# Research Papers — 2025-10 · bundle page 166 of 217

> Full-text markdown of papers #8251–8300 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/166
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/165.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/167.md)

### MeXtract: Light-Weight Metadata Extraction from Scientific Papers

Authors: Zaid Alyafeai, Maged S. Al-Shaibani, Bernard Ghanem
Published: 2025-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.06889v1

Metadata plays a critical role in indexing, documenting, and analyzing scientific literature, yet extracting it accurately and efficiently remains a challenging task. Traditional approaches often rely on rule-based or task-specific models, which struggle to generalize across domains and schema variations. In this paper, we present MeXtract, a family of lightweight language models designed for metadata extraction from scientific papers. The models, ranging from 0.5B to 3B parameters, are built by fine-tuning Qwen 2.5 counterparts. In their size family, MeXtract achieves state-of-the-art performance on metadata extraction on the MOLE benchmark. To further support evaluation, we extend the MOLE benchmark to incorporate model-specific metadata, providing an out-of-domain challenging subset. Our experiments show that fine-tuning on a given schema not only yields high accuracy but also transfers effectively to unseen schemas, demonstrating the robustness and adaptability of our approach. We release all the code, datasets, and models openly for the research community.

---

### M3Retrieve: Benchmarking Multimodal Retrieval for Medicine

Authors: Arkadeep Acharya, Akash Ghosh, Pradeepika Verma, Kitsuchart Pasupa, Sriparna Saha, Priti Singh
Published: 2025-10-08
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2510.06888v1

With the increasing use of RetrievalAugmented Generation (RAG), strong retrieval models have become more important than ever. In healthcare, multimodal retrieval models that combine information from both text and images offer major advantages for many downstream tasks such as question answering, cross-modal retrieval, and multimodal summarization, since medical data often includes both formats. However, there is currently no standard benchmark to evaluate how well these models perform in medical settings. To address this gap, we introduce M3Retrieve, a Multimodal Medical Retrieval Benchmark. M3Retrieve, spans 5 domains,16 medical fields, and 4 distinct tasks, with over 1.2 Million text documents and 164K multimodal queries, all collected under approved licenses. We evaluate leading multimodal retrieval models on this benchmark to explore the challenges specific to different medical specialities and to understand their impact on retrieval performance. By releasing M3Retrieve, we aim to enable systematic evaluation, foster model innovation, and accelerate research toward building more capable and reliable multimodal retrieval systems for medical applications. The dataset and the baselines code are available in this github page https://github.com/AkashGhosh/M3Retrieve.

---

### Lung Infection Severity Prediction Using Transformers with Conditional TransMix Augmentation and Cross-Attention

Authors: Bouthaina Slika, Fadi Dornaika, Fares Bougourzi, Karim Hammoudi
Published: 2025-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.06887v1

Lung infections, particularly pneumonia, pose serious health risks that can escalate rapidly, especially during pandemics. Accurate AI-based severity prediction from medical imaging is essential to support timely clinical decisions and optimize patient outcomes. In this work, we present a novel method applicable to both CT scans and chest X-rays for assessing lung infection severity. Our contributions are twofold: (i) QCross-Att-PVT, a Transformer-based architecture that integrates parallel encoders, a cross-gated attention mechanism, and a feature aggregator to capture rich multi-scale features; and (ii) Conditional Online TransMix, a custom data augmentation strategy designed to address dataset imbalance by generating mixed-label image patches during training. Evaluated on two benchmark datasets, RALO CXR and Per-COVID-19 CT, our method consistently outperforms several state-of-the-art deep learning models. The results emphasize the critical role of data augmentation and gated attention in improving both robustness and predictive accuracy. This approach offers a reliable, adaptable tool to support clinical diagnosis, disease monitoring, and personalized treatment planning. The source code of this work is available at https://github.com/bouthainas/QCross-Att-PVT.

---

### Multi-Dimensional Autoscaling of Stream Processing Services on Edge Devices

Authors: Boris Sedlak, Philipp Raith, Andrea Morichetta, Víctor Casamayor Pujol, Schahram Dustdar
Published: 2025-10-08
Categories: cs.DC, cs.AI, cs.LG, cs.PF
arXiv: https://arxiv.org/abs/2510.06882v2

Edge devices have limited resources, which inevitably leads to situations where stream processing services cannot satisfy their needs. While existing autoscaling mechanisms focus entirely on resource scaling, Edge devices require alternative ways to sustain the Service Level Objectives (SLOs) of competing services. To address these issues, we introduce a Multi-dimensional Autoscaling Platform (MUDAP) that supports fine-grained vertical scaling across both service- and resource-level dimensions. MUDAP supports service-specific scaling tailored to available parameters, e.g., scale data quality or model size for a particular service. To optimize the execution across services, we present a scaling agent based on Regression Analysis of Structural Knowledge (RASK). The RASK agent efficiently explores the solution space and learns a continuous regression model of the processing environment for inferring optimal scaling actions. We compared our approach with two autoscalers, the Kubernetes VPA and a reinforcement learning agent, for scaling up to 9 services on a single Edge device. Our results showed that RASK can infer an accurate regression model in merely 20 iterations (i.e., observe 200s of processing). By increasingly adding elasticity dimensions, RASK sustained the highest request load with 28% less SLO violations, compared to baselines.

---

### MoRE-GNN: Multi-omics Data Integration with a Heterogeneous Graph Autoencoder

Authors: Zhiyu Wang, Sonia Koszut, Pietro Liò, Francesco Ceccarelli
Published: 2025-10-08
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.06880v1

The integration of multi-omics single-cell data remains challenging due to high-dimensionality and complex inter-modality relationships. To address this, we introduce MoRE-GNN (Multi-omics Relational Edge Graph Neural Network), a heterogeneous graph autoencoder that combines graph convolution and attention mechanisms to dynamically construct relational graphs directly from data. Evaluations on six publicly available datasets demonstrate that MoRE-GNN captures biologically meaningful relationships and outperforms existing methods, particularly in settings with strong inter-modality correlations. Furthermore, the learned representations allow for accurate downstream cross-modal predictions. While performance may vary with dataset complexity, MoRE-GNN offers an adaptive, scalable and interpretable framework for advancing multi-omics integration.

---

### TGPR: Tree-Guided Policy Refinement for Robust Self-Debugging of LLMs

Authors: Daria Ozerova, Ekaterina Trofimova
Published: 2025-10-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.06878v1

Iterative refinement has been a promising paradigm to enable large language models (LLMs) to resolve difficult reasoning and problem-solving tasks. One of the key challenges, however, is how to effectively search through the enormous search space of possible refinements. Existing methods typically fall back on predefined heuristics, which are troubled by the exploration-exploitation dilemma and cannot adapt based on past refinement outcomes. We introduce Tree-Guided Policy Refinement (TGPR), a novel framework that combines GRPO with a Thompson-Sampling-based tree search. TGPR explores both failed and successful refinement paths actively, with denser training trajectories and more adaptive policies. On HumanEval, MBPP, and APPS benchmarks, our method achieves up to +4.2 percentage points absolute improvement in pass@1 (on MBPP) and up to +12.51 percentage points absolute improvement in pass@10 (on APPS) compared to a competitive GRPO baseline. Apart from debugging code, TGPR focuses on a principled approach to combining learned policies with structured search methods, offering a general framework for enhancing iterative refinement and stateful reasoning in LLMs.

---

### HARP-NeXt: High-Speed and Accurate Range-Point Fusion Network for 3D LiDAR Semantic Segmentation

Authors: Samir Abou Haidar, Alexandre Chariot, Mehdi Darouich, Cyril Joly, Jean-Emmanuel Deschaud
Published: 2025-10-08
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2510.06876v1

LiDAR semantic segmentation is crucial for autonomous vehicles and mobile robots, requiring high accuracy and real-time processing, especially on resource-constrained embedded systems. Previous state-of-the-art methods often face a trade-off between accuracy and speed. Point-based and sparse convolution-based methods are accurate but slow due to the complexity of neighbor searching and 3D convolutions. Projection-based methods are faster but lose critical geometric information during the 2D projection. Additionally, many recent methods rely on test-time augmentation (TTA) to improve performance, which further slows the inference. Moreover, the pre-processing phase across all methods increases execution time and is demanding on embedded platforms. Therefore, we introduce HARP-NeXt, a high-speed and accurate LiDAR semantic segmentation network. We first propose a novel pre-processing methodology that significantly reduces computational overhead. Then, we design the Conv-SE-NeXt feature extraction block to efficiently capture representations without deep layer stacking per network stage. We also employ a multi-scale range-point fusion backbone that leverages information at multiple abstraction levels to preserve essential geometric details, thereby enhancing accuracy. Experiments on the nuScenes and SemanticKITTI benchmarks show that HARP-NeXt achieves a superior speed-accuracy trade-off compared to all state-of-the-art methods, and, without relying on ensemble models or TTA, is comparable to the top-ranked PTv3, while running 24$\times$ faster. The code is available at https://github.com/SamirAbouHaidar/HARP-NeXt

---

### SaFeR-VLM: Toward Safety-aware Fine-grained Reasoning in Multimodal Models

Authors: Huahui Yi, Kun Wang, Qiankun Li, Miao Yu, Liang Lin, Gongli Xi, Hao Wu, Xuming Hu, Kang Li, Yang Liu
Published: 2025-10-08
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2510.06871v2

Multimodal Large Reasoning Models (MLRMs) demonstrate impressive cross-modal reasoning but often amplify safety risks under adversarial or unsafe prompts, a phenomenon we call the \textit{Reasoning Tax}. Existing defenses mainly act at the output level and do not constrain the reasoning process, leaving models exposed to implicit risks. In this paper, we propose SaFeR-VLM, a safety-aligned reinforcement learning framework that embeds safety directly into multimodal reasoning. The framework integrates four components: (I) QI-Safe-10K, a curated dataset emphasizing safety-critical and reasoning-sensitive cases; (II) safety-aware rollout, where unsafe generations undergo reflection and correction instead of being discarded; (III) structured reward modeling with multi-dimensional weighted criteria and explicit penalties for hallucinations and contradictions; and (IV) GRPO optimization, which reinforces both safe and corrected trajectories. This unified design shifts safety from a passive safeguard to an active driver of reasoning, enabling scalable and generalizable safety-aware reasoning. SaFeR-VLM further demonstrates robustness against both explicit and implicit risks, supporting dynamic and interpretable safety decisions beyond surface-level filtering. SaFeR-VLM-3B achieves average performance $70.13$ and $78.97$ on safety and helpfulness across six benchmarks, surpassing both same-scale and $>10\times$ larger models such as Skywork-R1V3-38B, Qwen2.5VL-72B, and GLM4.5V-106B. Remarkably, SaFeR-VLM-7B benefits from its increased scale to surpass GPT-5-mini and Gemini-2.5-Flash by \num{6.47} and \num{16.76} points respectively on safety metrics, achieving this improvement without any degradation in helpfulness performance. Our codes are available at https://github.com/HarveyYi/SaFeR-VLM.

---

### $λ$-GRPO: Unifying the GRPO Frameworks with Learnable Token Preferences

Authors: Yining Wang, Jinman Zhao, Chuangxin Zhao, Shuhao Guan, Gerald Penn, Shinan Liu
Published: 2025-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.06870v2

Reinforcement Learning with Human Feedback (RLHF) has been the dominant approach for improving the reasoning capabilities of Large Language Models (LLMs). Recently, Reinforcement Learning with Verifiable Rewards (RLVR) has simplified this paradigm by replacing the reward and value models with rule-based verifiers. A prominent example is Group Relative Policy Optimization (GRPO). However, GRPO inherently suffers from a length bias, since the same advantage is uniformly assigned to all tokens of a response. As a result, longer responses distribute the reward over more tokens and thus contribute disproportionately to gradient updates. Several variants, such as DAPO and Dr. GRPO, modify the token-level aggregation of the loss, yet these methods remain heuristic and offer limited interpretability regarding their implicit token preferences. In this work, we explore the possibility of allowing the model to learn its own token preference during optimization. We unify existing frameworks under a single formulation and introduce a learnable parameter $λ$ that adaptively controls token-level weighting. We use $λ$-GRPO to denote our method, and we find that $λ$-GRPO achieves consistent improvements over vanilla GRPO and DAPO on multiple mathematical reasoning benchmarks. On Qwen2.5 models with 1.5B, 3B, and 7B parameters, $λ$-GRPO improves average accuracy by $+1.9\%$, $+1.0\%$, and $+1.7\%$ compared to GRPO, respectively. Importantly, these gains come without any modifications to the training data or additional computational cost, highlighting the effectiveness and practicality of learning token preferences.

---

### Multi-hop Deep Joint Source-Channel Coding with Deep Hash Distillation for Semantically Aligned Image Recovery

Authors: Didrik Bergström, Deniz Gündüz, Onur Günlü
Published: 2025-10-08
Categories: cs.IT, cs.AI, cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2510.06868v2

We consider image transmission via deep joint source-channel coding (DeepJSCC) over multi-hop additive white Gaussian noise (AWGN) channels by training a DeepJSCC encoder-decoder pair with a pre-trained deep hash distillation (DHD) module to semantically cluster images, facilitating security-oriented applications through enhanced semantic consistency and improving the perceptual reconstruction quality. We train the DeepJSCC module to both reduce mean square error (MSE) and minimize cosine distance between DHD hashes of source and reconstructed images. Significantly improved perceptual quality as a result of semantic alignment is illustrated for different multi-hop settings, for which classical DeepJSCC may suffer from noise accumulation, measured by the learned perceptual image patch similarity (LPIPS) metric.

---

### Unlocking Latent Discourse Translation in LLMs Through Quality-Aware Decoding

Authors: Wafaa Mohammed, Vlad Niculae, Chrysoula Zerva
Published: 2025-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.06866v1

Large language models (LLMs) have emerged as strong contenders in machine translation.Yet, they still struggle to adequately handle discourse phenomena, such as pronoun resolution and lexical cohesion at the document level. In this study, we thoroughly investigate the discourse phenomena performance of LLMs in context-aware translation. We demonstrate that discourse knowledge is encoded within LLMs and propose the use of quality-aware decoding (QAD) to effectively extract this knowledge, showcasing its superiority over other decoding approaches through comprehensive analysis. Furthermore, we illustrate that QAD enhances the semantic richness of translations and aligns them more closely with human preferences.

---

### Towards Generalization of Graph Neural Networks for AC Optimal Power Flow

Authors: Olayiwola Arowolo, Jochen L. Cremer
Published: 2025-10-08
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.06860v2

AC Optimal Power Flow (ACOPF) is computationally intensive for large-scale grids, often requiring prohibitive solution times with conventional solvers. Machine learning offers significant speedups, but existing models struggle with scalability and topology flexibility. To address these challenges, we propose a Hybrid Heterogeneous Message Passing Neural Network (HH-MPNN) that integrates a heterogeneous graph neural network (GNN) with a scalable transformer and physics-informed positional encodings. Our architecture explicitly models distinct power system components to capture local features while using global attention for long-range dependencies. Evaluated on diverse benchmarks, including PGLearn and GridFM-DataKit datasets, HH-MPNN achieves less than 1% optimality gap on default topologies across grid sizes from 14 to 2,000 buses. For N-1 contingencies, our approach demonstrates zero-shot N-1 generalization with less than 3% optimality gap on several test cases despite training only on default topologies. We further develop an approach that ensures robust N-1 generalization to high-impact contingencies through targeted augmentation of the training data, showing that exhaustive simulation is unnecessary for topologically flexible models. Finally, size generalization experiments demonstrate that pre-training on small grids significantly improves performance on large-scale systems. Achieving computational speedups of up to 5,000 times compared to interior point solvers, these results advance practical, generalizable machine learning for real-time power system operations.

---

### Explaining raw data complexity to improve satellite onboard processing

Authors: Adrien Dorise, Marjorie Bellizzi, Adrien Girard, Benjamin Francesconi, Stéphane May
Published: 2025-10-08
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.06858v2

With increasing processing power, deploying AI models for remote sensing directly onboard satellites is becoming feasible. However, new constraints arise, mainly when using raw, unprocessed sensor data instead of preprocessed ground-based products. While current solutions primarily rely on preprocessed sensor images, few approaches directly leverage raw data. This study investigates the effects of utilising raw data on deep learning models for object detection and classification tasks. We introduce a simulation workflow to generate raw-like products from high-resolution L1 imagery, enabling systemic evaluation. Two object detection models (YOLOv11n and YOLOX-S) are trained on both raw and L1 datasets, and their performance is compared using standard detection metrics and explainability tools. Results indicate that while both models perform similarly at low to medium confidence thresholds, the model trained on raw data struggles with object boundary identification at high confidence levels. It suggests that adapting AI architectures with improved contouring methods can enhance object detection on raw images, improving onboard AI for remote sensing.

---

### Autoformalizer with Tool Feedback

Authors: Qi Guo, Jianing Wang, Jianfei Zhang, Deyang Kong, Xiangzhou Huang, Xiangyu Xi, Wei Wang, Jingang Wang, Xunliang Cai, Shikun Zhang, Wei Ye
Published: 2025-10-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.06857v1

Autoformalization addresses the scarcity of data for Automated Theorem Proving (ATP) by translating mathematical problems from natural language into formal statements. Efforts in recent work shift from directly prompting large language models to training an end-to-end formalizer model from scratch, achieving remarkable advancements. However, existing formalizer still struggles to consistently generate valid statements that meet syntactic validity and semantic consistency. To address this issue, we propose the Autoformalizer with Tool Feedback (ATF), a novel approach that incorporates syntactic and consistency information as tools into the formalization process. By integrating Lean 4 compilers for syntax corrections and employing a multi-LLMs-as-judge approach for consistency validation, the model is able to adaptively refine generated statements according to the tool feedback, enhancing both syntactic validity and semantic consistency. The training of ATF involves a cold-start phase on synthetic tool-calling data, an expert iteration phase to improve formalization capabilities, and Direct Preference Optimization to alleviate ineffective revisions. Experimental results show that ATF markedly outperforms a range of baseline formalizer models, with its superior performance further validated by human evaluations. Subsequent analysis reveals that ATF demonstrates excellent inference scaling properties. Moreover, we open-source Numina-ATF, a dataset containing 750K synthetic formal statements to facilitate advancements in autoformalization and ATP research.

---

### Online Generic Event Boundary Detection

Authors: Hyungrok Jung, Daneul Kim, Seunggyun Lim, Jeany Son, Jonghyun Choi
Published: 2025-10-08
Categories: cs.CV, eess.IV
arXiv: https://arxiv.org/abs/2510.06855v1

Generic Event Boundary Detection (GEBD) aims to interpret long-form videos through the lens of human perception. However, current GEBD methods require processing complete video frames to make predictions, unlike humans processing data online and in real-time. To bridge this gap, we introduce a new task, Online Generic Event Boundary Detection (On-GEBD), aiming to detect boundaries of generic events immediately in streaming videos. This task faces unique challenges of identifying subtle, taxonomy-free event changes in real-time, without the access to future frames. To tackle these challenges, we propose a novel On-GEBD framework, Estimator, inspired by Event Segmentation Theory (EST) which explains how humans segment ongoing activity into events by leveraging the discrepancies between predicted and actual information. Our framework consists of two key components: the Consistent Event Anticipator (CEA), and the Online Boundary Discriminator (OBD). Specifically, the CEA generates a prediction of the future frame reflecting current event dynamics based solely on prior frames. Then, the OBD measures the prediction error and adaptively adjusts the threshold using statistical tests on past errors to capture diverse, subtle event transitions. Experimental results demonstrate that Estimator outperforms all baselines adapted from recent online video understanding models and achieves performance comparable to prior offline-GEBD methods on the Kinetics-GEBD and TAPOS datasets.

---

### Enhancing Bankruptcy Prediction of Banks through Advanced Machine Learning Techniques: An Innovative Approach and Analysis

Authors: Zuherman Rustam, Sri Hartini, Sardar M. N. Islam, Fevi Novkaniza, Fiftitah R. Aszhari, Muhammad Rifqi
Published: 2025-10-08
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.06852v1

Context: Financial system stability is determined by the condition of the banking system. A bank failure can destroy the stability of the financial system, as banks are subject to systemic risk, affecting not only individual banks but also segments or the entire financial system. Calculating the probability of a bank going bankrupt is one way to ensure the banking system is safe and sound. Existing literature and limitations: Statistical models, such as Altman's Z-Score, are one of the common techniques for developing a bankruptcy prediction model. However, statistical methods rely on rigid and sometimes irrelevant assumptions, which can result in low forecast accuracy. New approaches are necessary. Objective of the research: Bankruptcy models are developed using machine learning techniques, such as logistic regression (LR), random forest (RF), and support vector machines (SVM). According to several studies, machine learning is also more accurate and effective than statistical methods for categorising and forecasting banking risk management. Present Research: The commercial bank data are derived from the annual financial statements of 44 active banks and 21 bankrupt banks in Turkey from 1994 to 2004, and the rural bank data are derived from the quarterly financial reports of 43 active and 43 bankrupt rural banks in Indonesia between 2013 and 2019. Five rural banks in Indonesia have also been selected to demonstrate the feasibility of analysing bank bankruptcy trends. Findings and implications: The results of the research experiments show that RF can forecast data from commercial banks with a 90% accuracy rate. Furthermore, the three machine learning methods proposed accurately predict the likelihood of rural bank bankruptcy. Contribution and Conclusion: The proposed innovative machine learning approach help to implement policies that reduce the costs of bankruptcy.

---

### Reconquering Bell sampling on qudits: stabilizer learning and testing, quantum pseudorandomness bounds, and more

Authors: Jonathan Allcock, Joao F. Doriguello, Gábor Ivanyos, Miklos Santha
Published: 2025-10-08
Categories: quant-ph, cs.CC, cs.DS, cs.LG
arXiv: https://arxiv.org/abs/2510.06848v3

Bell sampling is a simple yet powerful tool based on measuring two copies of a quantum state in the Bell basis, and has found applications in a plethora of problems related to stabiliser states and measures of magic. However, it was not known how to generalise the procedure from qubits to $d$-level systems -- qudits -- for all dimensions $d > 2$ in a useful way. Indeed, a prior work of the authors (arXiv'24) showed that the natural extension of Bell sampling to arbitrary dimensions fails to provide meaningful information about the quantum states being measured. In this paper, we overcome the difficulties encountered in previous works and develop a useful generalisation of Bell sampling to qudits of all $d\geq 2$. At the heart of our primitive is a new unitary, based on Lagrange's four-square theorem, that maps four copies of any stabiliser state $|\mathcal{S}\rangle$ to four copies of its complex conjugate $|\mathcal{S}^\ast\rangle$ (up to some Pauli operator), which may be of independent interest. We then demonstrate the utility of our new Bell sampling technique by lifting several known results from qubits to qudits for any $d\geq 2$: 1. Learning stabiliser states in $O(n^3)$ time with $O(n)$ samples; 2. Solving the Hidden Stabiliser Group Problem in $\tilde{O}(n^3/\varepsilon)$ time with $\tilde{O}(n/\varepsilon)$ samples; 3. Testing whether $|ψ\rangle$ has stabiliser size at least $d^t$ or is $\varepsilon$-far from all such states in $\tilde{O}(n^3/\varepsilon)$ time with $\tilde{O}(n/\varepsilon)$ samples; 4. Clifford circuits with at most $n/2$ single-qudit non-Clifford gates cannot prepare pseudorandom states; 5. Testing whether $|ψ\rangle$ has stabiliser fidelity at least $1-\varepsilon_1$ or at most $1-\varepsilon_2$ with $O(d^2\varepsilon_2/(\varepsilon_2-\varepsilon_1)^2)$ samples if $\varepsilon_1 = O(\varepsilon_2/d^{2})$.

---

### OpenJAI-v1.0: An Open Thai Large Language Model

Authors: Pontakorn Trakuekul, Attapol T. Rutherford, Jullajak Karnjanaekarin, Narongkorn Panitsrisit, Sumana Sumanakul
Published: 2025-10-08
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.06847v1

We introduce OpenJAI-v1.0, an open-source large language model for Thai and English, developed from the Qwen3-14B model. Our work focuses on boosting performance on practical tasks through carefully curated data across three key use cases: instruction following, long-context understanding, and tool use. Evaluation results show that OpenJAI-v1.0 improves on the capabilities of its base model and outperforms other leading open-source Thai models on a diverse suite of benchmarks, while avoiding catastrophic forgetting. OpenJAI-v1.0 is publicly released as another alternative NLP resource for the Thai AI community.

---

### Self-signals Driven Multi-LLM Debate for Efficient and Accurate Reasoning

Authors: Xuhang Chen, Zhifan Song, Deyi Ji, Shuo Gao, Lanyun Zhu
Published: 2025-10-08
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.06843v2

Large Language Models (LLMs) have exhibited impressive capabilities across diverse application domains. Recent work has explored Multi-LLM Agent Debate (MAD) as a way to enhance performance by enabling multiple LLMs to discuss and refine responses iteratively. Nevertheless, existing MAD methods predominantly focus on utilizing external structures, such as debate graphs, using LLM-as-a-Judge, while neglecting the application of self signals, such as token logits and attention, that arise during generation. This omission leads to redundant computation and potential performance degradation. In this paper, we shift the focus to the self signals of multi-LLM debate and introduce a Self-Signals Driven Multi-LLM Debate (SID), which leverages two types of self-signals: model-level confidence and token-level semantic focus, to adaptively guide the debate process. Our approach enables high-confidence agents to exit early at the model level and compress the redundant debate contents based on the attention mechanism. We evaluate our method on various LLMs and Multimodal LLMs across multiple challenging benchmarks. Experimental results demonstrate that our method not only outperforms existing MAD techniques in accuracy but also reduces token consumption, highlighting the effectiveness of utilizing self signals in enhancing both the performance and efficiency of multi-agent debate systems. Our code will be available at~\href{https://github.com/xuhang2019/SID}{\texttt{https://github.com/xuhang2019/SID}}.

---

### Continual Action Quality Assessment via Adaptive Manifold-Aligned Graph Regularization

Authors: Kanglei Zhou, Qingyi Pan, Xingxing Zhang, Hubert P. H. Shum, Frederick W. B. Li, Xiaohui Liang, Liyuan Wang
Published: 2025-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.06842v2

Action Quality Assessment (AQA) quantifies human actions in videos, supporting applications in sports scoring, rehabilitation, and skill evaluation. A major challenge lies in the non-stationary nature of quality distributions in real-world scenarios, which limits the generalization of conventional methods. We introduce Continual AQA (CAQA), which equips AQA with Continual Learning (CL) capabilities to handle evolving distributions while mitigating catastrophic forgetting. Although parameter-efficient fine-tuning of pretrained models has shown promise in continual learning, our empirical study shows that the evaluated adapter-based PEFT setting provides less effective downstream adaptation than FPFT for fine-grained AQA. Our empirical and theoretical analyses reveal two insights: (i) sufficiently expressive backbone adaptation is important for bridging the upstream--downstream representation gap; yet (ii) uncontrolled FPFT may induce overfitting and feature manifold shift, thereby aggravating forgetting. To address this, we propose Adaptive Manifold-Aligned Graph Regularization (MAGR++), which couples backbone fine-tuning that stabilizes shallow layers while adapting deeper ones with a two-step feature rectification pipeline: a manifold projector to translate deviated historical features into the current representation space, and a graph regularizer to align local and global distributions. We construct four CAQA benchmarks from three datasets with tailored evaluation protocols and strong baselines, enabling systematic cross-dataset comparison. Extensive experiments show that MAGR++ achieves state-of-the-art performance, with average correlation gains of 3.6% offline and 12.2% online over the strongest baseline, confirming its robustness and effectiveness.

---

### GAMBIT+: A Challenge Set for Evaluating Gender Bias in Machine Translation Quality Estimation Metrics

Authors: Giorgos Filandrianos, Orfeas Menis Mastromichalakis, Wafaa Mohammed, Giuseppe Attanasio, Chrysoula Zerva
Published: 2025-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.06841v1

Gender bias in machine translation (MT) systems has been extensively documented, but bias in automatic quality estimation (QE) metrics remains comparatively underexplored. Existing studies suggest that QE metrics can also exhibit gender bias, yet most analyses are limited by small datasets, narrow occupational coverage, and restricted language variety. To address this gap, we introduce a large-scale challenge set specifically designed to probe the behavior of QE metrics when evaluating translations containing gender-ambiguous occupational terms. Building on the GAMBIT corpus of English texts with gender-ambiguous occupations, we extend coverage to three source languages that are genderless or natural-gendered, and eleven target languages with grammatical gender, resulting in 33 source-target language pairs. Each source text is paired with two target versions differing only in the grammatical gender of the occupational term(s) (masculine vs. feminine), with all dependent grammatical elements adjusted accordingly. An unbiased QE metric should assign equal or near-equal scores to both versions. The dataset's scale, breadth, and fully parallel design, where the same set of texts is aligned across all languages, enables fine-grained bias analysis by occupation and systematic comparisons across languages.

---

### CNN-TFT explained by SHAP with multi-head attention weights for time series forecasting

Authors: Stefano F. Stefenon, João P. Matos-Carvalho, Valderi R. Q. Leithardt, Kin-Choong Yow
Published: 2025-10-08
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.06840v1

Convolutional neural networks (CNNs) and transformer architectures offer strengths for modeling temporal data: CNNs excel at capturing local patterns and translational invariances, while transformers effectively model long-range dependencies via self-attention. This paper proposes a hybrid architecture integrating convolutional feature extraction with a temporal fusion transformer (TFT) backbone to enhance multivariate time series forecasting. The CNN module first applies a hierarchy of one-dimensional convolutional layers to distill salient local patterns from raw input sequences, reducing noise and dimensionality. The resulting feature maps are then fed into the TFT, which applies multi-head attention to capture both short- and long-term dependencies and to weigh relevant covariates adaptively. We evaluate the CNN-TFT on a hydroelectric natural flow time series dataset. Experimental results demonstrate that CNN-TFT outperforms well-established deep learning models, with a mean absolute percentage error of up to 2.2%. The explainability of the model is obtained by a proposed Shapley additive explanations with multi-head attention weights (SHAP-MHAW). Our novel architecture, named CNN-TFT-SHAP-MHAW, is promising for applications requiring high-fidelity, multivariate time series forecasts, being available for future analysis at https://github.com/SFStefenon/CNN-TFT-SHAP-MHAW .

---

### Crossing Domains without Labels: Distant Supervision for Term Extraction

Authors: Elena Senger, Yuri Campbell, Rob van der Goot, Barbara Plank
Published: 2025-10-08
Categories: cs.IR, cs.CL
arXiv: https://arxiv.org/abs/2510.06838v1

Automatic Term Extraction (ATE) is a critical component in downstream NLP tasks such as document tagging, ontology construction and patent analysis. Current state-of-the-art methods require expensive human annotation and struggle with domain transfer, limiting their practical deployment. This highlights the need for more robust, scalable solutions and realistic evaluation settings. To address this, we introduce a comprehensive benchmark spanning seven diverse domains, enabling performance evaluation at both the document- and corpus-levels. Furthermore, we propose a robust LLM-based model that outperforms both supervised cross-domain encoder models and few-shot learning baselines and performs competitively with its GPT-4o teacher on this benchmark. The first step of our approach is generating psuedo-labels with this black-box LLM on general and scientific domains to ensure generalizability. Building on this data, we fine-tune the first LLMs for ATE. To further enhance document-level consistency, oftentimes needed for downstream tasks, we introduce lightweight post-hoc heuristics. Our approach exceeds previous approaches on 5/7 domains with an average improvement of 10 percentage points. We release our dataset and fine-tuned models to support future research in this area.

---

### Vectorized FlashAttention with Low-cost Exponential Computation in RISC-V Vector Processors

Authors: Vasileios Titopoulos, Kosmas Alexandridis, Giorgos Dimitrakopoulos
Published: 2025-10-08
Categories: cs.LG, cs.DC, cs.PF
arXiv: https://arxiv.org/abs/2510.06834v1

Attention is a core operation in numerous machine learning and artificial intelligence models. This work focuses on the acceleration of attention kernel using FlashAttention algorithm, in vector processors, particularly those based on the RISC-V instruction set architecture (ISA). This work represents the first effort to vectorize FlashAttention, minimizing scalar code and simplifying the computational complexity of evaluating exponentials needed by softmax used in attention. By utilizing a low-cost approximation for exponentials in floating-point arithmetic, we reduce the cost of computing the exponential function without the need to extend baseline vector ISA with new custom instructions. Also, appropriate tiling strategies are explored with the goal to improve memory locality. Experimental results highlight the scalability of our approach, demonstrating significant performance gains with the vectorized implementations when processing attention layers in practical applications.

---

### Early wind turbine alarm prediction based on machine learning: AlarmForecasting

Authors: Syed Shazaib Shah, Daoliang Tan
Published: 2025-10-08
Categories: cs.LG, physics.app-ph
arXiv: https://arxiv.org/abs/2510.06831v1

Alarm data is pivotal in curbing fault behavior in Wind Turbines (WTs) and forms the backbone for advancedpredictive monitoring systems. Traditionally, research cohorts have been confined to utilizing alarm data solelyas a diagnostic tool, merely indicative of unhealthy status. However, this study aims to offer a transformativeleap towards preempting alarms, preventing alarms from triggering altogether, and consequently avertingimpending failures. Our proposed Alarm Forecasting and Classification (AFC) framework is designed on twosuccessive modules: first, the regression module based on long short-term memory (LSTM) for time-series alarmforecasting, and thereafter, the classification module to implement alarm tagging on the forecasted alarm. Thisway, the entire alarm taxonomy can be forecasted reliably rather than a few specific alarms. 14 Senvion MM82turbines with an operational period of 5 years are used as a case study; the results demonstrated 82%, 52%,and 41% accurate forecasts for 10, 20, and 30 min alarm forecasts, respectively. The results substantiateanticipating and averting alarms, which is significant in curbing alarm frequency and enhancing operationalefficiency through proactive intervention.

---

### Lattice-allocated Real-time Line Segment Feature Detection and Tracking Using Only an Event-based Camera

Authors: Mikihiro Ikura, Arren Glover, Masayoshi Mizuno, Chiara Bartolozzi
Published: 2025-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.06829v1

Line segment extraction is effective for capturing geometric features of human-made environments. Event-based cameras, which asynchronously respond to contrast changes along edges, enable efficient extraction by reducing redundant data. However, recent methods often rely on additional frame cameras or struggle with high event rates. This research addresses real-time line segment detection and tracking using only a modern, high-resolution (i.e., high event rate) event-based camera. Our lattice-allocated pipeline consists of (i) velocity-invariant event representation, (ii) line segment detection based on a fitting score, (iii) and line segment tracking by perturbating endpoints. Evaluation using ad-hoc recorded dataset and public datasets demonstrates real-time performance and higher accuracy compared to state-of-the-art event-only and event-frame hybrid baselines, enabling fully stand-alone event camera operation in real-world settings.

---

### Recurrence-Complete Frame-based Action Models

Authors: Michael Keiblinger
Published: 2025-10-08
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.06828v1

In recent years, attention-like mechanisms have been used to great success in the space of large language models, unlocking scaling potential to a previously unthinkable extent. "Attention Is All You Need" famously claims RNN cells are not needed in conjunction with attention. We challenge this view. In this paper, we point to existing proofs that architectures with fully parallelizable forward or backward passes cannot represent classes of problems specifically interesting for long-running agentic tasks. We further conjecture a critical time t beyond which non-recurrence-complete models fail to aggregate inputs correctly, with concrete implications for agentic systems (e.g., software engineering agents). To address this, we introduce a recurrence-complete architecture and train it on GitHub-derived action sequences. Loss follows a power law in the trained sequence length while the parameter count remains fixed. Moreover, longer-sequence training always amortizes its linearly increasing wall-time cost, yielding lower loss as a function of wall time.

---

### StyleKeeper: Prevent Content Leakage using Negative Visual Query Guidance

Authors: Jaeseok Jeong, Junho Kim, Gayoung Lee, Yunjey Choi, Youngjung Uh
Published: 2025-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.06827v1

In the domain of text-to-image generation, diffusion models have emerged as powerful tools. Recently, studies on visual prompting, where images are used as prompts, have enabled more precise control over style and content. However, existing methods often suffer from content leakage, where undesired elements of the visual style prompt are transferred along with the intended style. To address this issue, we 1) extend classifier-free guidance (CFG) to utilize swapping self-attention and propose 2) negative visual query guidance (NVQG) to reduce the transfer of unwanted contents. NVQG employs negative score by intentionally simulating content leakage scenarios that swap queries instead of key and values of self-attention layers from visual style prompts. This simple yet effective method significantly reduces content leakage. Furthermore, we provide careful solutions for using a real image as visual style prompts. Through extensive evaluation across various styles and text prompts, our method demonstrates superiority over existing approaches, reflecting the style of the references, and ensuring that resulting images match the text prompts. Our code is available \href{https://github.com/naver-ai/StyleKeeper}{here}.

---

### Mid-Training of Large Language Models: A Survey

Authors: Kaixiang Mo, Yuxin Shi, Weiwei Weng, Zhiqiang Zhou, Shuman Liu, Haibo Zhang, Anxiang Zeng
Published: 2025-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.06826v1

Large language models (LLMs) are typically developed through large-scale pre-training followed by task-specific fine-tuning. Recent advances highlight the importance of an intermediate mid-training stage, where models undergo multiple annealing-style phases that refine data quality, adapt optimization schedules, and extend context length. This stage mitigates diminishing returns from noisy tokens, stabilizes convergence, and expands model capability in late training. Its effectiveness can be explained through gradient noise scale, the information bottleneck, and curriculum learning, which together promote generalization and abstraction. Despite widespread use in state-of-the-art systems, there has been no prior survey of mid-training as a unified paradigm. We introduce the first taxonomy of LLM mid-training spanning data distribution, learning-rate scheduling, and long-context extension. We distill practical insights, compile evaluation benchmarks, and report gains to enable structured comparisons across models. We also identify open challenges and propose avenues for future research and practice.

---

### Adaptive Tool Generation with Models as Tools and Reinforcement Learning

Authors: Chenpeng Wang, Xiaojie Cheng, Chunye Wang, Linfeng Yang, Lei Zhang
Published: 2025-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.06825v2

Tool-augmented language models have demonstrated strong capabilities, but their reliance on live API access creates scalability and reliability challenges during training and deployment. We propose MTR, a simulation-first training framework for tool-augmented reasoning. Instead of relying on live APIs, MTR learns from complete ReAct traces with schema-validated, simulated observations. Our approach operates through a multi-agent architecture where a ToolMaker generates task-specific, OpenAI-compatible tool interfaces, an AutoAgent produces structured think-act-observe sequences, and a ToolActor simulates realistic responses. Training proceeds in two stages: Stage-1 Supervised Fine-Tuning (SFT) teaches 'trace grammar' from complete reasoning sequences; Stage-2 Group Relative Policy Optimization (GRPO) optimizes strategy with a composite trace reward that balances answer correctness and internal consistency. Across four multi-hop QA benchmarks (HotpotQA, MuSiQue, 2WikiMultiHopQA, Bamboogle), MTR attains competitive Exact Match (EM) scores to live-API systems and excels on reasoning-intensive tasks, suggesting that effective tool reasoning can be learned from structured traces without live interactions.

---

### Efficient numeracy in language models through single-token number embeddings

Authors: Linus Kreitner, Paul Hager, Jonathan Mengedoht, Georgios Kaissis, Daniel Rueckert, Martin J. Menten
Published: 2025-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.06824v2

To drive progress in science and engineering, large language models (LLMs) must be able to process large amounts of numerical data and solve long calculations efficiently. This is currently only possible through the use of external tools or extensive reasoning chains, either weakening the numerical representations of LLMs or limiting the length of problems they can solve. We show that frontier LLMs require excessive amounts of reasoning tokens to solve even basic calculations, which is exacerbated by their tokenization strategies that split single numbers into multiple tokens. This motivates the need for efficient and effective single-token number encodings. We introduce a set of desiderata for such encodings and show that existing approaches fail to fulfill them. To address these shortcomings, we propose BitTokens, a novel encoding strategy that represents any number as a single token using its IEEE 754 binary floating-point representation. Through extensive experiments we show that our BitTokens allow even small language models to learn algorithms that solve basic arithmetic operations nearly perfectly. This newly gained efficiency could expand the length and complexity of problems language models can solve.

---

### Exposing Citation Vulnerabilities in Generative Engines

Authors: Riku Mochizuki, Shusuke Komatsu, Souta Noguchi, Kazuto Ataka
Published: 2025-10-08
Categories: cs.CR, cs.CL, cs.IR
arXiv: https://arxiv.org/abs/2510.06823v2

We analyze answers generated by generative engines (GEs) from the perspectives of citation publishers and the content-injection barrier, defined as the difficulty for attackers to manipulate answers to user prompts by placing malicious content on the web. GEs integrate two functions: web search and answer generation that cites web pages using large language models. Because anyone can publish information on the web, GEs are vulnerable to poisoning attacks. Existing studies of citation evaluation focus on how faithfully answer content reflects cited sources, leaving unexamined which web sources should be selected as citations to defend against poisoning attacks. To fill this gap, we introduce evaluation criteria that assess poisoning threats using the citation information contained in answers. Our criteria classify the publisher attributes of citations to estimate the content-injection barrier thereby revealing the threat of poisoning attacks in current GEs. We conduct experiments in political domains in Japan and the United States (U.S.) using our criteria and show that citations from official party websites (primary sources) are approximately \(25\%\)--\(45\%\) in the U.S. and \(60\%\)--\(65\%\) in Japan, indicating that U.S. political answers are at higher risk of poisoning attacks. We also find that sources with low content-injection barriers are frequently cited yet are poorly reflected in answer content. To mitigate this threat, we discuss how publishers of primary sources can increase exposure of their web content in answers and show that well-known techniques are limited by language differences.

---

### Efficient Discriminative Joint Encoders for Large Scale Vision-Language Reranking

Authors: Mitchell Keren Taraday, Shahaf Wagner, Chaim Baskin
Published: 2025-10-08
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.06820v2

Multimodal retrieval still leans on embedding-based models like CLIP for fast vector search over pre-computed image embeddings. Yet, unlike text retrieval, where joint-encoder rerankers are standard, comparable vision-language rerankers are largely absent. We find that seminal joint encoders such as BLIP are severely bottlenecked by an expensive visual feature-extraction stage, preventing practical deployment at scale. Motivated by this bottleneck, we introduce EDJE, an Efficient Discriminative Joint Encoder that precomputes vision tokens offline and compresses them via a lightweight attention-based adapter, so online inference runs only a compact joint encoder over a small set of visual tokens plus the text. EDJE preserves strong retrieval performance while drastically reducing storage and online compute, enabling high-throughput inference. Specifically, EDJE processes 50k image--text pairs/second while requiring 49kB of disk storage per image, matching prior art on Flickr (zero-shot) and COCO (fine-tuned) retrieval.

---

### The Unreasonable Effectiveness of Randomized Representations in Online Continual Graph Learning

Authors: Giovanni Donghi, Daniele Zambon, Luca Pasa, Cesare Alippi, Nicolò Navarin
Published: 2025-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.06819v1

Catastrophic forgetting is one of the main obstacles for Online Continual Graph Learning (OCGL), where nodes arrive one by one, distribution drifts may occur at any time and offline training on task-specific subgraphs is not feasible. In this work, we explore a surprisingly simple yet highly effective approach for OCGL: we use a fixed, randomly initialized encoder to generate robust and expressive node embeddings by aggregating neighborhood information, training online only a lightweight classifier. By freezing the encoder, we eliminate drifts of the representation parameters, a key source of forgetting, obtaining embeddings that are both expressive and stable. When evaluated across several OCGL benchmarks, despite its simplicity and lack of memory buffer, this approach yields consistent gains over state-of-the-art methods, with surprising improvements of up to 30% and performance often approaching that of the joint offline-training upper bound. These results suggest that in OCGL, catastrophic forgetting can be minimized without complex replay or regularization by embracing architectural simplicity and stability.

---

### BlackboxNLP-2025 MIB Shared Task: Exploring Ensemble Strategies for Circuit Localization Methods

Authors: Philipp Mondorf, Mingyang Wang, Sebastian Gerstner, Ahmad Dawar Hakimi, Yihong Liu, Leonor Veloso, Shijia Zhou, Hinrich Schütze, Barbara Plank
Published: 2025-10-08
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.06811v1

The Circuit Localization track of the Mechanistic Interpretability Benchmark (MIB) evaluates methods for localizing circuits within large language models (LLMs), i.e., subnetworks responsible for specific task behaviors. In this work, we investigate whether ensembling two or more circuit localization methods can improve performance. We explore two variants: parallel and sequential ensembling. In parallel ensembling, we combine attribution scores assigned to each edge by different methods-e.g., by averaging or taking the minimum or maximum value. In the sequential ensemble, we use edge attribution scores obtained via EAP-IG as a warm start for a more expensive but more precise circuit identification method, namely edge pruning. We observe that both approaches yield notable gains on the benchmark metrics, leading to a more precise circuit identification approach. Finally, we find that taking a parallel ensemble over various methods, including the sequential ensemble, achieves the best results. We evaluate our approach in the BlackboxNLP 2025 MIB Shared Task, comparing ensemble scores to official baselines across multiple model-task combinations.

---

### VA-Adapter: Adapting Ultrasound Foundation Model to Echocardiography Probe Guidance

Authors: Teng Wang, Haojun Jiang, Yuxuan Wang, Zhenguo Sun, Yujiao Deng, Shiji Song, Gao Huang
Published: 2025-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.06809v3

Echocardiography is a critical tool for detecting heart diseases, yet its steep operational difficulty causes a shortage of skilled personnel. Probe guidance systems, which assist in acquiring high-quality images, offer a promising solution to lower this operational barrier. However, robust probe guidance remains challenging due to significant individual variability. This variability manifests as differences in low-level features within two-dimensional (2D) images, which complicates image feature understanding, and differences in individual three-dimensional (3D) structures, which poses challenges for precise navigation. To address these challenges, we first propose leveraging the robust image representations learned by ultrasound foundation models from vast datasets. Yet, applying these models to probe navigation is non-trivial due to their lack of understanding of individual 3D structures. To this end, we meticulously design a Vision-Action Adapter (VA-Adapter) to online inject the capability of understanding individual 3D structures. Specifically, by embedding the VA-Adapter into the foundation model's image encoder, the model can infer cardiac anatomy from historical vision-action sequences, mimicking the cognitive process of a sonographer. Extensive experiments on a dataset with over 1.31M samples demonstrate that the VA-Adapter outperforms strong probe guidance models while requiring approximately 33 times fewer trained parameters. Code is available at https://github.com/LeapLabTHU/VA-Adapter.

---

### Overview of the Plagiarism Detection Task at PAN 2025

Authors: André Greiner-Petter, Maik Fröbe, Jan Philip Wahle, Terry Ruas, Bela Gipp, Akiko Aizawa, Martin Potthast
Published: 2025-10-08
Categories: cs.CL, cs.IR
arXiv: https://arxiv.org/abs/2510.06805v1

The generative plagiarism detection task at PAN 2025 aims at identifying automatically generated textual plagiarism in scientific articles and aligning them with their respective sources. We created a novel large-scale dataset of automatically generated plagiarism using three large language models: Llama, DeepSeek-R1, and Mistral. In this task overview paper, we outline the creation of this dataset, summarize and compare the results of all participants and four baselines, and evaluate the results on the last plagiarism detection task from PAN 2015 in order to interpret the robustness of the proposed approaches. We found that the current iteration does not invite a large variety of approaches as naive semantic similarity approaches based on embedding vectors provide promising results of up to 0.8 recall and 0.5 precision. In contrast, most of these approaches underperform significantly on the 2015 dataset, indicating a lack in generalizability.

---

### Quantum Computing Methods for Malware Detection

Authors: Eliška Krátká, Aurél Gábor Gábris
Published: 2025-10-08
Categories: quant-ph, cs.LG
arXiv: https://arxiv.org/abs/2510.06803v1

In this paper, we explore the potential of quantum computing in enhancing malware detection through the application of Quantum Machine Learning (QML). Our main objective is to investigate the performance of the Quantum Support Vector Machine (QSVM) algorithm compared to SVM. A publicly available dataset containing raw binaries of Portable Executable (PE) files was used for the classification. The QSVM algorithm, incorporating quantum kernels through different feature maps, was implemented and evaluated on a local simulator within the Qiskit SDK and IBM quantum computers. Experimental results from simulators and quantum hardware provide insights into the behavior and performance of quantum computers, especially in handling large-scale computations for malware detection tasks. The work summarizes the practical experience with using quantum hardware via the Qiskit interfaces. We describe in detail the critical issues encountered, as well as the fixes that had to be developed and applied to the base code of the Qiskit Machine Learning library. These issues include missing transpilation of the circuits submitted to IBM Quantum systems and exceeding the maximum job size limit due to the submission of all the circuits in one job.

---

### Capture and Interact: Rapid 3D Object Acquisition and Rendering with Gaussian Splatting in Unity

Authors: Islomjon Shukhratov, Sergey Gorinsky
Published: 2025-10-08
Categories: cs.GR, cs.CV
arXiv: https://arxiv.org/abs/2510.06802v1

Capturing and rendering three-dimensional (3D) objects in real time remain a significant challenge, yet hold substantial potential for applications in augmented reality, digital twin systems, remote collaboration and prototyping. We present an end-to-end pipeline that leverages 3D Gaussian Splatting (3D GS) to enable rapid acquisition and interactive rendering of real-world objects using a mobile device, cloud processing and a local computer. Users scan an object with a smartphone video, upload it for automated 3D reconstruction, and visualize it interactively in Unity at an average of 150 frames per second (fps) on a laptop. The system integrates mobile capture, cloud-based 3D GS and Unity rendering to support real-time telepresence. Our experiments show that the pipeline processes scans in approximately 10 minutes on a graphics processing unit (GPU) achieving real-time rendering on the laptop.

---

### FURINA: A Fully Customizable Role-Playing Benchmark via Scalable Multi-Agent Collaboration Pipeline

Authors: Haotian Wu, Shufan Jiang, Chios Chen, Yiyang Feng, Hehai Lin, Heqing Zou, Yao Shu, Chengwei Qin
Published: 2025-10-08
Categories: cs.CL, cs.AI, cs.HC, cs.MA
arXiv: https://arxiv.org/abs/2510.06800v3

As large language models (LLMs) advance in role-playing (RP) tasks, existing benchmarks quickly become obsolete due to their narrow scope, outdated interaction paradigms, and limited adaptability across diverse application scenarios. To address this gap, we introduce FURINA-Builder, a novel multi-agent collaboration pipeline that automatically constructs fully customizable RP benchmarks at any scale. It enables evaluation of arbitrary characters across diverse scenarios and prompt formats, as the first benchmark builder in RP area for adaptable assessment. FURINA-Builder simulates dialogues between a test character and other characters drawn from a well-constructed character-scene pool, while an LLM judge selects fine-grained evaluation dimensions and adjusts the test character's responses into final test utterances. Using this pipeline, we build FURINA-Bench, a new comprehensive role-playing benchmark featuring both established and synthesized test characters, each assessed with dimension-specific evaluation criteria. Human evaluation and preliminary separability analysis justify our pipeline and benchmark design. We conduct extensive evaluations of cutting-edge LLMs and find that o3 and DeepSeek-R1 achieve the best performance on English and Chinese RP tasks, respectively. Across all models, established characters consistently outperform synthesized ones, with reasoning capabilities further amplifying this disparity. Interestingly, we observe that model scale does not monotonically reduce hallucinations. More critically, for reasoning LLMs, we uncover a novel trade-off: reasoning improves RP performance but simultaneously increases RP hallucinations. This trade-off extends to a broader Pareto frontier between RP performance and reliability for all LLMs. These findings demonstrate the effectiveness of FURINA-Builder and the challenge posed by FURINA-Bench.

---

### Extreme Amodal Face Detection

Authors: Changlin Song, Yunzhong Hou, Michael Randall Barnes, Rahul Shome, Dylan Campbell
Published: 2025-10-08
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.06791v2

Extreme amodal detection is the task of inferring the 2D location of objects that are not fully visible in the input image but are visible within an expanded field-of-view. This differs from amodal detection, where the object is partially visible within the input image, but is occluded. In this paper, we consider the sub-problem of face detection, since this class provides motivating applications involving safety and privacy, but do not tailor our method specifically to this class. Existing approaches rely on image sequences so that missing detections may be interpolated from surrounding frames or make use of generative models to sample possible completions. In contrast, we consider the single-image task and propose a more efficient, sample-free approach that makes use of the contextual cues from the image to infer the presence of unseen faces. We design a heatmap-based extreme amodal object detector that addresses the problem of efficiently predicting a lot (the out-of-frame region) from a little (the image) with a selective coarse-to-fine decoder. Our method establishes strong results for this new task, even outperforming less efficient generative approaches. Code, data, and models are available at https://charliesong1999.github.io/exaft_web/.

---

### Get RICH or Die Scaling: Profitably Trading Inference Compute for Robustness

Authors: Tavish McDonald, Bo Lei, Stanislav Fort, Bhavya Kailkhura, Brian Bartoldson
Published: 2025-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.06790v3

Test-time reasoning has raised benchmark performances and even shown promise in addressing the historically intractable problem of making models robust to adversarially out-of-distribution (OOD) data. Indeed, recent work used reasoning to aid satisfaction of model specifications designed to thwart attacks, finding a striking correlation between LLM reasoning effort and robustness to jailbreaks. However, this benefit fades when stronger (e.g. gradient-based or multimodal) attacks are used. This may be expected as models often can't follow instructions on the adversarially OOD data created by such attacks, and instruction following is needed to act in accordance with the attacker-thwarting spec. Thus, we hypothesize that the test-time robustness benefits of specs are unlocked by initial robustness sufficient to follow instructions on OOD data. Namely, we posit the Robustness from Inference Compute Hypothesis (RICH): inference-compute defenses profit as the model's training data better reflects the components of attacked data. Guided by the RICH, we test models of varying initial-robustness levels, finding inference-compute adds robustness even to white-box multimodal attacks, provided the model has sufficient initial robustness. Further evidencing a rich-get-richer dynamic, InternVL 3.5 gpt-oss 20B gains little robustness when its test compute is scaled, but such scaling adds significant robustness if we first robustify its vision encoder (creating the first adversarially robust reasoning VLM in the process). Robustifying models makes attacked components of data more in-distribution (ID), and the RICH suggests this fuels compositional generalization -- understanding OOD data via its ID components -- to following spec instructions on adversarial data. Consistently, we find test-time defenses both build and depend on train-time data and defenses.

---

### Bionetta: Efficient Client-Side Zero-Knowledge Machine Learning Proving

Authors: Dmytro Zakharov, Oleksandr Kurbatov, Artem Sdobnov, Lev Soukhanov, Yevhenii Sekhin, Vitalii Volovyk, Mykhailo Velykodnyi, Mark Cherepovskyi, Kyrylo Baibula, Lasha Antadze, Pavlo Kravchenko, Volodymyr Dubinin et al.
Published: 2025-10-08
Categories: cs.CR, cs.CV
arXiv: https://arxiv.org/abs/2510.06784v2

In this report, we compare the performance of our UltraGroth-based zero-knowledge machine learning framework Bionetta to other tools of similar purpose such as EZKL, Lagrange's deep-prove, or zkml. The results show a significant boost in the proving time for custom-crafted neural networks: they can be proven even on mobile devices, enabling numerous client-side proving applications. While our scheme increases the cost of one-time preprocessing steps, such as circuit compilation and generating trusted setup, our approach is, to the best of our knowledge, the only one that is deployable on the native EVM smart contracts without overwhelming proof size and verification overheads.

---

### TTRV: Test-Time Reinforcement Learning for Vision Language Models

Authors: Akshit Singh, Shyam Marjit, Wei Lin, Paul Gavrikov, Serena Yeung-Levy, Hilde Kuehne, Rogerio Feris, Sivan Doveh, James Glass, M. Jehanzeb Mirza
Published: 2025-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.06783v2

Existing methods for extracting reward signals in Reinforcement Learning typically rely on labeled data and dedicated training splits, a setup that contrasts with how humans learn directly from their environment. In this work, we propose TTRV to enhance vision language understanding by adapting the model on the fly at inference time, without the need for any labeled data. Concretely, we enhance the Group Relative Policy Optimization (GRPO) framework by designing rewards based on the frequency of the base model's output, while inferring on each test sample multiple times. Further, we also propose to control the diversity of the model's output by simultaneously rewarding the model for obtaining low entropy of the output empirical distribution. Our approach delivers consistent gains across both object recognition and visual question answering (VQA), with improvements of up to 52.4% and 29.8%, respectively, and average boosts of 24.6% and 10.0% across 16 datasets. Remarkably, on image recognition, TTRV applied to InternVL 8B surpasses GPT-4o by an average of 2.3% over 8 benchmarks, while remaining highly competitive on VQA, demonstrating that test-time reinforcement learning can match or exceed the strongest proprietary models. Finally, we find many interesting properties of test-time RL for VLMs: for example, even in extremely data-constrained scenarios, where adaptation is performed on a single randomly chosen unlabeled test example, TTRV still yields non-trivial improvements of up to 5.5% in recognition tasks.

---

### GPT-5 Model Corrected GPT-4V's Chart Reading Errors, Not Prompting

Authors: Kaichun Yang, Jian Chen
Published: 2025-10-08
Categories: cs.HC, cs.CL, cs.CV
arXiv: https://arxiv.org/abs/2510.06782v1

We present a quantitative evaluation to understand the effect of zero-shot large-language model (LLMs) and prompting uses on chart reading tasks. We asked LLMs to answer 107 visualization questions to compare inference accuracies between the agentic GPT-5 and multimodal GPT-4V, for difficult image instances, where GPT-4V failed to produce correct answers. Our results show that model architecture dominates the inference accuracy: GPT5 largely improved accuracy, while prompt variants yielded only small effects. Pre-registration of this work is available here: https://osf.io/u78td/?view_only=6b075584311f48e991c39335c840ded3; the Google Drive materials are here:https://drive.google.com/file/d/1ll8WWZDf7cCNcfNWrLViWt8GwDNSvVrp/view.

---

### Foundations of LLM Knowledge Materialization: Termination, Reproducibility, Robustness

Authors: Luca Giordano, Simon Razniewski
Published: 2025-10-08
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.06780v3

Large Language Models (LLMs) encode substantial factual knowledge, yet measuring and systematizing this knowledge remains challenging. Converting it into structured format, for example through recursive extraction approaches such as the GPTKB methodology (Hu et al., 2025b), is still underexplored. Key open questions include whether such extraction can terminate, whether its outputs are reproducible, and how robust they are to variations. We systematically study LLM knowledge materialization using miniGPTKBs (domain-specific, tractable subcrawls), analyzing termination, reproducibility, and robustness across three categories of metrics: yield, lexical similarity, and semantic similarity. We experiment with four variations (seed, language, randomness, model) and three illustrative domains (from history, entertainment, and finance). Our findings show (i) high termination rates, though model-dependent; (ii) mixed reproducibility; and (iii) robustness that varies by perturbation type: high for seeds and temperature, lower for languages and models. These results suggest that LLM knowledge materialization can reliably surface core knowledge, while also revealing important limitations.

---

### Modeling COVID-19 Dynamics in German States Using Physics-Informed Neural Networks

Authors: Phillip Rothenbeck, Sai Karthikeya Vemuri, Niklas Penzel, Joachim Denzler
Published: 2025-10-08
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.06776v1

The COVID-19 pandemic has highlighted the need for quantitative modeling and analysis to understand real-world disease dynamics. In particular, post hoc analyses using compartmental models offer valuable insights into the effectiveness of public health interventions, such as vaccination strategies and containment policies. However, such compartmental models like SIR (Susceptible-Infectious-Recovered) often face limitations in directly incorporating noisy observational data. In this work, we employ Physics-Informed Neural Networks (PINNs) to solve the inverse problem of the SIR model using infection data from the Robert Koch Institute (RKI). Our main contribution is a fine-grained, spatio-temporal analysis of COVID-19 dynamics across all German federal states over a three-year period. We estimate state-specific transmission and recovery parameters and time-varying reproduction number (R_t) to track the pandemic progression. The results highlight strong variations in transmission behavior across regions, revealing correlations with vaccination uptake and temporal patterns associated with major pandemic phases. Our findings demonstrate the utility of PINNs in localized, long-term epidemiological modeling.

---

### Adaptive LLM-Symbolic Reasoning via Dynamic Logical Solver Composition

Authors: Lei Xu, Pierre Beckmann, Marco Valentino, André Freitas
Published: 2025-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.06774v1

Neuro-symbolic NLP methods aim to leverage the complementary strengths of large language models and formal logical solvers. However, current approaches are mostly static in nature, i.e., the integration of a target solver is predetermined at design time, hindering the ability to employ diverse formal inference strategies. To address this, we introduce an adaptive, multi-paradigm, neuro-symbolic inference framework that: (1) automatically identifies formal reasoning strategies from problems expressed in natural language; and (2) dynamically selects and applies specialized formal logical solvers via autoformalization interfaces. Extensive experiments on individual and multi-paradigm reasoning tasks support the following conclusions: LLMs are effective at predicting the necessary formal reasoning strategies with an accuracy above 90 percent. This enables flexible integration with formal logical solvers, resulting in our framework outperforming competing baselines by 27 percent and 6 percent compared to GPT-4o and DeepSeek-V3.1, respectively. Moreover, adaptive reasoning can even positively impact pure LLM methods, yielding gains of 10, 5, and 6 percent on zero-shot, CoT, and symbolic CoT settings with GPT-4o. Finally, although smaller models struggle with adaptive neuro-symbolic reasoning, post-training offers a viable path to improvement. Overall, this work establishes the foundations for adaptive LLM-symbolic reasoning, offering a path forward for unifying material and formal inferences on heterogeneous reasoning challenges.

---

### A deep multiple instance learning approach based on coarse labels for high-resolution land-cover mapping

Authors: Gianmarco Perantoni, Lorenzo Bruzzone
Published: 2025-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.06769v1

The quantity and the quality of the training labels are central problems in high-resolution land-cover mapping with machine-learning-based solutions. In this context, weak labels can be gathered in large quantities by leveraging on existing low-resolution or obsolete products. In this paper, we address the problem of training land-cover classifiers using high-resolution imagery (e.g., Sentinel-2) and weak low-resolution reference data (e.g., MODIS -derived land-cover maps). Inspired by recent works in Deep Multiple Instance Learning (DMIL), we propose a method that trains pixel-level multi-class classifiers and predicts low-resolution labels (i.e., patch-level classification), where the actual high-resolution labels are learned implicitly without direct supervision. This is achieved with flexible pooling layers that are able to link the semantics of the pixels in the high-resolution imagery to the low-resolution reference labels. Then, the Multiple Instance Learning (MIL) problem is re-framed in a multi-class and in a multi-label setting. In the former, the low-resolution annotation represents the majority of the pixels in the patch. In the latter, the annotation only provides us information on the presence of one of the land-cover classes in the patch and thus multiple labels can be considered valid for a patch at a time, whereas the low-resolution labels provide us only one label. Therefore, the classifier is trained with a Positive-Unlabeled Learning (PUL) strategy. Experimental results on the 2020 IEEE GRSS Data Fusion Contest dataset show the effectiveness of the proposed framework compared to standard training strategies.

---

### Function regression using the forward forward training and inferring paradigm

Authors: Shivam Padmani, Akshay Joshi
Published: 2025-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.06762v2

Function regression/approximation is a fundamental application of machine learning. Neural networks (NNs) can be easily trained for function regression using a sufficient number of neurons and epochs. The forward-forward learning algorithm is a novel approach for training neural networks without backpropagation, and is well suited for implementation in neuromorphic computing and physical analogs for neural networks. To the best of the authors' knowledge, the Forward Forward paradigm of training and inferencing NNs is currently only restricted to classification tasks. This paper introduces a new methodology for approximating functions (function regression) using the Forward-Forward algorithm. Furthermore, the paper evaluates the developed methodology on univariate and multivariate functions, and provides preliminary studies of extending the proposed Forward-Forward regression to Kolmogorov Arnold Networks, and Deep Physical Neural Networks.

---