# Research Papers — 2025-10 · bundle page 111 of 217

> Full-text markdown of papers #5501–5550 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/111
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/110.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/112.md)

### Modeling Cultural Bias in Facial Expression Recognition with Adaptive Agents

Authors: David Freire-Obregón, José Salas-Cáceres, Javier Lorenzo-Navarro, Oliverio J. Santana, Daniel Hernández-Sosa, Modesto Castrillón-Santana
Published: 2025-10-15
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.13557v1

Facial expression recognition (FER) must remain robust under both cultural variation and perceptually degraded visual conditions, yet most existing evaluations assume homogeneous data and high-quality imagery. We introduce an agent-based, streaming benchmark that reveals how cross-cultural composition and progressive blurring interact to shape face recognition robustness. Each agent operates in a frozen CLIP feature space with a lightweight residual adapter trained online at sigma=0 and fixed during testing. Agents move and interact on a 5x5 lattice, while the environment provides inputs with sigma-scheduled Gaussian blur. We examine monocultural populations (Western-only, Asian-only) and mixed environments with balanced (5/5) and imbalanced (8/2, 2/8) compositions, as well as different spatial contact structures. Results show clear asymmetric degradation curves between cultural groups: JAFFE (Asian) populations maintain higher performance at low blur but exhibit sharper drops at intermediate stages, whereas KDEF (Western) populations degrade more uniformly. Mixed populations exhibit intermediate patterns, with balanced mixtures mitigating early degradation, but imbalanced settings amplify majority-group weaknesses under high blur. These findings quantify how cultural composition and interaction structure influence the robustness of FER as perceptual conditions deteriorate.

---

### Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization

Authors: Yang Li, Zhichen Dong, Yuhan Sun, Weixun Wang, Shaopan Xiong, Yijia Luo, Jiashun Liu, Han Lu, Jiamang Wang, Wenbo Su, Bo Zheng, Junchi Yan
Published: 2025-10-15
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.13554v2

The reasoning pattern of Large language models (LLMs) remains opaque, and reinforcement learning (RL) typically applies uniform credit across an entire generation, blurring the distinction between pivotal and routine steps. This work positions attention as a privileged substrate that renders the internal logic of LLMs legible, not merely as a byproduct of computation, but as a mechanistic blueprint of reasoning itself. We first distinguish attention heads between locally and globally focused information processing and reveal that locally focused heads produce a sawtooth pattern near the diagonal indicating phrasal chunks, while globally focused heads expose tokens that exert broad downstream influence over future tokens. We formalize these with two metrics: 1) Windowed Average Attention Distance, which measures the extent of backward attention within a clipped window; 2) Future Attention Influence, which quantifies a token's global importance as the average attention it receives from subsequent tokens. Taken together, these signals reveal a recurring preplan-and-anchor mechanism, where the model first performs a long-range contextual reference to generate an introductory token, which is immediately followed by or coincides with a semantic anchor token that organizes subsequent reasoning. Leveraging these insights, we introduce three novel RL strategies that dynamically perform targeted credit assignment to critical nodes (preplan tokens, anchor tokens, and their temporal coupling) and show consistent performance gains across various reasoning tasks. By aligning optimization with the model's intrinsic reasoning rhythm, we aim to transform opaque optimization into an actionable structure-aware process, hoping to offer a potential step toward more transparent and effective optimization of LLM reasoning.

---

### Tandem Training for Language Models

Authors: Robert West, Ashton Anderson, Ece Kamar, Eric Horvitz
Published: 2025-10-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.13551v2

As language models continue to rapidly improve, we can expect their actions and reasoning to become difficult or impossible for weaker agents and humans to follow, undermining interpretability and oversight. With an eye on long-term futures, we pursue methods that encourage models to produce solutions that remain intelligible to weaker collaborators. We formalize intelligibility as handoff robustness: a strong model's solution is intelligible to a weaker model if randomly handing off control to the weaker model along the solution path does not cause failure. Building on this criterion, we introduce tandem training for language models, a reinforcement learning (RL) paradigm in which rollout tokens are intermittently and randomly sampled from a frozen weak model rather than the strong model being trained. Because rollouts succeed only when the strong model's actions and reasoning process can be continued by the weak model -- when the two can co-construct a successful solution -- optimizing standard RL objectives with tandem training implicitly incentivizes both correctness and intelligibility. In the GSM8K math reasoning task, tandem training reliably teaches models to abandon jargon and adapt their language to weaker partners while keeping task accuracy high. Our results demonstrate a promising route to building AI systems that remain auditable by weaker agents, with implications for human--AI collaboration and multi-agent communication.

---

### Accelerated Feature Detectors for Visual SLAM: A Comparative Study of FPGA vs GPU

Authors: Ruiqi Ye, Mikel Luján
Published: 2025-10-15
Categories: cs.CV, cs.ET, cs.PF, cs.RO
arXiv: https://arxiv.org/abs/2510.13546v1

Feature detection is a common yet time-consuming module in Simultaneous Localization and Mapping (SLAM) implementations, which are increasingly deployed on power-constrained platforms, such as drones. Graphics Processing Units (GPUs) have been a popular accelerator for computer vision in general, and feature detection and SLAM in particular. On the other hand, System-on-Chips (SoCs) with integrated Field Programmable Gate Array (FPGA) are also widely available. This paper presents the first study of hardware-accelerated feature detectors considering a Visual SLAM (V-SLAM) pipeline. We offer new insights by comparing the best GPU-accelerated FAST, Harris, and SuperPoint implementations against the FPGA-accelerated counterparts on modern SoCs (Nvidia Jetson Orin and AMD Versal). The evaluation shows that when using a non-learning-based feature detector such as FAST and Harris, their GPU implementations, and the GPU-accelerated V-SLAM can achieve better run-time performance and energy efficiency than the FAST and Harris FPGA implementations as well as the FPGA-accelerated V-SLAM. However, when considering a learning-based detector such as SuperPoint, its FPGA implementation can achieve better run-time performance and energy efficiency (up to 3.1$\times$ and 1.4$\times$ improvements, respectively) than the GPU implementation. The FPGA-accelerated V-SLAM can also achieve comparable run-time performance compared to the GPU-accelerated V-SLAM, with better FPS in 2 out of 5 dataset sequences. When considering the accuracy, the results show that the GPU-accelerated V-SLAM is more accurate than the FPGA-accelerated V-SLAM in general. Last but not least, the use of hardware acceleration for feature detection could further improve the performance of the V-SLAM pipeline by having the global bundle adjustment module invoked less frequently without sacrificing accuracy.

---

### In-Browser LLM-Guided Fuzzing for Real-Time Prompt Injection Testing in Agentic AI Browsers

Authors: Avihay Cohen
Published: 2025-10-15
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2510.13543v1

Large Language Model (LLM) based agents integrated into web browsers (often called agentic AI browsers) offer powerful automation of web tasks. However, they are vulnerable to indirect prompt injection attacks, where malicious instructions hidden in a webpage deceive the agent into unwanted actions. These attacks can bypass traditional web security boundaries, as the AI agent operates with the user privileges across sites. In this paper, we present a novel fuzzing framework that runs entirely in the browser and is guided by an LLM to automatically discover such prompt injection vulnerabilities in real time.

---

### ProtoTopic: Prototypical Network for Few-Shot Medical Topic Modeling

Authors: Martin Licht, Sara Ketabi, Farzad Khalvati
Published: 2025-10-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.13542v1

Topic modeling is a useful tool for analyzing large corpora of written documents, particularly academic papers. Despite a wide variety of proposed topic modeling techniques, these techniques do not perform well when applied to medical texts. This can be due to the low number of documents available for some topics in the healthcare domain. In this paper, we propose ProtoTopic, a prototypical network-based topic model used for topic generation for a set of medical paper abstracts. Prototypical networks are efficient, explainable models that make predictions by computing distances between input datapoints and a set of prototype representations, making them particularly effective in low-data or few-shot learning scenarios. With ProtoTopic, we demonstrate improved topic coherence and diversity compared to two topic modeling baselines used in the literature, demonstrating the ability of our model to generate medically relevant topics even with limited data.

---

### Learning Neural Parametric 3D Breast Shape Models for Metrical Surface Reconstruction From Monocular RGB Videos

Authors: Maximilian Weiherer, Antonia von Riedheim, Vanessa Brébant, Bernhard Egger, Christoph Palm
Published: 2025-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.13540v2

We present a neural parametric 3D breast shape model and, based on this model, introduce a low-cost and accessible 3D surface reconstruction pipeline capable of recovering accurate breast geometry from a monocular RGB video. In contrast to widely used, commercially available yet prohibitively expensive 3D breast scanning solutions and existing low-cost alternatives, our method requires neither specialized hardware nor proprietary software and can be used with any device that is able to record RGB videos. The key building blocks of our pipeline are a state-of-the-art, off-the-shelf Structure-from-motion pipeline, paired with a parametric breast model for robust and metrically correct surface reconstruction. Our model, similarly to the recently proposed implicit Regensburg Breast Shape Model (iRBSM), leverages implicit neural representations to model breast shapes. However, unlike the iRBSM, which employs a single global neural signed distance function (SDF), our approach -- inspired by recent state-of-the-art face models -- decomposes the implicit breast domain into multiple smaller regions, each represented by a local neural SDF anchored at anatomical landmark positions. When incorporated into our surface reconstruction pipeline, the proposed model, dubbed liRBSM (short for localized iRBSM), significantly outperforms the iRBSM in terms of reconstruction quality, yielding more detailed surface reconstruction than its global counterpart. Overall, we find that the introduced pipeline is able to recover high-quality 3D breast geometry within an error margin of less than 2 mm. Our method is fast (requires less than six minutes), fully transparent and open-source, and -- together with the model -- publicly available at https://rbsm.re-mic.de/local-implicit.

---

### K-Merge: Online Continual Merging of Adapters for On-device Large Language Models

Authors: Donald Shenaj, Ondrej Bohdal, Taha Ceritli, Mete Ozay, Pietro Zanuttigh, Umberto Michieli
Published: 2025-10-15
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.13537v2

On-device deployment of Large Language Models (LLMs) frequently leverages Low-Rank Adapters (LoRAs) to support diverse downstream tasks under tight resource constraints. To address the limited storage capacity of mobile devices, recent works have explored model merging techniques to fuse multiple LoRAs into a single one. In practice, however, LoRAs are often delivered incrementally, as users request support for new tasks (e.g., novel problem types or languages). This scenario introduces a new challenge: on-device online continual merging, where the objective is to incorporate new LoRAs while preserving the performance on previously supported tasks. In this paper, we propose a data-free and computationally efficient strategy for selecting and merging LoRAs when a new one becomes available, assuming the device can store only a limited number of adapters. Extensive experiments across real-world tasks demonstrate the superiority of our approach compared to alternative strategies while adhering to the storage budget and compute limitations of on-device settings. The project page is available at: https://donaldssh.github.io/K-Merge.

---

### High Semantic Features for the Continual Learning of Complex Emotions: a Lightweight Solution

Authors: Thibault Geoffroy, Gauthier Gerspacher, Lionel Prevost
Published: 2025-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.13534v2

Incremental learning is a complex process due to potential catastrophic forgetting of old tasks when learning new ones. This is mainly due to transient features that do not fit from task to task. In this paper, we focus on complex emotion recognition. First, we learn basic emotions and then, incrementally, like humans, complex emotions. We show that Action Units, describing facial muscle movements, are non-transient, highly semantical features that outperform those extracted by both shallow and deep convolutional neural networks. Thanks to this ability, our approach achieves interesting results when learning incrementally complex, compound emotions with an accuracy of 0.75 on the CFEE dataset and can be favorably compared to state-of-the-art results. Moreover, it results in a lightweight model with a small memory footprint.

---

### A Methodology for Assessing the Risk of Metric Failure in LLMs Within the Financial Domain

Authors: William Flanagan, Mukunda Das, Rajitha Ramanayake, Swanuja Maslekar, Meghana Mangipudi, Joong Ho Choi, Shruti Nair, Shambhavi Bhusan, Sanjana Dulam, Mouni Pendharkar, Nidhi Singh, Vashisth Doshi et al.
Published: 2025-10-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.13524v2

As Generative Artificial Intelligence is adopted across the financial services industry, a significant barrier to adoption and usage is measuring model performance. Historical machine learning metrics can oftentimes fail to generalize to GenAI workloads and are often supplemented using Subject Matter Expert (SME) Evaluation. Even in this combination, many projects fail to account for various unique risks present in choosing specific metrics. Additionally, many widespread benchmarks created by foundational research labs and educational institutions fail to generalize to industrial use. This paper explains these challenges and provides a Risk Assessment Framework to allow for better application of SME and machine learning Metrics

---

### Data-driven learning of feedback maps for explicit robust predictive control: an approximation theoretic view

Authors: Siddhartha Ganguly, Shubham Gupta, Debasish Chatterjee
Published: 2025-10-15
Categories: math.OC, cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2510.13522v1

We establish an algorithm to learn feedback maps from data for a class of robust model predictive control (MPC) problems. The algorithm accounts for the approximation errors due to the learning directly at the synthesis stage, ensuring recursive feasibility by construction. The optimal control problem consists of a linear noisy dynamical system, a quadratic stage and quadratic terminal costs as the objective, and convex constraints on the state, control, and disturbance sequences; the control minimizes and the disturbance maximizes the objective. We proceed via two steps -- (a) Data generation: First, we reformulate the given minmax problem into a convex semi-infinite program and employ recently developed tools to solve it in an exact fashion on grid points of the state space to generate (state, action) data. (b) Learning approximate feedback maps: We employ a couple of approximation schemes that furnish tight approximations within preassigned uniform error bounds on the admissible state space to learn the unknown feedback policy. The stability of the closed-loop system under the approximate feedback policies is also guaranteed under a standard set of hypotheses. Two benchmark numerical examples are provided to illustrate the results.

---

### Narrow Operator Models of Stellarator Equilibria in Fourier Zernike Basis

Authors: Timo Thun, Rory Conlin, Dario Panici, Daniel Böckenhoff
Published: 2025-10-15
Categories: physics.plasm-ph, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.13521v2

Numerical computation of the ideal Magnetohydrodynamic (MHD) equilibrium magnetic field is at the base of stellarator optimisation and provides the starting point for solving more sophisticated Partial Differential Equations (PDEs) like transport or turbulence models. Conventional approaches solve for a single stationary point of the ideal MHD equations, which is fully defined by three invariants and the numerical scheme employed by the solver. We present the first numerical approach that can solve for a continuous distribution of equilibria with fixed boundary and rotational transform, varying only the pressure invariant. This approach minimises the force residual by optimising parameters of multilayer perceptrons (MLP) that map from a scalar pressure multiplier to the Fourier Zernike basis as implemented in the modern stellarator equilibrium solver DESC.

---

### UniME-V2: MLLM-as-a-Judge for Universal Multimodal Embedding Learning

Authors: Tiancheng Gu, Kaicheng Yang, Kaichen Zhang, Xiang An, Ziyong Feng, Yueyi Zhang, Weidong Cai, Jiankang Deng, Lidong Bing
Published: 2025-10-15
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.13515v3

Universal multimodal embedding models are foundational to various tasks. Existing approaches typically employ in-batch negative mining by measuring the similarity of query-candidate pairs. However, these methods often struggle to capture subtle semantic differences among candidates and lack diversity in negative samples. Moreover, the embeddings exhibit limited discriminative ability in distinguishing false and hard negatives. In this paper, we leverage the advanced understanding capabilities of MLLMs to enhance representation learning and present a novel Universal Multimodal Embedding (UniME-V2) model. Our approach first constructs a potential hard negative set through global retrieval. We then introduce the MLLM-as-a-Judge mechanism, which utilizes MLLMs to assess the semantic alignment of query-candidate pairs and generate soft semantic matching scores. These scores serve as a foundation for hard negative mining, mitigating the impact of false negatives and enabling the identification of diverse, high-quality hard negatives. Furthermore, the semantic matching scores are used as soft labels to mitigate the rigid one-to-one mapping constraint. By aligning the similarity matrix with the soft semantic matching score matrix, the model learns semantic distinctions among candidates, significantly enhancing its discriminative capacity. To further improve performance, we propose UniME-V2-Reranker, a reranking model trained on our mined hard negatives through a joint pairwise and listwise optimization approach. We conduct comprehensive experiments on the MMEB benchmark and multiple retrieval tasks, demonstrating that our method achieves state-of-the-art performance on average across all tasks.

---

### Offline and Online KL-Regularized RLHF under Differential Privacy

Authors: Yulian Wu, Rushil Thareja, Praneeth Vepakomma, Francesco Orabona
Published: 2025-10-15
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.13512v1

In this paper, we study the offline and online settings of reinforcement learning from human feedback (RLHF) with KL-regularization -- a widely used objective function in large language model alignment -- under the $ε$ local differential privacy ($ε$-LDP) model on the label of the human preference. In the offline setting, we design an algorithm based on the principle of pessimism and derive a new suboptimality gap of $\tilde{O}(1/((e^ε-1)^2 n))$ on the KL-regularized objective under single-policy concentrability. We also prove its optimality by providing a matching lower bound where $n$ is the sample size. In the online setting, we are the first one to theoretically investigate the problem of KL-regularized RLHF with LDP. We design an optimism-based algorithm and derive a logarithmic regret bound of $O(d_{\mathcal{F}}\log (N_{\mathcal{F}}\cdot T) /(e^ε-1)^2 )$, where $T$ is the total time step, $N_{\mathcal{F}}$ is cardinality of the reward function space $\mathcal{F}$ and $d_{\mathcal{F}}$ is a variant of eluder dimension for RLHF. As a by-product of our analysis, our results also imply the first analysis for online KL-regularized RLHF without privacy. We implement our algorithm in the offline setting to verify our theoretical results and release our open source code at: https://github.com/rushil-thareja/PPKL-RLHF-Official.

---

### Confidence as a Reward: Transforming LLMs into Reward Models

Authors: He Du, Bowen Li, Chengxing Xie, Chang Gao, Kai Chen, Dacheng Tao
Published: 2025-10-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.13501v1

Reward models can significantly enhance the reasoning capabilities of large language models (LLMs), but they typically require extensive curated data and costly training. To mitigate these challenges, training-free approaches such as LLM-as-a-Judge leverage the intrinsic reasoning abilities of LLMs to evaluate responses, achieving promising results. Recent works have also indicated that model confidence can serve effectively as a reward metric, distinguishing between chain-of-thought (CoT) and non-CoT paths. However, the concept of using confidence as a reward has not been comprehensively studied. In this work, we systematically investigate Confidence-as-a-Reward (CRew), a simple yet powerful training-free method that utilizes token-level confidence in the model's final answers as a proxy for reward, especially suitable for close-ended tasks. Through extensive experiments on mathematical reasoning tasks, we demonstrate that CRew outperforms existing training-free reward approaches on the MATH500 and RewardMATH benchmarks, and even surpasses most trained reward models. We further identify a strong correlation between CRew scores and the actual reasoning performance of the model. Additionally, we find that CRew can effectively filter high-quality training data. Building upon these insights, we propose CRew-DPO, a training strategy that constructs preference data from confidence scores combined with correctness signals. Finetuning with CRew-DPO further enhances the model's judging capabilities and consistently outperforms existing self-training methods.

---

### MedREK: Retrieval-Based Editing for Medical LLMs with Key-Aware Prompts

Authors: Shujun Xia, Haokun Lin, Yichen Wu, Yinan Zhou, Zixuan Li, Zhongwei Wan, Xingrun Xing, Yefeng Zheng, Xiang Li, Caifeng Shan, Zhenan Sun, Quanzheng Li
Published: 2025-10-15
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.13500v2

LLMs hold great promise for healthcare applications, but the rapid evolution of medical knowledge and errors in training data often cause them to generate outdated or inaccurate information, limiting their applicability in high-stakes clinical practice. Model editing has emerged as a potential remedy without full retraining. While parameter-based editing often compromises locality and is thus ill-suited for the medical domain, retrieval-based editing offers a more viable alternative. However, it still faces two critical challenges: (1) representation overlap within the medical knowledge space often causes inaccurate retrieval and reduces editing accuracy; (2) existing methods are restricted to single-sample edits, while batch-editing remains largely unexplored despite its importance for real-world medical applications. To address these challenges, we first construct MedVersa, an enhanced benchmark with broader coverage of medical subjects, designed to evaluate both single and batch edits under strict locality constraints. We then propose MedREK, a retrieval-based editing framework that integrates a shared query-key module for precise matching with an attention-based prompt encoder for informative guidance. Experimental results on various medical benchmarks demonstrate that our MedREK achieves superior performance across different core metrics and provides the first validated solution for batch-editing in medical LLMs. Our code and dataset are available at https://github.com/mylittleriver/MedREK.

---

### ConsintBench: Evaluating Language Models on Real-World Consumer Intent Understanding

Authors: Xiaozhe Li, TianYi Lyu, Siyi Yang, Yuxi Gong, Yizhao Yang, Jinxuan Huang, Ligao Zhang, Zhuoyi Huang, Qingwen Liu
Published: 2025-10-15
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.13499v2

Understanding human intent is a complex, high-level task for large language models (LLMs), requiring analytical reasoning, contextual interpretation, dynamic information aggregation, and decision-making under uncertainty. Real-world public discussions, such as consumer product discussions, are rarely linear or involve a single user. Instead, they are characterized by interwoven and often conflicting perspectives, divergent concerns, goals, emotional tendencies, as well as implicit assumptions and background knowledge about usage scenarios. To accurately understand such explicit public intent, an LLM must go beyond parsing individual sentences; it must integrate multi-source signals, reason over inconsistencies, and adapt to evolving discourse, similar to how experts in fields like politics, economics, or finance approach complex, uncertain environments. Despite the importance of this capability, no large-scale benchmark currently exists for evaluating LLMs on real-world human intent understanding, primarily due to the challenges of collecting real-world public discussion data and constructing a robust evaluation pipeline. To bridge this gap, we introduce \bench, the first dynamic, live evaluation benchmark specifically designed for intent understanding, particularly in the consumer domain. \bench is the largest and most diverse benchmark of its kind, supporting real-time updates while preventing data contamination through an automated curation pipeline.

---

### DistilCLIP-EEG: Enhancing Epileptic Seizure Detection Through Multi-modal Learning and Knowledge Distillation

Authors: Zexin Wang, Lin Shi, Haoyu Wu, Junru Luo, Xiangzeng Kong, Jun Qi
Published: 2025-10-15
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.13497v1

Epilepsy is a prevalent neurological disorder marked by sudden, brief episodes of excessive neuronal activity caused by abnormal electrical discharges, which may lead to some mental disorders. Most existing deep learning methods for epilepsy detection rely solely on unimodal EEG signals, neglecting the potential benefits of multimodal information. To address this, we propose a novel multimodal model, DistilCLIP-EEG, based on the CLIP framework, which integrates both EEG signals and text descriptions to capture comprehensive features of epileptic seizures. The model involves an EEG encoder based on the Conformer architecture as a text encoder, the proposed Learnable BERT (BERT-LP) as prompt learning within the encoders. Both operate in a shared latent space for effective cross-modal representation learning. To enhance efficiency and adaptability, we introduce a knowledge distillation method where the trained DistilCLIP-EEG serves as a teacher to guide a more compact student model to reduce training complexity and time. On the TUSZ, AUBMC, and CHB-MIT datasets, both the teacher and student models achieved accuracy rates exceeding 97%. Across all datasets, the F1-scores were consistently above 0.94, demonstrating the robustness and reliability of the proposed framework. Moreover, the student model's parameter count and model size are approximately 58.1% of those of the teacher model, significantly reducing model complexity and storage requirements while maintaining high performance. These results highlight the potential of our proposed model for EEG-based epilepsy detection and establish a solid foundation for deploying lightweight models in resource-constrained settings.

---

### Data-intrinsic approximation in metric spaces

Authors: Jürgen Dölz, Michael Multerer
Published: 2025-10-15
Categories: math.NA, stat.ML
arXiv: https://arxiv.org/abs/2510.13496v3

Analysis and processing of data is a vital part of our modern society and requires vast amounts of computational resources. To reduce the computational burden, compressing and approximating data has become a central topic. We consider the approximation of labeled data samples, mathematically described as site-to-value maps between finite metric spaces. Within this setting, we identify the discrete modulus of continuity as an effective data-intrinsic quantity to measure regularity of site-to-value maps without imposing further structural assumptions. We investigate the consistency of the discrete modulus of continuity in the infinite data limit and propose an algorithm for its efficient computation. Building on these results, we present a sample based approximation theory for labeled data. For data subject to statistical uncertainty we consider multilevel approximation spaces and a variant of the multilevel Monte Carlo method to compute statistical quantities of interest. Our considerations connect approximation theory for labeled data in metric spaces to the covering problem for (random) balls on the one hand and the efficient evaluation of the discrete modulus of continuity to combinatorial optimization on the other hand. We provide extensive numerical studies to illustrate the feasibility of the approach and to validate our theoretical results.

---

### LiteraryQA: Towards Effective Evaluation of Long-document Narrative QA

Authors: Tommaso Bonomo, Luca Gioffré, Roberto Navigli
Published: 2025-10-15
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.13494v1

Question Answering (QA) on narrative text poses a unique challenge to current systems, requiring a deep understanding of long, complex documents. However, the reliability of NarrativeQA, the most widely used benchmark in this domain, is hindered by noisy documents and flawed QA pairs. In this work, we introduce LiteraryQA, a high-quality subset of NarrativeQA focused on literary works. Using a human- and LLM-validated pipeline, we identify and correct low-quality QA samples while removing extraneous text from source documents. We then carry out a meta-evaluation of automatic metrics to clarify how systems should be evaluated on LiteraryQA. This analysis reveals that all n-gram-based metrics have a low system-level correlation to human judgment, while LLM-as-a-Judge evaluations, even with small open-weight models, can strongly agree with the ranking identified by humans. Finally, we benchmark a set of long-context LLMs on LiteraryQA. We release our code and data at https://github.com/SapienzaNLP/LiteraryQA.

---

### ExpressNet-MoE: A Hybrid Deep Neural Network for Emotion Recognition

Authors: Deeptimaan Banerjee, Prateek Gothwal, Ashis Kumer Biswas
Published: 2025-10-15
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.13493v2

In many domains, including online education, healthcare, security, and human-computer interaction, facial emotion recognition (FER) is essential. Real-world FER is still difficult despite its significance because of some factors such as variable head positions, occlusions, illumination shifts, and demographic diversity. Engagement detection, which is essential for applications like virtual learning and customer services, is frequently challenging due to FER limitations by many current models. In this article, we propose ExpressNet-MoE, a novel hybrid deep learning model that blends both Convolution Neural Networks (CNNs) and Mixture of Experts (MoE) framework, to overcome the difficulties. Our model dynamically chooses the most pertinent expert networks, thus it aids in the generalization and providing flexibility to model across a wide variety of datasets. Our model improves on the accuracy of emotion recognition by utilizing multi-scale feature extraction to collect both global and local facial features. ExpressNet-MoE includes numerous CNN-based feature extractors, a MoE module for adaptive feature selection, and finally a residual network backbone for deep feature learning. To demonstrate efficacy of our proposed model we evaluated on several datasets, and compared with current state-of-the-art methods. Our model achieves accuracies of 74.77% on AffectNet (v7), 72.55% on AffectNet (v8), 84.29% on RAF-DB, and 64.66% on FER-2013. The results show how adaptive our model is and how it may be used to develop end-to-end emotion recognition systems in practical settings. Reproducible codes and results are made publicly accessible at https://github.com/DeeptimaanB/ExpressNet-MoE.

---

### Tahakom LLM Guidelines and Recipes: From Pre-training Data to an Arabic LLM

Authors: Areej AlOtaibi, Lina Alyahya, Raghad Alshabanah, Shahad Alfawzan, Shuruq Alarefei, Reem Alsabti, Nouf Alsubaie, Abdulaziz Alhuzaymi, Lujain Alkhelb, Majd Alsayari, Waad Alahmed, Omar Talabay et al.
Published: 2025-10-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.13481v2

Large Language Models (LLMs) have significantly advanced the field of natural language processing, enhancing capabilities in both language understanding and generation across diverse domains. However, developing LLMs for Arabic presents unique challenges. This paper explores these challenges by focusing on critical aspects such as data curation, tokenizer design, and evaluation. We detail our approach to the collection and filtration of Arabic pre-training datasets, assess the impact of various tokenizer designs on model performance, and examine the limitations of existing Arabic evaluation frameworks, for which we propose a systematic corrective methodology. To promote transparency and facilitate collaborative development, we share our data and methodologies, contributing to the advancement of language modeling, particularly for the Arabic language.

---

### Towards Blackwell Optimality: Bellman Optimality Is All You Can Get

Authors: Victor Boone, Adrienne Tuynman
Published: 2025-10-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.13476v1

Although average gain optimality is a commonly adopted performance measure in Markov Decision Processes (MDPs), it is often too asymptotic. Further incorporating measures of immediate losses leads to the hierarchy of bias optimalities, all the way up to Blackwell optimality. In this paper, we investigate the problem of identifying policies of such optimality orders. To that end, for each order, we construct a learning algorithm with vanishing probability of error. Furthermore, we characterize the class of MDPs for which identification algorithms can stop in finite time. That class corresponds to the MDPs with a unique Bellman optimal policy, and does not depend on the optimality order considered. Lastly, we provide a tractable stopping rule that when coupled to our learning algorithm triggers in finite time whenever it is possible to do so.

---

### Through the Lens of Doubt: Robust and Efficient Uncertainty Estimation for Visual Place Recognition

Authors: Emily Miller, Michael Milford, Muhammad Burhan Hafez, SD Ramchurn, Shoaib Ehsan
Published: 2025-10-15
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2510.13464v1

Visual Place Recognition (VPR) enables robots and autonomous vehicles to identify previously visited locations by matching current observations against a database of known places. However, VPR systems face significant challenges when deployed across varying visual environments, lighting conditions, seasonal changes, and viewpoints changes. Failure-critical VPR applications, such as loop closure detection in simultaneous localization and mapping (SLAM) pipelines, require robust estimation of place matching uncertainty. We propose three training-free uncertainty metrics that estimate prediction confidence by analyzing inherent statistical patterns in similarity scores from any existing VPR method. Similarity Distribution (SD) quantifies match distinctiveness by measuring score separation between candidates; Ratio Spread (RS) evaluates competitive ambiguity among top-scoring locations; and Statistical Uncertainty (SU) is a combination of SD and RS that provides a unified metric that generalizes across datasets and VPR methods without requiring validation data to select the optimal metric. All three metrics operate without additional model training, architectural modifications, or computationally expensive geometric verification. Comprehensive evaluation across nine state-of-the-art VPR methods and six benchmark datasets confirms that our metrics excel at discriminating between correct and incorrect VPR matches, and consistently outperform existing approaches while maintaining negligible computational overhead, making it deployable for real-time robotic applications across varied environmental conditions with improved precision-recall performance.

---

### Mobile Coverage Analysis using Crowdsourced Data

Authors: Timothy Wong, Tom Freeman, Joseph Feehily
Published: 2025-10-15
Categories: cs.AI, cs.CE, cs.NI, stat.AP
arXiv: https://arxiv.org/abs/2510.13459v2

Effective assessment of mobile network coverage and the precise identification of service weak spots are paramount for network operators striving to enhance user Quality of Experience (QoE). This paper presents a novel framework for mobile coverage and weak spot analysis utilising crowdsourced QoE data. The core of our methodology involves coverage analysis at the individual cell (antenna) level, subsequently aggregated to the site level, using empirical geolocation data. A key contribution of this research is the application of One-Class Support Vector Machine (OC-SVM) algorithm for calculating mobile network coverage. This approach models the decision hyperplane as the effective coverage contour, facilitating robust calculation of coverage areas for individual cells and entire sites. The same methodology is extended to analyse crowdsourced service loss reports, thereby identifying and quantifying geographically localised weak spots. Our findings demonstrate the efficacy of this novel framework in accurately mapping mobile coverage and, crucially, in highlighting granular areas of signal deficiency, particularly within complex urban environments.

---

### Text-to-3D by Stitching a Multi-view Reconstruction Network to a Video Generator

Authors: Hyojun Go, Dominik Narnhofer, Goutam Bhat, Prune Truong, Federico Tombari, Konrad Schindler
Published: 2025-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.13454v2

The rapid progress of large, pretrained models for both visual content generation and 3D reconstruction opens up new possibilities for text-to-3D generation. Intuitively, one could obtain a formidable 3D scene generator if one were able to combine the power of a modern latent text-to-video model as "generator" with the geometric abilities of a recent (feedforward) 3D reconstruction system as "decoder". We introduce VIST3A, a general framework that does just that, addressing two main challenges. First, the two components must be joined in a way that preserves the rich knowledge encoded in their weights. We revisit model stitching, i.e., we identify the layer in the 3D decoder that best matches the latent representation produced by the text-to-video generator and stitch the two parts together. That operation requires only a small dataset and no labels. Second, the text-to-video generator must be aligned with the stitched 3D decoder, to ensure that the generated latents are decodable into consistent, perceptually convincing 3D scene geometry. To that end, we adapt direct reward finetuning, a popular technique for human preference alignment. We evaluate the proposed VIST3A approach with different video generators and 3D reconstruction models. All tested pairings markedly improve over prior text-to-3D models that output Gaussian splats. Moreover, by choosing a suitable 3D base model, VIST3A also enables high-quality text-to-pointmap generation.

---

### Near-Infrared Hyperspectral Imaging Applications in Food Analysis -- Improving Algorithms and Methodologies

Authors: Ole-Christian Galbo Engstrøm
Published: 2025-10-15
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.13452v1

This thesis investigates the application of near-infrared hyperspectral imaging (NIR-HSI) for food quality analysis. The investigation is conducted through four studies operating with five research hypotheses. For several analyses, the studies compare models based on convolutional neural networks (CNNs) and partial least squares (PLS). Generally, joint spatio-spectral analysis with CNNs outperforms spatial analysis with CNNs and spectral analysis with PLS when modeling parameters where chemical and physical visual information are relevant. When modeling chemical parameters with a 2-dimensional (2D) CNN, augmenting the CNN with an initial layer dedicated to performing spectral convolution enhances its predictive performance by learning a spectral preprocessing similar to that applied by domain experts. Still, PLS-based spectral modeling performs equally well for analysis of the mean content of chemical parameters in samples and is the recommended approach. Modeling the spatial distribution of chemical parameters with NIR-HSI is limited by the ability to obtain spatially resolved reference values. Therefore, a study used bulk mean references for chemical map generation of fat content in pork bellies. A PLS-based approach gave non-smooth chemical maps and pixel-wise predictions outside the range of 0-100\%. Conversely, a 2D CNN augmented with a spectral convolution layer mitigated all issues arising with PLS. The final study attempted to model barley's germinative capacity by analyzing NIR spectra, RGB images, and NIR-HSI images. However, the results were inconclusive due to the dataset's low degree of germination. Additionally, this thesis has led to the development of two open-sourced Python packages. The first facilitates fast PLS-based modeling, while the second facilitates very fast cross-validation of PLS and other classical machine learning models with a new algorithm.

---

### $L_2$-Regularized Empirical Risk Minimization Guarantees Small Smooth Calibration Error

Authors: Masahiro Fujisawa, Futoshi Futami
Published: 2025-10-15
Categories: cs.LG, math.ST, stat.ML
arXiv: https://arxiv.org/abs/2510.13450v1

Calibration of predicted probabilities is critical for reliable machine learning, yet it is poorly understood how standard training procedures yield well-calibrated models. This work provides the first theoretical proof that canonical $L_{2}$-regularized empirical risk minimization directly controls the smooth calibration error (smCE) without post-hoc correction or specialized calibration-promoting regularizer. We establish finite-sample generalization bounds for smCE based on optimization error, regularization strength, and the Rademacher complexity. We then instantiate this theory for models in reproducing kernel Hilbert spaces, deriving concrete guarantees for kernel ridge and logistic regression. Our experiments confirm these specific guarantees, demonstrating that $L_{2}$-regularized ERM can provide a well-calibrated model without boosting or post-hoc recalibration. The source code to reproduce all experiments is available at https://github.com/msfuji0211/erm_calibration.

---

### Robust Minimax Boosting with Performance Guarantees

Authors: Santiago Mazuelas, Veronica Alvarez
Published: 2025-10-15
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.13445v1

Boosting methods often achieve excellent classification accuracy, but can experience notable performance degradation in the presence of label noise. Existing robust methods for boosting provide theoretical robustness guarantees for certain types of label noise, and can exhibit only moderate performance degradation. However, previous theoretical results do not account for realistic types of noise and finite training sizes, and existing robust methods can provide unsatisfactory accuracies, even without noise. This paper presents methods for robust minimax boosting (RMBoost) that minimize worst-case error probabilities and are robust to general types of label noise. In addition, we provide finite-sample performance guarantees for RMBoost with respect to the error obtained without noise and with respect to the best possible error (Bayes risk). The experimental results corroborate that RMBoost is not only resilient to label noise but can also provide strong classification accuracy.

---

### Neural Sum-of-Squares: Certifying the Nonnegativity of Polynomials with Transformers

Authors: Nico Pelleriti, Christoph Spiegel, Shiwei Liu, David Martínez-Rubio, Max Zimmer, Sebastian Pokutta
Published: 2025-10-15
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.13444v1

Certifying nonnegativity of polynomials is a well-known NP-hard problem with direct applications spanning non-convex optimization, control, robotics, and beyond. A sufficient condition for nonnegativity is the Sum of Squares (SOS) property, i.e., it can be written as a sum of squares of other polynomials. In practice, however, certifying the SOS criterion remains computationally expensive and often involves solving a Semidefinite Program (SDP), whose dimensionality grows quadratically in the size of the monomial basis of the SOS expression; hence, various methods to reduce the size of the monomial basis have been proposed. In this work, we introduce the first learning-augmented algorithm to certify the SOS criterion. To this end, we train a Transformer model that predicts an almost-minimal monomial basis for a given polynomial, thereby drastically reducing the size of the corresponding SDP. Our overall methodology comprises three key components: efficient training dataset generation of over 100 million SOS polynomials, design and training of the corresponding Transformer architecture, and a systematic fallback mechanism to ensure correct termination, which we analyze theoretically. We validate our approach on over 200 benchmark datasets, achieving speedups of over $100\times$ compared to state-of-the-art solvers and enabling the solution of instances where competing approaches fail. Our findings provide novel insights towards transforming the practical scalability of SOS programming.

---

### Steerable Conditional Diffusion for Domain Adaptation in PET Image Reconstruction

Authors: George Webber, Alexander Hammers, Andrew P. King, Andrew J. Reader
Published: 2025-10-15
Categories: physics.med-ph, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.13441v1

Diffusion models have recently enabled state-of-the-art reconstruction of positron emission tomography (PET) images while requiring only image training data. However, domain shift remains a key concern for clinical adoption: priors trained on images from one anatomy, acquisition protocol or pathology may produce artefacts on out-of-distribution data. We propose integrating steerable conditional diffusion (SCD) with our previously-introduced likelihood-scheduled diffusion (PET-LiSch) framework to improve the alignment of the diffusion model's prior to the target subject. At reconstruction time, for each diffusion step, we use low-rank adaptation (LoRA) to align the diffusion model prior with the target domain on the fly. Experiments on realistic synthetic 2D brain phantoms demonstrate that our approach suppresses hallucinated artefacts under domain shift, i.e. when our diffusion model is trained on perturbed images and tested on normal anatomy, our approach suppresses the hallucinated structure, outperforming both OSEM and diffusion model baselines qualitatively and quantitatively. These results provide a proof-of-concept that steerable priors can mitigate domain shift in diffusion-based PET reconstruction and motivate future evaluation on real data.

---

### Rectify and Align GPS Points to Parking Spots via Rank-1 Constraint

Authors: Jiaxing Deng, Junbiao Pang, Zhicheng Wang, Haitao Yu
Published: 2025-10-15
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.13439v1

Parking spots are essential components, providing vital mobile resources for residents in a city. Accurate Global Positioning System (GPS) points of parking spots are the core data for subsequent applications,e.g., parking management, parking policy, and urban development. However, high-rise buildings tend to cause GPS points to drift from the actual locations of parking spots; besides, the standard lower-cost GPS equipment itself has a certain location error. Therefore, it is a non-trivial task to correct a few wrong GPS points from a large number of parking spots in an unsupervised approach. In this paper, motivated by the physical constraints of parking spots (i.e., parking spots are parallel to the sides of roads), we propose an unsupervised low-rank method to effectively rectify errors in GPS points and further align them to the parking spots in a unified framework. The proposed unconventional rectification and alignment method is simple and yet effective for any type of GPS point errors. Extensive experiments demonstrate the superiority of the proposed method to solve a practical problem. The data set and the code are publicly accessible at:https://github.com/pangjunbiao/ITS-Parking-spots-Dataset.

---

### Near-Optimality of Contrastive Divergence Algorithms

Authors: Pierre Glaser, Kevin Han Huang, Arthur Gretton
Published: 2025-10-15
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.13438v1

We perform a non-asymptotic analysis of the contrastive divergence (CD) algorithm, a training method for unnormalized models. While prior work has established that (for exponential family distributions) the CD iterates asymptotically converge at an $O(n^{-1 / 3})$ rate to the true parameter of the data distribution, we show, under some regularity assumptions, that CD can achieve the parametric rate $O(n^{-1 / 2})$. Our analysis provides results for various data batching schemes, including the fully online and minibatch ones. We additionally show that CD can be near-optimal, in the sense that its asymptotic variance is close to the Cramér-Rao lower bound.

---

### Hybrid Interval Type-2 Mamdani-TSK Fuzzy System for Regression Analysis

Authors: Ashish Bhatia, Renato Cordeiro de Amorim, Vito De Feo
Published: 2025-10-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.13437v1

Regression analysis is employed to examine and quantify the relationships between input variables and a dependent and continuous output variable. It is widely used for predictive modelling in fields such as finance, healthcare, and engineering. However, traditional methods often struggle with real-world data complexities, including uncertainty and ambiguity. While deep learning approaches excel at capturing complex non-linear relationships, they lack interpretability and risk over-fitting on small datasets. Fuzzy systems provide an alternative framework for handling uncertainty and imprecision, with Mamdani and Takagi-Sugeno-Kang (TSK) systems offering complementary strengths: interpretability versus accuracy. This paper presents a novel fuzzy regression method that combines the interpretability of Mamdani systems with the precision of TSK models. The proposed approach introduces a hybrid rule structure with fuzzy and crisp components and dual dominance types, enhancing both accuracy and explainability. Evaluations on benchmark datasets demonstrate state-of-the-art performance in several cases, with rules maintaining a component similar to traditional Mamdani systems while improving precision through improved rule outputs. This hybrid methodology offers a balanced and versatile tool for predictive modelling, addressing the trade-off between interpretability and accuracy inherent in fuzzy systems. In the 6 datasets tested, the proposed approach gave the best fuzzy methodology score in 4 datasets, out-performed the opaque models in 2 datasets and produced the best overall score in 1 dataset with the improvements in RMSE ranging from 0.4% to 19%.

---

### $M^2PO$: Multi-Perspective Multi-Pair Preference Optimization for Machine Translation

Authors: Hao Wang, Linlong Xu, Heng Liu, Yangyang Liu, Xiaohu Zhao, Bo Zeng, Liangying Shao, Yichen Dong, Xinwei Wu, Jiang Zhou, Tianyu Dong, xiangxiang Zeng et al.
Published: 2025-10-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.13434v2

Aligning Large Language Models (LLMs) with human preferences is pivotal for Machine Translation (MT), yet current approaches are often hindered by misleading reward signals. Our analysis reveals that prevailing Quality Estimation (QE) models exhibit a systematic blind spot toward partial errors, specifically partial hallucinations and omissions, often favoring superficially fluent but unfaithful translations. To address this issue, we propose $M^2PO$ (Multi-Perspective Multi-Pair Preference Optimization), a data-centric framework for preference optimization in machine translation. First, to correct the bias toward fluency, $M^2PO$ uses a dual-perspective mechanism that decouples semantic fidelity from fluency and prioritizes faithfulness through a curriculum strategy. Second, after correcting this bias, partial errors fall between perfect and severely incorrect translations, making them difficult to learn through standard best-versus-worst comparisons. We therefore introduce a multi-pair objective that leverages the full candidate list to capture these fine-grained error signals. Experiments on WMT23, WMT24, and FLORES-200 show that $M^2PO$ enables a 9B model to outperform leading open-source baselines and achieve parity with proprietary models such as GPT-4o and Gemini-2.0-Flash, demonstrating strong potential for efficient and high-fidelity LLM-based translation. Our code and dataset will be released.

---

### Beyond Pixels: A Differentiable Pipeline for Probing Neuronal Selectivity in 3D

Authors: Pavithra Elumalai, Mohammad Bashiri, Goirik Chakrabarty, Suhas Shrinivasan, Fabian H. Sinz
Published: 2025-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.13433v1

Visual perception relies on inference of 3D scene properties such as shape, pose, and lighting. To understand how visual sensory neurons enable robust perception, it is crucial to characterize their selectivity to such physically interpretable factors. However, current approaches mainly operate on 2D pixels, making it difficult to isolate selectivity for physical scene properties. To address this limitation, we introduce a differentiable rendering pipeline that optimizes deformable meshes to obtain MEIs directly in 3D. The method parameterizes mesh deformations with radial basis functions and learns offsets and scales that maximize neuronal responses while enforcing geometric regularity. Applied to models of monkey area V4, our approach enables probing neuronal selectivity to interpretable 3D factors such as pose and lighting. This approach bridges inverse graphics with systems neuroscience, offering a way to probe neural selectivity with physically grounded, 3D stimuli beyond conventional pixel-based methods.

---

### CoDS: Enhancing Collaborative Perception in Heterogeneous Scenarios via Domain Separation

Authors: Yushan Han, Hui Zhang, Honglei Zhang, Chuntao Ding, Yuanzhouhan Cao, Yidong Li
Published: 2025-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.13432v2

Collaborative perception has been proven to improve individual perception in autonomous driving through multi-agent interaction. Nevertheless, most methods often assume identical encoders for all agents, which does not hold true when these models are deployed in real-world applications. To realize collaborative perception in actual heterogeneous scenarios, existing methods usually align neighbor features to those of the ego vehicle, which is vulnerable to noise from domain gaps and thus fails to address feature discrepancies effectively. Moreover, they adopt transformer-based modules for domain adaptation, which causes the model inference inefficiency on mobile devices. To tackle these issues, we propose CoDS, a Collaborative perception method that leverages Domain Separation to address feature discrepancies in heterogeneous scenarios. The CoDS employs two feature alignment modules, i.e., Lightweight Spatial-Channel Resizer (LSCR) and Distribution Alignment via Domain Separation (DADS). Besides, it utilizes the Domain Alignment Mutual Information (DAMI) loss to ensure effective feature alignment. Specifically, the LSCR aligns the neighbor feature across spatial and channel dimensions using a lightweight convolutional layer. Subsequently, the DADS mitigates feature distribution discrepancy with encoder-specific and encoder-agnostic domain separation modules. The former removes domain-dependent information and the latter captures task-related information. During training, the DAMI loss maximizes the mutual information between aligned heterogeneous features to enhance the domain separation process. The CoDS employs a fully convolutional architecture, which ensures high inference efficiency. Extensive experiments demonstrate that the CoDS effectively mitigates feature discrepancies in heterogeneous scenarios and achieves a trade-off between detection accuracy and inference efficiency.

---

### Modeling Adoptive Cell Therapy in Bladder Cancer from Sparse Biological Data using PINNs

Authors: Kayode Olumoyin, Katarzyna Rejniak
Published: 2025-10-15
Categories: cs.LG, q-bio.CB, q-bio.PE
arXiv: https://arxiv.org/abs/2510.13431v1

Physics-informed neural networks (PINNs) are neural networks that embed the laws of dynamical systems modeled by differential equations into their loss function as constraints. In this work, we present a PINN framework applied to oncology. Here, we seek to learn time-varying interactions due to a combination therapy in a tumor microenvironment. In oncology, experimental data are often sparse and composed of a few time points of tumor volume. By embedding inductive biases derived from prior information about a dynamical system, we extend the physics-informed neural networks (PINN) and incorporate observed biological constraints as regularization agents. The modified PINN algorithm is able to steer itself to a reasonable solution and can generalize well with only a few training examples. We demonstrate the merit of our approach by learning the dynamics of treatment applied intermittently in an ordinary differential equation (ODE) model of a combination therapy. The algorithm yields a solution to the ODE and time-varying forms of some of the ODE model parameters. We demonstrate a strong convergence using metrics such as the mean squared error (MSE), mean absolute error (MAE), and mean absolute percentage error (MAPE).

---

### Evaluating Arabic Large Language Models: A Survey of Benchmarks, Methods, and Gaps

Authors: Ahmed Alzubaidi, Shaikha Alsuwaidi, Basma El Amel Boussaha, Leen AlQadi, Omar Alkaabi, Mohammed Alyafeai, Hamza Alobeidli, Hakim Hacid
Published: 2025-10-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.13430v2

This survey provides the first systematic review of Arabic LLM benchmarks, analyzing 40+ evaluation benchmarks across NLP tasks, knowledge domains, cultural understanding, and specialized capabilities. We propose a taxonomy organizing benchmarks into four categories: Knowledge, NLP Tasks, Culture and Dialects, and Target-Specific evaluations. Our analysis reveals significant progress in benchmark diversity while identifying critical gaps: limited temporal evaluation, insufficient multi-turn dialogue assessment, and cultural misalignment in translated datasets. We examine three primary approaches: native collection, translation, and synthetic generation discussing their trade-offs regarding authenticity, scale, and cost. This work serves as a comprehensive reference for Arabic NLP researchers, providing insights into benchmark methodologies, reproducibility standards, and evaluation metrics while offering recommendations for future development.

---

### Ultra High-Resolution Image Inpainting with Patch-Based Content Consistency Adapter

Authors: Jianhui Zhang, Sheng Cheng, Qirui Sun, Jia Liu, Wang Luyang, Chaoyu Feng, Chen Fang, Lei Lei, Jue Wang, Shuaicheng Liu
Published: 2025-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.13419v1

In this work, we present Patch-Adapter, an effective framework for high-resolution text-guided image inpainting. Unlike existing methods limited to lower resolutions, our approach achieves 4K+ resolution while maintaining precise content consistency and prompt alignment, two critical challenges in image inpainting that intensify with increasing resolution and texture complexity. Patch-Adapter leverages a two-stage adapter architecture to scale the diffusion model's resolution from 1K to 4K+ without requiring structural overhauls: (1) Dual Context Adapter learns coherence between masked and unmasked regions at reduced resolutions to establish global structural consistency; and (2) Reference Patch Adapter implements a patch-level attention mechanism for full-resolution inpainting, preserving local detail fidelity through adaptive feature fusion. This dual-stage architecture uniquely addresses the scalability gap in high-resolution inpainting by decoupling global semantics from localized refinement. Experiments demonstrate that Patch-Adapter not only resolves artifacts common in large-scale inpainting but also achieves state-of-the-art performance on the OpenImages and Photo-Concept-Bucket datasets, outperforming existing methods in both perceptual quality and text-prompt adherence.

---

### Reinforcement Learning Meets Masked Generative Models: Mask-GRPO for Text-to-Image Generation

Authors: Yifu Luo, Xinhao Hu, Keyu Fan, Haoyuan Sun, Zeyu Chen, Bo Xia, Tiantian Zhang, Yongzhe Chang, Xueqian Wang
Published: 2025-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.13418v2

Reinforcement learning (RL) has garnered increasing attention in text-to-image (T2I) generation. However, most existing RL approaches are tailored to either diffusion models or autoregressive models, overlooking an important alternative: masked generative models. In this work, we propose Mask-GRPO, the first method to incorporate Group Relative Policy Optimization (GRPO)-based RL into this overlooked paradigm. Our core insight is to redefine the transition probability, which is different from current approaches, and formulate the unmasking process as a multi-step decision-making problem. To further enhance our method, we explore several useful strategies, including removing the KL constraint, applying the reduction strategy, and filtering out low-quality samples. Using Mask-GRPO, we improve a base model, Show-o, with substantial improvements on standard T2I benchmarks and preference alignment, outperforming existing state-of-the-art approaches. The code is available on https://github.com/xingzhejun/Mask-GRPO

---

### Assessing LLM Reasoning Through Implicit Causal Chain Discovery in Climate Discourse

Authors: Liesbeth Allein, Nataly Pineda-Castañeda, Andrea Rocci, Marie-Francine Moens
Published: 2025-10-15
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.13417v2

How does a cause lead to an effect, and which intermediate causal steps explain their connection? This work scrutinizes the mechanistic causal reasoning capabilities of large language models (LLMs) to answer these questions through the task of implicit causal chain discovery. In a diagnostic evaluation framework, we instruct nine LLMs to generate all possible intermediate causal steps linking given cause-effect pairs in causal chain structures. These pairs are drawn from recent resources in argumentation studies featuring polarized discussion on climate change. Our analysis reveals that LLMs vary in the number and granularity of causal steps they produce. Although they are generally self-consistent and confident about the intermediate causal connections in the generated chains, their judgments are mainly driven by associative pattern matching rather than genuine causal reasoning. Nonetheless, human evaluations confirmed the logical coherence and integrity of the generated chains. Our baseline causal chain discovery approach, insights from our diagnostic evaluation, and benchmark dataset with causal chains lay a solid foundation for advancing future work in implicit, mechanistic causal reasoning in argumentation settings.

---

### Semantic Communication Enabled Holographic Video Processing and Transmission

Authors: Jingkai Ying, Zhiyuan Qi, Yulong Feng, Zhijin Qin, Zhu Han, Rahim Tafazolli, Yonina C. Eldar
Published: 2025-10-15
Categories: eess.IV, cs.AI, cs.IT, cs.MM, eess.SP
arXiv: https://arxiv.org/abs/2510.13408v1

Holographic video communication is considered a paradigm shift in visual communications, becoming increasingly popular for its ability to offer immersive experiences. This article provides an overview of holographic video communication and outlines the requirements of a holographic video communication system. Particularly, following a brief review of semantic com- munication, an architecture for a semantic-enabled holographic video communication system is presented. Key technologies, including semantic sampling, joint semantic-channel coding, and semantic-aware transmission, are designed based on the proposed architecture. Two related use cases are presented to demonstrate the performance gain of the proposed methods. Finally, potential research topics are discussed to pave the way for the realization of semantic-enabled holographic video communications.

---

### Investigating Lexical Change through Cross-Linguistic Colexification Patterns

Authors: Kim Gfeller, Sabine Stoll, Chundra Cathcart, Paul Widmer
Published: 2025-10-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.13407v1

One of the most intriguing features of language is its constant change, with ongoing shifts in how meaning is expressed. Despite decades of research, the factors that determine how and why meanings evolve remain only partly understood. Colexification -- the phenomenon of expressing multiple distinct concepts using the same word form -- serves as a valuable window onto the dynamics of meaning change across languages. Here, we apply phylogenetic comparative models to dictionary data from three language families, Austronesian, Indo-European, and Uralic, in order to shed light on the evolutionary dynamics underlying the colexification of concept pairs. We assess the effects of three predictors: associativity, borrowability, and usage frequency. Our results show that more closely related concept pairs are colexified across a larger portion of the family tree and exhibit slower rates of change. In contrast, concept pairs that are more frequent and more prone to borrowing tend to change more rapidly and are less often colexified. We also find considerable differences between the language families under study, suggesting that areal and cultural factors may play a role.

---

### When Embedding Models Meet: Procrustes Bounds and Applications

Authors: Lucas Maystre, Alvaro Ortega Gonzalez, Charles Park, Rares Dolga, Tudor Berariu, Yu Zhao, Kamil Ciosek
Published: 2025-10-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.13406v1

Embedding models trained separately on similar data often produce representations that encode stable information but are not directly interchangeable. This lack of interoperability raises challenges in several practical applications, such as model retraining, partial model upgrades, and multimodal search. Driven by these challenges, we study when two sets of embeddings can be aligned by an orthogonal transformation. We show that if pairwise dot products are approximately preserved, then there exists an isometry that closely aligns the two sets, and we provide a tight bound on the alignment error. This insight yields a simple alignment recipe, Procrustes post-processing, that makes two embedding models interoperable while preserving the geometry of each embedding space. Empirically, we demonstrate its effectiveness in three applications: maintaining compatibility across retrainings, combining different models for text retrieval, and improving mixed-modality search, where it achieves state-of-the-art performance.

---

### Optimizing Storage Overhead of User Behavior Log for ML-embedded Mobile Apps

Authors: Chen Gong, Yan Zhuang, Zhenzhe Zheng, Yiliu Chen, Sheng Wang, Fan Wu, Guihai Chen
Published: 2025-10-15
Categories: cs.LG, cs.NI
arXiv: https://arxiv.org/abs/2510.13405v1

Machine learning (ML) models are increasingly integrated into modern mobile apps to enable personalized and intelligent services. These models typically rely on rich input features derived from historical user behaviors to capture user intents. However, as ML-driven services become more prevalent, recording necessary user behavior data imposes substantial storage cost on mobile apps, leading to lower system responsiveness and more app uninstalls. To address this storage bottleneck, we present AdaLog, a lightweight and adaptive system designed to improve the storage efficiency of user behavior log in ML-embedded mobile apps, without compromising model inference accuracy or latency. We identify two key inefficiencies in current industrial practices of user behavior log: (i) redundant logging of overlapping behavior data across different features and models, and (ii) sparse storage caused by storing behaviors with heterogeneous attribute descriptions in a single log file. To solve these issues, AdaLog first formulates the elimination of feature-level redundant data as a maximum weighted matching problem in hypergraphs, and proposes a hierarchical algorithm for efficient on-device deployment. Then, AdaLog employs a virtually hashed attribute design to distribute heterogeneous behaviors into a few log files with physically dense storage. Finally, to ensure scalability to dynamic user behavior patterns, AdaLog designs an incremental update mechanism to minimize the I/O operations needed for adapting outdated behavior log. We implement a prototype of AdaLog and deploy it into popular mobile apps in collaboration with our industry partner. Evaluations on real-world user data show that AdaLog reduces behavior log size by 19% to 44% with minimal system overhead (only 2 seconds latency and 15 MB memory usage), providing a more efficient data foundation for broader adoption of on-device ML.

---

### SWIR-LightFusion: Multi-spectral Semantic Fusion of Synthetic SWIR with Thermal IR (LWIR/MWIR) and RGB

Authors: Muhammad Ishfaq Hussain, Ma Van Linh, Zubia Naz, Unse Fatima, Yeongmin Ko, Moongu Jeon
Published: 2025-10-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.13404v2

Enhancing scene understanding in adverse visibility conditions remains a critical challenge for surveillance and autonomous navigation systems. Conventional imaging modalities, such as RGB and thermal infrared (MWIR / LWIR), when fused, often struggle to deliver comprehensive scene information, particularly under conditions of atmospheric interference or inadequate illumination. To address these limitations, Short-Wave Infrared (SWIR) imaging has emerged as a promising modality due to its ability to penetrate atmospheric disturbances and differentiate materials with improved clarity. However, the advancement and widespread implementation of SWIR-based systems face significant hurdles, primarily due to the scarcity of publicly accessible SWIR datasets. In response to this challenge, our research introduces an approach to synthetically generate SWIR-like structural/contrast cues (without claiming spectral reproduction) images from existing LWIR data using advanced contrast enhancement techniques. We then propose a multimodal fusion framework integrating synthetic SWIR, LWIR, and RGB modalities, employing an optimized encoder-decoder neural network architecture with modality-specific encoders and a softmax-gated fusion head. Comprehensive experiments on public RGB-LWIR benchmarks (M3FD, TNO, CAMEL, MSRS, RoadScene) and an additional private real RGB-MWIR-SWIR dataset demonstrate that our synthetic-SWIR-enhanced fusion framework improves fused-image quality (contrast, edge definition, structural fidelity) while maintaining real-time performance. We also add fair trimodal baselines (LP, LatLRR, GFF) and cascaded trimodal variants of U2Fusion/SwinFusion under a unified protocol. The outcomes highlight substantial potential for real-world applications in surveillance and autonomous systems.

---

### F-BFQ: Flexible Block Floating-Point Quantization Accelerator for LLMs

Authors: Jude Haris, José Cano
Published: 2025-10-15
Categories: cs.AR, cs.DC, cs.LG
arXiv: https://arxiv.org/abs/2510.13401v1

Large Language Models (LLMs) have become increasingly prominent for daily tasks, from improving sound-totext translation to generating additional frames for the latest video games. With the help of LLM inference frameworks, such as llama.cpp, which support optimizations such as KV-caching and quantization, it is now easier than ever to deploy LLMs on edge devices. Quantization is fundamental to enable LLMs on resource-constrained edge devices, and llama.cpp utilizes block floating point (BFP) quantization to drastically reduce the bit width of weights and input tensors, the memory footprint, and the computational power required to run LLMs. LLMs are typically quantized with mixed BFP quantization across the model layers to reduce the loss of model accuracy due to quantization. Therefore, to efficiently accelerate across the layers of BFP-quantized LLMs, specialized accelerators need to support different BFP variants without reconfiguration. To address this issue, we propose a Flexible Block FloatingPoint Quantization (F-BFQ) accelerator, which can dynamically switch between two BFP quantization variants and perform matrix multiplication (MatMul) operations. Our initial F-BFQ accelerator design, deployed on the AMD Kria board, reduces inference time by 1.4x on average over the Arm NEON-based CPU execution across three BFP quantized LLMs while achieving 5.2 tokens per second (~3.9 words per second).

---

### From Minimal Existence to Human Definition: The CES-IMU-HSG Theoretical Framework

Authors: Kei Itoh
Published: 2025-10-15
Categories: cs.NE, cs.AI, cs.LO
arXiv: https://arxiv.org/abs/2510.13400v1

This study presents an inter-universal mathematical-logical framework constructed upon the minimal axiom Cogito, ergo sum (CES), integrating the Intermediate Meta-Universe (IMU) and the Hierarchical State Grid (HSG). The CES defines existence as a reflexive correspondence --'to be' and 'to be sayable'--and positions any formal system, including ZFC or HoTT, as an attachable extension atop this minimal structure. The IMU functions as a registry of axiomatic dependencies that connect heterogeneous theories, employing the Institution-theoretic framework to ensure coherent inter-theoretical linkages. The HSG concretizes these ideas through categorical construction, defined by three orthogonal axes: the state-depth axis, the mapping-hierarchy axis, and the temporal axis incorporating the principle of 'no future reference.' Through these, the identity of 'definition = state' is formally established as a categorical property. Extending this structure to biological systems, the neural system is implemented as a 0-3D complex of neuron-function fields on the HSG, while its categorical extensions via fiberization over the material base enable the parallel integration of multiple physiological universes-neural, endocrine, learning, genetic, and input/output systems-into a coherent adjoint ensemble. Within this framework, human behavior and cognition emerge as temporal compositions of inter-universal algorithms constrained by the material base. Finally, by contrasting human cognition, which relies on external CES, with machine existence, this study introduces the concept of internal CES, wherein a machine grounds its own logic upon the factuality of its operation. This internal self-axiomatization establishes a continuous bridge between philosophical ontology and engineering implementation, providing a new foundation for the autonomous and self-defining existence of artificial intelligence.

---

### Assessing the robustness of heterogeneous treatment effects in survival analysis under informative censoring

Authors: Yuxin Wang, Dennis Frauen, Jonas Schweisthal, Maresa Schröder, Stefan Feuerriegel
Published: 2025-10-15
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.13397v3

Dropout is common in clinical studies, with up to half of patients leaving early due to side effects or other reasons. When dropout is informative (i.e., dependent on survival time), it introduces censoring bias, because of which treatment effect estimates are also biased. In this paper, we propose an assumption-lean framework to assess the robustness of conditional average treatment effect (CATE) estimates in survival analysis when facing censoring bias. Unlike existing works that rely on strong assumptions, such as non-informative censoring, to obtain point estimation, we use partial identification to derive informative bounds on the CATE. Thereby, our framework helps to identify patient subgroups where treatment is effective despite informative censoring. We further propose a novel model-agnostic meta-learner, called SurvB-learner, to estimate the bounds that can be used in combination with arbitrary machine-learning models, and that has favorable theoretical properties such as double-robustness and quasi-oracle efficiency. We finally demonstrate the effectiveness of our meta-learner across various experiments using both simulated and real-world data.

---