaluation framework, uncovering key failure modes. To address these, we propose an agent-based architecture that combines LLM reasoning with lightweight visual modules, enabling fine-grained analysis and iterative refinement of reasoning chains. Our results highlight future visual reasoning models should focus on integrating a broader set of specialized tools for analyzing visual content. Our system achieves significant gains (+10.3 on MMMU, +6.0 on MathVista over a 7B baseline), matching or surpassing much larger models. We will release our framework and evaluation suite to facilitate future research.

---

### Neurosymbolic Characterization for Reliable Access Control Policy Analysis

Authors: Adarsh Vatsa, Bethel Hall, William Eiers
Published: 2025-10-23
Categories: cs.SE, cs.AI, cs.FL
arXiv: https://arxiv.org/abs/2510.20692v3

Access control policies are reliability-critical configuration artifacts in cloud systems, yet administrators frequently struggle to verify that a policy permits exactly what they intend. This verification gap cannot be remedied by using LLMs to synthesize policies: we find that reasoning and non-reasoning LLMs fluently explain policy behavior but cannot reason about policy semantics with reliability-grade precision, even when the specification is the LLM's own explanation. We formulate this impasse as the Verifiable Synthesis Paradox: the verification gap persists regardless of how the policy was authored. To remedy this, we introduce PolicySummarizer, a neurosymbolic tool that pairs finite-state automata with an LLM-based simplification to generate precise human-readable characterizations of requests allowed by a policy. PolicySummarizer uses model counting to guarantee the fidelity of the generated characterization by rejecting characterizations that fall below a user-configured threshold in favor of the formally derived one. On 546 AWS, 100 Microsoft Azure, and 100 Google Cloud Platform policies, PolicySummarizer achieves a mean similarity score of 0.93 and a 2.7x improvement over an SMT-based baseline. In a user study, PolicySummarizer raised policy-change-review accuracy from 39% to 93% on the hardest sub-task while reducing self-reported mental demand. We release PolicySummarizer as an open-source tool.

---

### Exploring Large Language Models for Access Control Policy Synthesis and Summarization

Authors: Adarsh Vatsa, Bethel Hall, William Eiers
Published: 2025-10-23
Categories: cs.SE, cs.AI, cs.FL, D.4.6; D.2.4; I.2.2; I.2.7; F.3.1; F.4.3
arXiv: https://arxiv.org/abs/2510.20692v1

Cloud computing is ubiquitous, with a growing number of services being hosted on the cloud every day. Typical cloud compute systems allow administrators to write policies implementing access control rules which specify how access to private data is governed. These policies must be manually written, and due to their complexity can often be error prone. Moreover, existing policies often implement complex access control specifications and thus can be difficult to precisely analyze in determining their behavior works exactly as intended. Recently, Large Language Models (LLMs) have shown great success in automated code synthesis and summarization. Given this success, they could potentially be used for automatically generating access control policies or aid in understanding existing policies. In this paper, we explore the effectiveness of LLMs for access control policy synthesis and summarization. Specifically, we first investigate diverse LLMs for access control policy synthesis, finding that: although LLMs can effectively generate syntactically correct policies, they have permissiveness issues, generating policies equivalent to the given specification 45.8% of the time for non-reasoning LLMs, and 93.7% of the time for reasoning LLMs. We then investigate how LLMs can be used to analyze policies by introducing a novel semantic-based request summarization approach which leverages LLMs to generate a precise characterization of the requests allowed by a policy. Our results show that while there are significant hurdles in leveraging LLMs for automated policy generation, LLMs show promising results when combined with symbolic approaches in analyzing existing policies.

---

### Plan Then Retrieve: Reinforcement Learning-Guided Complex Reasoning over Knowledge Graphs

Authors: Yanlin Song, Ben Liu, Víctor Gutiérrez-Basulto, Zhiwei Hu, Qianqian Xie, Min Peng, Sophia Ananiadou, Jeff Z. Pan
Published: 2025-10-23
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.20691v3

Knowledge Graph Question Answering aims to answer natural language questions by reasoning over structured knowledge graphs. While large language models have advanced KGQA through their strong reasoning capabilities, existing methods continue to struggle to fully exploit both the rich knowledge encoded in KGs and the reasoning capabilities of LLMs, particularly in complex scenarios. They often assume complete KG coverage and lack mechanisms to judge when external information is needed, and their reasoning remains locally myopic, failing to maintain coherent multi-step planning, leading to reasoning failures even when relevant knowledge exists. We propose Graph-RFT, a novel two-stage reinforcement fine-tuning KGQA framework with a 'plan-KGsearch-and-Websearch-during-think' paradigm, that enables LLMs to perform autonomous planning and adaptive retrieval scheduling across KG and web sources under incomplete knowledge conditions. Graph-RFT introduces a chain-of-thought fine-tuning method with a customized plan-retrieval dataset activates structured reasoning and resolves the GRPO cold-start problem. It then introduces a novel plan-retrieval guided reinforcement learning process integrates explicit planning and retrieval actions with a multi-reward design, enabling coverage-aware retrieval scheduling. It employs a Cartesian-inspired planning module to decompose complex questions into ordered subquestions, and logical expression to guide tool invocation for globally consistent multi-step reasoning. This reasoning retrieval process is optimized with a multi-reward combining outcome and retrieval specific signals, enabling the model to learn when and how to combine KG and web retrieval effectively.

---

### Plan Then Retrieve: Reinforcement Learning-Guided Complex Reasoning over Knowledge Graphs

Authors: Yanlin Song, Ben Liu, Víctor Gutiérrez-Basulto, Zhiwei Hu, Qianqian Xie, Min Peng, Sophia Ananiadou, Jeff Z. Pan
Published: 2025-10-23
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.20691v1

Knowledge Graph Question Answering aims to answer natural language questions by reasoning over structured knowledge graphs. While large language models have advanced KGQA through their strong reasoning capabilities, existing methods continue to struggle to fully exploit both the rich knowledge encoded in KGs and the reasoning capabilities of LLMs, particularly in complex scenarios. They often assume complete KG coverage and lack mechanisms to judge when external information is needed, and their reasoning remains locally myopic, failing to maintain coherent multi-step planning, leading to reasoning failures even when relevant knowledge exists. We propose Graph-RFT, a novel two-stage reinforcement fine-tuning KGQA framework with a 'plan-KGsearch-and-Websearch-during-think' paradigm, that enables LLMs to perform autonomous planning and adaptive retrieval scheduling across KG and web sources under incomplete knowledge conditions. Graph-RFT introduces a chain-of-thought fine-tuning method with a customized plan-retrieval dataset activates structured reasoning and resolves the GRPO cold-start problem. It then introduces a novel plan-retrieval guided reinforcement learning process integrates explicit planning and retrieval actions with a multi-reward design, enabling coverage-aware retrieval scheduling. It employs a Cartesian-inspired planning module to decompose complex questions into ordered subquestions, and logical expression to guide tool invocation for globally consistent multi-step reasoning. This reasoning retrieval process is optimized with a multi-reward combining outcome and retrieval specific signals, enabling the model to learn when and how to combine KG and web retrieval effectively.

---

### Neural Diversity Regularizes Hallucinations in Language Models

Authors: Kushal Chakrabarti, Nirmal Balachundhar
Published: 2025-10-23
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.20690v3

Language models continue to hallucinate despite increases in parameters, compute, and data. We propose neural diversity -- decorrelated parallel representations -- as a principled mechanism that reduces hallucination rates at fixed parameter and data budgets. While existing mitigation strategies largely target accuracy, we provide the first formal tail bounds for hallucination probability in ensembled language models, reframing it as a second-moment reliability problem and explaining 94.3% of empirical reliability variation seen across parallel configurations. We introduce ND-LoRA (Neural Diversity Low-Rank Adaptation), combining parallel LoRA adapters with Barlow Twins regularization, and reduce hallucinations by up to 25.6% (and 14.6% on average) while preserving general accuracy. Ablations show LoRA adapters and regularization act synergistically, causal interventions prove neurodiversity as the mediating factor and correlational studies indicate scale: a 0.1% neural correlation increase is associated with a 3.8% hallucination increase. Finally, task-dependent optimality emerges: different tasks require different optimal amounts of neurodiversity. Together, our results highlight neural diversity as a third axis of scaling -- orthogonal to parameters and data -- to improve the reliability of language models at fixed budgets.

---

### Neural Diversity Regularizes Hallucinations in Small Models

Authors: Kushal Chakrabarti, Nirmal Balachundhar
Published: 2025-10-23
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.20690v1

Language models continue to hallucinate despite increases in parameters, compute, and data. We propose neural diversity -- decorrelated parallel representations -- as a principled mechanism that reduces hallucination rates at fixed parameter and data budgets. Inspired by portfolio theory, where uncorrelated assets reduce risk by $\sqrt{P}$, we prove hallucination probability is bounded by representational correlation: $P(H) \leq f(\sigma^2((1-\rho(P))/P + \rho(P)), \mu^2)$, which predicts that language models need an optimal amount of neurodiversity. To validate this, we introduce ND-LoRA (Neural Diversity Low-Rank Adaptation), combining parallel LoRA adapters with Barlow Twins regularization, and demonstrate that ND-LoRA reduces hallucinations by up to 25.6% (and 14.6% on average) without degrading general accuracy. Ablations show LoRA adapters and regularization act synergistically, causal interventions prove neurodiversity as the mediating factor and correlational analyses indicate scale: a 0.1% neural correlation increase is associated with a 3.8% hallucination increase. Finally, task-dependent optimality emerges: different tasks require different amounts of optimal neurodiversity. Together, our results highlight neural diversity as a third axis of scaling -- orthogonal to parameters and data -- to improve the reliability of language models at fixed budgets.

---

### A Scalable, Causal, and Energy Efficient Framework for Neural Decoding with Spiking Neural Networks

Authors: Georgios Mentzelopoulos, Ioannis Asmanis, Konrad P. Kording, Eva L. Dyer, Kostas Daniilidis, Flavia Vitale
Published: 2025-10-23
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.20683v1

Brain-computer interfaces (BCIs) promise to enable vital functions, such as speech and prosthetic control, for individuals with neuromotor impairments. Central to their success are neural decoders, models that map neural activity to intended behavior. Current learning-based decoding approaches fall into two classes: simple, causal models that lack generalization, or complex, non-causal models that generalize and scale offline but struggle in real-time settings. Both face a common challenge, their reliance on power-hungry artificial neural network backbones, which makes integration into real-world, resource-limited systems difficult. Spiking neural networks (SNNs) offer a promising alternative. Because they operate causally these models are suitable for real-time use, and their low energy demands make them ideal for battery-constrained environments. To this end, we introduce Spikachu: a scalable, causal, and energy-efficient neural decoding framework based on SNNs. Our approach processes binned spikes directly by projecting them into a shared latent space, where spiking modules, adapted to the timing of the input, extract relevant features; these latent representations are then integrated and decoded to generate behavioral predictions. We evaluate our approach on 113 recording sessions from 6 non-human primates, totaling 43 hours of recordings. Our method outperforms causal baselines when trained on single sessions using between 2.26 and 418.81 times less energy. Furthermore, we demonstrate that scaling up training to multiple sessions and subjects improves performance and enables few-shot transfer to unseen sessions, subjects, and tasks. Overall, Spikachu introduces a scalable, online-compatible neural decoding framework based on SNNs, whose performance is competitive relative to state-of-the-art models while consuming orders of magnitude less energy.

---

### R2-SVC: Towards Real-World Robust and Expressive Zero-shot Singing Voice Conversion

Authors: Junjie Zheng, Gongyu Chen, Chaofan Ding, Zihao Chen
Published: 2025-10-23
Categories: cs.SD, cs.AI, eess.AS
arXiv: https://arxiv.org/abs/2510.20677v1

In real-world singing voice conversion (SVC) applications, environmental noise and the demand for expressive output pose significant challenges. Conventional methods, however, are typically designed without accounting for real deployment scenarios, as both training and inference usually rely on clean data. This mismatch hinders practical use, given the inevitable presence of diverse noise sources and artifacts from music separation. To tackle these issues, we propose R2-SVC, a robust and expressive SVC framework. First, we introduce simulation-based robustness enhancement through random fundamental frequency ($F_0$) perturbations and music separation artifact simulations (e.g., reverberation, echo), substantially improving performance under noisy conditions. Second, we enrich speaker representation using domain-specific singing data: alongside clean vocals, we incorporate DNSMOS-filtered separated vocals and public singing corpora, enabling the model to preserve speaker timbre while capturing singing style nuances. Third, we integrate the Neural Source-Filter (NSF) model to explicitly represent harmonic and noise components, enhancing the naturalness and controllability of converted singing. R2-SVC achieves state-of-the-art results on multiple SVC benchmarks under both clean and noisy conditions.

---

### Analyticup E-commerce Product Search Competition Technical Report from Team Tredence_AICOE

Authors: Rakshith R, Shubham Sharma, Mohammed Sameer Khan, Ankush Chopra
Published: 2025-10-23
Categories: cs.IR, cs.CL
arXiv: https://arxiv.org/abs/2510.20674v1

This study presents the multilingual e-commerce search system developed by the Tredence_AICOE team. The competition features two multilingual relevance tasks: Query-Category (QC) Relevance, which evaluates how well a user's search query aligns with a product category, and Query-Item (QI) Relevance, which measures the match between a multilingual search query and an individual product listing. To ensure full language coverage, we performed data augmentation by translating existing datasets into languages missing from the development set, enabling training across all target languages. We fine-tuned Gemma-3 12B and Qwen-2.5 14B model for both tasks using multiple strategies. The Gemma-3 12B (4-bit) model achieved the best QC performance using original and translated data, and the best QI performance using original, translated, and minority class data creation. These approaches secured 4th place on the final leaderboard, with an average F1-score of 0.8857 on the private test set.

---

### Efficient Multi-bit Quantization Network Training via Weight Bias Correction and Bit-wise Coreset Sampling

Authors: Jinhee Kim, Jae Jun An, Kang Eun Jeon, Jong Hwan Ko
Published: 2025-10-23
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.20673v1

Multi-bit quantization networks enable flexible deployment of deep neural networks by supporting multiple precision levels within a single model. However, existing approaches suffer from significant training overhead as full-dataset updates are repeated for each supported bit-width, resulting in a cost that scales linearly with the number of precisions. Additionally, extra fine-tuning stages are often required to support additional or intermediate precision options, further compounding the overall training burden. To address this issue, we propose two techniques that greatly reduce the training overhead without compromising model utility: (i) Weight bias correction enables shared batch normalization and eliminates the need for fine-tuning by neutralizing quantization-induced bias across bit-widths and aligning activation distributions; and (ii) Bit-wise coreset sampling strategy allows each child model to train on a compact, informative subset selected via gradient-based importance scores by exploiting the implicit knowledge transfer phenomenon. Experiments on CIFAR-10/100, TinyImageNet, and ImageNet-1K with both ResNet and ViT architectures demonstrate that our method achieves competitive or superior accuracy while reducing training time up to 7.88x. Our code is released at https://github.com/a2jinhee/EMQNet_jk.

---

### GRACE: Graph Neural Networks for Locus-of-Care Prediction under Extreme Class Imbalance

Authors: Subham Kumar, Lekhansh Shukla, Animesh Mukherjee, Koustav Rudra, Prakrithi Shivaprakash
Published: 2025-10-23
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.20671v2

Determining the appropriate locus of care for addiction patients is one of the most critical clinical decisions that affects patient treatment outcomes and effective use of resources. With a lack of sufficient specialized treatment resources, such as inpatient beds or staff, there is an unmet need to develop an automated framework for the same. Current decision-making approaches suffer from severe class imbalances in addiction datasets. To address this limitation, we propose a novel graph neural network (GRACE) framework that formalizes locus of care prediction as a structured learning problem. In addition, we propose a new approach of obtaining an unbiased meta-graph to train a GNN to overcome the class imbalance problem. Experimental results with real-world data show an improvement of 11-35% in terms of the F1 score of the minority class over competitive baselines. Further, if we jointly finetune the base embedding fed into GRACE as input together with the rest of the GNN component of GRACE, there is a remarkable boost of 15.8% in performance.

---

### GRACE: GRaph-based Addiction Care prEdiction

Authors: Subham Kumar, Prakrithi Shivaprakash, Koustav Rudra, Lekhansh Shukla, Animesh Mukherjee
Published: 2025-10-23
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.20671v1

Determining the appropriate locus of care for addiction patients is one of the most critical clinical decisions that affects patient treatment outcomes and effective use of resources. With a lack of sufficient specialized treatment resources, such as inpatient beds or staff, there is an unmet need to develop an automated framework for the same. Current decision-making approaches suffer from severe class imbalances in addiction datasets. To address this limitation, we propose a novel graph neural network (GRACE) framework that formalizes locus of care prediction as a structured learning problem. Further, we perform extensive feature engineering and propose a new approach of obtaining an unbiased meta-graph to train a GNN to overcome the class imbalance problem. Experimental results in real-world data show an improvement of 11-35% in terms of the F1 score of the minority class over competitive baselines. The codes and note embeddings are available at https://anonymous.4open.science/r/GRACE-F8E1/.

---

### \textsc{CantoNLU}: A benchmark for Cantonese natural language understanding

Authors: Junghyun Min, York Hay Ng, Sophia Chan, Helena Shunhua Zhao, En-Shiun Annie Lee
Published: 2025-10-23
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.20670v1

Cantonese, although spoken by millions, remains under-resourced due to policy and diglossia. To address this scarcity of evaluation frameworks for Cantonese, we introduce \textsc{\textbf{CantoNLU}}, a benchmark for Cantonese natural language understanding (NLU). This novel benchmark spans seven tasks covering syntax and semantics, including word sense disambiguation, linguistic acceptability judgment, language detection, natural language inference, sentiment analysis, part-of-speech tagging, and dependency parsing. In addition to the benchmark, we provide model baseline performance across a set of models: a Mandarin model without Cantonese training, two Cantonese-adapted models obtained by continual pre-training a Mandarin model on Cantonese text, and a monolingual Cantonese model trained from scratch. Results show that Cantonese-adapted models perform best overall, while monolingual models perform better on syntactic tasks. Mandarin models remain competitive in certain settings, indicating that direct transfer may be sufficient when Cantonese domain data is scarce. We release all datasets, code, and model weights to facilitate future research in Cantonese NLP.

---

### HybridSOMSpikeNet: A Deep Model with Differentiable Soft Self-Organizing Maps and Spiking Dynamics for Waste Classification

Authors: Debojyoti Ghosh, Adrijit Goswami
Published: 2025-10-23
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.20669v1

Accurate waste classification is vital for achieving sustainable waste management and reducing the environmental footprint of urbanization. Misclassification of recyclable materials contributes to landfill accumulation, inefficient recycling, and increased greenhouse gas emissions. To address these issues, this study introduces HybridSOMSpikeNet, a hybrid deep learning framework that integrates convolutional feature extraction, differentiable self-organization, and spiking-inspired temporal processing to enable intelligent and energy-efficient waste classification. The proposed model employs a pre-trained ResNet-152 backbone to extract deep spatial representations, followed by a Differentiable Soft Self-Organizing Map (Soft-SOM) that enhances topological clustering and interpretability. A spiking neural head accumulates temporal activations over discrete time steps, improving robustness and generalization. Trained on a ten-class waste dataset, HybridSOMSpikeNet achieved a test accuracy of 97.39%, outperforming several state-of-the-art architectures while maintaining a lightweight computational profile suitable for real-world deployment. Beyond its technical innovations, the framework provides tangible environmental benefits. By enabling precise and automated waste segregation, it supports higher recycling efficiency, reduces contamination in recyclable streams, and minimizes the ecological and operational costs of waste processing. The approach aligns with global sustainability priorities, particularly the United Nations Sustainable Development Goals (SDG 11 and SDG 12), by contributing to cleaner cities, circular economy initiatives, and intelligent environmental management systems.

---