# Research Papers — 2025-10 · bundle page 25 of 217

> Full-text markdown of papers #1201–1250 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/25
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/24.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/26.md)

### Symbolic Snapshot Ensembles

Authors: Mingyue Liu, Andrew Cropper
Published: 2025-10-28
Categories: cs.LG, cs.LO
arXiv: https://arxiv.org/abs/2510.24633v1

Inductive logic programming (ILP) is a form of logical machine learning. Most ILP algorithms learn a single hypothesis from a single training run. Ensemble methods train an ILP algorithm multiple times to learn multiple hypotheses. In this paper, we train an ILP algorithm only once and save intermediate hypotheses. We then combine the hypotheses using a minimum description length weighting scheme. Our experiments on multiple benchmarks, including game playing and visual reasoning, show that our approach improves predictive accuracy by 4% with less than 1% computational overhead.

---

### Bridging Simulators with Conditional Optimal Transport

Authors: Justine Zeghal, Benjamin Remy, Yashar Hezaveh, Francois Lanusse, Laurence Perreault Levasseur
Published: 2025-10-28
Categories: astro-ph.CO, stat.ML
arXiv: https://arxiv.org/abs/2510.24631v1

We propose a new field-level emulator that bridges two simulators using unpaired simulation datasets. Our method leverages a flow-based approach to learn the likelihood transport from one simulator to the other. Since multiple transport maps exist, we employ Conditional Optimal Transport Flow Matching (COT-FM) to ensure that the transformation minimally distorts the underlying structure of the data. We demonstrate the effectiveness of this approach by bridging weak lensing simulators: a Lagrangian Perturbation Theory (LPT) to a N-body Particle-Mesh (PM). We demonstrate that our emulator captures the full correction between the simulators by showing that it enables full-field inference to accurately recover the true posterior, validating its accuracy beyond traditional summary statistics.

---

### "Mm, Wat?" Detecting Other-initiated Repair Requests in Dialogue

Authors: Anh Ngo, Nicolas Rollet, Catherine Pelachaud, Chloe Clavel
Published: 2025-10-28
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.24628v1

Maintaining mutual understanding is a key component in human-human conversation to avoid conversation breakdowns, in which repair, particularly Other-Initiated Repair (OIR, when one speaker signals trouble and prompts the other to resolve), plays a vital role. However, Conversational Agents (CAs) still fail to recognize user repair initiation, leading to breakdowns or disengagement. This work proposes a multimodal model to automatically detect repair initiation in Dutch dialogues by integrating linguistic and prosodic features grounded in Conversation Analysis. The results show that prosodic cues complement linguistic features and significantly improve the results of pretrained text and audio embeddings, offering insights into how different features interact. Future directions include incorporating visual cues, exploring multilingual and cross-context corpora to assess the robustness and generalizability.

---

### Relative Scaling Laws for LLMs

Authors: William Held, David Hall, Percy Liang, Diyi Yang
Published: 2025-10-28
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.24626v2

Scaling laws describe how language models improve with additional data, parameters, and compute. While widely used, they are typically measured on aggregate test sets. Aggregate evaluations yield clean trends but average over heterogeneous subpopulations, obscuring performance disparities. We introduce relative scaling laws, which track how performance gaps between test distributions evolve with scale rather than focusing solely on absolute error. Using 255 decoder-only Transformers trained under matched-compute (IsoFLOP) budgets from $10^{18}$--$10^{20}$ FLOPs on standard pretraining datasets, we find diverse trajectories: academic domains on MMLU converge toward parity; regional English dialects shift depending on population size; and clusters of AI risk behaviours split, with capability- and influence-related risks increasing during pretraining while adversarial risks do not. These results show that although scaling improves overall performance, it is not a universal equalizer. To support further study, we release all model checkpoints from this work to enable practitioners to measure relative alongside traditional scaling laws, in order to better prioritize robustness challenges in light of the bitter lesson.

---

### GroundLoc: Efficient Large-Scale Outdoor LiDAR-Only Localization

Authors: Nicolai Steinke, Daniel Goehring
Published: 2025-10-28
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2510.24623v1

In this letter, we introduce GroundLoc, a LiDAR-only localization pipeline designed to localize a mobile robot in large-scale outdoor environments using prior maps. GroundLoc employs a Bird's-Eye View (BEV) image projection focusing on the perceived ground area and utilizes the place recognition network R2D2, or alternatively, the non-learning approach Scale-Invariant Feature Transform (SIFT), to identify and select keypoints for BEV image map registration. Our results demonstrate that GroundLoc outperforms state-of-the-art methods on the SemanticKITTI and HeLiPR datasets across various sensors. In the multi-session localization evaluation, GroundLoc reaches an Average Trajectory Error (ATE) well below 50 cm on all Ouster OS2 128 sequences while meeting online runtime requirements. The system supports various sensor models, as evidenced by evaluations conducted with Velodyne HDL-64E, Ouster OS2 128, Aeva Aeries II, and Livox Avia sensors. The prior maps are stored as 2D raster image maps, which can be created from a single drive and require only 4 MB of storage per square kilometer. The source code is available at https://github.com/dcmlr/groundloc.

---

### Coreset for Robust Geometric Median: Eliminating Size Dependency on Outliers

Authors: Ziyi Fang, Lingxiao Huang, Runkai Yang
Published: 2025-10-28
Categories: cs.DS, cs.CG, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.24621v1

We study the robust geometric median problem in Euclidean space $\mathbb{R}^d$, with a focus on coreset construction.A coreset is a compact summary of a dataset $P$ of size $n$ that approximates the robust cost for all centers $c$ within a multiplicative error $\varepsilon$. Given an outlier count $m$, we construct a coreset of size $\tilde{O}(\varepsilon^{-2} \cdot \min\{\varepsilon^{-2}, d\})$ when $n \geq 4m$, eliminating the $O(m)$ dependency present in prior work (Huang et al., 2022 & 2023). For the special case of $d = 1$, we achieve an optimal coreset size of $\tildeΘ(\varepsilon^{-1/2} + \frac{m}{n} \varepsilon^{-1})$, revealing a clear separation from the vanilla case studied in (Huang et al., 2023; Afshani and Chris, 2024). Our results further extend to robust $(k,z)$-clustering in various metric spaces, eliminating the $m$-dependence under mild data assumptions. The key technical contribution is a novel non-component-wise error analysis, enabling substantial reduction of outlier influence, unlike prior methods that retain them.Empirically, our algorithms consistently outperform existing baselines in terms of size-accuracy tradeoffs and runtime, even when data assumptions are violated across a wide range of datasets.

---

### Zero-Shot Cross-Lingual Transfer using Prefix-Based Adaptation

Authors: Snegha A, Sayambhu Sen, Piyush Singh Pasi, Abhishek Singhania, Preethi Jyothi
Published: 2025-10-28
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.24619v1

With the release of new large language models (LLMs) like Llama and Mistral, zero-shot cross-lingual transfer has become increasingly feasible due to their multilingual pretraining and strong generalization capabilities. However, adapting these decoder-only LLMs to new tasks across languages remains challenging. While parameter-efficient fine-tuning (PeFT) techniques like Low-Rank Adaptation (LoRA) are widely used, prefix-based techniques such as soft prompt tuning, prefix tuning, and Llama Adapter are less explored, especially for zero-shot transfer in decoder-only models. We present a comprehensive study of three prefix-based methods for zero-shot cross-lingual transfer from English to 35+ high- and low-resource languages. Our analysis further explores transfer across linguistic families and scripts, as well as the impact of scaling model sizes from 1B to 24B. With Llama 3.1 8B, prefix methods outperform LoRA-baselines by up to 6% on the Belebele benchmark. Similar improvements were observed with Mistral v0.3 7B as well. Despite using only 1.23M learning parameters with prefix tuning, we achieve consistent improvements across diverse benchmarks. These findings highlight the potential of prefix-based techniques as an effective and scalable alternative to LoRA, particularly in low-resource multilingual settings.

---

### Statistical physics of deep learning: Optimal learning of a multi-layer perceptron near interpolation

Authors: Jean Barbier, Francesco Camilli, Minh-Toan Nguyen, Mauro Pastore, Rudy Skerk
Published: 2025-10-28
Categories: stat.ML, cond-mat.dis-nn, cond-mat.stat-mech, cs.IT, cs.LG
arXiv: https://arxiv.org/abs/2510.24616v5

For four decades statistical physics has been providing a framework to analyse neural networks. A long-standing question remained on its capacity to tackle deep learning models capturing rich feature learning effects, thus going beyond the narrow networks or kernel methods analysed until now. We positively answer through the study of the supervised learning of a multi-layer perceptron. Importantly, (i) its width scales as the input dimension, making it more prone to feature learning than ultra wide networks, and more expressive than narrow ones or ones with fixed embedding layers; and (ii) we focus on the challenging interpolation regime where the number of trainable parameters and data are comparable, which forces the model to adapt to the task. We consider the matched teacher-student setting. Therefore, we provide the fundamental limits of learning random deep neural network targets and identify the sufficient statistics describing what is learnt by an optimally trained network as the data budget increases. A rich phenomenology emerges with various learning transitions. With enough data, optimal performance is attained through the model's "specialisation" towards the target, but it can be hard to reach for training algorithms which get attracted by sub-optimal solutions predicted by the theory. Specialisation occurs inhomogeneously across layers, propagating from shallow towards deep ones, but also across neurons in each layer. Furthermore, deeper targets are harder to learn. Despite its simplicity, the Bayes-optimal setting provides insights on how the depth, non-linearity and finite (proportional) width influence neural networks in the feature learning regime that are potentially relevant in much more general settings.

---

### Semi-supervised and unsupervised learning for health indicator extraction from guided waves in aerospace composite structures

Authors: James Josep Perry, Pablo Garcia-Conde Ortiz, George Konstantinou, Cornelie Vergouwen, Edlyn Santha Kumaran, Morteza Moradi
Published: 2025-10-28
Categories: cs.LG, cs.CE, eess.SP
arXiv: https://arxiv.org/abs/2510.24614v2

Health indicators (HIs) are central to diagnosing and prognosing the condition of aerospace composite structures, enabling efficient maintenance and operational safety. However, extracting reliable HIs remains challenging due to variability in material properties, stochastic damage evolution, and diverse damage modes. Manufacturing defects (e.g., disbonds) and in-service incidents (e.g., bird strikes) further complicate this process. This study presents a comprehensive data-driven framework that learns HIs via two learning approaches integrated with multi-domain signal processing. Because ground-truth HIs are unavailable, a semi-supervised and an unsupervised approach are proposed: (i) a diversity deep semi-supervised anomaly detection (Diversity-DeepSAD) approach augmented with continuous auxiliary labels used as hypothetical damage proxies, which overcomes the limitation of prior binary labels that only distinguish healthy and failed states while neglecting intermediate degradation, and (ii) a degradation-trend-constrained variational autoencoder (DTC-VAE), in which the monotonicity criterion is embedded via an explicit trend constraint. Guided waves with multiple excitation frequencies are used to monitor single-stiffener composite structures under fatigue loading. Time, frequency, and time-frequency representations are explored, and per-frequency HIs are fused via unsupervised ensemble learning to mitigate frequency dependence and reduce variance. Using fast Fourier transform features, the augmented Diversity-DeepSAD model achieved 81.6% performance, while DTC-VAE delivered the most consistent HIs with 92.3% performance, outperforming existing baselines.

---

### Long-Context Modeling with Dynamic Hierarchical Sparse Attention for Memory-Constrained LLM Inference

Authors: Siheng Xiong, Joe Zou, Faramarz Fekri, Yae Jee Cho
Published: 2025-10-28
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.24606v2

The quadratic cost of attention limits the scalability of long-context LLMs, especially under limited hardware memory budgets. While attention is often sparse, existing static sparse methods cannot adapt to task- or input-dependent variations, and recent dynamic approaches rely on predefined templates or heuristics that may sacrifice generality. We propose Dynamic Hierarchical Sparse Attention (DHSA), a data-driven framework that predicts attention sparsity online while keeping the LLM backbone frozen. DHSA performs hierarchical routing by estimating importance at the chunk level and propagating it to token-level interactions, preserving causally important dependencies while enabling efficient sparsification. Across Needle-in-a-Haystack test, LongBench and RULER, DHSA maintains near-dense accuracy in highly sparse regimes, achieving 12--20% relative accuracy gains over Block Sparse Attention at comparable prefill cost. With a memory-efficient tiled backend, DHSA delivers up to $10\times$ prefill speedup at 128K context length. On LLaMA-3.1-8B (4-bit), DHSA scales to 100K context on a single 24GB GPU, where dense attention fails. We provide complementary GPU and CPU backends, enabling DHSA to run across diverse hardware environments and multiple open-weight model families. These results demonstrate DHSA as an efficient and adaptable solution for memory-constrained long-context LLM inference.

---

### Diffusion LLM with Native Variable Generation Lengths: Let (EOS) Lead the Way

Authors: Yicun Yang, Cong Wang, Shaobo Wang, Zichen Wen, Biqing Qi, Hanlin Xu, Linfeng Zhang
Published: 2025-10-28
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.24605v1

Diffusion-based large language models (dLLMs) have exhibited substantial potential for parallel text generation, which may enable more efficient generation compared to autoregressive models. However, current dLLMs suffer from fixed generation lengths, which indicates the generation lengths of dLLMs have to be determined before decoding as a hyper-parameter, leading to issues in efficiency and flexibility. To solve these problems, in this work, we propose to train a diffusion LLM with native variable generation lengths, abbreviated as dLLM-Var. Concretely, we aim to train a model to accurately predict the (EOS) token in the generated text, which makes a dLLM be able to natively infer in a block diffusion manner, while still maintaining the ability of global bi-directional (full) attention and high parallelism. Experiments on standard benchmarks demonstrate that our method achieves a 30.1x speedup over traditional dLLM inference paradigms and a 2.4x speedup relative to autoregressive models such as Qwen and Llama. Our method achieves higher accuracy and faster inference, elevating dLLMs beyond mere academic novelty and supporting their practical use in real-world applications. Codes and models have been released.

---

### Comparison of generalised additive models and neural networks in applications: A systematic review

Authors: Jessica Doohan, Lucas Kook, Kevin Burke
Published: 2025-10-28
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.24601v2

Neural networks have become a popular tool in predictive modelling, more commonly associated with machine learning and artificial intelligence than with statistics. Generalised Additive Models (GAMs) are flexible non-linear statistical models that retain interpretability. Both are state-of-the-art in their own right, with their respective advantages and disadvantages. This paper analyses how these two model classes have performed on real-world tabular data. Following PRISMA guidelines, we conducted a systematic review of papers that performed empirical comparisons of GAMs and neural networks. Eligible papers were identified, yielding 143 papers, with 430 datasets. Key attributes at both paper and dataset levels were extracted and reported. Beyond summarising comparisons, we analyse reported performance metrics using mixed-effects modelling to investigate potential characteristics that can explain and quantify observed differences, including application area, study year, sample size, number of predictors, and neural network complexity. Across datasets, no consistent evidence of superiority was found for either GAMs or neural networks when considering the most frequently reported metrics (RMSE, $R^2$, and AUC). Neural networks tended to outperform in larger datasets and in those with more predictors, but this advantage narrowed over time. Conversely, GAMs remained competitive, particularly in smaller data settings, while retaining interpretability. Reporting of dataset characteristics and neural network complexity was incomplete in much of the literature, limiting transparency and reproducibility. This review highlights that GAMs and neural networks should be viewed as complementary approaches rather than competitors. For many tabular applications, the performance trade-off is modest, and interpretability may favour GAMs.

---

### A Novel XAI-Enhanced Quantum Adversarial Networks for Velocity Dispersion Modeling in MaNGA Galaxies

Authors: Sathwik Narkedimilli, N V Saran Kumar, Aswath Babu H, Manjunath K Vanahalli, Manish M, Aik Beng Ng, Vinija Jain, Aman Chadha
Published: 2025-10-28
Categories: cs.LG, cs.CR
arXiv: https://arxiv.org/abs/2510.24598v2

Current quantum machine learning approaches often face challenges balancing predictive accuracy, robustness, and interpretability. To address this, we propose a novel quantum adversarial framework that integrates a hybrid quantum neural network (QNN) with classical deep learning layers, guided by an evaluator model with LIME-based interpretability, and extended through quantum GAN and self-supervised variants. In the proposed model, an adversarial evaluator concurrently guides the QNN by computing feedback loss, thereby optimizing both prediction accuracy and model explainability. Empirical evaluations show that the Vanilla model achieves RMSE = 0.27, MSE = 0.071, MAE = 0.21, and R^2 = 0.59, delivering the most consistent performance across regression metrics compared to adversarial counterparts. These results demonstrate the potential of combining quantum-inspired methods with classical architectures to develop lightweight, high-performance, and interpretable predictive models, advancing the applicability of QML beyond current limitations.

---

### ReForm: Reflective Autoformalization with Prospective Bounded Sequence Optimization

Authors: Guoxin Chen, Jing Wu, Xinjie Chen, Wayne Xin Zhao, Ruihua Song, Chengxi Li, Kai Fan, Dayiheng Liu, Minpeng Liao
Published: 2025-10-28
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.24592v3

Autoformalization, which translates natural language mathematics into machine-verifiable formal statements, is critical for using formal mathematical reasoning to solve math problems stated in natural language. While Large Language Models can generate syntactically correct formal statements, they often fail to preserve the original problem's semantic intent. This limitation arises from the LLM approaches' treating autoformalization as a simplistic translation task which lacks mechanisms for self-reflection and iterative refinement that human experts naturally employ. To address these issues, we propose ReForm, a Reflective Autoformalization method that tightly integrates semantic consistency evaluation into the autoformalization process. This enables the model to iteratively generate formal statements, assess its semantic fidelity, and self-correct identified errors through progressive refinement. To effectively train this reflective model, we introduce Prospective Bounded Sequence Optimization (PBSO), which employs different rewards at different sequence positions to ensure that the model develops both accurate autoformalization and correct semantic validations, preventing superficial critiques that would undermine the purpose of reflection. Extensive experiments across four autoformalization benchmarks demonstrate that ReForm achieves an average improvement of 22.6 percentage points over the strongest baselines. To further ensure evaluation reliability, we introduce ConsistencyCheck, a benchmark of 859 expert-annotated items that not only validates LLMs as judges but also reveals that autoformalization is inherently difficult: even human experts produce semantic errors in up to 38.5% of cases.

---

### ReplicationBench: Can AI Agents Replicate Astrophysics Research Papers?

Authors: Christine Ye, Sihan Yuan, Suchetha Cooray, Steven Dillmann, Ian L. V. Roque, Dalya Baron, Philipp Frank, Sergio Martin-Alvarez, Nolan Koblischke, Frank J Qu, Diyi Yang, Risa Wechsler et al.
Published: 2025-10-28
Categories: cs.CL, astro-ph.IM
arXiv: https://arxiv.org/abs/2510.24591v2

Frontier AI agents show increasing promise as scientific research assistants, and may eventually be useful for extended, open-ended research workflows. However, in order to use agents for novel research, we must first assess the underlying faithfulness and correctness of their work. To evaluate agents as research assistants, we introduce ReplicationBench, an evaluation framework that tests whether agents can replicate entire research papers drawn from the astrophysics literature. Astrophysics, where research relies heavily on archival data and computational study while requiring little real-world experimentation, is a particularly useful testbed for AI agents in scientific research. We split each paper into tasks which require agents to replicate the paper's core contributions, including the experimental setup, derivations, data analysis, and codebase. Each task is co-developed with the original paper authors and targets a key scientific result, enabling objective evaluation of both faithfulness (adherence to original methods) and correctness (technical accuracy of results). ReplicationBench is extremely challenging for current frontier language models: even the best-performing language models score under 20%. We analyze ReplicationBench trajectories in collaboration with domain experts and find a rich, diverse set of failure modes for agents in scientific research. ReplicationBench establishes the first benchmark of paper-scale, expert-validated astrophysics research tasks, reveals insights about agent performance generalizable to other domains of data-driven science, and provides a scalable framework for measuring AI agents' reliability in scientific research.

---

### Physics-Inspired Gaussian Kolmogorov-Arnold Networks for X-ray Scatter Correction in Cone-Beam CT

Authors: Xu Jiang, Huiying Pan, Ligen Shi, Jianing Sun, Wenfeng Xu, Xing Zhao
Published: 2025-10-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.24579v1

Cone-beam CT (CBCT) employs a flat-panel detector to achieve three-dimensional imaging with high spatial resolution. However, CBCT is susceptible to scatter during data acquisition, which introduces CT value bias and reduced tissue contrast in the reconstructed images, ultimately degrading diagnostic accuracy. To address this issue, we propose a deep learning-based scatter artifact correction method inspired by physical prior knowledge. Leveraging the fact that the observed point scatter probability density distribution exhibits rotational symmetry in the projection domain. The method uses Gaussian Radial Basis Functions (RBF) to model the point scatter function and embeds it into the Kolmogorov-Arnold Networks (KAN) layer, which provides efficient nonlinear mapping capabilities for learning high-dimensional scatter features. By incorporating the physical characteristics of the scattered photon distribution together with the complex function mapping capacity of KAN, the model improves its ability to accurately represent scatter. The effectiveness of the method is validated through both synthetic and real-scan experiments. Experimental results show that the model can effectively correct the scatter artifacts in the reconstructed images and is superior to the current methods in terms of quantitative metrics.

---

### Physics-Informed Extreme Learning Machine (PIELM): Opportunities and Challenges

Authors: He Yang, Fei Ren, Francesco Calabro, Hai-Sui Yu, Xiaohui Chen, Pei-Zhi Zhuang
Published: 2025-10-28
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.24577v2

We are delighted to see the recent development of physics-informed extreme learning machine (PIELM) for its higher computational efficiency and accuracy compared to other physics-informed machine learning (PIML) paradigms. Since a comprehensive summary or review of PIELM is currently unavailable, we would like to take this opportunity to share our perspectives and experiences on this promising research direction. We can see that many efforts have been made to solve ordinary/partial differential equations (ODEs/PDEs) characterized by sharp gradients, nonlinearities, high-frequency behavior, hard constraints, uncertainty, multiphysics coupling, and interpretability. Despite these encouraging successes, many pressing challenges remain to be tackled, which also provides opportunities to develop more robust, interpretable, and generalizable PIELM frameworks for scientific and engineering applications.

---

### DistDF: Time-Series Forecasting Needs Joint-Distribution Wasserstein Alignment

Authors: Hao Wang, Licheng Pan, Yuan Lu, Zhixuan Chu, Xiaoxi Li, Shuting He, Zhichao Chen, Haoxuan Li, Qingsong Wen, Zhouchen Lin
Published: 2025-10-28
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.24574v3

Training time-series forecasting models requires aligning the conditional distribution of model forecasts with that of the label sequence. The standard direct forecast (DF) approach resorts to minimizing the conditional negative log-likelihood, typically estimated by the mean squared error. However, this estimation proves biased when the label sequence exhibits autocorrelation. In this paper, we propose DistDF, which achieves alignment by minimizing a distributional discrepancy between the conditional distributions of forecast and label sequences. Since such conditional discrepancies are difficult to estimate from finite time-series observations, we introduce a joint-distribution Wasserstein discrepancy for time-series forecasting, which provably upper bounds the conditional discrepancy of interest. The proposed discrepancy is tractable, differentiable, and readily compatible with gradient-based optimization. Extensive experiments show that DistDF improves diverse forecasting models and achieves leading performance. Code is available at https://anonymous.4open.science/r/DistDF-F66B.

---

### BEST-RQ-Based Self-Supervised Learning for Whisper Domain Adaptation

Authors: Raphaël Bagat, Irina Illina, Emmanuel Vincent
Published: 2025-10-28
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.24570v2

Automatic Speech Recognition (ASR) systems, despite large multilingual training, struggle in low-resource scenarios where labeled data is scarce. We propose BEARD (BEST-RQ Encoder Adaptation with Re-training and Distillation), a novel framework designed to adapt Whisper's encoder with unlabeled data. Unlike traditional self-supervised learning methods, BEARD uniquely combines a BEST-RQ objective with knowledge distillation from a frozen teacher encoder, ensuring the encoder's complementarity with the pre-trained decoder. Our experiments focus on the ATCO2 corpus from the challenging Air Traffic Control (ATC) communications domain, characterized by non-native speech, noise, and specialized phraseology. Using about 5,000 hours of untranscribed speech for BEARD and 2 hours of transcribed speech for fine-tuning, the proposed approach significantly outperforms previous baseline and fine-tuned model, achieving a relative improvement of 12% compared to the fine-tuned model. To the best of our knowledge, this is the first work to use a self-supervised learning objective for domain adaptation of Whisper.

---

### OSWorld-MCP: Benchmarking MCP Tool Invocation In Computer-Use Agents

Authors: Hongrui Jia, Jitong Liao, Xi Zhang, Haiyang Xu, Tianbao Xie, Chaoya Jiang, Ming Yan, Si Liu, Wei Ye, Fei Huang
Published: 2025-10-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.24563v2

With advances in decision-making and reasoning capabilities, multimodal agents show strong potential in computer application scenarios. Past evaluations have mainly assessed GUI interaction skills, while tool invocation abilities, such as those enabled by the Model Context Protocol (MCP), have been largely overlooked. Comparing agents with integrated tool invocation to those evaluated only on GUI interaction is inherently unfair. We present OSWorld-MCP, the first comprehensive and fair benchmark for assessing computer-use agents' tool invocation, GUI operation, and decision-making abilities in a real-world environment. We design a novel automated code-generation pipeline to create tools and combine them with a curated selection from existing tools. Rigorous manual validation yields 158 high-quality tools (covering 7 common applications), each verified for correct functionality, practical applicability, and versatility. Extensive evaluations of state-of-the-art multimodal agents on OSWorld-MCP show that MCP tools generally improve task success rates (e.g., from 8.3% to 20.4% for OpenAI o3 at 15 steps, from 40.1% to 43.3% for Claude 4 Sonnet at 50 steps), underscoring the importance of assessing tool invocation capabilities. However, even the strongest models have relatively low tool invocation rates, Only 36.3%, indicating room for improvement and highlighting the benchmark's challenge. By explicitly measuring MCP tool usage skills, OSWorld-MCP deepens understanding of multimodal agents and sets a new standard for evaluating performance in complex, tool-assisted environments. Our code, environment, and data are publicly available at https://osworld-mcp.github.io.

---

### LoRA-DA: Data-Aware Initialization for Low-Rank Adaptation via Asymptotic Analysis

Authors: Qingyue Zhang, Chang Chu, Tianren Peng, Qi Li, Xiangyang Luo, Zhihao Jiang, Shao-Lun Huang
Published: 2025-10-28
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.24561v3

LoRA has become a widely adopted method for PEFT, and its initialization methods have attracted increasing attention. However, existing methods have notable limitations: many methods do not incorporate target-domain data, while gradient-based methods exploit data only at a shallow level by relying on one-step gradient decomposition. In this paper, we establish a theoretical framework for data-aware LoRA initialization. Starting from minimizing the expectation of the parameter discrepancy between the fine-tuned and target models, we derive an optimization problem with two components: a bias term, which is related to the parameter distance between the fine-tuned and target models, and is approximated using a Fisher-gradient formulation to preserve anisotropy; and a variance term, which accounts for the uncertainty introduced by sampling stochasticity through the Fisher information. Solving this problem yields an optimal initialization strategy for LoRA, based on which we develop an efficient algorithm, LoRA-DA. Empirical results across multiple benchmarks demonstrate that LoRA-DA consistently improves final accuracy over existing initialization methods. Additional studies show faster, more stable convergence, robustness across ranks, and only a small initialization overhead for LoRA-DA. The source code is available at https://github.com/zqy0126/LoRA-DA.

---

### Enforcing boundary conditions for physics-informed neural operators

Authors: Niklas Göschel, Sebastian Götschel, Daniel Ruprecht
Published: 2025-10-28
Categories: math.NA, cs.LG
arXiv: https://arxiv.org/abs/2510.24557v1

Machine-learning based methods like physics-informed neural networks and physics-informed neural operators are becoming increasingly adept at solving even complex systems of partial differential equations. Boundary conditions can be enforced either weakly by penalizing deviations in the loss function or strongly by training a solution structure that inherently matches the prescribed values and derivatives. The former approach is easy to implement but the latter can provide benefits with respect to accuracy and training times. However, previous approaches to strongly enforcing Neumann or Robin boundary conditions require a domain with a fully $C^1$ boundary and, as we demonstrate, can lead to instability if those boundary conditions are posed on a segment of the boundary that is piecewise $C^1$ but only $C^0$ globally. We introduce a generalization of the approach by Sukumar \& Srivastava (doi: 10.1016/j.cma.2021.114333), and a new approach based on orthogonal projections that overcome this limitation. The performance of these new techniques is compared against weakly and semi-weakly enforced boundary conditions for the scalar Darcy flow equation and the stationary Navier-Stokes equations.

---

### Generative AI for Healthcare: Fundamentals, Challenges, and Perspectives

Authors: Gang Chen, Changshuo Liu, Gene Anne Ooi, Marcus Tan, Zhongle Xie, Jianwei Yin, James Wei Luen Yip, Wenqiao Zhang, Jiaqi Zhu, Beng Chin Ooi
Published: 2025-10-28
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.24551v1

Generative Artificial Intelligence (GenAI) is taking the world by storm. It promises transformative opportunities for advancing and disrupting existing practices, including healthcare. From large language models (LLMs) for clinical note synthesis and conversational assistance to multimodal systems that integrate medical imaging, electronic health records, and genomic data for decision support, GenAI is transforming the practice of medicine and the delivery of healthcare, such as diagnosis and personalized treatments, with great potential in reducing the cognitive burden on clinicians, thereby improving overall healthcare delivery. However, GenAI deployment in healthcare requires an in-depth understanding of healthcare tasks and what can and cannot be achieved. In this paper, we propose a data-centric paradigm in the design and deployment of GenAI systems for healthcare. Specifically, we reposition the data life cycle by making the medical data ecosystem as the foundational substrate for generative healthcare systems. This ecosystem is designed to sustainably support the integration, representation, and retrieval of diverse medical data and knowledge. With effective and efficient data processing pipelines, such as semantic vector search and contextual querying, it enables GenAI-powered operations for upstream model components and downstream clinical applications. Ultimately, it not only supplies foundation models with high-quality, multimodal data for large-scale pretraining and domain-specific fine-tuning, but also serves as a knowledge retrieval backend to support task-specific inference via the agentic layer. The ecosystem enables the deployment of GenAI for high-quality and effective healthcare delivery.

---

### Dual-Mind World Models: A General Framework for Learning in Dynamic Wireless Networks

Authors: Lingyi Wang, Rashed Shelim, Walid Saad, Naren Ramakrishnan
Published: 2025-10-28
Categories: cs.IT, cs.LG
arXiv: https://arxiv.org/abs/2510.24546v1

Despite the popularity of reinforcement learning (RL) in wireless networks, existing approaches that rely on model-free RL (MFRL) and model-based RL (MBRL) are data inefficient and short-sighted. Such RL-based solutions cannot generalize to novel network states since they capture only statistical patterns rather than the underlying physics and logic from wireless data. These limitations become particularly challenging in complex wireless networks with high dynamics and long-term planning requirements. To address these limitations, in this paper, a novel dual-mind world model-based learning framework is proposed with the goal of optimizing completeness-weighted age of information (CAoI) in a challenging mmWave V2X scenario. Inspired by cognitive psychology, the proposed dual-mind world model encompasses a pattern-driven System 1 component and a logic-driven System 2 component to learn dynamics and logic of the wireless network, and to provide long-term link scheduling over reliable imagined trajectories. Link scheduling is learned through end-to-end differentiable imagined trajectories with logical consistency over an extended horizon rather than relying on wireless data obtained from environment interactions. Moreover, through imagination rollouts, the proposed world model can jointly reason network states and plan link scheduling. During intervals without observations, the proposed method remains capable of making efficient decisions. Extensive experiments are conducted on a realistic simulator based on Sionna with real-world physical channel, ray-tracing, and scene objects with material properties. Simulation results show that the proposed world model achieves a significant improvement in data efficiency and achieves strong generalization and adaptation to unseen environments, compared to the state-of-the-art RL baselines, and the world model approach with only System 1.

---

### Open Korean Historical Corpus: A Millennia-Scale Diachronic Collection of Public Domain Texts

Authors: Seyoung Song, Nawon Kim, Songeun Chae, Kiwoong Park, Jiho Jin, Haneul Yoo, Kyunghyun Cho, Alice Oh
Published: 2025-10-28
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.24541v2

The history of the Korean language is characterized by a discrepancy between its spoken and written forms and a pivotal shift from Chinese characters to the Hangul alphabet. However, this linguistic evolution has remained largely unexplored in NLP due to a lack of accessible historical corpora. To address this gap, we introduce the Open Korean Historical Corpus, a large-scale, openly licensed dataset spanning 1,300 years and 6 languages, as well as under-represented writing systems like Korean-style Sinitic (Idu) and Hanja-Hangul mixed script. This corpus contains 17.7 million documents and 5.1 billion tokens from 19 sources, ranging from the 7th century to 2025. We leverage this resource to quantitatively analyze major linguistic shifts: (1) Idu usage peaked in the 1860s before declining sharply; (2) the transition from Hanja to Hangul was a rapid transformation starting around 1890; and (3) North Korea's lexical divergence causes modern tokenizers to produce up to 51 times higher out-of-vocabulary rates. This work provides a foundational resource for quantitative diachronic analysis by capturing the history of the Korean language. Moreover, it can serve as a pre-training corpus for large language models, potentially improving their understanding of Sino-Korean vocabulary in modern Hangul as well as archaic writing systems.

---

### Dark & Stormy: Modeling Humor in Sentences from the Bulwer-Lytton Fiction Contest

Authors: Venkata S Govindarajan, Laura Biester
Published: 2025-10-28
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.24538v2

Textual humor is enormously diverse and computational studies need to account for this range, including intentionally bad humor. In this paper, we curate and analyze a novel corpus of sentences from the Bulwer-Lytton Fiction Contest to better understand "bad" humor in English. Standard humor detection models perform poorly on our corpus, and an analysis of literary devices finds that these sentences combine features common in existing humor datasets (e.g., puns, irony) with metaphor, metafiction and simile. LLMs prompted to synthesize contest-style sentences imitate the form but exaggerate the effect by over-using certain literary devices, and including far more novel adjective-noun bigrams than human writers. Data, code and analysis are available at https://github.com/venkatasg/bulwer-lytton

---

### Quantum-Resistant Networks Using Post-Quantum Cryptography

Authors: Xin Jin, Nitish Kumar Chandra, Mohadeseh Azari, Kaushik P. Seshadreesan, Junyu Liu
Published: 2025-10-28
Categories: quant-ph, cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2510.24534v1

Quantum networks rely on both quantum and classical channels for coordinated operation. Current architectures employ entanglement distribution and key exchange over quantum channels but often assume that classical communication is sufficiently secure. In practice, classical channels protected by traditional cryptography remain vulnerable to quantum adversaries, since large-scale quantum computers could break widely used public-key schemes and reduce the effective security of symmetric cryptography. This perspective presents a quantum-resistant network architecture that secures classical communication with post-quantum cryptographic techniques while supporting entanglement-based communication over quantum channels. Beyond cryptographic protection, the framework incorporates continuous monitoring of both quantum and classical layers, together with orchestration across heterogeneous infrastructures, to ensure end-to-end security. Collectively, these mechanisms provide a pathway toward scalable, robust, and secure quantum networks that remain dependable against both classical and quantum-era threats.

---

### Levée d'ambiguïtés par grammaires locales

Authors: Eric G. C. Laporte
Published: 2025-10-28
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.24530v1

Many words are ambiguous in terms of their part of speech (POS). However, when a word appears in a text, this ambiguity is generally much reduced. Disambiguating POS involves using context to reduce the number of POS associated with words, and is one of the main challenges of lexical tagging. The problem of labeling words by POS frequently arises in natural language processing, for example for spelling correction, grammar or style checking, expression recognition, text-to-speech conversion, text corpus analysis, etc. Lexical tagging systems are thus useful as an initial component of many natural language processing systems. A number of recent lexical tagging systems produce multiple solutions when the text is lexically ambiguous or the uniquely correct solution cannot be found. These contributions aim to guarantee a zero silence rate: the correct tag(s) for a word must never be discarded. This objective is unrealistic for systems that tag each word uniquely. This article concerns a lexical disambiguation method adapted to the objective of a zero silence rate and implemented in Silberztein's INTEX system (1993). We present here a formal description of this method. We show that to verify a local disambiguation grammar in this framework, it is not sufficient to consider the transducer paths separately: one needs to verify their interactions. Similarly, if a combination of multiple transducers is used, the result cannot be predicted by considering them in isolation. Furthermore, when examining the initial labeling of a text as produced by INTEX, ideas for disambiguation rules come spontaneously, but grammatical intuitions may turn out to be inaccurate, often due to an unforeseen construction or ambiguity. If a zero silence rate is targeted, local grammars must be carefully tested. This is where a detailed specification of what a grammar will do once applied to texts would be necessary.

---

### From Cross-Task Examples to In-Task Prompts: A Graph-Based Pseudo-Labeling Framework for In-context Learning

Authors: Zihan Chen, Song Wang, Xingbo Fu, Chengshuai Shi, Zhenyu Lei, Cong Shen, Jundong Li
Published: 2025-10-28
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.24528v1

The capability of in-context learning (ICL) enables large language models (LLMs) to perform novel tasks without parameter updates by conditioning on a few input-output examples. However, collecting high-quality examples for new or challenging tasks can be costly and labor-intensive. In this work, we propose a cost-efficient two-stage pipeline that reduces reliance on LLMs for data labeling. Our approach first leverages readily available cross-task examples to prompt an LLM and pseudo-label a small set of target task instances. We then introduce a graph-based label propagation method that spreads label information to the remaining target examples without additional LLM queries. The resulting fully pseudo-labeled dataset is used to construct in-task demonstrations for ICL. This pipeline combines the flexibility of cross-task supervision with the scalability of LLM-free propagation. Experiments across five tasks demonstrate that our method achieves strong performance while lowering labeling costs.

---

### Unsupervised Machine-Learning Pipeline for Data-Driven Defect Detection and Characterisation: Application to Displacement Cascades

Authors: Samuel Del Fré, Andrée de Backer, Christophe Domain, Ludovic Thuinet, Charlotte S. Becquart
Published: 2025-10-28
Categories: cond-mat.mtrl-sci, cs.LG
arXiv: https://arxiv.org/abs/2510.24523v1

Neutron irradiation produces, within a few picoseconds, displacement cascades that are sequences of atomic collisions generating point and extended defects which subsequently affects the long-term evolution of materials. The diversity of these defects, characterized morphologically and statistically, defines what is called the "primary damage". In this work, we present a fully unsupervised machine learning (ML) workflow that detects and classifies these defects directly from molecular dynamics data. Local environments are encoded by the Smooth Overlap of Atomic Positions (SOAP) vector, anomalous atoms are isolated with autoencoder neural networks (AE), embedded with Uniform Manifold Approximation and Projection (UMAP) and clustered using Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN). Applied to 80 keV displacement cascades in Ni, Fe$_7$0Ni$_{10}$Cr$_{20}$, and Zr, the AE successfully identify the small fraction of outlier atoms that participate in defect formation. HDBSCAN then partitions the UMAP latent space of AE-flagged SOAP descriptors into well defined groups representing vacancy- and interstitial-dominated regions and, within each, separates small from large aggregates, assigning 99.7 % of outliers to compact physical motifs. A signed cluster-identification score confirms this separation, and cluster size scales with net defect counts (R2 > 0.89). Statistical cross analyses between the ML outlier map and several conventional detectors (centrosymmetry, dislocation extraction, etc.) reveal strong overlap and complementary coverage, all achieved without template or threshold tuning. This ML workflow thus provides an efficient tool for the quantitative mapping of structural anomalies in materials, particularly those arising from irradiation damage in displacement cascades.

---

### Audio Signal Processing Using Time Domain Mel-Frequency Wavelet Coefficient

Authors: Rinku Sebastian, Simon O'Keefe, Martin Trefzer
Published: 2025-10-28
Categories: cs.SD, cs.AI, eess.AS
arXiv: https://arxiv.org/abs/2510.24519v2

Extracting features from the speech is the most critical process in speech signal processing. Mel Frequency Cepstral Coefficients (MFCC) are the most widely used features in the majority of the speaker and speech recognition applications, as the filtering in this feature is similar to the filtering taking place in the human ear. But the main drawback of this feature is that it provides only the frequency information of the signal but does not provide the information about at what time which frequency is present. The wavelet transform, with its flexible time-frequency window, provides time and frequency information of the signal and is an appropriate tool for the analysis of non-stationary signals like speech. On the other hand, because of its uniform frequency scaling, a typical wavelet transform may be less effective in analysing speech signals, have poorer frequency resolution in low frequencies, and be less in line with human auditory perception. Hence, it is necessary to develop a feature that incorporates the merits of both MFCC and wavelet transform. A great deal of studies are trying to combine both these features. The present Wavelet Transform based Mel-scaled feature extraction methods require more computation when a wavelet transform is applied on top of Mel-scale filtering, since it adds extra processing steps. Here we are proposing a method to extract Mel scale features in time domain combining the concept of wavelet transform, thus reducing the computational burden of time-frequency conversion and the complexity of wavelet extraction. Combining our proposed Time domain Mel frequency Wavelet Coefficient(TMFWC) technique with the reservoir computing methodology has significantly improved the efficiency of audio signal processing.

---

### Latent Sketchpad: Sketching Visual Thoughts to Elicit Multimodal Reasoning in MLLMs

Authors: Huanyu Zhang, Wenshan Wu, Chengzu Li, Ning Shang, Yan Xia, Yangyu Huang, Yifan Zhang, Li Dong, Zhang Zhang, Liang Wang, Tieniu Tan, Furu Wei
Published: 2025-10-28
Categories: cs.CV, cs.CL
arXiv: https://arxiv.org/abs/2510.24514v1

While Multimodal Large Language Models (MLLMs) excel at visual understanding, they often struggle in complex scenarios that require visual planning and imagination. Inspired by how humans use sketching as a form of visual thinking to develop and communicate ideas, we introduce Latent Sketchpad, a framework that equips MLLMs with an internal visual scratchpad. The internal visual representations of MLLMs have traditionally been confined to perceptual understanding. We repurpose them to support generative visual thought without compromising reasoning ability. Building on frontier MLLMs, our approach integrates visual generation directly into their native autoregressive reasoning process. It allows the model to interleave textual reasoning with the generation of visual latents. These latents guide the internal thought process and can be translated into sketch images for interpretability. To realize this, we introduce two components: a Context-Aware Vision Head autoregressively produces visual representations, and a pretrained Sketch Decoder renders these into human-interpretable images. We evaluate the framework on our new dataset MazePlanning. Experiments across various MLLMs show that Latent Sketchpad delivers comparable or even superior reasoning performance to their backbone. It further generalizes across distinct frontier MLLMs, including Gemma3 and Qwen2.5-VL. By extending model's textual reasoning to visual thinking, our framework opens new opportunities for richer human-computer interaction and broader applications. More details and resources are available on our project page: https://latent-sketchpad.github.io/.

---

### CritiCal: Can Critique Help LLM Uncertainty or Confidence Calibration?

Authors: Qing Zong, Jiayu Liu, Tianshi Zheng, Chunyang Li, Baixuan Xu, Haochen Shi, Weiqi Wang, Zhaowei Wang, Chunkit Chan, Yangqiu Song
Published: 2025-10-28
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.24505v1

Accurate confidence calibration in Large Language Models (LLMs) is critical for safe use in high-stakes domains, where clear verbalized confidence enhances user trust. Traditional methods that mimic reference confidence expressions often fail to capture the reasoning needed for accurate confidence assessment. We propose natural language critiques as a solution, ideally suited for confidence calibration, as precise gold confidence labels are hard to obtain and often require multiple generations. This paper studies how natural language critiques can enhance verbalized confidence, addressing: (1) What to critique: uncertainty (question-focused) or confidence (answer-specific)? Analysis shows confidence suits multiple-choice tasks, while uncertainty excels in open-ended scenarios. (2) How to critique: self-critique or critique calibration training? We propose Self-Critique, enabling LLMs to critique and optimize their confidence beyond mere accuracy, and CritiCal, a novel Critique Calibration training method that leverages natural language critiques to improve confidence calibration, moving beyond direct numerical optimization. Experiments show that CritiCal significantly outperforms Self-Critique and other competitive baselines, even surpassing its teacher model, GPT-4o, in complex reasoning tasks. CritiCal also shows robust generalization in out-of-distribution settings, advancing LLM's reliability.

---

### Local Performance vs. Out-of-Distribution Generalization: An Empirical Analysis of Personalized Federated Learning in Heterogeneous Data Environments

Authors: Mortesa Hussaini, Jan Theiß, Anthony Stein
Published: 2025-10-28
Categories: cs.LG, cs.AI, cs.CV, cs.DC, cs.MA
arXiv: https://arxiv.org/abs/2510.24503v1

In the context of Federated Learning with heterogeneous data environments, local models tend to converge to their own local model optima during local training steps, deviating from the overall data distributions. Aggregation of these local updates, e.g., with FedAvg, often does not align with the global model optimum (client drift), resulting in an update that is suboptimal for most clients. Personalized Federated Learning approaches address this challenge by exclusively focusing on the average local performances of clients' models on their own data distribution. Generalization to out-of-distribution samples, which is a substantial benefit of FedAvg and represents a significant component of robustness, appears to be inadequately incorporated into the assessment and evaluation processes. This study involves a thorough evaluation of Federated Learning approaches, encompassing both their local performance and their generalization capabilities. Therefore, we examine different stages within a single communication round to enable a more nuanced understanding of the considered metrics. Furthermore, we propose and incorporate a modified approach of FedAvg, designated as Federated Learning with Individualized Updates (FLIU), extending the algorithm by a straightforward individualization step with an adaptive personalization factor. We evaluate and compare the approaches empirically using MNIST and CIFAR-10 under various distributional conditions, including benchmark IID and pathological non-IID, as well as additional novel test environments with Dirichlet distribution specifically developed to stress the algorithms on complex data heterogeneity.

---

### MIMIC-Sepsis: A Curated Benchmark for Modeling and Learning from Sepsis Trajectories in the ICU

Authors: Yong Huang, Zhongqi Yang, Amir Rahmani
Published: 2025-10-28
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.24500v1

Sepsis is a leading cause of mortality in intensive care units (ICUs), yet existing research often relies on outdated datasets, non-reproducible preprocessing pipelines, and limited coverage of clinical interventions. We introduce MIMIC-Sepsis, a curated cohort and benchmark framework derived from the MIMIC-IV database, designed to support reproducible modeling of sepsis trajectories. Our cohort includes 35,239 ICU patients with time-aligned clinical variables and standardized treatment data, including vasopressors, fluids, mechanical ventilation and antibiotics. We describe a transparent preprocessing pipeline-based on Sepsis-3 criteria, structured imputation strategies, and treatment inclusion-and release it alongside benchmark tasks focused on early mortality prediction, length-of-stay estimation, and shock onset classification. Empirical results demonstrate that incorporating treatment variables substantially improves model performance, particularly for Transformer-based architectures. MIMIC-Sepsis serves as a robust platform for evaluating predictive and sequential models in critical care research.

---

### Design and Optimization of Cloud Native Homomorphic Encryption Workflows for Privacy-Preserving ML Inference

Authors: Tejaswini Bollikonda
Published: 2025-10-28
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2510.24498v1

As machine learning (ML) models become increasingly deployed through cloud infrastructures, the confidentiality of user data during inference poses a significant security challenge. Homomorphic Encryption (HE) has emerged as a compelling cryptographic technique that enables computation on encrypted data, allowing predictions to be generated without decrypting sensitive inputs. However, the integration of HE within large scale cloud native pipelines remains constrained by high computational overhead, orchestration complexity, and model compatibility issues. This paper presents a systematic framework for the design and optimization of cloud native homomorphic encryption workflows that support privacy-preserving ML inference. The proposed architecture integrates containerized HE modules with Kubernetes-based orchestration, enabling elastic scaling and parallel encrypted computation across distributed environments. Furthermore, optimization strategies including ciphertext packing, polynomial modulus adjustment, and operator fusion are employed to minimize latency and resource consumption while preserving cryptographic integrity. Experimental results demonstrate that the proposed system achieves up to 3.2times inference acceleration and 40% reduction in memory utilization compared to conventional HE pipelines. These findings illustrate a practical pathway for deploying secure ML-as-a-Service (MLaaS) systems that guarantee data confidentiality under zero-trust cloud conditions.

---

### Online neural fusion of distortionless differential beamformers for robust speech enhancement

Authors: Yuanhang Qian, Kunlong Zhao, Jilu Jin, Xueqin Luo, Gongping Huang, Jingdong Chen, Jacob Benesty
Published: 2025-10-28
Categories: cs.SD, cs.AI, eess.AS
arXiv: https://arxiv.org/abs/2510.24497v1

Fixed beamforming is widely used in practice since it does not depend on the estimation of noise statistics and provides relatively stable performance. However, a single beamformer cannot adapt to varying acoustic conditions, which limits its interference suppression capability. To address this, adaptive convex combination (ACC) algorithms have been introduced, where the outputs of multiple fixed beamformers are linearly combined to improve robustness. Nevertheless, ACC often fails in highly non-stationary scenarios, such as rapidly moving interference, since its adaptive updates cannot reliably track rapid changes. To overcome this limitation, we propose a frame-online neural fusion framework for multiple distortionless differential beamformers, which estimates the combination weights through a neural network. Compared with conventional ACC, the proposed method adapts more effectively to dynamic acoustic environments, achieving stronger interference suppression while maintaining the distortionless constraint.

---

### Diffusion Models for Wireless Transceivers: From Pilot-Efficient Channel Estimation to AI-Native 6G Receivers

Authors: Yuzhi Yang, Sen Yan, Weijie Zhou, Brahim Mefgouda, Ridong Li, Zhaoyang Zhang, Mérouane Debbah
Published: 2025-10-28
Categories: eess.SP, cs.AI
arXiv: https://arxiv.org/abs/2510.24495v1

With the development of artificial intelligence (AI) techniques, implementing AI-based techniques to improve wireless transceivers becomes an emerging research topic. Within this context, AI-based channel characterization and estimation become the focus since these methods have not been solved by traditional methods very well and have become the bottleneck of transceiver efficiency in large-scale orthogonal frequency division multiplexing (OFDM) systems. Specifically, by formulating channel estimation as a generative AI problem, generative AI methods such as diffusion models (DMs) can efficiently deal with rough initial estimations and have great potential to cooperate with traditional signal processing methods. This paper focuses on the transceiver design of OFDM systems based on DMs, provides an illustration of the potential of DMs in wireless transceivers, and points out the related research directions brought by DMs. We also provide a proof-of-concept case study of further adapting DMs for better wireless receiver performance.

---

### A word association network methodology for evaluating implicit biases in LLMs compared to humans

Authors: Katherine Abramski, Giulio Rossetti, Massimo Stella
Published: 2025-10-28
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.24488v1

As Large language models (LLMs) become increasingly integrated into our lives, their inherent social biases remain a pressing concern. Detecting and evaluating these biases can be challenging because they are often implicit rather than explicit in nature, so developing evaluation methods that assess the implicit knowledge representations of LLMs is essential. We present a novel word association network methodology for evaluating implicit biases in LLMs based on simulating semantic priming within LLM-generated word association networks. Our prompt-based approach taps into the implicit relational structures encoded in LLMs, providing both quantitative and qualitative assessments of bias. Unlike most prompt-based evaluation methods, our method enables direct comparisons between various LLMs and humans, providing a valuable point of reference and offering new insights into the alignment of LLMs with human cognition. To demonstrate the utility of our methodology, we apply it to both humans and several widely used LLMs to investigate social biases related to gender, religion, ethnicity, sexual orientation, and political party. Our results reveal both convergences and divergences between LLM and human biases, providing new perspectives on the potential risks of using LLMs. Our methodology contributes to a systematic, scalable, and generalizable framework for evaluating and comparing biases across multiple LLMs and humans, advancing the goal of transparent and socially responsible language technologies.

---

### Fast and accurate neural reflectance transformation imaging through knowledge distillation

Authors: Tinsae G. Dulecha, Leonardo Righetto, Ruggero Pintus, Enrico Gobbetti, Andrea Giachetti
Published: 2025-10-28
Categories: cs.CV, cs.GR
arXiv: https://arxiv.org/abs/2510.24486v1

Reflectance Transformation Imaging (RTI) is very popular for its ability to visually analyze surfaces by enhancing surface details through interactive relighting, starting from only a few tens of photographs taken with a fixed camera and variable illumination. Traditional methods like Polynomial Texture Maps (PTM) and Hemispherical Harmonics (HSH) are compact and fast, but struggle to accurately capture complex reflectance fields using few per-pixel coefficients and fixed bases, leading to artifacts, especially in highly reflective or shadowed areas. The NeuralRTI approach, which exploits a neural autoencoder to learn a compact function that better approximates the local reflectance as a function of light directions, has been shown to produce superior quality at comparable storage cost. However, as it performs interactive relighting with custom decoder networks with many parameters, the rendering step is computationally expensive and not feasible at full resolution for large images on limited hardware. Earlier attempts to reduce costs by directly training smaller networks have failed to produce valid results. For this reason, we propose to reduce its computational cost through a novel solution based on Knowledge Distillation (DisK-NeuralRTI). ...

---

### Sample-efficient and Scalable Exploration in Continuous-Time RL

Authors: Klemens Iten, Lenart Treven, Bhavya Sukhija, Florian Dörfler, Andreas Krause
Published: 2025-10-28
Categories: cs.LG, cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2510.24482v2

Reinforcement learning algorithms are typically designed for discrete-time dynamics, even though the underlying real-world control systems are often continuous in time. In this paper, we study the problem of continuous-time reinforcement learning, where the unknown system dynamics are represented using nonlinear ordinary differential equations (ODEs). We leverage probabilistic models, such as Gaussian processes and Bayesian neural networks, to learn an uncertainty-aware model of the underlying ODE. Our algorithm, COMBRL, greedily maximizes a weighted sum of the extrinsic reward and model epistemic uncertainty. This yields a scalable and sample-efficient approach to continuous-time model-based RL. We show that COMBRL achieves sublinear regret in the reward-driven setting, and in the unsupervised RL setting (i.e., without extrinsic rewards), we provide a sample complexity bound. In our experiments, we evaluate COMBRL in both standard and unsupervised RL settings and demonstrate that it scales better, is more sample-efficient than prior methods, and outperforms baselines across several deep RL tasks.

---

### Talk2Ref: A Dataset for Reference Prediction from Scientific Talks

Authors: Frederik Broy, Maike Züfle, Jan Niehues
Published: 2025-10-28
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.24478v1

Scientific talks are a growing medium for disseminating research, and automatically identifying relevant literature that grounds or enriches a talk would be highly valuable for researchers and students alike. We introduce Reference Prediction from Talks (RPT), a new task that maps long, and unstructured scientific presentations to relevant papers. To support research on RPT, we present Talk2Ref, the first large-scale dataset of its kind, containing 6,279 talks and 43,429 cited papers (26 per talk on average), where relevance is approximated by the papers cited in the talk's corresponding source publication. We establish strong baselines by evaluating state-of-the-art text embedding models in zero-shot retrieval scenarios, and propose a dual-encoder architecture trained on Talk2Ref. We further explore strategies for handling long transcripts, as well as training for domain adaptation. Our results show that fine-tuning on Talk2Ref significantly improves citation prediction performance, demonstrating both the challenges of the task and the effectiveness of our dataset for learning semantic representations from spoken scientific content. The dataset and trained models are released under an open license to foster future research on integrating spoken scientific communication into citation recommendation systems.

---

### Mitigating Hallucination in Large Language Models: A Capability-Oriented Survey on RAG, Reasoning, and Agentic Systems

Authors: Yihan Li, Xiyuan Fu, Ghanshyam Verma, Paul Buitelaar, Mingming Liu
Published: 2025-10-28
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.24476v2

Hallucination remains one of the key obstacles to the reliable deployment of large language models (LLMs). Although various mitigation approaches have been proposed, existing studies often analyze different technical paradigms independently, lacking a unified perspective to understand the underlying mechanisms of different approaches and their correspondence with different types of hallucinations. This survey adopts a capability enhancement perspective to systematically examine hallucination mitigation approaches, focusing on Retrieval-Augmented Generation (RAG), reasoning enhancement, and their integration within agentic systems. Based on their primary mitigation mechanisms, we categorize hallucinations into knowledge-based hallucinations and logic-based hallucinations, analyze how RAG and reasoning enhancement methods respectively improve knowledge acquisition and reasoning reliability, and further discuss the integration mechanisms of retrieval and reasoning capabilities in Agentic Systems for mitigating composite hallucinations. By considering the applicability, mitigation mechanisms, and limitations of different approaches, this survey establishes a unified analytical framework connecting hallucination types, key capability dimensions, and technical paradigms.

---

### Decoupled MeanFlow: Turning Flow Models into Flow Maps for Accelerated Sampling

Authors: Kyungmin Lee, Sihyun Yu, Jinwoo Shin
Published: 2025-10-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.24474v1

Denoising generative models, such as diffusion and flow-based models, produce high-quality samples but require many denoising steps due to discretization error. Flow maps, which estimate the average velocity between timesteps, mitigate this error and enable faster sampling. However, their training typically demands architectural changes that limit compatibility with pretrained flow models. We introduce Decoupled MeanFlow, a simple decoding strategy that converts flow models into flow map models without architectural modifications. Our method conditions the final blocks of diffusion transformers on the subsequent timestep, allowing pretrained flow models to be directly repurposed as flow maps. Combined with enhanced training techniques, this design enables high-quality generation in as few as 1 to 4 steps. Notably, we find that training flow models and subsequently converting them is more efficient and effective than training flow maps from scratch. On ImageNet 256x256 and 512x512, our models attain 1-step FID of 2.16 and 2.12, respectively, surpassing prior art by a large margin. Furthermore, we achieve FID of 1.51 and 1.68 when increasing the steps to 4, which nearly matches the performance of flow models while delivering over 100x faster inference.

---

### Methodology for Comparing Machine Learning Algorithms for Survival Analysis

Authors: Lucas Buk Cardoso, Simone Aldrey Angelo, Yasmin Pacheco Gil Bonilha, Fernando Maia, Adeylson Guimarães Ribeiro, Maria Paula Curado, Gisele Aparecida Fernandes, Vanderlei Cunha Parro, Flávio Almeida de Magalhães Cipparrone, Alexandre Dias Porto Chiavegatto Filho, Victor Wünsch Filho, Tatiana Natasha Toporcov
Published: 2025-10-28
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.24473v3

This study presents a comparative methodological analysis of six machine learning models for survival analysis (MLSA). Using data from nearly 45,000 colorectal cancer patients in the Hospital-Based Cancer Registries of São Paulo, we evaluated Random Survival Forest (RSF), Gradient Boosting for Survival Analysis (GBSA), Survival SVM (SSVM), XGBoost-Cox (XGB-Cox), XGBoost-AFT (XGB-AFT), and LightGBM (LGBM), capable of predicting survival considering censored data. Hyperparameter optimization was performed with different samplers, and model performance was assessed using the Concordance Index (C-Index), C-Index IPCW, time-dependent AUC, and Integrated Brier Score (IBS). Survival curves produced by the models were compared with predictions from classification algorithms, and predictor interpretation was conducted using SHAP and permutation importance. XGB-AFT achieved the best performance (C-Index = 0.7618; IPCW = 0.7532), followed by GBSA and RSF. The results highlight the potential and applicability of MLSA to improve survival prediction and support decision making.

---

### Iterative Critique-Refine Framework for Enhancing LLM Personalization

Authors: Durga Prasad Maram, Dhruvin Gandhi, Zonghai Yao, Gayathri Akkinapalli, Franck Dernoncourt, Yu Wang, Ryan A. Rossi, Nesreen K. Ahmed
Published: 2025-10-28
Categories: cs.CL, cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2510.24469v2

Personalized text generation requires models not only to produce coherent text but also to align with a target user's style, tone, and topical focus. Existing retrieval-augmented approaches such as LaMP and PGraphRAG enrich profiles with user and neighbor histories, but they stop at generation and often yield outputs that drift in tone, topic, or style. We present PerFine, a unified, training-free critique-refine framework that enhances personalization through iterative, profile-grounded feedback. In each iteration, an LLM generator produces a draft conditioned on the retrieved profile, and a critic LLM - also conditioned on the same profile - provides structured feedback on tone, vocabulary, sentence structure, and topicality. The generator then revises, while a novel knockout strategy retains the stronger draft across iterations. We further study additional inference-time strategies such as Best-of-N and Topic Extraction to balance quality and efficiency. Across Yelp, Goodreads, and Amazon datasets, PerFine consistently improves personalization over PGraphRAG, with G-Eval gains of +8.5-12%, steady improvements over 3-5 refinement iterations, and scalability with increasing critic size. These results highlight that post-hoc, profile-aware feedback offers a powerful paradigm for personalized LLM generation that is both training-free and model-agnostic.

---

### Non-Singularity of the Gradient Descent map for Neural Networks with Piecewise Analytic Activations

Authors: Alexandru Crăciun, Debarghya Ghoshdastidar
Published: 2025-10-28
Categories: math.OC, cs.LG
arXiv: https://arxiv.org/abs/2510.24466v1

The theory of training deep networks has become a central question of modern machine learning and has inspired many practical advancements. In particular, the gradient descent (GD) optimization algorithm has been extensively studied in recent years. A key assumption about GD has appeared in several recent works: the \emph{GD map is non-singular} -- it preserves sets of measure zero under preimages. Crucially, this assumption has been used to prove that GD avoids saddle points and maxima, and to establish the existence of a computable quantity that determines the convergence to global minima (both for GD and stochastic GD). However, the current literature either assumes the non-singularity of the GD map or imposes restrictive assumptions, such as Lipschitz smoothness of the loss (for example, Lipschitzness does not hold for deep ReLU networks with the cross-entropy loss) and restricts the analysis to GD with small step-sizes. In this paper, we investigate the neural network map as a function on the space of weights and biases. We also prove, for the first time, the non-singularity of the gradient descent (GD) map on the loss landscape of realistic neural network architectures (with fully connected, convolutional, or softmax attention layers) and piecewise analytic activations (which includes sigmoid, ReLU, leaky ReLU, etc.) for almost all step-sizes. Our work significantly extends the existing results on the convergence of GD and SGD by guaranteeing that they apply to practical neural network settings and has the potential to unlock further exploration of learning dynamics.

---

### Kineo: Calibration-Free Metric Motion Capture From Sparse RGB Cameras

Authors: Charles Javerliat, Pierre Raimbaud, Guillaume Lavoué
Published: 2025-10-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.24464v2

Markerless multiview motion capture is often constrained by the need for precise camera calibration, limiting accessibility for non-experts and in-the-wild captures. Existing calibration-free approaches mitigate this requirement but suffer from high computational cost and reduced reconstruction accuracy. We present Kineo, a fully automatic, calibration-free pipeline for markerless motion capture from videos captured by unsynchronized, uncalibrated, consumer-grade RGB cameras. Kineo leverages 2D keypoints from off-the-shelf detectors to simultaneously calibrate cameras, including Brown-Conrady distortion coefficients, and reconstruct 3D keypoints and dense scene point maps at metric scale. A confidence-driven spatio-temporal keypoint sampling strategy, combined with graph-based global optimization, ensures robust calibration at a fixed computational cost independent of sequence length. We further introduce a pairwise reprojection consensus score to quantify 3D reconstruction reliability for downstream tasks. Evaluations on EgoHumans and Human3.6M demonstrate substantial improvements over prior calibration-free methods. Compared to previous state-of-the-art approaches, Kineo reduces camera translation error by approximately 83-85%, camera angular error by 86-92%, and world mean-per-joint error (W-MPJPE) by 83-91%. Kineo is also efficient in real-world scenarios, processing multi-view sequences faster than their duration in specific configuration (e.g., 36min to process 1h20min of footage). The full pipeline and evaluation code are openly released to promote reproducibility and practical adoption at https://liris-xr.github.io/kineo/.

---

### Adaptive Surrogate Gradients for Sequential Reinforcement Learning in Spiking Neural Networks

Authors: Korneel Van den Berghe, Stein Stroobants, Vijay Janapa Reddi, G. C. H. E. de Croon
Published: 2025-10-28
Categories: cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2510.24461v1

Neuromorphic computing systems are set to revolutionize energy-constrained robotics by achieving orders-of-magnitude efficiency gains, while enabling native temporal processing. Spiking Neural Networks (SNNs) represent a promising algorithmic approach for these systems, yet their application to complex control tasks faces two critical challenges: (1) the non-differentiable nature of spiking neurons necessitates surrogate gradients with unclear optimization properties, and (2) the stateful dynamics of SNNs require training on sequences, which in reinforcement learning (RL) is hindered by limited sequence lengths during early training, preventing the network from bridging its warm-up period. We address these challenges by systematically analyzing surrogate gradient slope settings, showing that shallower slopes increase gradient magnitude in deeper layers but reduce alignment with true gradients. In supervised learning, we find no clear preference for fixed or scheduled slopes. The effect is much more pronounced in RL settings, where shallower slopes or scheduled slopes lead to a 2.1x improvement in both training and final deployed performance. Next, we propose a novel training approach that leverages a privileged guiding policy to bootstrap the learning process, while still exploiting online environment interactions with the spiking policy. Combining our method with an adaptive slope schedule for a real-world drone position control task, we achieve an average return of 400 points, substantially outperforming prior techniques, including Behavioral Cloning and TD3BC, which achieve at most --200 points under the same conditions. This work advances both the theoretical understanding of surrogate gradient learning in SNNs and practical training methodologies for neuromorphic controllers demonstrated in real-world robotic systems.

---

### Affordance Representation and Recognition for Autonomous Agents

Authors: Habtom Kahsay Gidey, Niklas Huber, Alexander Lenz, Alois Knoll
Published: 2025-10-28
Categories: cs.AI, cs.MA, cs.SE
arXiv: https://arxiv.org/abs/2510.24459v1

The autonomy of software agents is fundamentally dependent on their ability to construct an actionable internal world model from the structured data that defines their digital environment, such as the Document Object Model (DOM) of web pages and the semantic descriptions of web services. However, constructing this world model from raw structured data presents two critical challenges: the verbosity of raw HTML makes it computationally intractable for direct use by foundation models, while the static nature of hardcoded API integrations prevents agents from adapting to evolving services. This paper introduces a pattern language for world modeling from structured data, presenting two complementary architectural patterns. The DOM Transduction Pattern addresses the challenge of web page complexity by distilling} a verbose, raw DOM into a compact, task-relevant representation or world model optimized for an agent's reasoning core. Concurrently, the Hypermedia Affordances Recognition Pattern enables the agent to dynamically enrich its world model by parsing standardized semantic descriptions to discover and integrate the capabilities of unknown web services at runtime. Together, these patterns provide a robust framework for engineering agents that can efficiently construct and maintain an accurate world model, enabling scalable, adaptive, and interoperable automation across the web and its extended resources.

---