# Research Papers — 2025-10 · bundle page 133 of 217

> Full-text markdown of papers #6601–6650 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/133
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/132.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/134.md)

### Structure Over Signal: A Globalized Approach to Multi-relational GNNs for Stock Prediction

Authors: Amber Li, Aruzhan Abil, Juno Marques Oda
Published: 2025-10-12
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.10775v1

In financial markets, Graph Neural Networks have been successfully applied to modeling relational data, effectively capturing nonlinear inter-stock dependencies. Yet, existing models often fail to efficiently propagate messages during macroeconomic shocks. In this paper, we propose OmniGNN, an attention-based multi-relational dynamic GNN that integrates macroeconomic context via heterogeneous node and edge types for robust message passing. Central to OmniGNN is a sector node acting as a global intermediary, enabling rapid shock propagation across the graph without relying on long-range multi-hop diffusion. The model leverages Graph Attention Networks (GAT) to weigh neighbor contributions and employs Transformers to capture temporal dynamics across multiplex relations. Experiments show that OmniGNN outperforms existing stock prediction models on public datasets, particularly demonstrating strong robustness during the COVID-19 period.

---

### ParsVoice: A Large-Scale Multi-Speaker Persian Speech Corpus for Text-to-Speech Synthesis

Authors: Mohammad Javad Ranjbar Kalahroodi, Heshaam Faili, Azadeh Shakery
Published: 2025-10-12
Categories: cs.SD, cs.AI, cs.HC, cs.LG
arXiv: https://arxiv.org/abs/2510.10774v4

Persian remains substantially underrepresented in open speech-text resources, limiting progress in multi-speaker text-to-speech (TTS), speech-language modelling, and low-resource speech processing. We introduce ParsVoice, the largest publicly available Persian speech-text corpus tailored for training multi-speaker TTS systems, along with a scalable pipeline to construct high-quality speech-text data from long-form audiobook recordings. The pipeline combines a fine-tuned ParsBERT sentence-completion classifier, ASR-based boundary optimization, punctuation restoration, speaker identification, and a multi-dimensional quality assessment that covers both audio and Persian-specific text properties. The resulting release contains a 2,200-hour TTS-ready subset with 1.36 million aligned segments from 1,815 automatically inferred speaker IDs, making it more than 25 times larger than the largest previously available open Persian TTS dataset. To validate the corpus, we fine-tune XTTSv2, a zero-shot multilingual TTS model that operates directly on raw Persian text without phoneme representations. The resulting model achieves a naturalness MOS of 3.6/5 and a speaker-similarity MOS of 4.0/5. ParsVoice, its metadata, and the corpus-construction pipeline are publicly available on Hugging Face: https://huggingface.co/datasets/MohammadJRanjbar/ParsVoice and GitHub: https://github.com/MohammadJRanjbar/ParsVoice, supporting reproducible research on Persian speech synthesis and low-resource speech-language technologies.

---

### Understanding Sampler Stochasticity in Training Diffusion Models for RLHF

Authors: Jiayuan Sheng, Hanyang Zhao, Haoxian Chen, David D. Yao, Wenpin Tang
Published: 2025-10-12
Categories: cs.LG, cs.AI, math.OC
arXiv: https://arxiv.org/abs/2510.10767v2

Reinforcement Learning from Human Feedback (RLHF) is increasingly used to fine-tune diffusion models, but a key challenge arises from the mismatch between stochastic samplers used during training and deterministic samplers used during inference. In practice, models are fine-tuned using stochastic SDE samplers to encourage exploration, while inference typically relies on deterministic ODE samplers for efficiency and stability. This discrepancy induces a reward gap, raising concerns about whether high-quality outputs can be expected during inference. In this paper, we theoretically characterize this reward gap and provide non-vacuous bounds for general diffusion models, along with sharper convergence rates for Variance Exploding (VE) and Variance Preserving (VP) Gaussian models. Methodologically, we adopt the generalized denoising diffusion implicit models (gDDIM) framework to support arbitrarily high levels of stochasticity, preserving data marginals throughout. Empirically, our findings through large-scale experiments on text-to-image models using denoising diffusion policy optimization (DDPO) and mixed group relative policy optimization (MixGRPO) validate that reward gaps consistently narrow over training, and ODE sampling quality improves when models are updated using higher-stochasticity SDE training.

---

### GPS Spoofing Attack Detection in Autonomous Vehicles Using Adaptive DBSCAN

Authors: Ahmad Mohammadi, Reza Ahmari, Vahid Hemmati, Frederick Owusu-Ambrose, Mahmoud Nabil Mahmoud, Parham Kebria, Abdollah Homaifar, Mehrdad Saif
Published: 2025-10-12
Categories: cs.CR, cs.AI, eess.SY
arXiv: https://arxiv.org/abs/2510.10766v1

As autonomous vehicles become an essential component of modern transportation, they are increasingly vulnerable to threats such as GPS spoofing attacks. This study presents an adaptive detection approach utilizing a dynamically tuned Density Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm, designed to adjust the detection threshold (ε) in real-time. The threshold is updated based on the recursive mean and standard deviation of displacement errors between GPS and in-vehicle sensors data, but only at instances classified as non-anomalous. Furthermore, an initial threshold, determined from 120,000 clean data samples, ensures the capability to identify even subtle and gradual GPS spoofing attempts from the beginning. To assess the performance of the proposed method, five different subsets from the real-world Honda Research Institute Driving Dataset (HDD) are selected to simulate both large and small magnitude GPS spoofing attacks. The modified algorithm effectively identifies turn-by-turn, stop, overshoot, and multiple small biased spoofing attacks, achieving detection accuracies of 98.621%, 99.960.1%, 99.880.1%, and 98.380.1%, respectively. This work provides a substantial advancement in enhancing the security and safety of AVs against GPS spoofing threats.

---

### EGD-YOLO: A Lightweight Multimodal Framework for Robust Drone-Bird Discrimination via Ghost-Enhanced YOLOv8n and EMA Attention under Adverse Condition

Authors: Sudipto Sarkar, Mohammad Asif Hasan, Khondokar Ashik Shahriar, Fablia Labiba, Nahian Tasnim, Sheikh Anawarul Haq Fattah
Published: 2025-10-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.10765v1

Identifying drones and birds correctly is essential for keeping the skies safe and improving security systems. Using the VIP CUP 2025 dataset, which provides both RGB and infrared (IR) images, this study presents EGD-YOLOv8n, a new lightweight yet powerful model for object detection. The model improves how image features are captured and understood, making detection more accurate and efficient. It uses smart design changes and attention layers to focus on important details while reducing the amount of computation needed. A special detection head helps the model adapt to objects of different shapes and sizes. We trained three versions: one using RGB images, one using IR images, and one combining both. The combined model achieved the best accuracy and reliability while running fast enough for real-time use on common GPUs.

---

### Optimally Deep Networks -- Adapting Model Depth to Datasets for Superior Efficiency

Authors: Shaharyar Ahmed Khan Tareen, Filza Khan Tareen
Published: 2025-10-12
Categories: cs.LG, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2510.10764v4

Deep neural networks (DNNs) have provided brilliant performance across various tasks. However, this success often comes at the cost of unnecessarily large model sizes, high computational demands, and substantial memory footprints. Typically, powerful architectures are trained at full depths but not all datasets or tasks require such high model capacity. Training big and deep architectures on relatively low-complexity datasets frequently leads to wasted computation, unnecessary energy consumption, and excessive memory usage, which in turn makes deployment of models on resource-constrained devices impractical. To address this problem, we introduce the concept of Optimally Deep Networks (ODNs), which provides a balance between model depth and task complexity. Specifically, we propose a NAS like training strategy called progressive depth expansion, which begins by training neural networks at shallower depths and incrementally increases their depth as the earlier blocks converge, continuing this process until the target accuracy is reached. ODNs use only the optimal depth for the tasks at hand, removing redundant layers. This cuts down future training and inference costs, lowers the model memory footprint, enhances computational efficiency, and facilitates deployment on edge devices. Empirical results show that the optimal depths of ResNet-18 and ResNet-34 for MNIST and SVHN, achieve up to 98.64 % and 96.44 % reduction in memory footprint, while maintaining a competitive accuracy of 99.31 % and 96.08 %, respectively.

---

### Large Language Models for Full-Text Methods Assessment: A Case Study on Mediation Analysis

Authors: Wenqing Zhang, Trang Nguyen, Elizabeth A. Stuart, Yiqun T. Chen
Published: 2025-10-12
Categories: cs.CL, stat.AP
arXiv: https://arxiv.org/abs/2510.10762v1

Systematic reviews are crucial for synthesizing scientific evidence but remain labor-intensive, especially when extracting detailed methodological information. Large language models (LLMs) offer potential for automating methodological assessments, promising to transform evidence synthesis. Here, using causal mediation analysis as a representative methodological domain, we benchmarked state-of-the-art LLMs against expert human reviewers across 180 full-text scientific articles. Model performance closely correlated with human judgments (accuracy correlation 0.71; F1 correlation 0.97), achieving near-human accuracy on straightforward, explicitly stated methodological criteria. However, accuracy sharply declined on complex, inference-intensive assessments, lagging expert reviewers by up to 15%. Errors commonly resulted from superficial linguistic cues -- for instance, models frequently misinterpreted keywords like "longitudinal" or "sensitivity" as automatic evidence of rigorous methodological approache, leading to systematic misclassifications. Longer documents yielded lower model accuracy, whereas publication year showed no significant effect. Our findings highlight an important pattern for practitioners using LLMs for methods review and synthesis from full texts: current LLMs excel at identifying explicit methodological features but require human oversight for nuanced interpretations. Integrating automated information extraction with targeted expert review thus provides a promising approach to enhance efficiency and methodological rigor in evidence synthesis across diverse scientific fields.

---

### Restricted Receptive Fields for Face Verification

Authors: Kagan Ozturk, Aman Bhatta, Haiyu Wu, Patrick Flynn, Kevin W. Bowyer
Published: 2025-10-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.10753v2

Understanding how deep neural networks make decisions is crucial for analyzing their behavior and diagnosing failure cases. In computer vision, a common approach to improve interpretability is to assign importance to individual pixels using post-hoc methods. Although they are widely used to explain black-box models, their fidelity to the model's actual reasoning is uncertain due to the lack of reliable evaluation metrics. This limitation motivates an alternative approach, which is to design models whose decision processes are inherently interpretable. To this end, we propose a face similarity metric that breaks down global similarity into contributions from restricted receptive fields. Our method defines the similarity between two face images as the sum of patch-level similarity scores, providing a locally additive explanation without relying on post-hoc analysis. We show that the proposed approach achieves competitive verification performance even with patches as small as 28x28 within 112x112 face images, and surpasses state-of-the-art methods when using 56x56 patches.

---

### Uncovering Anomalous Events for Marine Environmental Monitoring via Visual Anomaly Detection

Authors: Laura Weihl, Stefan H. Bengtson, Nejc Novak, Malte Pedersen
Published: 2025-10-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.10750v2

Underwater video monitoring is a promising strategy for assessing marine biodiversity, but the vast volume of uneventful footage makes manual inspection highly impractical. In this work, we explore the use of visual anomaly detection (VAD) based on deep neural networks to automatically identify interesting or anomalous events. We introduce AURA, the first multi-annotator benchmark dataset for underwater VAD, and evaluate four VAD models across two marine scenes. We demonstrate the importance of robust frame selection strategies to extract meaningful video segments. Our comparison against multiple annotators reveals that VAD performance of current models varies dramatically and is highly sensitive to both the amount of training data and the variability in visual content that defines "normal" scenes. Our results highlight the value of soft and consensus labels and offer a practical approach for supporting scientific exploration and scalable biodiversity monitoring.

---

### How Patterns Dictate Learnability in Sequential Data

Authors: Mario Morawski, Anais Despres, Rémi Rehm
Published: 2025-10-12
Categories: stat.ML, cs.IT, cs.LG
arXiv: https://arxiv.org/abs/2510.10744v1

Sequential data - ranging from financial time series to natural language - has driven the growing adoption of autoregressive models. However, these algorithms rely on the presence of underlying patterns in the data, and their identification often depends heavily on human expertise. Misinterpreting these patterns can lead to model misspecification, resulting in increased generalization error and degraded performance. The recently proposed evolving pattern (EvoRate) metric addresses this by using the mutual information between the next data point and its past to guide regression order estimation and feature selection. Building on this idea, we introduce a general framework based on predictive information, defined as the mutual information between the past and the future, $I(X_{past}; X_{future})$. This quantity naturally defines an information-theoretic learning curve, which quantifies the amount of predictive information available as the observation window grows. Using this formalism, we show that the presence or absence of temporal patterns fundamentally constrains the learnability of sequential models: even an optimal predictor cannot outperform the intrinsic information limit imposed by the data. We validate our framework through experiments on synthetic data, demonstrating its ability to assess model adequacy, quantify the inherent complexity of a dataset, and reveal interpretable structure in sequential data.

---

### Seeing My Future: Predicting Situated Interaction Behavior in Virtual Reality

Authors: Yuan Xu, Zimu Zhang, Xiaoxuan Ma, Wentao Zhu, Yu Qiao, Yizhou Wang
Published: 2025-10-12
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.10742v1

Virtual and augmented reality systems increasingly demand intelligent adaptation to user behaviors for enhanced interaction experiences. Achieving this requires accurately understanding human intentions and predicting future situated behaviors - such as gaze direction and object interactions - which is vital for creating responsive VR/AR environments and applications like personalized assistants. However, accurate behavioral prediction demands modeling the underlying cognitive processes that drive human-environment interactions. In this work, we introduce a hierarchical, intention-aware framework that models human intentions and predicts detailed situated behaviors by leveraging cognitive mechanisms. Given historical human dynamics and the observation of scene contexts, our framework first identifies potential interaction targets and forecasts fine-grained future behaviors. We propose a dynamic Graph Convolutional Network (GCN) to effectively capture human-environment relationships. Extensive experiments on challenging real-world benchmarks and live VR environment demonstrate the effectiveness of our approach, achieving superior performance across all metrics and enabling practical applications for proactive VR systems that anticipate user behaviors and adapt virtual environments accordingly.

---

### A Stochastic Differential Equation Framework for Multi-Objective LLM Interactions: Dynamical Systems Analysis with Code Generation Applications

Authors: Shivani Shukla, Himanshu Joshi
Published: 2025-10-12
Categories: cs.LG, cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2510.10739v1

We introduce a general stochastic differential equation framework for modelling multiobjective optimization dynamics in iterative Large Language Model (LLM) interactions. Our framework captures the inherent stochasticity of LLM responses through explicit diffusion terms and reveals systematic interference patterns between competing objectives via an interference matrix formulation. We validate our theoretical framework using iterative code generation as a proof-of-concept application, analyzing 400 sessions across security, efficiency, and functionality objectives. Our results demonstrate strategy-dependent convergence behaviors with rates ranging from 0.33 to 1.29, and predictive accuracy achieving R2 = 0.74 for balanced approaches. This work proposes the feasibility of dynamical systems analysis for multi-objective LLM interactions, with code generation serving as an initial validation domain.

---

### Proficiency-Aware Adaptation and Data Augmentation for Robust L2 ASR

Authors: Ling Sun, Charlotte Zhu, Shuju Shi
Published: 2025-10-12
Categories: cs.SD, cs.AI
arXiv: https://arxiv.org/abs/2510.10738v1

General-purpose ASR underperforms for atypical speakers, such as L2 learners, reinforcing bias and limiting use in education and accessibility. Using the CEFR-graded Speak and Improve corpus, we show that naive fine-tuning of Whisper reduces average WER but simultaneously widens disparities and disproportionately harms lower-level learners. To address this, we propose two strategies: (i) proficiency-aware multitask learning, jointly optimizing ASR with proficiency classification, and (ii) targeted augmentation, applying spectrogram masking to low-proficiency speech to counter imbalance. These approaches reduce WER by up to 29.4 percent (relative) and insertion/deletion errors by as much as 58.6 percent (relative). Crucially, despite the severe imbalance of the dataset reflecting real-world distributions, both strategies consistently narrow proficiency gaps, advancing equitable ASR for L2 learners.

---

### Controllable Generative Trajectory Prediction via Weak Preference Alignment

Authors: Yongxi Cao, Julian F. Schumann, Jens Kober, Joni Pajarinen, Arkady Zgonnikov
Published: 2025-10-12
Categories: cs.RO, cs.LG
arXiv: https://arxiv.org/abs/2510.10731v1

Deep generative models such as conditional variational autoencoders (CVAEs) have shown great promise for predicting trajectories of surrounding agents in autonomous vehicle planning. State-of-the-art models have achieved remarkable accuracy in such prediction tasks. Besides accuracy, diversity is also crucial for safe planning because human behaviors are inherently uncertain and multimodal. However, existing methods generally lack a scheme to generate controllably diverse trajectories, which is arguably more useful than randomly diversified trajectories, to the end of safe planning. To address this, we propose PrefCVAE, an augmented CVAE framework that uses weakly labeled preference pairs to imbue latent variables with semantic attributes. Using average velocity as an example attribute, we demonstrate that PrefCVAE enables controllable, semantically meaningful predictions without degrading baseline accuracy. Our results show the effectiveness of preference supervision as a cost-effective way to enhance sampling-based generative models.

---

### Provable Anytime Ensemble Sampling Algorithms in Nonlinear Contextual Bandits

Authors: Jiazheng Sun, Weixin Wang, Pan Xu
Published: 2025-10-12
Categories: cs.LG, cs.AI, stat.ML
arXiv: https://arxiv.org/abs/2510.10730v3

We provide a unified algorithmic framework for ensemble sampling in nonlinear contextual bandits and develop corresponding regret bounds for two most common nonlinear contextual bandit settings: Generalized Linear Model Ensemble Sampling (GLM-ES) for generalized linear contextual bandits and Neural Ensemble Sampling (Neural-ES) for neural contextual bandits. Both methods maintain multiple estimators for the reward model parameters via maximum likelihood estimation on randomly perturbed data. We prove high-probability frequentist regret bounds of $\widetilde{\mathcal{O}}(d^{3/2} \sqrt{T} + d^{4})$ for GLM-ES and $\widetilde{\mathcal{O}}(\widetilde{d}^{3/2} \sqrt{T})$ for Neural-ES, where $d$ is the dimension of feature vectors, $\widetilde{d}$ is the effective dimension of a neural tangent kernel (NTK) matrix and $T$ is the number of rounds. The regret bound of GLM-ES matches the state-of-the-art result of randomized exploration algorithms in generalized linear bandit setting. In the theoretical analysis, we introduce techniques that address challenges specific to nonlinear models. Practically, we remove fixed-time horizon assumption by developing anytime versions of our algorithms, suitable when $T$ is unknown. Finally, we empirically evaluate GLM-ES, Neural-ES and their anytime variants, demonstrating strong performance. Overall, our results establish ensemble sampling as a provable and practical randomized exploration approach for nonlinear contextual bandits.

---

### Sarcasm Detection Using Deep Convolutional Neural Networks: A Modular Deep Learning Framework

Authors: Manas Zambre, Sarika Bobade
Published: 2025-10-12
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.10729v1

Sarcasm is a nuanced and often misinterpreted form of communication, especially in text, where tone and body language are absent. This paper proposes a modular deep learning framework for sarcasm detection, leveraging Deep Convolutional Neural Networks (DCNNs) and contextual models such as BERT to analyze linguistic, emotional, and contextual cues. The system integrates sentiment analysis, contextual embeddings, linguistic feature extraction, and emotion detection through a multi-layer architecture. While the model is in the conceptual stage, it demonstrates feasibility for real-world applications such as chatbots and social media analysis.

---

### Rough Path Signatures: Learning Neural RDEs for Portfolio Optimization

Authors: Ali Atiah Alzahrani
Published: 2025-10-12
Categories: q-fin.MF, cs.LG
arXiv: https://arxiv.org/abs/2510.10728v3

We tackle high-dimensional, path-dependent valuation and control and introduce a deep BSDE/2BSDE solver that couples truncated log-signatures with a neural rough differential equation (RDE) backbone. The architecture aligns stochastic analysis with sequence-to-path learning: a CVaR-tilted terminal objective targets left-tail risk, while an optional second-order (2BSDE) head supplies curvature estimates for risk-sensitive control. Under matched compute and parameter budgets, the method improves accuracy, tail fidelity, and training stability across Asian and barrier option pricing and portfolio control: at d=200 it achieves CVaR(0.99)=9.80% versus 12.00-13.10% for strong baselines, attains the lowest HJB residual (0.011), and yields the lowest RMSEs for Z and Gamma. Ablations over truncation depth, local windows, and tilt parameters confirm complementary gains from the sequence-to-path representation and the 2BSDE head. Taken together, the results highlight a bidirectional dialogue between stochastic analysis and modern deep learning: stochastic tools inform representations and objectives, while sequence-to-path models expand the class of solvable financial models at scale.

---

### WorldMirror: Universal 3D World Reconstruction with Any-Prior Prompting

Authors: Yifan Liu, Zhiyuan Min, Zhenwei Wang, Junta Wu, Tengfei Wang, Yixuan Yuan, Yawei Luo, Chunchao Guo
Published: 2025-10-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.10726v2

We present WorldMirror, a unified feed-forward model for comprehensive 3D geometric prediction tasks. Unlike existing methods constrained to image-only inputs or customized for a specific task, our framework flexibly integrates diverse geometric priors, including camera poses, intrinsics, and depth maps, while simultaneously generating multiple 3D representations: dense point clouds, multi-view depth maps, camera parameters, surface normals, and 3D Gaussians. Remarkably, prior injection yields universal gains across all tasks, suggesting that input flexibility and multi-task prediction are mutually reinforcing. WorldMirror achieves state-of-the-art performance across diverse benchmarks from camera, point map, depth, and surface normal estimation to novel view synthesis, while maintaining the efficiency of feed-forward inference.

---

### SS-DPPN: A self-supervised dual-path foundation model for the generalizable cardiac audio representation

Authors: Ummy Maria Muna, Md Mehedi Hasan Shawon, Md Jobayer, Sumaiya Akter, Md Rakibul Hasan, Md. Golam Rabiul Alam
Published: 2025-10-12
Categories: cs.SD, cs.AI
arXiv: https://arxiv.org/abs/2510.10719v1

The automated analysis of phonocardiograms is vital for the early diagnosis of cardiovascular disease, yet supervised deep learning is often constrained by the scarcity of expert-annotated data. In this paper, we propose the Self-Supervised Dual-Path Prototypical Network (SS-DPPN), a foundation model for cardiac audio representation and classification from unlabeled data. The framework introduces a dual-path contrastive learning based architecture that simultaneously processes 1D waveforms and 2D spectrograms using a novel hybrid loss. For the downstream task, a metric-learning approach using a Prototypical Network was used that enhances sensitivity and produces well-calibrated and trustworthy predictions. SS-DPPN achieves state-of-the-art performance on four cardiac audio benchmarks. The framework demonstrates exceptional data efficiency with a fully supervised model on three-fold reduction in labeled data. Finally, the learned representations generalize successfully across lung sound classification and heart rate estimation. Our experiments and findings validate SS-DPPN as a robust, reliable, and scalable foundation model for physiological signals.

---

### HYPERDOA: Robust and Efficient DoA Estimation using Hyperdimensional Computing

Authors: Rajat Bhattacharjya, Woohyeok Park, Arnab Sarkar, Hyunwoo Oh, Mohsen Imani, Nikil Dutt
Published: 2025-10-12
Categories: eess.SP, cs.AI, cs.AR, cs.SC
arXiv: https://arxiv.org/abs/2510.10718v2

Direction of Arrival (DoA) estimation techniques face a critical trade-off, as classical methods often lack accuracy in challenging, low signal-to-noise ratio (SNR) conditions, while modern deep learning approaches are too energy-intensive and opaque for resource-constrained, safety-critical systems. We introduce HYPERDOA, a novel estimator leveraging Hyperdimensional Computing (HDC). The framework introduces two distinct feature extraction strategies -- Mean Spatial-Lag Autocorrelation and Spatial Smoothing -- for its HDC pipeline, and then reframes DoA estimation as a pattern recognition problem. This approach leverages HDC's inherent robustness to noise and its transparent algebraic operations to bypass the expensive matrix decompositions and "black-box" nature of classical and deep learning methods, respectively. Our evaluation demonstrates that HYPERDOA achieves ~35.39% higher accuracy than state-of-the-art methods in low-SNR, coherent-source scenarios. Crucially, it also consumes ~93% less energy than competing neural baselines on an embedded NVIDIA Jetson Xavier NX platform. This dual advantage in accuracy and efficiency establishes HYPERDOA as a robust and viable solution for mission-critical applications on edge devices.

---

### VLM-Guided Adaptive Negative Prompting for Creative Generation

Authors: Shelly Golan, Yotam Nitzan, Zongze Wu, Or Patashnik
Published: 2025-10-12
Categories: cs.GR, cs.CV
arXiv: https://arxiv.org/abs/2510.10715v1

Creative generation is the synthesis of new, surprising, and valuable samples that reflect user intent yet cannot be envisioned in advance. This task aims to extend human imagination, enabling the discovery of visual concepts that exist in the unexplored spaces between familiar domains. While text-to-image diffusion models excel at rendering photorealistic scenes that faithfully match user prompts, they still struggle to generate genuinely novel content. Existing approaches to enhance generative creativity either rely on interpolation of image features, which restricts exploration to predefined categories, or require time-intensive procedures such as embedding optimization or model fine-tuning. We propose VLM-Guided Adaptive Negative-Prompting, a training-free, inference-time method that promotes creative image generation while preserving the validity of the generated object. Our approach utilizes a vision-language model (VLM) that analyzes intermediate outputs of the generation process and adaptively steers it away from conventional visual concepts, encouraging the emergence of novel and surprising outputs. We evaluate creativity through both novelty and validity, using statistical metrics in the CLIP embedding space. Through extensive experiments, we show consistent gains in creative novelty with negligible computational overhead. Moreover, unlike existing methods that primarily generate single objects, our approach extends to complex scenarios, such as generating coherent sets of creative objects and preserving creativity within elaborate compositional prompts. Our method integrates seamlessly into existing diffusion pipelines, offering a practical route to producing creative outputs that venture beyond the constraints of textual descriptions.

---

### Deep Learning in Astrophysics

Authors: Yuan-Sen Ting
Published: 2025-10-12
Categories: astro-ph.IM, astro-ph.CO, astro-ph.EP, astro-ph.GA, astro-ph.HE, cs.AI
arXiv: https://arxiv.org/abs/2510.10713v2

Deep learning has generated diverse perspectives in astronomy, with ongoing discussions between proponents and skeptics motivating this review. We examine how neural networks complement classical statistics, extending our data analytical toolkit for modern surveys. Astronomy offers unique opportunities through encoding physical symmetries, conservation laws, and differential equations directly into architectures, creating models that generalize beyond training data. Yet challenges persist as unlabeled observations number in billions while confirmed examples with known properties remain scarce and expensive. This review demonstrates how deep learning incorporates domain knowledge through architectural design, with built-in assumptions guiding models toward physically meaningful solutions. We evaluate where these methods offer genuine advances versus claims requiring careful scrutiny. - Neural architectures overcome bias-variance trade-offs among scalability, expressivity, and data efficiency by encoding physical symmetries and conservation laws into network structure, enabling learning from limited labeled data. - Simulation-based inference and anomaly detection extract information from complex, non-Gaussian distributions where analytical likelihoods fail, enabling field-level cosmological analysis and systematic discovery of rare phenomena. - Multiscale neural modeling bridges resolution gaps in astronomical simulations, learning effective subgrid physics from expensive high-fidelity runs to enhance large-volume calculations where direct computation remains prohibitive. - Emerging paradigms-reinforcement learning for telescope operations, foundation models learning from minimal examples, and large language model agents for research automation-show promise though are still developing in astronomical applications.

---

### Missing Data Multiple Imputation for Tabular Q-Learning in Online RL

Authors: Kyla Chasalow, Skyler Wu, Susan Murphy
Published: 2025-10-12
Categories: stat.ML, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.10709v1

Missing data in online reinforcement learning (RL) poses challenges compared to missing data in standard tabular data or in offline policy learning. The need to impute and act at each time step means that imputation cannot be put off until enough data exist to produce stable imputation models. It also means future data collection and learning depend on previous imputations. This paper proposes fully online imputation ensembles. We find that maintaining multiple imputation pathways may help balance the need to capture uncertainty under missingness and the need for efficiency in online settings. We consider multiple approaches for incorporating these pathways into learning and action selection. Using a Grid World experiment with various types of missingness, we provide preliminary evidence that multiple imputation pathways may be a useful framework for constructing simple and efficient online missing data RL methods.

---

### Designing ReLU Generative Networks to Enumerate Trees with a Given Tree Edit Distance

Authors: Mamoona Ghafoor, Tatsuya Akutsu
Published: 2025-10-12
Categories: cs.LG, cs.DM
arXiv: https://arxiv.org/abs/2510.10706v3

The generation of trees with a specified tree edit distance has significant applications across various fields, including computational biology, structured data analysis, and image processing. Recently, generative networks have been increasingly employed to synthesize new data that closely resembles the original datasets. However, the appropriate size and depth of generative networks required to generate data with a specified tree edit distance remain unclear. In this paper, we theoretically establish the existence and construction of generative networks capable of producing trees similar to a given tree with respect to the tree edit distance. Specifically, for a given rooted, ordered, and vertex-labeled tree T of size n + 1 with labels from an alphabet Σ, and a non-negative integer d, we prove that all rooted, ordered, and vertex-labeled trees over Σwith tree edit distance at most d from T can be generated using a ReLU-based generative network with size O(n^3 ) and constant depth. The proposed networks were implemented and evaluated for generating trees with up to 21 nodes. Due to their deterministic architecture, the networks successfully generated all valid trees within the specified tree edit distance. In contrast, state-of-the-art graph generative models GraphRNN and GraphGDP, which rely on non-deterministic mechanisms, produced significantly fewer valid trees, achieving validation rates of only up to 35% and 48%, respectively. These findings provide a theoretical foundation towards construction of compact generative models and open new directions for exact and valid tree-structured data generation. An implementation of the proposed networks is available at https://github.com/MGANN-KU/TreeGen_ReLUNetworks.

---

### Learning-Augmented Streaming Algorithms for Correlation Clustering

Authors: Yinhao Dong, Shan Jiang, Shi Li, Pan Peng
Published: 2025-10-12
Categories: cs.DS, cs.LG
arXiv: https://arxiv.org/abs/2510.10705v1

We study streaming algorithms for Correlation Clustering. Given a graph as an arbitrary-order stream of edges, with each edge labeled as positive or negative, the goal is to partition the vertices into disjoint clusters, such that the number of disagreements is minimized. In this paper, we give the first learning-augmented streaming algorithms for the problem on both complete and general graphs, improving the best-known space-approximation tradeoffs. Based on the works of Cambus et al. (SODA'24) and Ahn et al. (ICML'15), our algorithms use the predictions of pairwise distances between vertices provided by a predictor. For complete graphs, our algorithm achieves a better-than-$3$ approximation under good prediction quality, while using $\tilde{O}(n)$ total space. For general graphs, our algorithm achieves an $O(\log |E^-|)$ approximation under good prediction quality using $\tilde{O}(n)$ total space, improving the best-known non-learning algorithm in terms of space efficiency. Experimental results on synthetic and real-world datasets demonstrate the superiority of our proposed algorithms over their non-learning counterparts.

---

### Adaptive Selection of Symbolic Languages for Improving LLM Logical Reasoning

Authors: Xiangyu Wang, Haocheng Yang, Fengxiang Cheng, Fenrong Liu
Published: 2025-10-12
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.10703v1

Large Language Models (LLMs) still struggle with complex logical reasoning. While previous works achieve remarkable improvements, their performance is highly dependent on the correctness of translating natural language (NL) problems into a symbolic language (SL). Though numerous works focusing on improving this translation accuracy, they only consider the similarity between the meaning of SL and NL, overlooking another crucial influencing factor, the selection of the target SL type itself. For example, first-order logic language specializes in logical reasoning with categorical syllogisms and complex quantifiers, while Boolean satisfiability formalism excels at representing constraint satisfaction like partial problems. To our knowledge, this is the first paper to claim and verify that different NL logical reasoning problem corresponds to different optimal SL formalization for translation. Based on this, we propose a methods to improve the logical reasoning performance of LLMs by adaptively selecting the most suitable SL for each problem prior to translation. Specifically, we leverage LLMs to select the target SL among first-order logic, logic programming and Boolean satisfiability and then translate the problem in NL to target SL expressions as well as employ the corresponding logical solver to derive the final answer. Experimental results on benchmarks show that our adaptive selection method significantly outperforms translating all into single SL and randomly selecting the SL. On a mixed dataset of these benchmarks, our approach achieves 96% accuracy, which improving performance by 25% compared to the second highest accuracy from the first-order logic translation.

---

### Attention-Enhanced LSTM Modeling for Improved Temperature and Rainfall Forecasting in Bangladesh

Authors: Usman Gani Joy, Shahadat kabir, Tasnim Niger
Published: 2025-10-12
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.10702v1

Accurate climate forecasting is vital for Bangladesh, a region highly susceptible to climate change impacts on temperature and rainfall. Existing models often struggle to capture long-range dependencies and complex temporal patterns in climate data. This study introduces an advanced Long Short-Term Memory (LSTM) model integrated with an attention mechanism to enhance the prediction of temperature and rainfall dynamics. Utilizing comprehensive datasets from 1901-2023, sourced from NASA's POWER Project for temperature and the Humanitarian Data Exchange for rainfall, the model effectively captures seasonal and long-term trends. It outperforms baseline models, including XGBoost, Simple LSTM, and GRU, achieving a test MSE of 0.2411 (normalized units), MAE of 0.3860 degrees C, R^2 of 0.9834, and NRMSE of 0.0370 for temperature, and MSE of 1283.67 mm^2, MAE of 22.91 mm, R^2 of 0.9639, and NRMSE of 0.0354 for rainfall on monthly forecasts. The model demonstrates improved robustness with only a 20 percent increase in MSE under simulated climate trends (compared to an approximately 2.2-fold increase in baseline models without trend features) and a 50 percent degradation under regional variations (compared to an approximately 4.8-fold increase in baseline models without enhancements). These results highlight the model's ability to improve forecasting precision and offer potential insights into the physical processes governing climate variability in Bangladesh, supporting applications in climate-sensitive sectors.

---

### Extended Triangular Method: A Generalized Algorithm for Contradiction Separation Based Automated Deduction

Authors: Yang Xu, Shuwei Chen, Jun Liu, Feng Cao, Xingxing He
Published: 2025-10-12
Categories: cs.AI, cs.LO
arXiv: https://arxiv.org/abs/2510.10701v1

Automated deduction lies at the core of Artificial Intelligence (AI), underpinning theorem proving, formal verification, and logical reasoning. Despite decades of progress, reconciling deductive completeness with computational efficiency remains an enduring challenge. Traditional reasoning calculi, grounded in binary resolution, restrict inference to pairwise clause interactions and thereby limit deductive synergy among multiple clauses. The Contradiction Separation Extension (CSE) framework, introduced in 2018, proposed a dynamic multi-clause reasoning theory that redefined logical inference as a process of contradiction separation rather than sequential resolution. While that work established the theoretical foundation, its algorithmic realization remained unformalized and unpublished. This work presents the Extended Triangular Method (ETM), a generalized contradiction-construction algorithm that formalizes and extends the internal mechanisms of contradiction separation. The ETM unifies multiple contradiction-building strategies, including the earlier Standard Extension method, within a triangular geometric framework that supports flexible clause interaction and dynamic synergy. ETM serves as the algorithmic core of several high-performance theorem provers, CSE, CSE-E, CSI-E, and CSI-Enig, whose competitive results in standard first-order benchmarks (TPTP problem sets and CASC 2018-2015) empirically validate the effectiveness and generality of the proposed approach. By bridging theoretical abstraction and operational implementation, ETM advances the contradiction separation paradigm into a generalized, scalable, and practically competitive model for automated reasoning, offering new directions for future research in logical inference and theorem proving.

---

### Mean-square and sublinear convergence of a stochastic proximal point algorithm in metric spaces of nonpositive curvature

Authors: Nicholas Pischke
Published: 2025-10-12
Categories: math.OC, cs.LG
arXiv: https://arxiv.org/abs/2510.10697v2

We define a stochastic variant of the proximal point algorithm in the general setting of nonlinear Hadamard spaces for approximating zeros of the mean of a stochastically perturbed monotone vector field. Generalizing previous work by P. Bianchi, we prove the convergence of this method under a suitable strong monotonicity assumption in (separable) Hilbert-Hadamard spaces, that is assuming that all tangent spaces isometrically embed into Hilbert spaces (covering, but not being limited to, the setting of Hadamard manifolds). Moreover, our convergence proof is fully effective and allows for the construction of explicit rates of convergence for the iteration towards the (unique) solution both in mean and almost surely. These rates are moreover highly uniform, being independent of most data surrounding the iteration, space or distribution. In that generality, these rates are novel already in the context of Hilbert spaces. Sublinear nonasymptotic guarantees under additional second-moment conditions on the Yosida approximates and special cases of stochastic convex minimization are discussed.

---

### Stock Prediction via a Dual Relation Fusion Network incorporating Static and Dynamic Relations

Authors: Long Chen, Huixin Bai, Mingxin Wang, Xiaohua Huang, Ying Liu, Jie Zhao, Ziyu Guan
Published: 2025-10-12
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.10695v1

Accurate modeling of inter-stock relationships is critical for stock price forecasting. However, existing methods predominantly focus on single-state relationships, neglecting the essential complementarity between dynamic and static inter-stock relations. To solve this problem, we propose a Dual Relation Fusion Network (DRFN) to capture the long-term relative stability of stock relation structures while retaining the flexibility to respond to sudden market shifts. Our approach features a novel relative static relation component that models time-varying long-term patterns and incorporates overnight informational influences. We capture dynamic inter-stock relationships through distance-aware mechanisms, while evolving long-term structures via recurrent fusion of dynamic relations from the prior day with the pre-defined static relations. Experiments demonstrate that our method significantly outperforms the baselines across different markets, with high sensitivity to the co-movement of relational strength and stock price.

---

### Digital Twin-enabled Multi-generation Control Co-Design with Deep Reinforcement Learning

Authors: Ying-Kuan Tsai, Vispi Karkaria, Yi-Ping Chen, Wei Chen
Published: 2025-10-12
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.10694v1

Control Co-Design (CCD) integrates physical and control system design to improve the performance of dynamic and autonomous systems. Despite advances in uncertainty-aware CCD methods, real-world uncertainties remain highly unpredictable. Multi-generation design addresses this challenge by considering the full lifecycle of a product: data collected from each generation informs the design of subsequent generations, enabling progressive improvements in robustness and efficiency. Digital Twin (DT) technology further strengthens this paradigm by creating virtual representations that evolve over the lifecycle through real-time sensing, model updating, and adaptive re-optimization. This paper presents a DT-enabled CCD framework that integrates Deep Reinforcement Learning (DRL) to jointly optimize physical design and controller. DRL accelerates real-time decision-making by allowing controllers to continuously learn from data and adapt to uncertain environments. Extending this approach, the framework employs a multi-generation paradigm, where each cycle of deployment, operation, and redesign uses collected data to refine DT models, improve uncertainty quantification through quantile regression, and inform next-generation designs of both physical components and controllers. The framework is demonstrated on an active suspension system, where DT-enabled learning from road conditions and driving behaviors yields smoother and more stable control trajectories. Results show that the method significantly enhances dynamic performance, robustness, and efficiency. Contributions of this work include: (1) extending CCD into a lifecycle-oriented multi-generation framework, (2) leveraging DTs for continuous model updating and informed design, and (3) employing DRL to accelerate adaptive real-time decision-making.

---

### High-Dimensional Learning Dynamics of Quantized Models with Straight-Through Estimator

Authors: Yuma Ichikawa, Shuhei Kashiwamura, Ayaka Sakata
Published: 2025-10-12
Categories: stat.ML, cond-mat.dis-nn, cs.AI, cs.LG, math.ST
arXiv: https://arxiv.org/abs/2510.10693v1

Quantized neural network training optimizes a discrete, non-differentiable objective. The straight-through estimator (STE) enables backpropagation through surrogate gradients and is widely used. While previous studies have primarily focused on the properties of surrogate gradients and their convergence, the influence of quantization hyperparameters, such as bit width and quantization range, on learning dynamics remains largely unexplored. We theoretically show that in the high-dimensional limit, STE dynamics converge to a deterministic ordinary differential equation. This reveals that STE training exhibits a plateau followed by a sharp drop in generalization error, with plateau length depending on the quantization range. A fixed-point analysis quantifies the asymptotic deviation from the unquantized linear model. We also extend analytical techniques for stochastic gradient descent to nonlinear transformations of weights and inputs.

---

### Dynamic Gaussian Splatting from Defocused and Motion-blurred Monocular Videos

Authors: Xuankai Zhang, Junjin Xiao, Qing Zhang
Published: 2025-10-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.10691v3

This paper presents a unified framework that allows high-quality dynamic Gaussian Splatting from both defocused and motion-blurred monocular videos. Due to the significant difference between the formation processes of defocus blur and motion blur, existing methods are tailored for either one of them, lacking the ability to simultaneously deal with both of them. Although the two can be jointly modeled as blur kernel-based convolution, the inherent difficulty in estimating accurate blur kernels greatly limits the progress in this direction. In this work, we go a step further towards this direction. Particularly, we propose to estimate per-pixel reliable blur kernels using a blur prediction network that exploits blur-related scene and camera information and is subject to a blur-aware sparsity constraint. Besides, we introduce a dynamic Gaussian densification strategy to mitigate the lack of Gaussians for incomplete regions, and boost the performance of novel view synthesis by incorporating unseen view information to constrain scene optimization. Extensive experiments show that our method outperforms the state-of-the-art methods in generating photorealistic novel view synthesis from defocused and motion-blurred monocular videos. Our code is available at https://github.com/hhhddddddd/dydeblur.

---

### Second-order Optimization under Heavy-Tailed Noise: Hessian Clipping and Sample Complexity Limits

Authors: Abdurakhmon Sadiev, Peter Richtárik, Ilyas Fatkhullin
Published: 2025-10-12
Categories: math.OC, cs.LG
arXiv: https://arxiv.org/abs/2510.10690v1

Heavy-tailed noise is pervasive in modern machine learning applications, arising from data heterogeneity, outliers, and non-stationary stochastic environments. While second-order methods can significantly accelerate convergence in light-tailed or bounded-noise settings, such algorithms are often brittle and lack guarantees under heavy-tailed noise -- precisely the regimes where robustness is most critical. In this work, we take a first step toward a theoretical understanding of second-order optimization under heavy-tailed noise. We consider a setting where stochastic gradients and Hessians have only bounded $p$-th moments, for some $p\in (1,2)$, and establish tight lower bounds on the sample complexity of any second-order method. We then develop a variant of normalized stochastic gradient descent that leverages second-order information and provably matches these lower bounds. To address the instability caused by large deviations, we introduce a novel algorithm based on gradient and Hessian clipping, and prove high-probability upper bounds that nearly match the fundamental limits. Our results provide the first comprehensive sample complexity characterization for second-order optimization under heavy-tailed noise. This positions Hessian clipping as a robust and theoretically sound strategy for second-order algorithm design in heavy-tailed regimes.

---

### OmniVideoBench: Towards Audio-Visual Understanding Evaluation for Omni MLLMs

Authors: Caorui Li, Yu Chen, Yiyan Ji, Jin Xu, Zhenyu Cui, Shihao Li, Yuanxing Zhang, Wentao Wang, Zhenghao Song, Dingling Zhang, Ying He, Haoxiang Liu et al.
Published: 2025-10-12
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.10689v3

Recent advances in multimodal large language models (MLLMs) have demonstrated substantial potential in video understanding. However, existing benchmarks fail to comprehensively evaluate synergistic reasoning capabilities across audio and visual modalities, often neglecting either one of the modalities or integrating them in a logically inconsistent manner. To bridge this gap, we introduce OmniVideoBench, a large-scale and rigorously designed benchmark dedicated to assessing synergistic audio-visual understanding, with a strong emphasis on modality complementarity and logical consistency. Specifically, OmniVideoBench comprises 1000 high-quality question-answer(QA) pairs, each annotated with step-by-step reasoning traces, derived from 628 diverse videos ranging from several seconds to 30 minutes, and manually verified to guarantee complete correctness and uniqueness. Moreover, OmniVideoBench encompasses 13 carefully designed question types, covering temporal reasoning, spatial localization, counting, causal inference, summarization, and beyond, thereby capturing the essential challenges of video understanding. Evaluation of multiple MLLMs on OmniVideoBench reveals a pronounced gap between model performance and human reasoning, with open-source models lagging significantly behind their closed-source counterparts, underscoring the inherent difficulty of genuine audio-visual reasoning. We will release OmniVideoBench to foster the development of MLLMs with stronger and more generalizable reasoning capabilities.

---

### LSZone: A Lightweight Spatial Information Modeling Architecture for Real-time In-car Multi-zone Speech Separation

Authors: Jun Chen, Shichao Hu, Jiuxin Lin, Wenjie Li, Zihan Zhang, Xingchen Li, JinJiang Liu, Longshuai Xiao, Chao Weng, Lei Xie, Zhiyong Wu
Published: 2025-10-12
Categories: cs.SD, cs.AI
arXiv: https://arxiv.org/abs/2510.10687v1

In-car multi-zone speech separation, which captures voices from different speech zones, plays a crucial role in human-vehicle interaction. Although previous SpatialNet has achieved notable results, its high computational cost still hinders real-time applications in vehicles. To this end, this paper proposes LSZone, a lightweight spatial information modeling architecture for real-time in-car multi-zone speech separation. We design a spatial information extraction-compression (SpaIEC) module that combines Mel spectrogram and Interaural Phase Difference (IPD) to reduce computational burden while maintaining performance. Additionally, to efficiently model spatial information, we introduce an extremely lightweight Conv-GRU crossband-narrowband processing (CNP) module. Experimental results demonstrate that LSZone, with a complexity of 0.56G MACs and a real-time factor (RTF) of 0.37, delivers impressive performance in complex noise and multi-speaker scenarios.

---

### Action-Dynamics Modeling and Cross-Temporal Interaction for Online Action Understanding

Authors: Xinyu Yang, Zheheng Jiang, Feixiang Zhou, Yihang Zhu, Na Lv, Nan Xing, Nishan Canagarajah, Huiyu Zhou
Published: 2025-10-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.10682v2

Action understanding, encompassing action detection and anticipation, plays a crucial role in numerous practical applications. However, untrimmed videos are often characterized by substantial redundant information and noise. Moreover, in modeling action understanding, the influence of the agent's intention on the action is often overlooked. Motivated by these issues, we propose a novel framework called the State-Specific Model (SSM), designed to unify and enhance both action detection and anticipation tasks. In the proposed framework, the Critical State-Based Memory Compression module compresses frame sequences into critical states, reducing information redundancy. The Action Pattern Learning module constructs a state-transition graph with multi-dimensional edges to model action dynamics in complex scenarios, on the basis of which potential future cues can be generated to represent intention. Furthermore, our Cross-Temporal Interaction module models the mutual influence between intentions and past as well as current information through cross-temporal interactions, thereby refining present and future features and ultimately realizing simultaneous action detection and anticipation. Extensive experiments on multiple benchmark datasets -- including EPIC-Kitchens-100, THUMOS'14, TVSeries, and the introduced Parkinson's Disease Mouse Behaviour (PDMB) dataset -- demonstrate the superior performance of our proposed framework compared to other state-of-the-art approaches. These results highlight the importance of action dynamics learning and cross-temporal interactions, laying a foundation for future action understanding research.

---

### RePro: Training Language Models to Faithfully Recycle the Web for Pretraining

Authors: Zichun Yu, Chenyan Xiong
Published: 2025-10-12
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.10681v2

High-quality data is a cornerstone of large language model (LLM) pretraining, yet its growth has not kept pace with the needs of frontier models. In this paper, we introduce RePro, a novel web recycling method that trains a relatively small LM with reinforcement learning to generate effective and faithful rephrasings of pretraining data. Specifically, we design one quality reward and three faithfulness rewards, optimizing the LM rephraser to convert organic data into high-quality rephrasings while maintaining its core semantics and structure. In our experiment, we train a rephraser as small as 1B parameters to recycle 72B tokens sampled from DCLM-RefinedWeb. Pretraining results on 400M, 1.4B, and 2.8B models demonstrate that RePro delivers 3.7%-14.5% relative accuracy gains over organic-only baseline on 22 downstream tasks, doubling the performance gains achieved by the state-of-the-art web recycling method that prompts a 70B rephraser. Experiments with different amounts of recycled data highlight that RePro improves organic data efficiency by 2-3x. Individual and distributional analyses validate that RePro preserves more critical information and faithfully reflects the characteristics of organic data compared to prompting-based methods. Together, these results show that RePro provides an efficient and controllable path to effectively recycle organic data for pretraining. Our code is available at https://github.com/cxcscmu/RePro.

---

### Synergistic Modality-and-Slice Memory Framework for Cross-Modal 3D Brain Tumor Segmentation

Authors: Yuxiang Luo, Qing Xu, Hai Huang, Yuqi Ouyang, Xiangjian He, Zhen Chen, Wenting Duan, Jiebo Luo
Published: 2025-10-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.10679v2

The 3D multi-modal brain tumor segmentation is critical to multi-modal healthcare, and it requires accurate identification of distinct internal anatomical subregions. While the recent prompt-based segmentation paradigms enable interactive experiences for clinicians, existing methods ignore cross-modal correlations and rely on labor-intensive category-specific prompts, limiting their applicability in real-world scenarios. To address these issues, we propose the MSM-Seg, a synergistic framework for multi-modal brain tumor segmentation. The MSM-Seg introduces a dual-memory segmentation paradigm that synergistically integrates multi-modal and inter-slice information with an efficient category-agnostic prompt for brain tumor understanding. To this end, we first devise a modality-and-slice memory attention (MSMA) to exploit the complex cross-modal correlations and spatial-slice dependencies among the input scans. \cz{Then, we propose a multi-scale category-agnostic prompt encoder (MCP-Encoder) to provide whole tumor region guidance for decoding.} Moreover, we devise a modality-adaptive fusion decoder (MF-Decoder) that leverages the complementary decoding information across different modalities to improve segmentation accuracy. Extensive experiments on different MRI datasets demonstrate that our MSM-Seg framework outperforms state-of-the-art methods in multi-modal metastases and glioma tumor segmentation. The code is available at https://github.com/xq141839/MSM-Seg.

---

### Unlocking LLM Safeguards for Low-Resource Languages via Reasoning and Alignment with Minimal Training Data

Authors: Zhuowei Chen, Bowei Zhang, Nankai Lin, Tian Hou, Lianxi Wang
Published: 2025-10-12
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.10677v1

Recent advances in LLMs have enhanced AI capabilities, but also increased the risk posed by malicious requests, highlighting the need for effective LLM safeguards to detect such queries. Existing approaches largely rely on classifier-based methods that lack interpretability and perform poorly on low-resource languages. To address these limitations, we propose ConsistentGuard, a novel reasoning-based multilingual safeguard, which enhances explainability via reasoning and boosts knowledge transfer between languages through alignment. With only 1,000 training samples, our method demonstrates superior performance on three datasets across six languages, outperforming larger models trained with significantly more data, and exhibits strong interpretability and generalization ability. We also contribute a multilingual benchmark extension and release our codes to support future research.

---

### Bhasha-Rupantarika: Algorithm-Hardware Co-design approach for Multilingual Neural Machine Translation

Authors: Mukul Lokhande, Tanushree Dewangan, Mohd Sharik Mansoori, Tejas Chaudhari, Akarsh J., Damayanti Lokhande, Adam Teman, Santosh Kumar Vishvakarma
Published: 2025-10-12
Categories: cs.AR, cs.CL, cs.RO, eess.AS
arXiv: https://arxiv.org/abs/2510.10676v1

This paper introduces Bhasha-Rupantarika, a light and efficient multilingual translation system tailored through algorithm-hardware codesign for resource-limited settings. The method investigates model deployment at sub-octet precision levels (FP8, INT8, INT4, and FP4), with experimental results indicating a 4.1x reduction in model size (FP4) and a 4.2x speedup in inference speed, which correlates with an increased throughput of 66 tokens/s (improvement by 4.8x). This underscores the importance of ultra-low precision quantization for real-time deployment in IoT devices using FPGA accelerators, achieving performance on par with expectations. Our evaluation covers bidirectional translation between Indian and international languages, showcasing its adaptability in low-resource linguistic contexts. The FPGA deployment demonstrated a 1.96x reduction in LUTs and a 1.65x decrease in FFs, resulting in a 2.2x enhancement in throughput compared to OPU and a 4.6x enhancement compared to HPTA. Overall, the evaluation provides a viable solution based on quantisation-aware translation along with hardware efficiency suitable for deployable multilingual AI systems. The entire codes (https://github.com/mukullokhande99/Bhasha-Rupantarika/) and dataset for reproducibility are publicly available, facilitating rapid integration and further development by researchers.

---

### Simpliflow: A Lightweight Open-Source Framework for Rapid Creation and Deployment of Generative Agentic AI Workflows

Authors: Deven Panchal
Published: 2025-10-12
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.10675v2

Generative Agentic AI systems are emerging as a powerful paradigm for automating complex, multi-step tasks. However, many existing frameworks for building these systems introduce significant complexity, a steep learning curve, and substantial boilerplate code, hindering rapid prototyping and deployment. This paper introduces simpliflow, a lightweight, open-source Python framework designed to address these challenges. simpliflow enables the rapid development and orchestration of linear, deterministic agentic workflows through a declarative, JSON-based configuration. Its modular architecture decouples agent management, workflow execution, and post-processing, promoting ease of use and extensibility. By integrating with LiteLLM, it supports over 100 Large Language Models (LLMs) out-of-the-box. We present the architecture, operational flow, and core features of simpliflow, demonstrating its utility through diverse use cases ranging from software development simulation to real-time system interaction. A comparative analysis with prominent frameworks like LangChain and AutoGen highlights simpliflow's unique position as a tool optimized for simplicity, control, and speed in deterministic workflow environments.

---

### Image-to-Video Transfer Learning based on Image-Language Foundation Models: A Comprehensive Survey

Authors: Jinxuan Li, Chaolei Tan, Haoxuan Chen, Jianxin Ma, Jian-Fang Hu, Jianhuang Lai, Wei-Shi Zheng
Published: 2025-10-12
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.10671v3

Image-Language Foundation Models (ILFMs) have demonstrated remarkable success in vision-language understanding, providing transferable multimodal representations that generalize across diverse downstream image-based tasks. The advancement of video-text research has spurred growing interest in extending image-based models to the video domain. This paradigm, termed as image-to-video transfer learning, effectively mitigates the substantial data and computational demands compared to training video-language models from scratch while achieves comparable or even stronger model performance. This survey provides the first comprehensive review of this emerging field, which begins by summarizing the widely used ILFMs and their capabilities. We then systematically classify existing image-to-video transfer learning techniques into two broad root categories (frozen features and adapted features), along with numerous fine-grained subcategories, based on the paradigm for transferring image understanding capability to video tasks. Building upon the task-specific nature of image-to-video transfer, this survey methodically elaborates these strategies and details their applications across a spectrum of video-text learning tasks, ranging from fine-grained settings (e.g., spatio-temporal video grounding) to coarse-grained ones (e.g., video question answering). We further present a detailed experimental analysis to investigate the efficacy of different image-to-video transfer learning paradigms on a range of downstream video understanding tasks. Finally, we identify prevailing challenges and highlight promising directions for future research. By offering a comprehensive and structured overview, this survey aims to establish a structured roadmap for advancing video-text learning based on existing ILFM, and to inspire future research directions in this rapidly evolving domain. Github repository is available.

---

### AdaViewPlanner: Adapting Video Diffusion Models for Viewpoint Planning in 4D Scenes

Authors: Yu Li, Menghan Xia, Gongye Liu, Jianhong Bai, Xintao Wang, Conglang Zhang, Yuxuan Lin, Ruihang Chu, Pengfei Wan, Yujiu Yang
Published: 2025-10-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.10670v1

Recent Text-to-Video (T2V) models have demonstrated powerful capability in visual simulation of real-world geometry and physical laws, indicating its potential as implicit world models. Inspired by this, we explore the feasibility of leveraging the video generation prior for viewpoint planning from given 4D scenes, since videos internally accompany dynamic scenes with natural viewpoints. To this end, we propose a two-stage paradigm to adapt pre-trained T2V models for viewpoint prediction, in a compatible manner. First, we inject the 4D scene representation into the pre-trained T2V model via an adaptive learning branch, where the 4D scene is viewpoint-agnostic and the conditional generated video embeds the viewpoints visually. Then, we formulate viewpoint extraction as a hybrid-condition guided camera extrinsic denoising process. Specifically, a camera extrinsic diffusion branch is further introduced onto the pre-trained T2V model, by taking the generated video and 4D scene as input. Experimental results show the superiority of our proposed method over existing competitors, and ablation studies validate the effectiveness of our key technical designs. To some extent, this work proves the potential of video generation models toward 4D interaction in real world.

---

### BrowserAgent: Building Web Agents with Human-Inspired Web Browsing Actions

Authors: Tao Yu, Zhengbo Zhang, Zhiheng Lyu, Junhao Gong, Hongzhu Yi, Xinming Wang, Yuxuan Zhou, Jiabing Yang, Ping Nie, Yan Huang, Wenhu Chen
Published: 2025-10-12
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.10666v2

Efficiently solving real-world problems with LLMs increasingly hinges on their ability to interact with dynamic web environments and autonomously acquire external information. While recent research like Search-R1 and WebDancer demonstrates strong performance in solving web tasks, they heavily rely on additional tools to convert the interactive web environment into static text content. This is in contrast to human browsing behaviors, which involve diverse interactions with the browser, such as scrolling, clicking, and typing. In this paper, we propose BrowserAgent, a more interactive agent that solves complex tasks through human-inspired browser actions. BrowserAgent operates directly on raw web pages via Playwright through a set of predefined browser actions. We adopt a two-stage training (Supervised Fine-Tuning (SFT) and Rejection Fine-Tuning (RFT)) to improve the model's generalization abilities. Despite using significantly less training data than Search-R1, BrowserAgent achieves more competitive results across different Open-QA tasks. Additionally, we introduce an explicit memory mechanism to store key conclusions across steps, further enhancing the model's reasoning capabilities for long-horizon tasks. Notably, BrowserAgent-7B can achieve around 20\% improvement over Search-R1 on multi-hop QA tasks like HotpotQA, 2Wiki, and Bamboogle. These results indicate that BrowserAgent can serve as a more advanced framework for more interactive and scalable web agents.

---

### Information-Computation Tradeoffs for Noiseless Linear Regression with Oblivious Contamination

Authors: Ilias Diakonikolas, Chao Gao, Daniel M. Kane, John Lafferty, Ankit Pensia
Published: 2025-10-12
Categories: cs.DS, math.ST, stat.ML
arXiv: https://arxiv.org/abs/2510.10665v1

We study the task of noiseless linear regression under Gaussian covariates in the presence of additive oblivious contamination. Specifically, we are given i.i.d.\ samples from a distribution $(x, y)$ on $\mathbb{R}^d \times \mathbb{R}$ with $x \sim \mathcal{N}(0,\mathbf{I}_d)$ and $y = x^\top β+ z$, where $z$ is drawn independently of $x$ from an unknown distribution $E$. Moreover, $z$ satisfies $\mathbb{P}_E(z = 0) = α>0$. The goal is to accurately recover the regressor $β$ to small $\ell_2$-error. Ignoring computational considerations, this problem is known to be solvable using $O(d/α)$ samples. On the other hand, the best known polynomial-time algorithms require $Ω(d/α^2)$ samples. Here we provide formal evidence that the quadratic dependence in $1/α$ is inherent for efficient algorithms. Specifically, we show that any efficient Statistical Query algorithm for this task requires VSTAT complexity at least $\tildeΩ(d^{1/2}/α^2)$.

---

### Scalable Face Security Vision Foundation Model for Deepfake, Diffusion, and Spoofing Detection

Authors: Gaojian Wang, Feng Lin, Tong Wu, Zhisheng Yan, Kui Ren
Published: 2025-10-12
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.10663v1

With abundant, unlabeled real faces, how can we learn robust and transferable facial representations to boost generalization across various face security tasks? We make the first attempt and propose FS-VFM, a scalable self-supervised pre-training framework, to learn fundamental representations of real face images. We introduce three learning objectives, namely 3C, that synergize masked image modeling (MIM) and instance discrimination (ID), empowering FS-VFM to encode both local patterns and global semantics of real faces. Specifically, we formulate various facial masking strategies for MIM and devise a simple yet effective CRFR-P masking, which explicitly prompts the model to pursue meaningful intra-region Consistency and challenging inter-region Coherency. We present a reliable self-distillation mechanism that seamlessly couples MIM with ID to establish underlying local-to-global Correspondence. After pre-training, vanilla vision transformers (ViTs) serve as universal Vision Foundation Models for downstream Face Security tasks: cross-dataset deepfake detection, cross-domain face anti-spoofing, and unseen diffusion facial forensics. To efficiently transfer the pre-trained FS-VFM, we further propose FS-Adapter, a lightweight plug-and-play bottleneck atop the frozen backbone with a novel real-anchor contrastive objective. Extensive experiments on 11 public benchmarks demonstrate that our FS-VFM consistently generalizes better than diverse VFMs, spanning natural and facial domains, fully, weakly, and self-supervised paradigms, small, base, and large ViT scales, and even outperforms SOTA task-specific methods, while FS-Adapter offers an excellent efficiency-performance trade-off. The code and models are available on https://fsfm-3c.github.io/fsvfm.html.

---

### AGENTIQL: An Agent-Inspired Multi-Expert Framework for Text-to-SQL Generation

Authors: Omid Reza Heidari, Siobhan Reid, Yassine Yaakoubi
Published: 2025-10-12
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.10661v2

LLMs have advanced text-to-SQL generation, yet monolithic architectures struggle with complex reasoning and schema diversity. We propose AGENTIQL, an agent-inspired multi-expert framework that combines a reasoning agent for question decomposition, a coding agent for sub-query generation, and a refinement step for column selection. An adaptive router further balances efficiency and accuracy by selecting between our modular pipeline and a baseline parser. Several steps in the pipeline can be executed in parallel, making the framework scalable to larger workloads. Evaluated on the Spider benchmark, AGENTIQL improves execution accuracy and interpretability and achieves up to 86.07% EX with 14B models using the Planner&Executor merging strategy. The attained performance is contingent upon the efficacy of the routing mechanism, thereby narrowing the gap to GPT-4-based SOTA (89.65% EX) while using much smaller open-source LLMs. Beyond accuracy, AGENTIQL enhances transparency by exposing intermediate reasoning steps, offering a robust, scalable, and interpretable approach to semantic parsing.

---

### Stability Under Scrutiny: Benchmarking Representation Paradigms for Online HD Mapping

Authors: Hao Shan, Ruikai Li, Han Jiang, Yizhe Fan, Ziyang Yan, Bohan Li, Xiaoshuai Hao, Hao Zhao, Zhiyong Cui, Yilong Ren, Haiyang Yu
Published: 2025-10-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.10660v1

As one of the fundamental modules in autonomous driving, online high-definition (HD) maps have attracted significant attention due to their cost-effectiveness and real-time capabilities. Since vehicles always cruise in highly dynamic environments, spatial displacement of onboard sensors inevitably causes shifts in real-time HD mapping results, and such instability poses fundamental challenges for downstream tasks. However, existing online map construction models tend to prioritize improving each frame's mapping accuracy, while the mapping stability has not yet been systematically studied. To fill this gap, this paper presents the first comprehensive benchmark for evaluating the temporal stability of online HD mapping models. We propose a multi-dimensional stability evaluation framework with novel metrics for Presence, Localization, and Shape Stability, integrated into a unified mean Average Stability (mAS) score. Extensive experiments on 42 models and variants show that accuracy (mAP) and stability (mAS) represent largely independent performance dimensions. We further analyze the impact of key model design choices on both criteria, identifying architectural and training factors that contribute to high accuracy, high stability, or both. To encourage broader focus on stability, we will release a public benchmark. Our work highlights the importance of treating temporal stability as a core evaluation criterion alongside accuracy, advancing the development of more reliable autonomous driving systems. The benchmark toolkit, code, and models will be available at https://stablehdmap.github.io/.

---

### You're Not Gonna Believe This: A Computational Analysis of Factual Appeals and Sourcing in Partisan News

Authors: Guy Mor-Lan, Tamir Sheafer, Shaul R. Shenhav
Published: 2025-10-12
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.10658v1

While media bias is widely studied, the epistemic strategies behind factual reporting remain computationally underexplored. This paper analyzes these strategies through a large-scale comparison of CNN and Fox News. To isolate reporting style from topic selection, we employ an article matching strategy to compare reports on the same events and apply the FactAppeal framework to a corpus of over 470K articles covering two highly politicized periods: the COVID-19 pandemic and the Israel-Hamas war. We find that CNN's reporting contains more factual statements and is more likely to ground them in external sources. The outlets also exhibit sharply divergent sourcing patterns: CNN builds credibility by citing Experts} and Expert Documents, constructing an appeal to formal authority, whereas Fox News favors News Reports and direct quotations. This work quantifies how partisan outlets use systematically different epistemic strategies to construct reality, adding a new dimension to the study of media bias.

---