# Research Papers — 2025-10 · bundle page 141 of 217

> Full-text markdown of papers #7001–7050 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/141
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/140.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/142.md)

### Context-Aware Visual Prompting: Automating Geospatial Web Dashboards with Large Language Models and Agent Self-Validation for Decision Support

Authors: Haowen Xu, Jose Tupayachi, Xiao-Ying Yu
Published: 2025-10-10
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2511.20656v1

The development of web-based geospatial dashboards for risk analysis and decision support is often challenged by the difficulty in visualization of big, multi-dimensional environmental data, implementation complexity, and limited automation. We introduce a generative AI framework that harnesses Large Language Models (LLMs) to automate the creation of interactive geospatial dashboards from user-defined inputs including UI wireframes, requirements, and data sources. By incorporating a structured knowledge graph, the workflow embeds domain knowledge into the generation process and enable accurate and context-aware code completions. A key component of our approach is the Context-Aware Visual Prompting (CAVP) mechanism, which extracts encodes and interface semantics from visual layouts to guide LLM driven generation of codes. The new framework also integrates a self-validation mechanism that uses an agent-based LLM and Pass@k evaluation alongside semantic metrics to assure output reliability. Dashboard snippets are paired with data visualization codebases and ontological representations, enabling a pipeline that produces scalable React-based completions using the MVVM architectural pattern. Our results demonstrate improved performance over baseline approaches and expanded functionality over third party platforms, while incorporating multi-page, fully functional interfaces. We successfully developed a framework to implement LLMs, demonstrated the pipeline for automated code generation, deployment, and performed chain-of-thought AI agents in self-validation. This integrative approach is guided by structured knowledge and visual prompts, providing an innovative geospatial solution in enhancing risk analysis and decision making.

---

### Safe Farming: Development of a Prevention System to Mitigate Vertebrates Crop Raiding

Authors: Razi Iqbal
Published: 2025-10-10
Categories: cs.NI, cs.AI, cs.ET
arXiv: https://arxiv.org/abs/2511.17520v1

One of the main problems for farmers is the protection of their crops, before and after harvesting, from animals and birds. To overcome this problem, this paper proposes a model of safe farming in which the crops will be protected from vertebrates attack through a prevention system that is based on Wirelesses Sensors Networks. Different sensor nodes are placed around the field that detect animals or birds existence and generate required signals and information. This information is passed to the Repelling and Notifying System (RNS) that is installed at the field through a short range wireless technology, ZigBee. As RNS receives the information, it generates ultrasonic sounds that are unbearable for animals and birds, which causes them to run away from the field. These ultrasonic sounds are generated in a frequency range that only animals and birds can hear, while humans cannot notice the sound. The paper also proposes a notifying system. It will inform the farmer about animals or birds intrusion in the field through SMS, but doesn't need any action from the farmer. The low cost and power efficiency of the proposed system is a key advantage for developing countries where cost and power are major players in any system feasibility.

---

### SAJD: Self-Adaptive Jamming Attack Detection in AI/ML Integrated 5G O-RAN Networks

Authors: Md Habibur Rahman, Md Sharif Hossen, Nathan H. Stephenson, Vijay K. Shah, Aloizio Da Silva
Published: 2025-10-10
Categories: cs.NI, cs.AI
arXiv: https://arxiv.org/abs/2511.17519v1

The open radio access network (O-RAN) enables modular, intelligent, and programmable 5G network architectures through the adoption of software-defined networking (SDN), network function virtualization (NFV), and implementation of standardized open interfaces. It also facilitates closed loop control and (non/near) real-time optimization of radio access network (RAN) through the integration of non-real-time applications (rApps) and near-real-time applications (xApps). However, one of the security concerns for O-RAN that can severely undermine network performance and subject it to a prominent threat to the security & reliability of O-RAN networks is jamming attacks. To address this, we introduce SAJD-a self-adaptive jammer detection framework that autonomously detects jamming attacks in artificial intelligence (AI) / machine learning (ML)-integrated O-RAN environments. The SAJD framework forms a closed-loop system that includes near-real-time inference of radio signal jamming interference via our developed ML-based xApp, as well as continuous monitoring and retraining pipelines through rApps. Specifically, a labeler rApp is developed that uses live telemetry (i.e., KPIs) to detect model drift, triggers unsupervised data labeling, executes model training/retraining using the integrated & open-source ClearML framework, and updates deployed models on the fly, without service disruption. Experiments on O-RAN-compliant testbed demonstrate that the SAJD framework outperforms state-of-the-art (offline-trained with manual labels) jamming detection approach in accuracy and adaptability under various dynamic and previously unseen interference scenarios.

---

### iEEG Seizure Detection with a Sparse Hyperdimensional Computing Accelerator

Authors: Stef Cuyckens, Ryan Antonio, Chao Fang, Marian Verhelst
Published: 2025-10-10
Categories: cs.AR, cs.LG
arXiv: https://arxiv.org/abs/2511.05503v1

Implantable devices for reliable intracranial electroencephalography (iEEG) require efficient, accurate, and real-time detection of seizures. Dense hyperdimensional computing (HDC) proves to be efficient over neural networks; however, it still consumes considerable switching power for an ultra-low energy application. Sparse HDC, on the other hand, has the potential of further reducing the energy consumption, yet at the expense of having to support more complex operations and introducing an extra hyperparameter, the maximum hypervector density. To improve the energy and area efficiency of the sparse HDC operations, this work introduces the compressed item memory (CompIM) and simplifies the spatial bundling. We also analyze how a proper hyperparameter choice improves the detection delay compared to dense HDC. Ultimately, our optimizations achieve a 1.73x more energy- and 2.20x more area-efficient hardware design than the naive sparse implementation. We are also 7.50x more energy- and 3.24x more area-efficient than the dense HDC implementation. This work highlights the hardware advantages of sparse HDC, demonstrating its potential to enable smaller brain implants with a substantially extended battery life compared to the current state-of-the-art.

---

### Constructive Lyapunov Functions via Topology-Preserving Neural Networks

Authors: Jaehong Oh
Published: 2025-10-10
Categories: eess.SY, cs.LG
arXiv: https://arxiv.org/abs/2510.24730v1

We prove that ONN achieves order-optimal performance on convergence rate ($μ\propto λ_2$), edge efficiency ($E = N$ for minimal connectivity $k = 2$), and computational complexity ($O(N d^2)$). Empirical validation on 3M-node semantic networks demonstrates 99.75\% improvement over baseline methods, confirming exponential convergence ($μ= 3.2 \times 10^{-4}$) and topology preservation. ORTSF integration into transformers achieves 14.7\% perplexity reduction and 2.3 faster convergence on WikiText-103. We establish deep connections to optimal control (Hamilton-Jacobi-Bellman), information geometry (Fisher-efficient natural gradient), topological data analysis (persistent homology computation in $O(KN)$), discrete geometry (Ricci flow), and category theory (adjoint functors). This work transforms Massera's abstract existence theorem into a concrete, scalable algorithm with provable guarantees, opening pathways for constructive stability analysis in neural networks, robotics, and distributed systems.

---

### A Quantum-Inspired Algorithm for Solving Sudoku Puzzles and the MaxCut Problem

Authors: Max B. Zhao, Fei Li
Published: 2025-10-10
Categories: cs.AI, cs.ET, cs.NE, quant-ph
arXiv: https://arxiv.org/abs/2510.19835v1

We propose and evaluate a quantum-inspired algorithm for solving Quadratic Unconstrained Binary Optimization (QUBO) problems, which are mathematically equivalent to finding ground states of Ising spin-glass Hamiltonians. The algorithm employs Matrix Product States (MPS) to compactly represent large superpositions of spin configurations and utilizes a discrete driving schedule to guide the MPS toward the ground state. At each step, a driver Hamiltonian -- incorporating a transverse magnetic field -- is combined with the problem Hamiltonian to enable spin flips and facilitate quantum tunneling. The MPS is updated using the standard Density Matrix Renormalization Group (DMRG) method, which iteratively minimizes the system's energy via multiple sweeps across the spin chain. Despite its heuristic nature, the algorithm reliably identifies global minima, not merely near-optimal solutions, across diverse QUBO instances. We first demonstrate its effectiveness on intermediate-level Sudoku puzzles from publicly available sources, involving over $200$ Ising spins with long-range couplings dictated by constraint satisfaction. We then apply the algorithm to MaxCut problems from the Biq Mac library, successfully solving instances with up to $251$ nodes and $3,265$ edges. We discuss the advantages of this quantum-inspired approach, including its scalability, generalizability, and suitability for industrial-scale QUBO applications.

---

### CARLE: A Hybrid Deep-Shallow Learning Framework for Robust and Explainable RUL Estimation of Rolling Element Bearings

Authors: Waleed Razzaq, Yun-Bo Zhao
Published: 2025-10-10
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.17846v1

Prognostic Health Management (PHM) systems monitor and predict equipment health. A key task is Remaining Useful Life (RUL) estimation, which predicts how long a component, such as a rolling element bearing, will operate before failure. Many RUL methods exist but often lack generalizability and robustness under changing operating conditions. This paper introduces CARLE, a hybrid AI framework that combines deep and shallow learning to address these challenges. CARLE uses Res-CNN and Res-LSTM blocks with multi-head attention and residual connections to capture spatial and temporal degradation patterns, and a Random Forest Regressor (RFR) for stable, accurate RUL prediction. A compact preprocessing pipeline applies Gaussian filtering for noise reduction and Continuous Wavelet Transform (CWT) for time-frequency feature extraction. We evaluate CARLE on the XJTU-SY and PRONOSTIA bearing datasets. Ablation studies measure each component's contribution, while noise and cross-domain experiments test robustness and generalization. Comparative results show CARLE outperforms several state-of-the-art methods, especially under dynamic conditions. Finally, we analyze model interpretability with LIME and SHAP to assess transparency and trustworthiness.

---

### MAT-Agent: Adaptive Multi-Agent Training Optimization

Authors: Jusheng Zhang, Kaitong Cai, Yijia Fan, Ningyuan Liu, Keze Wang
Published: 2025-10-10
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.17845v1

Multi-label image classification demands adaptive training strategies to navigate complex, evolving visual-semantic landscapes, yet conventional methods rely on static configurations that falter in dynamic settings. We propose MAT-Agent, a novel multi-agent framework that reimagines training as a collaborative, real-time optimization process. By deploying autonomous agents to dynamically tune data augmentation, optimizers, learning rates, and loss functions, MAT-Agent leverages non-stationary multi-armed bandit algorithms to balance exploration and exploitation, guided by a composite reward harmonizing accuracy, rare-class performance, and training stability. Enhanced with dual-rate exponential moving average smoothing and mixed-precision training, it ensures robustness and efficiency. Extensive experiments across Pascal VOC, COCO, and VG-256 demonstrate MAT-Agent's superiority: it achieves an mAP of 97.4 (vs. 96.2 for PAT-T), OF1 of 92.3, and CF1 of 91.4 on Pascal VOC; an mAP of 92.8 (vs. 92.0 for HSQ-CvN), OF1 of 88.2, and CF1 of 87.1 on COCO; and an mAP of 60.9, OF1 of 70.8, and CF1 of 61.1 on VG-256. With accelerated convergence and robust cross-domain generalization, MAT-Agent offers a scalable, intelligent solution for optimizing complex visual models, paving the way for adaptive deep learning advancements.

---

### Modeling Layered Consciousness with Multi-Agent Large Language Models

Authors: Sang Hun Kim, Jongmin Lee, Dongkyu Park, So Young Lee, Yosep Chong
Published: 2025-10-10
Categories: cs.CL, cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2510.17844v1

We propose a multi-agent framework for modeling artificial consciousness in large language models (LLMs), grounded in psychoanalytic theory. Our \textbf{Psychodynamic Model} simulates self-awareness, preconsciousness, and unconsciousness through agent interaction, guided by a Personalization Module combining fixed traits and dynamic needs. Using parameter-efficient fine-tuning on emotionally rich dialogues, the system was evaluated across eight personalized conditions. An LLM as a judge approach showed a 71.2\% preference for the fine-tuned model, with improved emotional depth and reduced output variance, demonstrating its potential for adaptive, personalized cognition.

---

### GRETEL: A Goal-driven Retrieval and Execution-based Trial Framework for LLM Tool Selection Enhancing

Authors: Zongze Wu, Yani Guo, Churong Liang, Runnan Li
Published: 2025-10-10
Categories: cs.LG, cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2510.17843v1

Despite remarkable advances in Large Language Model capabilities, tool retrieval for agent-based systems remains fundamentally limited by reliance on semantic similarity, which fails to capture functional viability. Current methods often retrieve textually relevant but functionally inoperative tools due to parameter mismatches, authentication failures, and execution constraints--a phenomenon we term the semantic-functional gap. We introduce GRETEL, to address this gap through systematic empirical validation. GRETEL implements an agentic workflow that processes semantically retrieved candidates through sandboxed plan-execute-evaluate cycles, generating execution-grounded evidence to distinguish truly functional tools from merely descriptive matches. Our comprehensive evaluation on the ToolBench benchmark demonstrates substantial improvements across all metrics: Pass Rate (at 10) increases from 0.690 to 0.826, Recall (at 10) improves from 0.841 to 0.867, and NDCG (at 10) rises from 0.807 to 0.857.. These results establish that execution-based validation provides a more reliable foundation for tool selection than semantic similarity alone, enabling more robust agent performance in real-world applications.

---

### How Good Are LLMs at Processing Tool Outputs?

Authors: Kiran Kate, Yara Rizk, Poulami Ghosh, Ashu Gulati, Tathagata Chakraborti, Zidane Wright, Mayank Agarwal
Published: 2025-10-10
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.15955v2

Most realistic task automation problems require large language models (LLMs) to call tools, which often return complex JSON responses. These responses must be further processed to derive the information necessary for task completion. The ability of LLMs to do so is under-studied. In this paper, we study the tool response processing task and LLMs' abilities to process structured (JSON) responses. We created a dataset for this task, and evaluated 15 open and closed weight models using multiple prompting approaches. Our results show that JSON processing remains a difficult task even for frontier models across multiple prompting strategies. The optimal response processing strategy depends on both the nature and size of the tool outputs, as well as the complexity of the required reasoning. Variations in processing approaches can lead to performance differences ranging from 3\% to 50\%.

---

### Fire-EnSF: Wildfire Spread Data Assimilation using Ensemble Score Filter

Authors: Hongzheng Shi, Yuhang Wang, Xiao Liu
Published: 2025-10-10
Categories: cs.LG, cs.CE, stat.AP
arXiv: https://arxiv.org/abs/2510.15954v1

As wildfires become increasingly destructive and expensive to control, effective management of active wildfires requires accurate, real-time fire spread predictions. To enhance the forecasting accuracy of active fires, data assimilation plays a vital role by integrating observations (such as remote-sensing data) and fire predictions generated from numerical models. This paper provides a comprehensive investigation on the application of a recently proposed diffusion-model-based filtering algorithm -- the Ensemble Score Filter (EnSF) -- to the data assimilation problem for real-time active wildfire spread predictions. Leveraging a score-based generative diffusion model, EnSF has been shown to have superior accuracy for high-dimensional nonlinear filtering problems, making it an ideal candidate for the filtering problems of wildfire spread models. Technical details are provided, and our numerical investigations demonstrate that EnSF provides superior accuracy, stability, and computational efficiency, establishing it as a robust and practical method for wildfire data assimilation. Our code has been made publicly available.

---

### Executable Epistemology: The Structured Cognitive Loop as an Architecture of Intentional Understanding

Authors: Myung Ho Kim
Published: 2025-10-10
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.15952v4

Large language models exhibit intelligence without genuine epistemic understanding, exposing a key gap: the absence of epistemic architecture. This paper introduces the Structured Cognitive Loop (SCL) as an executable epistemological framework for emergent intelligence. Unlike traditional AI research asking "what is intelligence?" (ontological), SCL asks "under what conditions does cognition emerge?" (epistemological). Grounded in philosophy of mind and cognitive phenomenology, SCL bridges conceptual philosophy and implementable cognition. Drawing on process philosophy, enactive cognition, and extended mind theory, we define intelligence not as a property but as a performed process -- a continuous loop of judgment, memory, control, action, and regulation. SCL makes three contributions. First, it operationalizes philosophical insights into computationally interpretable structures, enabling "executable epistemology" -- philosophy as structural experiment. Second, it shows that functional separation within cognitive architecture yields more coherent and interpretable behavior than monolithic prompt based systems, supported by agent evaluations. Third, it redefines intelligence: not representational accuracy but the capacity to reconstruct its own epistemic state through intentional understanding. This framework impacts philosophy of mind, epistemology, and AI. For philosophy, it allows theories of cognition to be enacted and tested. For AI, it grounds behavior in epistemic structure rather than statistical regularity. For epistemology, it frames knowledge not as truth possession but as continuous reconstruction within a phenomenologically coherent loop. We situate SCL within debates on cognitive phenomenology, emergence, normativity, and intentionality, arguing that real progress requires not larger models but architectures that realize cognitive principles structurally.

---

### Attention to Non-Adopters

Authors: Kaitlyn Zhou, Kristina Gligorić, Myra Cheng, Michelle S. Lam, Vyoma Raman, Boluwatife Aminu, Caeley Woo, Michael Brockman, Hannah Cha, Dan Jurafsky
Published: 2025-10-10
Categories: cs.CY, cs.CL, cs.HC, cs.LG
arXiv: https://arxiv.org/abs/2510.15951v1

Although language model-based chat systems are increasingly used in daily life, most Americans remain non-adopters of chat-based LLMs -- as of June 2025, 66% had never used ChatGPT. At the same time, LLM development and evaluation rely mainly on data from adopters (e.g., logs, preference data), focusing on the needs and tasks for a limited demographic group of adopters in terms of geographic location, education, and gender. In this position paper, we argue that incorporating non-adopter perspectives is essential for developing broadly useful and capable LLMs. We contend that relying on methods that focus primarily on adopters will risk missing a range of tasks and needs prioritized by non-adopters, entrenching inequalities in who benefits from LLMs, and creating oversights in model development and evaluation. To illustrate this claim, we conduct case studies with non-adopters and show: how non-adopter needs diverge from those of current users, how non-adopter needs point us towards novel reasoning tasks, and how to systematically integrate non-adopter needs via human-centered methods.

---

### Cross-dataset Multivariate Time-series Model for Parkinson's Diagnosis via Keyboard Dynamics

Authors: Arianna Francesconi, Donato Cappetta, Fabio Rebecchi, Paolo Soda, Valerio Guarrasi, Rosa Sicilia
Published: 2025-10-10
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.15950v1

Parkinson's disease (PD) presents a growing global challenge, affecting over 10 million individuals, with prevalence expected to double by 2040. Early diagnosis remains difficult due to the late emergence of motor symptoms and limitations of traditional clinical assessments. In this study, we propose a novel pipeline that leverages keystroke dynamics as a non-invasive and scalable biomarker for remote PD screening and telemonitoring. Our methodology involves three main stages: (i) preprocessing of data from four distinct datasets, extracting four temporal signals and addressing class imbalance through the comparison of three methods; (ii) pre-training eight state-of-the-art deep-learning architectures on the two largest datasets, optimizing temporal windowing, stride, and other hyperparameters; (iii) fine-tuning on an intermediate-sized dataset and performing external validation on a fourth, independent cohort. Our results demonstrate that hybrid convolutional-recurrent and transformer-based models achieve strong external validation performance, with AUC-ROC scores exceeding 90% and F1-Score over 70%. Notably, a temporal convolutional model attains an AUC-ROC of 91.14% in external validation, outperforming existing methods that rely solely on internal validation. These findings underscore the potential of keystroke dynamics as a reliable digital biomarker for PD, offering a promising avenue for early detection and continuous monitoring.

---

### ATLAS: Adaptive Trading with LLM AgentS Through Dynamic Prompt Optimization and Multi-Agent Coordination

Authors: Charidimos Papadakis, Angeliki Dimitriou, Giorgos Filandrianos, Maria Lymperaiou, Konstantinos Thomas, Giorgos Stamou
Published: 2025-10-10
Categories: q-fin.TR, cs.AI
arXiv: https://arxiv.org/abs/2510.15949v5

Large language models show promise for financial decision-making, yet deploying them as autonomous trading agents raises fundamental challenges: how to adapt instructions when rewards arrive late and obscured by market noise, how to synthesize heterogeneous information streams into coherent decisions, and how to bridge the gap between model outputs and executable market actions. We present ATLAS (Adaptive Trading with LLM AgentS), a unified multi-agent framework that integrates structured information from markets, news, and corporate fundamentals to support robust trading decisions. Within ATLAS, the central trading agent operates in an order-aware action space, ensuring that outputs correspond to executable market orders rather than abstract signals. The agent can incorporate feedback while trading using Adaptive-OPRO, a novel prompt-optimization technique that dynamically adapts the prompt by incorporating real-time, stochastic feedback, leading to increasing performance over time. Across regime-specific equity studies and multiple LLM families, Adaptive-OPRO consistently outperforms fixed prompts, while reflection-based feedback fails to provide systematic gains.

---

### VisuoAlign: Safety Alignment of LVLMs with Multimodal Tree Search

Authors: MingSheng Li, Guangze Zhao, Sichen Liu
Published: 2025-10-10
Categories: cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2510.15948v1

Large Vision-Language Models (LVLMs) have achieved remarkable progress in multimodal perception and generation, yet their safety alignment remains a critical challenge.Existing defenses and vulnerable to multimodal jailbreaks, as visual inputs introduce new attack surfaces, reasoning chains lack safety supervision, and alignment often degrades under modality fusion.To overcome these limitation, we propose VisuoAlign, a framework for multi-modal safety alignment via prompt-guided tree search.VisuoAlign embeds safety constrains into the reasoning process through visual-textual interactive prompts, employs Monte Carlo Tree Search(MCTS) to systematically construct diverse safety-critical prompt trajectories, and introduces prompt-based scaling to ensure real-time risk detection and compliant responses.Extensive experiments demonstrate that VisuoAlign proactively exposes risks, enables comprehensive dataset generation, and significantly improves the robustness of LVLMs against complex cross-modal threats.

---

### WaveNet's Precision in EEG Classification

Authors: Casper van Laar, Khubaib Ahmed
Published: 2025-10-10
Categories: cs.LG, cs.AI, eess.SP, q-bio.NC
arXiv: https://arxiv.org/abs/2510.15947v2

This study introduces a WaveNet-based deep learning model designed to automate the classification of intracranial electroencephalography (iEEG) signals into physiological activity, pathological (epileptic) activity, power-line noise, and other non-cerebral artifacts. Traditional methods for iEEG signal classification, which rely on expert visual review, are becoming increasingly impractical due to the growing complexity and volume of iEEG recordings. Leveraging a publicly available annotated dataset from Mayo Clinic and St. Anne's University Hospital, the WaveNet model was trained, validated, and tested on 209,231 samples using a 70/20/10 split. The model achieved a classification accuracy exceeding previous non-specialized CNN- and LSTM-based approaches and was benchmarked against a Temporal Convolutional Network (TCN) baseline. Notably, the model achieves high discrimination of noise and artifact classes, with precisions of 0.98 and approximately 1, respectively. Classification between physiological and pathological signals exhibits a modest but clinically interpretable overlap, with F1-scores of 0.96 and 0.90 and 175 and 272 cross-class false positives, respectively, reflecting inherent clinical overlap. WaveNet's architecture, originally developed for raw audio synthesis, is well-suited for iEEG data due to its use of dilated causal convolutions and residual connections, enabling the capture of both fine-grained and long-range temporal dependencies. The study also details the preprocessing pipeline, including dynamic dataset partitioning, the use of focal loss to address class imbalance, and normalization steps that support high model performance. While the results demonstrate strong in-distribution performance, generalizability across datasets and clinical settings has yet to be established.

---

### Fall into a Pit, Gain in a Wit: Cognitive-Guided Harmful Meme Detection via Misjudgment Risk Pattern Retrieval

Authors: Wenshuo Wang, Ziyou Jiang, Junjie Wang, Mingyang Li, Jie Huang, Yuekai Huang, Zhiyuan Chang, Feiyan Duan, Qing Wang
Published: 2025-10-10
Categories: cs.LG, cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2510.15946v3

Internet memes have emerged as a popular multimodal medium, yet they are increasingly weaponized to convey harmful opinions through subtle rhetorical devices like irony and metaphor. Existing detection approaches, including Multimodal Large Language Model (MLLM)-based techniques, struggle with these implicit expressions, leading to frequent misjudgments. This paper introduces PatMD, a novel approach that detects harmful memes by learning from and proactively mitigating these potential misjudgment risks. Our core idea is to move beyond superficial content-level matching and instead identify the underlying misjudgment risk patterns, proactively guiding the MLLMs to avoid known misjudgment pitfalls. We first construct a knowledge base where each meme is deconstructed into a misjudgment risk pattern explaining why it might be misjudged, either overlooking harmful undertones (false negative) or overinterpreting benign content (false positive). For a given target meme, PatMD retrieves relevant patterns and utilizes them to dynamically guide the MLLM's reasoning. Experiments on a benchmark of 6,626 memes across 5 harmful detection tasks show that PatMD outperforms state-of-the-art baselines, achieving an average of 8.30% improvement in F1-score and 7.71% improvement in accuracy, while exhibiting consistent robustness on unseen and adversarial memes.

---

### PC-UNet: An Enforcing Poisson Statistics U-Net for Positron Emission Tomography Denoising

Authors: Yang Shi, Jingchao Wang, Liangsi Lu, Mingxuan Huang, Ruixin He, Yifeng Xie, Hanqian Liu, Minzhe Guo, Yangyang Liang, Weipeng Zhang, Zimeng Li, Xuhang Chen
Published: 2025-10-10
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.14995v1

Positron Emission Tomography (PET) is crucial in medicine, but its clinical use is limited due to high signal-to-noise ratio doses increasing radiation exposure. Lowering doses increases Poisson noise, which current denoising methods fail to handle, causing distortions and artifacts. We propose a Poisson Consistent U-Net (PC-UNet) model with a new Poisson Variance and Mean Consistency Loss (PVMC-Loss) that incorporates physical data to improve image fidelity. PVMC-Loss is statistically unbiased in variance and gradient adaptation, acting as a Generalized Method of Moments implementation, offering robustness to minor data mismatches. Tests on PET datasets show PC-UNet improves physical consistency and image fidelity, proving its ability to integrate physical information effectively.

---

### SIMBA UQ: Similarity-Based Aggregation for Uncertainty Quantification in Large Language Models

Authors: Debarun Bhattacharjya, Balaji Ganesan, Junkyu Lee, Radu Marinescu, Katsiaryna Mirylenka, Michael Glass, Xiao Shou
Published: 2025-10-10
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.13836v1

When does a large language model (LLM) know what it does not know? Uncertainty quantification (UQ) provides measures of uncertainty, such as an estimate of the confidence in an LLM's generated output, and is therefore increasingly recognized as a crucial component of trusted AI systems. Black-box UQ methods do not require access to internal model information from the generating LLM and therefore have numerous real-world advantages, such as robustness to system changes, adaptability to choice of LLM, reduced costs, and computational tractability. In this paper, we investigate the effectiveness of UQ techniques that are primarily but not necessarily entirely black-box, where the consistency between a generated output and other sampled generations is used as a proxy for confidence in its correctness. We propose a high-level non-verbalized similarity-based aggregation framework that subsumes a broad swath of UQ approaches suitable for complex generative tasks, as well as introduce specific novel techniques from the framework that train confidence estimation models using small training sets. Through an empirical study with datasets spanning the diverse tasks of question answering, summarization, and text-to-SQL, we demonstrate that our proposed similarity-based methods can yield better calibrated confidences than baselines.

---

### ConDABench: Interactive Evaluation of Language Models for Data Analysis

Authors: Avik Dutta, Priyanshu Gupta, Hosein Hasanbeig, Rahul Pratap Singh, Harshit Nigam, Sumit Gulwani, Arjun Radhakrishna, Gustavo Soares, Ashish Tiwari
Published: 2025-10-10
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.13835v1

Real-world data analysis tasks often come with under-specified goals and unclean data. User interaction is necessary to understand and disambiguate a user's intent, and hence, essential to solving these complex tasks. Existing benchmarks for evaluating LLMs on data analysis tasks do not capture these complexities or provide first-class support for interactivity. We introduce ConDABench, a framework for generating conversational data analysis (ConDA) benchmarks and evaluating external tools on the generated benchmarks. \bench consists of (a) a multi-agent workflow for generating realistic benchmarks from articles describing insights gained from public datasets, (b) 1,420 ConDA problems generated using this workflow, and (c) an evaluation harness that, for the first time, makes it possible to systematically evaluate conversational data analysis tools on the generated ConDA problems. Evaluation of state-of-the-art LLMs on the benchmarks reveals that while the new generation of models are better at solving more instances, they are not necessarily better at solving tasks that require sustained, long-form engagement. ConDABench is an avenue for model builders to measure progress towards truly collaborative models that can complete complex interactive tasks.

---

### Entropy Meets Importance: A Unified Head Importance-Entropy Score for Stable and Efficient Transformer Pruning

Authors: Minsik Choi, Hyegang Son, Changhoon Kim, Young Geun Kim
Published: 2025-10-10
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.13832v2

Transformer-based models have achieved remarkable performance in NLP tasks. However, their structural characteristics-multiple layers and attention heads-introduce efficiency challenges in inference and deployment. To address these challenges, various pruning methods have recently been proposed. Notably, gradient-based methods using Head Importance Scores (HIS) have gained traction for interpretability, efficiency, and ability to identify redundant heads. However, HIS alone has limitations as it captures only the gradient-driven contribution, overlooking the diversity of attention patterns. To overcome these limitations, we introduce a novel pruning criterion, HIES (Head Importance-Entropy Score), which integrates head importance scores with attention entropy, providing complementary evidence on per-head contribution. Empirically, HIES-based pruning yields up to 15.2% improvement in model quality and 2.04x improvement in stability over HIS-only methods, enabling substantial model compression without sacrificing either accuracy or stability. Code will be released upon publication.

---

### Informed Routing in LLMs: Smarter Token-Level Computation for Faster Inference

Authors: Chao Han, Yijuan Liang, Zihao Xuan, Daokuan Wu, Wei Zhang, Xiaoyu Shen
Published: 2025-10-10
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.13831v1

The deployment of large language models (LLMs) in real-world applications is increasingly limited by their high inference cost. While recent advances in dynamic token-level computation allocation attempt to improve efficiency by selectively activating model components per token, existing methods rely on greedy routing--a myopic execute-or-skip mechanism that often leads to irreversible information loss and suboptimal token selection. This paper introduces informed routing, a new paradigm that proactively addresses these issues. The key insight is to assess not only a token's immediate importance but also its recoverability, i.e., how well its transformation can be approximated. To this end, we propose the Lightweight Feature Forecaster (LFF), a small predictive module that estimates a unit's output before routing decisions are made. This enables a flexible execute-or-approximate policy that preserves model fidelity while drastically reducing computation. Extensive experiments on both language modeling and reasoning tasks show that informed routing achieves state-of-the-art efficiency-performance trade-offs across multiple sparsity levels. Notably, even without final LoRA fine-tuning, our method matches or surpasses strong baselines that require full fine-tuning, all while reducing training time by over 50%. The code is available at: https://github.com/EIT-NLP/informed-routing

---

### Users as Annotators: LLM Preference Learning from Comparison Mode

Authors: Zhongze Cai, Xiaocheng Li
Published: 2025-10-10
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.13830v2

Pairwise preference data have played an important role in the alignment of large language models (LLMs). Each sample of such data consists of a prompt, two different responses to the prompt, and a binary label indicating which of the two responses is better. The labels are usually annotated by professional human annotators. In this paper, we consider an alternative approach to collect pairwise preference data -- user annotation from comparison mode. With the increasingly wider adoption of LLMs among the population, users are contributing more and more of their preference labels through their daily interactions with the LLMs. The upside of such labels is that users are the best experts in judging the responses to their own queries/prompts, but the downside is the lack of quality control in these labels. In this paper, we consider a new idea of generating two responses from two different models or two different versions of the same model. The asymmetry allows us to make an inference of the user's data quality through our proposed user behavior model. We develop an expectation-maximization algorithm to estimate a latent quality factor of the user, and filter users' annotation data accordingly. The downstream task shows the effectiveness of our approach in both capturing the user behavior and data filtering for LLM alignment.

---

### A Linguistics-Aware LLM Watermarking via Syntactic Predictability

Authors: Shinwoo Park, Hyejin Park, Hyeseon An, Yo-Sub Han
Published: 2025-10-10
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.13829v4

As large language models (LLMs) continue to advance rapidly, reliable governance tools have become critical. Publicly verifiable watermarking is particularly essential for fostering a trustworthy AI ecosystem. A central challenge persists: balancing text quality against detection robustness. Recent studies have sought to navigate this trade-off by leveraging signals from model output distributions (e.g., token-level entropy); however, their reliance on these model-specific signals presents a significant barrier to public verification, as the detection process requires access to the logits of the underlying model. We introduce STELA, a novel framework that aligns watermark strength with the linguistic degrees of freedom inherent in language. STELA dynamically modulates the signal using part-of-speech (POS) n-gram-modeled linguistic indeterminacy, weakening it in grammatically constrained contexts to preserve quality and strengthening it in contexts with greater linguistic flexibility to enhance detectability. Our detector operates without access to any model logits, thus facilitating publicly verifiable detection. Through extensive experiments on typologically diverse languages-analytic English, isolating Chinese, and agglutinative Korean-we show that STELA surpasses prior methods in detection robustness. Our code is available at https://github.com/Shinwoo-Park/stela_watermark.

---

### From Explainability to Action: A Generative Operational Framework for Integrating XAI in Clinical Mental Health Screening

Authors: Ratna Kandala, Akshata Kishore Moharir, Divya Arvinda Nayak
Published: 2025-10-10
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.13828v1

Explainable Artificial Intelligence (XAI) has been presented as the critical component for unlocking the potential of machine learning in mental health screening (MHS). However, a persistent lab-to-clinic gap remains. Current XAI techniques, such as SHAP and LIME, excel at producing technically faithful outputs such as feature importance scores, but fail to deliver clinically relevant, actionable insights that can be used by clinicians or understood by patients. This disconnect between technical transparency and human utility is the primary barrier to real-world adoption. This paper argues that this gap is a translation problem and proposes the Generative Operational Framework, a novel system architecture that leverages Large Language Models (LLMs) as a central translation engine. This framework is designed to ingest the raw, technical outputs from diverse XAI tools and synthesize them with clinical guidelines (via RAG) to automatically generate human-readable, evidence-backed clinical narratives. To justify our solution, we provide a systematic analysis of the components it integrates, tracing the evolution from intrinsic models to generative XAI. We demonstrate how this framework directly addresses key operational barriers, including workflow integration, bias mitigation, and stakeholder-specific communication. This paper also provides a strategic roadmap for moving the field beyond the generation of isolated data points toward the delivery of integrated, actionable, and trustworthy AI in clinical practice.

---

### Bridging the Semantic Gap: Contrastive Rewards for Multilingual Text-to-SQL with GRPO

Authors: Ashish Kattamuri, Ishita Prasad, Meetu Malhotra, Arpita Vats, Rahul Raja, Albert Lie
Published: 2025-10-10
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.13827v2

Current Text-to-SQL methods are evaluated and only focused on executable queries, overlooking the semantic alignment challenge -- both in terms of the semantic meaning of the query and the correctness of the execution results. Even execution accuracy itself shows significant drops when moving from English to other languages, with an average decline of 6 percentage points across non-English languages. We address these challenges by presenting a new framework that combines Group Relative Policy Optimization (GRPO) within a multilingual contrastive reward signal to enhance both task efficiency and semantic accuracy in Text-to-SQL systems in cross-lingual scenarios. Our method teaches models to obtain better correspondence between SQL generation and user intent by combining a reward signal based on semantic similarity. On the seven-language MultiSpider dataset, fine-tuning the LLaMA-3-3B model with GRPO improved the execution accuracy up to 87.4 percent (+26 pp over zero-shot) and semantic accuracy up to 52.29 percent (+32.86 pp). Adding our contrastive reward signal in the GRPO framework further improved the average semantic accuracy to 59.14 percent (+6.85 pp, up to +10 pp for Vietnamese). Our experiments showcase that a smaller, parameter-efficient 3B LLaMA model fine-tuned with our contrastive reward signal outperforms a much larger zero-shot 8B LLaMA model, with an uplift of 7.43 pp in execution accuracy (from 81.43 percent on the 8B model to 88.86 percent on the 3B model), and nearly matches its semantic accuracy (59.14 percent vs. 68.57 percent) -- all using just 3,000 reinforcement learning training examples. These results demonstrate how we can improve the performance of Text-to-SQL systems with contrastive rewards for directed semantic alignment, without requiring large-scale training datasets.

---

### Rebalancing with Calibrated Sub-classes (RCS): A Statistical Fusion-based Framework for Robust Imbalanced Classification across Modalities

Authors: Priyobrata Mondal, Faizanuddin Ansari, Swagatam Das
Published: 2025-10-10
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.13656v2

Class imbalance, where certain classes have insufficient data, poses a critical challenge for robust classification, often biasing models toward majority classes. Distribution calibration offers a promising avenue to address this by estimating more accurate class distributions. In this work, we propose Rebalancing with Calibrated Sub-classes (RCS) - a novel distribution calibration framework for robust imbalanced classification. RCS aims to fuse statistical information from the majority and intermediate class distributions via a weighted mixture of Gaussian components to estimate minority class parameters more accurately. An encoder-decoder network is trained to preserve structural relationships in imbalanced datasets and prevent feature disentanglement. Post-training, encoder-extracted feature vectors are leveraged to generate synthetic samples guided by the calibrated distributions. This fusion-based calibration effectively mitigates overgeneralization by incorporating neighborhood distribution information rather than relying solely on majority-class statistics. Extensive experiments on diverse image, text, and tabular datasets demonstrate that RCS consistently outperforms several baseline and state-of-the-art methods, highlighting its effectiveness and broad applicability in addressing real-world imbalanced classification challenges.

---

### Classifier-Augmented Generation for Structured Workflow Prediction

Authors: Thomas Gschwind, Shramona Chakraborty, Nitin Gupta, Sameep Mehta
Published: 2025-10-10
Categories: cs.CL, cs.AI, cs.DB, cs.LG
arXiv: https://arxiv.org/abs/2510.12825v1

ETL (Extract, Transform, Load) tools such as IBM DataStage allow users to visually assemble complex data workflows, but configuring stages and their properties remains time consuming and requires deep tool knowledge. We propose a system that translates natural language descriptions into executable workflows, automatically predicting both the structure and detailed configuration of the flow. At its core lies a Classifier-Augmented Generation (CAG) approach that combines utterance decomposition with a classifier and stage-specific few-shot prompting to produce accurate stage predictions. These stages are then connected into non-linear workflows using edge prediction, and stage properties are inferred from sub-utterance context. We compare CAG against strong single-prompt and agentic baselines, showing improved accuracy and efficiency, while substantially reducing token usage. Our architecture is modular, interpretable, and capable of end-to-end workflow generation, including robust validation steps. To our knowledge, this is the first system with a detailed evaluation across stage prediction, edge layout, and property generation for natural-language-driven ETL authoring.

---

### Evidence Without Injustice: A New Counterfactual Test for Fair Algorithms

Authors: Michele Loi, Marcello Di Bello, Nicolò Cangiotti
Published: 2025-10-10
Categories: cs.CY, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.12822v2

The growing philosophical literature on algorithmic fairness has examined statistical criteria such as equalized odds and calibration, causal and counterfactual approaches, and the role of structural and compounding injustices. Yet an important dimension has been overlooked: whether the evidential value of an algorithmic output itself depends on structural injustice. We contrast a predictive policing algorithm, which relies on historical crime data, with a camera-based system that records ongoing offenses, where both are designed to guide police deployment. In evaluating the moral acceptability of acting on a piece of evidence, we must ask not only whether the evidence is probative in the actual world, but also whether it would remain probative in nearby worlds without the relevant injustices. The predictive policing algorithm fails this test, but the camera-based system passes it. When evidence fails the test, it is morally problematic to use it punitively, more so than evidence that passes the test.

---

### Celebrity Profiling on Short Urdu Text using Twitter Followers' Feed

Authors: Muhammad Hamza, Rizwan Jafar
Published: 2025-10-10
Categories: cs.SI, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.11739v1

Social media has become an essential part of the digital age, serving as a platform for communication, interaction, and information sharing. Celebrities are among the most active users and often reveal aspects of their personal and professional lives through online posts. Platforms such as Twitter provide an opportunity to analyze language and behavior for understanding demographic and social patterns. Since followers frequently share linguistic traits and interests with the celebrities they follow, textual data from followers can be used to predict celebrity demographics. However, most existing research in this field has focused on English and other high-resource languages, leaving Urdu largely unexplored. This study applies modern machine learning and deep learning techniques to the problem of celebrity profiling in Urdu. A dataset of short Urdu tweets from followers of subcontinent celebrities was collected and preprocessed. Multiple algorithms were trained and compared, including Logistic Regression, Support Vector Machines, Random Forests, Convolutional Neural Networks, and Long Short-Term Memory networks. The models were evaluated using accuracy, precision, recall, F1-score, and cumulative rank (cRank). The best performance was achieved for gender prediction with a cRank of 0.65 and an accuracy of 0.65, followed by moderate results for age, profession, and fame prediction. These results demonstrate that follower-based linguistic features can be effectively leveraged using machine learning and neural approaches for demographic prediction in Urdu, a low-resource language.

---

### SeeingSounds: Learning Audio-to-Visual Alignment via Text

Authors: Simone Carnemolla, Matteo Pennisi, Chiara Russo, Simone Palazzo, Daniela Giordano, Concetto Spampinato
Published: 2025-10-10
Categories: cs.SD, cs.AI, cs.CV, cs.MM
arXiv: https://arxiv.org/abs/2510.11738v1

We introduce SeeingSounds, a lightweight and modular framework for audio-to-image generation that leverages the interplay between audio, language, and vision-without requiring any paired audio-visual data or training on visual generative models. Rather than treating audio as a substitute for text or relying solely on audio-to-text mappings, our method performs dual alignment: audio is projected into a semantic language space via a frozen language encoder, and, contextually grounded into the visual domain using a vision-language model. This approach, inspired by cognitive neuroscience, reflects the natural cross-modal associations observed in human perception. The model operates on frozen diffusion backbones and trains only lightweight adapters, enabling efficient and scalable learning. Moreover, it supports fine-grained and interpretable control through procedural text prompt generation, where audio transformations (e.g., volume or pitch shifts) translate into descriptive prompts (e.g., "a distant thunder") that guide visual outputs. Extensive experiments across standard benchmarks confirm that SeeingSounds outperforms existing methods in both zero-shot and supervised settings, establishing a new state of the art in controllable audio-to-visual generation.

---

### AI Agents for the Dhumbal Card Game: A Comparative Study

Authors: Sahaj Raj Malla
Published: 2025-10-10
Categories: cs.AI, cs.GT, cs.LG
arXiv: https://arxiv.org/abs/2510.11736v1

This study evaluates Artificial Intelligence (AI) agents for Dhumbal, a culturally significant multiplayer card game with imperfect information, through a systematic comparison of rule-based, search-based, and learning-based strategies. We formalize Dhumbal's mechanics and implement diverse agents, including heuristic approaches (Aggressive, Conservative, Balanced, Opportunistic), search-based methods such as Monte Carlo Tree Search (MCTS) and Information Set Monte Carlo Tree Search (ISMCTS), and reinforcement learning approaches including Deep Q-Network (DQN) and Proximal Policy Optimization (PPO), and a random baseline. Evaluation involves within-category tournaments followed by a cross-category championship. Performance is measured via win rate, economic outcome, Jhyap success, cards discarded per round, risk assessment, and decision efficiency. Statistical significance is assessed using Welch's t-test with Bonferroni correction, effect sizes via Cohen's d, and 95% confidence intervals (CI). Across 1024 simulated rounds, the rule-based Aggressive agent achieves the highest win rate (88.3%, 95% CI: (86.3, 90.3)), outperforming ISMCTS (9.0%) and PPO (1.5%) through effective exploitation of Jhyap declarations. The study contributes a reproducible AI framework, insights into heuristic efficacy under partial information, and open-source code, thereby advancing AI research and supporting digital preservation of cultural games.

---

### Scaling Law in LLM Simulated Personality: More Detailed and Realistic Persona Profile Is All You Need

Authors: Yuqi Bai, Tianyu Huang, Kun Sun, Yuting Chen
Published: 2025-10-10
Categories: cs.CY, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.11734v1

This research focuses on using large language models (LLMs) to simulate social experiments, exploring their ability to emulate human personality in virtual persona role-playing. The research develops an end-to-end evaluation framework, including individual-level analysis of stability and identifiability, as well as population-level analysis called progressive personality curves to examine the veracity and consistency of LLMs in simulating human personality. Methodologically, this research proposes important modifications to traditional psychometric approaches (CFA and construct validity) which are unable to capture improvement trends in LLMs at their current low-level simulation, potentially leading to remature rejection or methodological misalignment. The main contributions of this research are: proposing a systematic framework for LLM virtual personality evaluation; empirically demonstrating the critical role of persona detail in personality simulation quality; and identifying marginal utility effects of persona profiles, especially a Scaling Law in LLM personality simulation, offering operational evaluation metrics and a theoretical foundation for applying large language models in social science experiments.

---

### Serial-Parallel Dual-Path Architecture for Speaking Style Recognition

Authors: Guojian Li, Qijie Shao, Zhixian Zhao, Shuiyuan Wang, Zhonghua Fu, Lei Xie
Published: 2025-10-10
Categories: cs.SD, cs.AI, eess.AS
arXiv: https://arxiv.org/abs/2510.11732v1

Speaking Style Recognition (SSR) identifies a speaker's speaking style characteristics from speech. Existing style recognition approaches primarily rely on linguistic information, with limited integration of acoustic information, which restricts recognition accuracy improvements. The fusion of acoustic and linguistic modalities offers significant potential to enhance recognition performance. In this paper, we propose a novel serial-parallel dual-path architecture for SSR that leverages acoustic-linguistic bimodal information. The serial path follows the ASR+STYLE serial paradigm, reflecting a sequential temporal dependency, while the parallel path integrates our designed Acoustic-Linguistic Similarity Module (ALSM) to facilitate cross-modal interaction with temporal simultaneity. Compared to the existing SSR baseline -- the OSUM model, our approach reduces parameter size by 88.4% and achieves a 30.3% improvement in SSR accuracy for eight styles on the test set.

---

### Phase-Aware Deep Learning with Complex-Valued CNNs for Audio Signal Applications

Authors: Naman Agrawal
Published: 2025-10-10
Categories: cs.LG, cs.AI, cs.SD
arXiv: https://arxiv.org/abs/2510.09926v1

This study explores the design and application of Complex-Valued Convolutional Neural Networks (CVCNNs) in audio signal processing, with a focus on preserving and utilizing phase information often neglected in real-valued networks. We begin by presenting the foundational theoretical concepts of CVCNNs, including complex convolutions, pooling layers, Wirtinger-based differentiation, and various complex-valued activation functions. These are complemented by critical adaptations of training techniques, including complex batch normalization and weight initialization schemes, to ensure stability in training dynamics. Empirical evaluations are conducted across three stages. First, CVCNNs are benchmarked on standard image datasets, where they demonstrate competitive performance with real-valued CNNs, even under synthetic complex perturbations. Although our focus is audio signal processing, we first evaluate CVCNNs on image datasets to establish baseline performance and validate training stability before applying them to audio tasks. In the second experiment, we focus on audio classification using Mel-Frequency Cepstral Coefficients (MFCCs). CVCNNs trained on real-valued MFCCs slightly outperform real CNNs, while preserving phase in input workflows highlights challenges in exploiting phase without architectural modifications. Finally, a third experiment introduces GNNs to model phase information via edge weighting, where the inclusion of phase yields measurable gains in both binary and multi-class genre classification. These results underscore the expressive capacity of complex-valued architectures and confirm phase as a meaningful and exploitable feature in audio processing applications. While current methods show promise, especially with activations like cardioid, future advances in phase-aware design will be essential to leverage the potential of complex representations in neural networks.

---

### HeadsUp! High-Fidelity Portrait Image Super-Resolution

Authors: Renjie Li, Zihao Zhu, Xiaoyu Wang, Zhengzhong Tu
Published: 2025-10-10
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.09924v1

Portrait pictures, which typically feature both human subjects and natural backgrounds, are one of the most prevalent forms of photography on social media. Existing image super-resolution (ISR) techniques generally focus either on generic real-world images or strictly aligned facial images (i.e., face super-resolution). In practice, separate models are blended to handle portrait photos: the face specialist model handles the face region, and the general model processes the rest. However, these blending approaches inevitably introduce blending or boundary artifacts around the facial regions due to different model training recipes, while human perception is particularly sensitive to facial fidelity. To overcome these limitations, we study the portrait image supersolution (PortraitISR) problem, and propose HeadsUp, a single-step diffusion model that is capable of seamlessly restoring and upscaling portrait images in an end-to-end manner. Specifically, we build our model on top of a single-step diffusion model and develop a face supervision mechanism to guide the model in focusing on the facial region. We then integrate a reference-based mechanism to help with identity restoration, reducing face ambiguity in low-quality face restoration. Additionally, we have built a high-quality 4K portrait image ISR dataset dubbed PortraitSR-4K, to support model training and benchmarking for portrait images. Extensive experiments show that HeadsUp achieves state-of-the-art performance on the PortraitISR task while maintaining comparable or higher performance on both general image and aligned face datasets.

---

### AutoGD: Automatic Learning Rate Selection for Gradient Descent

Authors: Nikola Surjanovic, Alexandre Bouchard-Côté, Trevor Campbell
Published: 2025-10-10
Categories: cs.LG, math.OC, stat.CO, stat.ML
arXiv: https://arxiv.org/abs/2510.09923v1

The performance of gradient-based optimization methods, such as standard gradient descent (GD), greatly depends on the choice of learning rate. However, it can require a non-trivial amount of user tuning effort to select an appropriate learning rate schedule. When such methods appear as inner loops of other algorithms, expecting the user to tune the learning rates may be impractical. To address this, we introduce AutoGD: a gradient descent method that automatically determines whether to increase or decrease the learning rate at a given iteration. We establish the convergence of AutoGD, and show that we can recover the optimal rate of GD (up to a constant) for a broad class of functions without knowledge of smoothness constants. Experiments on a variety of traditional problems and variational inference optimization tasks demonstrate strong performance of the method, along with its extensions to AutoBFGS and AutoLBFGS.

---

### Advancing Intoxication Detection: A Smartwatch-Based Approach

Authors: Manuel Segura, Pere Vergés, Richard Ky, Ramesh Arangott, Angela Kristine Garcia, Thang Dihn Trong, Makoto Hyodo, Alexandru Nicolau, Tony Givargis, Sergio Gago-Masague
Published: 2025-10-10
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.09916v1

Excess alcohol consumption leads to serious health risks and severe consequences for both individuals and their communities. To advocate for healthier drinking habits, we introduce a groundbreaking mobile smartwatch application approach to just-in-time interventions for intoxication warnings. In this work, we have created a dataset gathering TAC, accelerometer, gyroscope, and heart rate data from the participants during a period of three weeks. This is the first study to combine accelerometer, gyroscope, and heart rate smartwatch data collected over an extended monitoring period to classify intoxication levels. Previous research had used limited smartphone motion data and conventional machine learning (ML) algorithms to classify heavy drinking episodes; in this work, we use smartwatch data and perform a thorough evaluation of different state-of-the-art classifiers such as the Transformer, Bidirectional Long Short-Term Memory (bi-LSTM), Gated Recurrent Unit (GRU), One-Dimensional Convolutional Neural Networks (1D-CNN), and Hyperdimensional Computing (HDC). We have compared performance metrics for the algorithms and assessed their efficiency on resource-constrained environments like mobile hardware. The HDC model achieved the best balance between accuracy and efficiency, demonstrating its practicality for smartwatch-based applications.

---

### Enhancing Faithfulness in Abstractive Summarization via Span-Level Fine-Tuning

Authors: Sicong Huang, Qianqi Yan, Shengze Wang, Ian Lane
Published: 2025-10-10
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.09915v1

Abstractive summarization using large language models (LLMs) has become an essential tool for condensing information. However, despite their ability to generate fluent summaries, these models sometimes produce unfaithful summaries, introducing hallucinations at the word, phrase, or concept level. Existing mitigation strategies, such as post-processing corrections or contrastive learning with synthetically generated negative samples, fail to fully address the diverse errors that can occur in LLM-generated summaries. In this paper, we investigate fine-tuning strategies to reduce the occurrence of unfaithful spans in generated summaries. First, we automatically generate summaries for the set of source documents in the training set with a variety of LLMs and then use GPT-4o to annotate any hallucinations it detects at the span-level. Leveraging these annotations, we fine-tune LLMs with both hallucination-free summaries and annotated unfaithful spans to enhance model faithfulness. In this paper, we introduce a new dataset that contains both faithful and unfaithful summaries with span-level labels and we evaluate three techniques to fine-tuning a LLM to improve the faithfulness of the resulting summarization: gradient ascent, unlikelihood training, and task vector negation. Experimental results show that all three approaches successfully leverage span-level annotations to improve faithfulness, with unlikelihood training being the most effective.

---

### Augmenting generative models with biomedical knowledge graphs improves targeted drug discovery

Authors: Aditya Malusare, Vineet Punyamoorty, Vaneet Aggarwal
Published: 2025-10-10
Categories: cs.LG, cs.AI, q-bio.QM
arXiv: https://arxiv.org/abs/2510.09914v1

Recent breakthroughs in generative modeling have demonstrated remarkable capabilities in molecular generation, yet the integration of comprehensive biomedical knowledge into these models has remained an untapped frontier. In this study, we introduce K-DREAM (Knowledge-Driven Embedding-Augmented Model), a novel framework that leverages knowledge graphs to augment diffusion-based generative models for drug discovery. By embedding structured information from large-scale knowledge graphs, K-DREAM directs molecular generation toward candidates with higher biological relevance and therapeutic suitability. This integration ensures that the generated molecules are aligned with specific therapeutic targets, moving beyond traditional heuristic-driven approaches. In targeted drug design tasks, K-DREAM generates drug candidates with improved binding affinities and predicted efficacy, surpassing current state-of-the-art generative models. It also demonstrates flexibility by producing molecules designed for multiple targets, enabling applications to complex disease mechanisms. These results highlight the utility of knowledge-enhanced generative models in rational drug design and their relevance to practical therapeutic development.

---

### Don't Throw Away Your Pretrained Model

Authors: Shangbin Feng, Wenhao Yu, Yike Wang, Hongming Zhang, Yulia Tsvetkov, Dong Yu
Published: 2025-10-10
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.09913v1

Alignment training has tradeoffs: it helps language models (LMs) gain in reasoning and instruction following but might lose out on skills such as creativity and calibration, where unaligned base models are better at. We aim to make the best of both worlds through model collaboration, where different models in the training pipeline collaborate and complement each other. Since LM responses feature interleaving skills that favor different models, we propose Switch Generation, where pretrained and aligned model versions take turns to ``speak'' in a response sequence. Specifically, we train a switcher LM by learning from outcomes of choosing different models to generate the next segment across diverse queries and contexts. At inference time, the switcher LM guides different model checkpoints to dynamically generate the next segment where their strengths are most needed. Extensive experiments with 8 model collaboration baselines and 18 datasets show that 1) model collaboration consistently outperforms individual models on 16 out of 18 tasks, and 2) Switch Generation further outperforms baselines by 12.9% on average. Further analysis reveals that Switch Generation discovers compositional skills to solve problems where individual models struggle and generalizes to unseen models and tasks, reusing and repurposing by-products in expensive model training pipelines that are otherwise discarded.

---

### SpectralCA: Bi-Directional Cross-Attention for Next-Generation UAV Hyperspectral Vision

Authors: D. V. Brovko
Published: 2025-10-10
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.09912v1

The relevance of this research lies in the growing demand for unmanned aerial vehicles (UAVs) capable of operating reliably in complex environments where conventional navigation becomes unreliable due to interference, poor visibility, or camouflage. Hyperspectral imaging (HSI) provides unique opportunities for UAV-based computer vision by enabling fine-grained material recognition and object differentiation, which are critical for navigation, surveillance, agriculture, and environmental monitoring. The aim of this work is to develop a deep learning architecture integrating HSI into UAV perception for navigation, object detection, and terrain classification. Objectives include: reviewing existing HSI methods, designing a hybrid 2D/3D convolutional architecture with spectral-spatial cross-attention, training, and benchmarking. The methodology is based on the modification of the Mobile 3D Vision Transformer (MDvT) by introducing the proposed SpectralCA block. This block employs bi-directional cross-attention to fuse spectral and spatial features, enhancing accuracy while reducing parameters and inference time. Experimental evaluation was conducted on the WHU-Hi-HongHu dataset, with results assessed using Overall Accuracy, Average Accuracy, and the Kappa coefficient. The findings confirm that the proposed architecture improves UAV perception efficiency, enabling real-time operation for navigation, object recognition, and environmental monitoring tasks. Keywords: SpectralCA, deep learning, computer vision, hyperspectral imaging, unmanned aerial vehicle, object detection, semi-supervised learning.

---

### Learning with Incomplete Context: Linear Contextual Bandits with Pretrained Imputation

Authors: Hao Yan, Heyan Zhang, Yongyi Guo
Published: 2025-10-10
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.09908v3

The rise of large-scale pretrained models has made it feasible to generate predictive or synthetic features at low cost, raising the question of how to incorporate such surrogate predictions into downstream decision-making. We study this problem in the setting of online linear contextual bandits, where contexts may be complex, nonstationary, and only partially observed. In addition to bandit data, we assume access to an auxiliary dataset containing fully observed contexts--common in practice since such data are collected without adaptive interventions. We propose PULSE-UCB, an algorithm that leverages pretrained models trained on the auxiliary data to impute missing features during online decision-making. We establish regret guarantees that decompose into a standard bandit term plus an additional component reflecting pretrained model quality. In the i.i.d. context case with Hölder-smooth missing features, PULSE-UCB achieves near-optimal performance, supported by matching lower bounds. Our results quantify how uncertainty in predicted contexts affects decision quality and how much historical data is needed to improve downstream learning.

---

### Agentic Property-Based Testing: Finding Bugs Across the Python Ecosystem

Authors: Muhammad Maaz, Liam DeVoe, Zac Hatfield-Dodds, Nicholas Carlini
Published: 2025-10-10
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2510.09907v1

Property-based testing (PBT) is a lightweight formal method, typically implemented as a randomized testing framework. Users specify the input domain for their test using combinators supplied by the PBT framework, and the expected properties or invariants as a unit-test function. The framework then searches for a counterexample, e.g. by generating inputs and calling the test function. In this work, we demonstrate an LLM-based agent which analyzes Python modules, infers function-specific and cross-function properties from code and documentation, synthesizes and executes PBTs, reflects on outputs of these tests to confirm true bugs, and finally outputs actionable bug reports for the developer. We perform an extensive evaluation of our agent across 100 popular Python packages. Of the bug reports generated by the agent, we found after manual review that 56\% were valid bugs and 32\% were valid bugs that we would report to maintainers. We then developed a ranking rubric to surface high-priority valid bugs to developers, and found that of the 21 top-scoring bugs, 86\% were valid and 81\% we would report. The bugs span diverse failure modes from serialization failures to numerical precision errors to flawed cache implementations. We reported 5 bugs, 4 with patches, including to NumPy and cloud computing SDKs, with 3 patches merged successfully. Our results suggest that LLMs with PBT provides a rigorous and scalable method for autonomously testing software. Our code and artifacts are available at: https://github.com/mmaaz-git/agentic-pbt.

---

### The Personalization Trap: How User Memory Alters Emotional Reasoning in LLMs

Authors: Xi Fang, Weijie Xu, Yuchong Zhang, Stephanie Eckman, Scott Nickleach, Chandan K. Reddy
Published: 2025-10-10
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.09905v2

When an AI assistant remembers that Sarah is a single mother working two jobs, does it interpret her stress differently than if she were a wealthy executive? As personalized AI systems increasingly incorporate long-term user memory, understanding how this memory shapes emotional reasoning is critical. We investigate how user memory affects emotional intelligence in large language models (LLMs) by evaluating 15 models on human-validated emotional intelligence tests. We find that identical scenarios paired with different user profiles produce systematically divergent emotional interpretations. Across validated user-independent emotional scenarios and diverse user profiles, systematic biases emerged in several high-performing LLMs where advantaged profiles received more accurate emotional interpretations. Moreover, LLMs demonstrate significant disparities across demographic factors in emotion reasoning and supportive recommendations tasks, indicating that personalization mechanisms can embed social hierarchies into models' emotional reasoning. These results highlight a key challenge for memory-enhanced AI: systems designed for personalization may reinforce social inequalities. To mitigate these disparities, we curate a general-purpose preference dataset designed to reduce demographic profiles' influence on emotional understanding.

---

### Stability of Transformers under Layer Normalization

Authors: Kelvin Kan, Xingjian Li, Benjamin J. Zhang, Tuhin Sahai, Stanley Osher, Krishna Kumar, Markos A. Katsoulakis
Published: 2025-10-10
Categories: cs.LG, cs.AI, math.OC
arXiv: https://arxiv.org/abs/2510.09904v2

Despite their widespread use, training deep Transformers can be unstable. Layer normalization, a standard component, improves training stability, but its placement has often been ad-hoc. In this paper, we conduct a principled study on the forward (hidden states) and backward (gradient) stability of Transformers under different layer normalization placements. Our theory provides key insights into the training dynamics: whether training drives Transformers toward regular solutions or pathological behaviors. For forward stability, we derive explicit bounds on the growth of hidden states in trained Transformers. For backward stability, we analyze how layer normalization affects the backpropagation of gradients, thereby explaining the training dynamics of each layer normalization placement. Our analysis also guides the scaling of residual steps in Transformer blocks, where appropriate choices can further improve stability and performance. Our numerical results corroborate our theoretical findings. Beyond these results, our framework provides a principled way to sanity-check the stability of Transformers under new architectural modifications, offering guidance for future designs.

---

### An uncertainty-aware framework for data-efficient multi-view animal pose estimation

Authors: Lenny Aharon, Keemin Lee, Karan Sikka, Selmaan Chettih, Cole Hurwitz, Liam Paninski, Matthew R Whiteway
Published: 2025-10-10
Categories: cs.CV, q-bio.QM
arXiv: https://arxiv.org/abs/2510.09903v1

Multi-view pose estimation is essential for quantifying animal behavior in scientific research, yet current methods struggle to achieve accurate tracking with limited labeled data and suffer from poor uncertainty estimates. We address these challenges with a comprehensive framework combining novel training and post-processing techniques, and a model distillation procedure that leverages the strengths of these techniques to produce a more efficient and effective pose estimator. Our multi-view transformer (MVT) utilizes pretrained backbones and enables simultaneous processing of information across all views, while a novel patch masking scheme learns robust cross-view correspondences without camera calibration. For calibrated setups, we incorporate geometric consistency through 3D augmentation and a triangulation loss. We extend the existing Ensemble Kalman Smoother (EKS) post-processor to the nonlinear case and enhance uncertainty quantification via a variance inflation technique. Finally, to leverage the scaling properties of the MVT, we design a distillation procedure that exploits improved EKS predictions and uncertainty estimates to generate high-quality pseudo-labels, thereby reducing dependence on manual labels. Our framework components consistently outperform existing methods across three diverse animal species (flies, mice, chickadees), with each component contributing complementary benefits. The result is a practical, uncertainty-aware system for reliable pose estimation that enables downstream behavioral analyses under real-world data constraints.

---

### If you can distinguish, you can express: Galois theory, Stone--Weierstrass, machine learning, and linguistics

Authors: Ben Blum-Smith, Claudia Brugman, Thomas Conners, Soledad Villar
Published: 2025-10-10
Categories: math.HO, stat.ML
arXiv: https://arxiv.org/abs/2510.09902v3

This essay develops a parallel between the Fundamental Theorem of Galois Theory and the Stone--Weierstrass theorem: both can be viewed as assertions that tie the distinguishing power of a class of objects to their expressive power. We provide an elementary theorem connecting the relevant notions of "distinguishing power". We also discuss machine learning and data science contexts in which these theorems, and more generally the theme of links between distinguishing power and expressive power, appear. Finally, we discuss the same theme in the context of linguistics, where it appears as a foundational principle, and illustrate it with several examples.

---