# Research Papers — 2025-10 · bundle page 99 of 217

> Full-text markdown of papers #4901–4950 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/99
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/98.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/100.md)

### GUIrilla: A Scalable Framework for Automated Desktop UI Exploration

Authors: Sofiya Garkot, Maksym Shamrai, Ivan Synytsia, Mariya Hirna
Published: 2025-10-16
Categories: cs.LG, cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2510.16051v2

The performance and generalization of foundation models for interactive systems critically depend on the availability of large-scale, realistic training data. While recent advances in large language models (LLMs) have improved GUI understanding, progress in desktop automation remains constrained by the scarcity of high-quality, publicly available desktop interaction data, particularly for macOS. We introduce GUIRILLA, a scalable data crawling framework for automated exploration of desktop GUIs. GUIRILLA is not an autonomous agent; instead, it systematically collects realistic interaction traces and accessibility metadata intended to support the training, evaluation, and stabilization of downstream foundation models and GUI agents. The framework targets macOS, a largely underrepresented platform in existing resources, and organizes explored interfaces into hierarchical MacApp Trees derived from accessibility states and user actions. As part of this work, we release these MacApp Trees as a reusable structural representation of macOS applications, enabling downstream analysis, retrieval, testing, and future agent training. We additionally release macapptree, an open-source library for reproducible accessibility-driven GUI data collection, along with the full framework implementation to support open research in desktop autonomy.

---

### In the Mood to Exclude: Revitalizing Trespass to Chattels in the Era of GenAI Scraping

Authors: David Atkinson
Published: 2025-10-16
Categories: cs.CY, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.16049v2

GenAI companies are strip-mining the web. Their scraping bots harvest content at an unprecedented scale, circumventing technical barriers to fuel billion-dollar models while creators receive nothing. Courts have enabled this exploitation by misunderstanding what property rights protect online. The prevailing view treats websites as mere repositories of intellectual property and dismisses trespass claims absent server damage. That framework grants AI companies presumptive access while ignoring the economic devastation they inflict. But the content is severable from the website itself. This paper reframes the debate: websites are personal property as integrated digital assets subject to the same exclusionary rights as physical chattels. When scrapers bypass access controls and divert traffic that sustains a website's value, they commit actionable trespass. The law need not create new protections; it need only apply existing property principles to digital space. Courts and litigants have struggled to police unwanted, large-scale scraping because copyright preemption often narrows available claims, leaving copyright and its fair use defense as the primary battleground. Trespass to chattels offers a superior path, grounded in the fundamental right to exclude unwanted intrusions. Reviving this tort would protect not only content creators but also the digital ecosystem. Such protection would discourage exploitative scraping, preserve incentives for content creation, help protect privacy and personal data, and safeguard autonomy and expression. Reaffirming website owners' right to exclude is essential to maintaining a fair and sustainable online environment.

---

### Open Shouldn't Mean Exempt: Open-Source Exceptionalism and Generative AI

Authors: David Atkinson
Published: 2025-10-16
Categories: cs.CY, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.16048v2

Open-source status should not shield generative artificial intelligence systems from ethical or legal accountability. Through a rigorous analysis of regulatory, legal, and policy frameworks, this Article contends that open-source GenAI must be held to the same standards as proprietary systems. While recognizing the value of openness for scientific advancement, I propose a narrowly tailored safe harbor for bona fide, non-commercial research, conditioned on strict compliance with defined criteria. This Article critically examines and refutes the core claims of open-source exceptionalism--namely, that open-source GenAI disrupts entrenched oligopolies, democratizes access, and uniquely drives innovation. The evidence shows that open-source GenAI can facilitate unlawful conduct, exacerbate environmental harms, and reinforce existing power structures. Rhetoric around "democratization" and "innovation" often serves as an unsubstantiated basis for regulatory exemptions not afforded to proprietary systems. This Article ultimately advocates for a framework that promotes responsible AI development, balancing openness with robust legal and ethical safeguards and a clear-eyed assessment of societal impacts.

---

### Algorithms for dynamic scheduling in manufacturing, towards digital factories Improving Deadline Feasibility and Responsiveness via Temporal Networks

Authors: Ioan Hedea
Published: 2025-10-16
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.16047v1

Modern manufacturing systems must meet hard delivery deadlines while coping with stochastic task durations caused by process noise, equipment variability, and human intervention. Traditional deterministic schedules break down when reality deviates from nominal plans, triggering costly last-minute repairs. This thesis combines offline constraint-programming (CP) optimisation with online temporal-network execution to create schedules that remain feasible under worst-case uncertainty. First, we build a CP model of the flexible job-shop with per-job deadline tasks and insert an optimal buffer $Δ^*$ to obtain a fully pro-active baseline. We then translate the resulting plan into a Simple Temporal Network with Uncertainty (STNU) and verify dynamic controllability, which guarantees that a real-time dispatcher can retime activities for every bounded duration realisation without violating resource or deadline constraints. Extensive Monte-Carlo simulations on the open Kacem~1--4 benchmark suite show that our hybrid approach eliminates 100\% of deadline violations observed in state-of-the-art meta-heuristic schedules, while adding only 3--5\% makespan overhead. Scalability experiments confirm that CP solve-times and STNU checks remain sub-second on medium-size instances. The work demonstrates how temporal-network reasoning can bridge the gap between proactive buffering and dynamic robustness, moving industry a step closer to truly digital, self-correcting factories.

---

### AMS-QUANT: Adaptive Mantissa Sharing for Floating-point Quantization

Authors: Mengtao Lv, Ruiqi Zhu, Xinyu Wang, Yun Li
Published: 2025-10-16
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.16045v1

Large language models (LLMs) have demonstrated remarkable capabilities in various kinds of tasks, while the billion or even trillion parameters bring storage and efficiency bottlenecks for inference. Quantization, particularly floating-point quantization, is known to be capable of speeding up LLM inference by reducing memory footprint and data movement during the inference process. For the first time, we advance the floating-point quantization exploration from integer bitwidths to non-integer bit-widths, namely AMS-Quant, to further approach the quantization sweet spot. AMS-Quant incorporates two novel techniques to put it into effect: (1) it proposes Mantissa-bit Sharing, which groups k quantized weights and lets them share the least significant mantissa bit, allowing us to further approach the minimum quantization bit-width without accuracy loss. (2) It introduces Adaptive Searching, which employs an offline optimization strategy to minimize the accuracy degradation introduced by sharing. Moreover, AMS-Quant is also prototyped as efficient CUDA Linear kernels, which translates memory savings into wall-clock latency reduction by reducing memory access. Extensive experiments on large-scale datasets and models show that AMS-Quant can quantize the model to FP-5.33-e2m3 and FP4.25-e2m2, and significantly speed up the LLM decoding over FP16 inference (2.8x and 3.2x), with negligible accuracy loss.

---

### A Novel GPT-Based Framework for Anomaly Detection in System Logs

Authors: Zeng Zhang, Wenjie Yin, Xiaoqi Li
Published: 2025-10-16
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2510.16044v2

Identification of anomalous events within system logs constitutes a pivotal element within the frame- work of cybersecurity defense strategies. However, this process faces numerous challenges, including the management of substantial data volumes, the distribution of anomalies, and the precision of con- ventional methods. To address this issue, the present paper puts forward a proposal for an intelligent detection method for system logs based on Genera- tive Pre-trained Transformers (GPT). The efficacy of this approach is attributable to a combination of structured input design and a Focal Loss op- timization strategy, which collectively result in a substantial enhancement of the performance of log anomaly detection. The initial approach involves the conversion of raw logs into event ID sequences through the use of the Drain parser. Subsequently, the Focal Loss loss function is employed to address the issue of class imbalance. The experimental re- sults demonstrate that the optimized GPT-2 model significantly outperforms the unoptimized model in a range of key metrics, including precision, recall, and F1 score. In specific tasks, comparable or superior performance has been demonstrated to that of the GPT-3.5 API.

---

### Does Capital Dream of Artificial Labour?

Authors: Marcin Korecki, Cesare Carissimo
Published: 2025-10-16
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2510.16042v1

This paper investigates the concept of Labour as an expression of `timenergy' - a fusion of time and energy - and its entanglement within the system of Capital. We define Labour as the commodified, quantifiable expansion of timenergy, in contrast to Capital, which is capable of accumulation and abstraction. We explore Labour's historical evolution, its coercive and alienating nature, and its transformation through automation and artificial intelligence. Using a game-theoretic, agent-based simulation, we model interactions between Capital and Labour in production processes governed by Cobb-Douglas functions. Our results show that despite theoretical symmetry, learning agents disproportionately gravitate toward capital-intensive processes, revealing Capital's superior organizational influence due to its accumulative capacity. We argue that Capital functions as an artificially alive system animated by the living Labour it consumes, and question whether life can sustain itself without the infrastructures of Capital in a future of increasing automation. This study offers both a critique of and a framework for understanding Labour's subjugation within the Capital system.

---

### Kelle: Co-design KV Caching and eDRAM for Efficient LLM Serving in Edge Computing

Authors: Tianhua Xia, Sai Qian Zhang
Published: 2025-10-16
Categories: cs.AR, cs.AI
arXiv: https://arxiv.org/abs/2510.16040v1

Running Large Language Models (LLMs) on edge devices is crucial for reducing latency, improving real-time processing, and enhancing privacy. By performing inference directly on the device, data does not need to be sent to the cloud, ensuring faster responses and reducing reliance on network connectivity. However, implementing LLMs on edge devices presents challenges, particularly with managing key-value (KV) caches, which plays a pivotal role in LLM serving. As the input text lengthens, the size of the KV cache increases linearly with the sequence length, leading to a significant memory footprint and data access costs. On the other hand, edge devices have limited memory and computational power, making it hard to store and efficiently access the large caches needed for LLM inference. To mitigate the substantial overhead caused by KV cache, we propose using embedded DRAM (eDRAM) as the primary storage for LLM serving in edge device, which offers higher storage density compared to SRAM. However, to ensure data integrity, eDRAM needs periodic refresh operations, which are power-intensive. To reduce eDRAM costs and improve overall system performance, we propose~\textit{Kelle}, a software-hardware co-design solution optimized for deploying LLMs on eDRAM-based edge systems. Combined with our fine-grained memory eviction, recomputation, and refresh control algorithms, the \textit{Kelle} accelerator delivers a $3.9\times$ speedup and $4.5\times$ energy savings compared to existing baseline solutions.

---

### Vector Quantization in the Brain: Grid-like Codes in World Models

Authors: Xiangyuan Peng, Xingsi Dong, Si Wu
Published: 2025-10-16
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.16039v1

We propose Grid-like Code Quantization (GCQ), a brain-inspired method for compressing observation-action sequences into discrete representations using grid-like patterns in attractor dynamics. Unlike conventional vector quantization approaches that operate on static inputs, GCQ performs spatiotemporal compression through an action-conditioned codebook, where codewords are derived from continuous attractor neural networks and dynamically selected based on actions. This enables GCQ to jointly compress space and time, serving as a unified world model. The resulting representation supports long-horizon prediction, goal-directed planning, and inverse modeling. Experiments across diverse tasks demonstrate GCQ's effectiveness in compact encoding and downstream performance. Our work offers both a computational tool for efficient sequence modeling and a theoretical perspective on the formation of grid-like codes in neural systems.

---

### Membership Inference over Diffusion-models-based Synthetic Tabular Data

Authors: Peini Cheng, Amir Bahmani
Published: 2025-10-16
Categories: cs.CR, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.16037v1

This study investigates the privacy risks associated with diffusion-based synthetic tabular data generation methods, focusing on their susceptibility to Membership Inference Attacks (MIAs). We examine two recent models, TabDDPM and TabSyn, by developing query-based MIAs based on the step-wise error comparison method. Our findings reveal that TabDDPM is more vulnerable to these attacks. TabSyn exhibits resilience against our attack models. Our work underscores the importance of evaluating the privacy implications of diffusion models and encourages further research into robust privacy-preserving mechanisms for synthetic data generation.

---

### IAD-GPT: Advancing Visual Knowledge in Multimodal Large Language Model for Industrial Anomaly Detection

Authors: Zewen Li, Zitong Yu, Qilang Ye, Weicheng Xie, Wei Zhuo, Linlin Shen
Published: 2025-10-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.16036v1

The robust causal capability of Multimodal Large Language Models (MLLMs) hold the potential of detecting defective objects in Industrial Anomaly Detection (IAD). However, most traditional IAD methods lack the ability to provide multi-turn human-machine dialogues and detailed descriptions, such as the color of objects, the shape of an anomaly, or specific types of anomalies. At the same time, methods based on large pre-trained models have not fully stimulated the ability of large models in anomaly detection tasks. In this paper, we explore the combination of rich text semantics with both image-level and pixel-level information from images and propose IAD-GPT, a novel paradigm based on MLLMs for IAD. We employ Abnormal Prompt Generator (APG) to generate detailed anomaly prompts for specific objects. These specific prompts from the large language model (LLM) are used to activate the detection and segmentation functions of the pre-trained visual-language model (i.e., CLIP). To enhance the visual grounding ability of MLLMs, we propose Text-Guided Enhancer, wherein image features interact with normal and abnormal text prompts to dynamically select enhancement pathways, which enables language models to focus on specific aspects of visual data, enhancing their ability to accurately interpret and respond to anomalies within images. Moreover, we design a Multi-Mask Fusion module to incorporate mask as expert knowledge, which enhances the LLM's perception of pixel-level anomalies. Extensive experiments on MVTec-AD and VisA datasets demonstrate our state-of-the-art performance on self-supervised and few-shot anomaly detection and segmentation tasks, such as MVTec-AD and VisA datasets. The codes are available at \href{https://github.com/LiZeWen1225/IAD-GPT}{https://github.com/LiZeWen1225/IAD-GPT}.

---

### RoBCtrl: Attacking GNN-Based Social Bot Detectors via Reinforced Manipulation of Bots Control Interaction

Authors: Yingguang Yang, Xianghua Zeng, Qi Wu, Hao Peng, Yutong Xia, Hao Liu, Bin Chong, Philip S. Yu
Published: 2025-10-16
Categories: cs.LG, cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2510.16035v1

Social networks have become a crucial source of real-time information for individuals. The influence of social bots within these platforms has garnered considerable attention from researchers, leading to the development of numerous detection technologies. However, the vulnerability and robustness of these detection methods is still underexplored. Existing Graph Neural Network (GNN)-based methods cannot be directly applied due to the issues of limited control over social agents, the black-box nature of bot detectors, and the heterogeneity of bots. To address these challenges, this paper proposes the first adversarial multi-agent Reinforcement learning framework for social Bot control attacks (RoBCtrl) targeting GNN-based social bot detectors. Specifically, we use a diffusion model to generate high-fidelity bot accounts by reconstructing existing account data with minor modifications, thereby evading detection on social platforms. To the best of our knowledge, this is the first application of diffusion models to mimic the behavior of evolving social bots effectively. We then employ a Multi-Agent Reinforcement Learning (MARL) method to simulate bots adversarial behavior. We categorize social accounts based on their influence and budget. Different agents are then employed to control bot accounts across various categories, optimizing the attachment strategy through reinforcement learning. Additionally, a hierarchical state abstraction based on structural entropy is designed to accelerate the reinforcement learning. Extensive experiments on social bot detection datasets demonstrate that our framework can effectively undermine the performance of GNN-based detectors.

---

### Disaster Management in the Era of Agentic AI Systems: A Vision for Collective Human-Machine Intelligence for Augmented Resilience

Authors: Bo Li, Junwei Ma, Kai Yin, Yiming Xiao, Chia-Wei Hsu, Ali Mostafavi
Published: 2025-10-16
Categories: cs.MA, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.16034v2

The escalating frequency and severity of disasters routinely overwhelm traditional response capabilities, exposing critical vulnerability in disaster management. Current practices are hindered by fragmented data streams, siloed technologies, resource constraints, and the erosion of institutional memory, which collectively impede timely and effective decision making. This study introduces Disaster Copilot, a vision for a multi-agent artificial intelligence system designed to overcome these systemic challenges by unifying specialized AI tools within a collaborative framework. The proposed architecture utilizes a central orchestrator to coordinate diverse sub-agents, each specializing in critical domains such as predictive risk analytics, situational awareness, and impact assessment. By integrating multi-modal data, the system delivers a holistic, real-time operational picture and serve as the essential AI backbone required to advance Disaster Digital Twins from passive models to active, intelligent environments. Furthermore, it ensures functionality in resource-limited environments through on-device orchestration and incorporates mechanisms to capture institutional knowledge, mitigating the impact of staff turnover. We detail the system architecture and propose a three-phased roadmap emphasizing the parallel growth of technology, organizational capacity, and human-AI teaming. Disaster Copilot offers a transformative vision, fostering collective human-machine intelligence to build more adaptive, data-driven and resilient communities.

---

### Global-focal Adaptation with Information Separation for Noise-robust Transfer Fault Diagnosis

Authors: Junyu Ren, Wensheng Gan, Guangyu Zhang, Wei Zhong, Philip S. Yu
Published: 2025-10-16
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.16033v1

Existing transfer fault diagnosis methods typically assume either clean data or sufficient domain similarity, which limits their effectiveness in industrial environments where severe noise interference and domain shifts coexist. To address this challenge, we propose an information separation global-focal adversarial network (ISGFAN), a robust framework for cross-domain fault diagnosis under noise conditions. ISGFAN is built on an information separation architecture that integrates adversarial learning with an improved orthogonal loss to decouple domain-invariant fault representation, thereby isolating noise interference and domain-specific characteristics. To further strengthen transfer robustness, ISGFAN employs a global-focal domain-adversarial scheme that constrains both the conditional and marginal distributions of the model. Specifically, the focal domain-adversarial component mitigates category-specific transfer obstacles caused by noise in unsupervised scenarios, while the global domain classifier ensures alignment of the overall distribution. Experiments conducted on three public benchmark datasets demonstrate that the proposed method outperforms other prominent existing approaches, confirming the superiority of the ISGFAN framework. Data and code are available at https://github.com/JYREN-Source/ISGFAN

---

### A Comprehensive Evaluation of Graph Neural Networks and Physics Informed Learning for Surrogate Modelling of Finite Element Analysis

Authors: Nayan Kumar Singh
Published: 2025-10-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.15750v1

Although Finite Element Analysis (FEA) is an integral part of the product design lifecycle, the analysis is computationally expensive, making it unsuitable for many design optimization problems. The deep learning models can be a great solution. However, selecting the architecture that emulates the FEA with great accuracy is a challenge. This paper presents a comprehensive evaluation of graph neural networks (GNNs) and 3D U-Nets as surrogates for FEA of parametric I-beams. We introduce a Physics-Informed Neural Network (PINN) framework, governed by the Navier Cauchy equations, to enforce physical laws. Crucially, we demonstrate that a curriculum learning strategy, pretraining on data followed by physics informed fine tuning, is essential for stabilizing training. Our results show that GNNs fundamentally outperform the U-Net. Even the worst performer among GNNs, the GCN framework, achieved a relative L2 error of 8.7% while the best framework among U Net, U Net with attention mechanism trained on high resolution data, achieved 13.0% score. Among the graph-based architectures, the Message Passing Neural Networks (MPNN) and Graph Transformers achieved the highest accuracy, achieving a relative L2 score of 3.5% and 2.6% respectively. The inclusion of physics fundamental laws (PINN) significantly improved the generalization, reducing error by up to 11.3% on high-signal tasks. While the Graph Transformer is the most accurate model, it is more 37.5% slower during inference when compared to second best model, MPNN PINN. The PINN enhanced MPNN (MPNN PINN) provides the most practical solution. It offers a good compromise between predictive performance, model size, and inference speed.

---

### HyperAIRI: a plug-and-play algorithm for precise hyperspectral image reconstruction in radio interferometry

Authors: Chao Tang, Arwa Dabbech, Adrian Jackson, Yves Wiaux
Published: 2025-10-16
Categories: astro-ph.IM, cs.LG, eess.IV
arXiv: https://arxiv.org/abs/2510.15198v2

The next-generation radio-interferometric (RI) telescopes require imaging algorithms capable of forming high-resolution high-dynamic-range images from large data volumes spanning wide frequency bands. Recently, AIRI, a plug-and-play (PnP) approach taking the forward-backward algorithmic structure (FB), has demonstrated state-of-the-art performance in monochromatic RI imaging by alternating a data-fidelity step with a regularization step via learned denoisers. In this work, we introduce HyperAIRI, its hyperspectral extension, underpinned by learned hyperspectral denoisers enforcing a power-law spectral model. For each spectral channel, the HyperAIRI denoiser takes as input its current image estimate, alongside estimates of its two immediate neighboring channels and the spectral index map, and provides as output its associated denoised image. To ensure convergence of HyperAIRI, the denoisers are trained with a Jacobian regularization enforcing non-expansiveness. To accommodate varying dynamic ranges, we assemble a shelf of pre-trained denoisers, each tailored to a specific dynamic range. At each HyperAIRI iteration, the spectral channels of the target image cube are updated in parallel using dynamic-range-matched denoisers from the pre-trained shelf. The denoisers are also endowed with a spatial image faceting functionality, enabling scalability to varied image sizes. Additionally, we formally introduce Hyper-uSARA, a variant of the optimization-based algorithm HyperSARA, promoting joint sparsity across spectral channels via the $\ell_{2,1}$-norm, also adopting FB. We evaluate HyperAIRI's performance on simulated and real observations. We showcase its superior performance compared to its optimization-based counterpart Hyper-uSARA, CLEAN's hyperspectral variant in WSClean, and the monochromatic imaging algorithms AIRI and uSARA.

---

### Salient Concept-Aware Generative Data Augmentation

Authors: Tianchen Zhao, Xuanbai Chen, Zhihua Li, Jun Fang, Dongsheng An, Xiang Xu, Zhuowen Tu, Yifan Xing
Published: 2025-10-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.15194v1

Recent generative data augmentation methods conditioned on both image and text prompts struggle to balance between fidelity and diversity, as it is challenging to preserve essential image details while aligning with varied text prompts. This challenge arises because representations in the synthesis process often become entangled with non-essential input image attributes such as environmental contexts, creating conflicts with text prompts intended to modify these elements. To address this, we propose a personalized image generation framework that uses a salient concept-aware image embedding model to reduce the influence of irrelevant visual details during the synthesis process, thereby maintaining intuitive alignment between image and text inputs. By generating images that better preserve class-discriminative features with additional controlled variations, our framework effectively enhances the diversity of training datasets and thereby improves the robustness of downstream models. Our approach demonstrates superior performance across eight fine-grained vision datasets, outperforming state-of-the-art augmentation methods with averaged classification accuracy improvements by 0.73% and 6.5% under conventional and long-tail settings, respectively.

---

### Structure-R1: Dynamically Leveraging Structural Knowledge in LLM Reasoning through Reinforcement Learning

Authors: Junlin Wu, Xianrui Zhong, Jiashuo Sun, Bolian Li, Bowen Jin, Jiawei Han, Qingkai Zeng
Published: 2025-10-16
Categories: cs.CL, cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2510.15191v1

Large language models (LLMs) have demonstrated remarkable advances in reasoning capabilities. However, their performance remains constrained by limited access to explicit and structured domain knowledge. Retrieval-Augmented Generation (RAG) addresses this by incorporating external information as context to augment reasoning. Nevertheless, traditional RAG systems typically operate over unstructured and fragmented text, resulting in low information density and suboptimal reasoning. To overcome these limitations, we propose \textsc{Structure-R1}, a novel framework that transforms retrieved content into structured representations optimized for reasoning. Leveraging reinforcement learning, \textsc{Structure-R1} learns a content representation policy that dynamically generates and adapts structural formats based on the demands of multi-step reasoning. Unlike prior methods that rely on fixed schemas, our approach adopts a generative paradigm capable of producing task-specific structures tailored to individual queries. To ensure the quality and reliability of these representations, we introduce a self-reward structural verification mechanism that checks whether the generated structures are both correct and self-contained. Extensive experiments on seven knowledge-intensive benchmarks show that \textsc{Structure-R1} consistently achieves competitive performance with a 7B-scale backbone model and matches the performance of much larger models. Additionally, our theoretical analysis demonstrates how structured representations enhance reasoning by improving information density and contextual clarity. Our code and data are available at: https://github.com/jlwu002/sr1.

---

### OCR-APT: Reconstructing APT Stories from Audit Logs using Subgraph Anomaly Detection and LLMs

Authors: Ahmed Aly, Essam Mansour, Amr Youssef
Published: 2025-10-16
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2510.15188v2

Advanced Persistent Threats (APTs) are stealthy cyberattacks that often evade detection in system-level audit logs. Provenance graphs model these logs as connected entities and events, revealing relationships that are missed by linear log representations. Existing systems apply anomaly detection to these graphs but often suffer from high false positive rates and coarse-grained alerts. Their reliance on node attributes like file paths or IPs leads to spurious correlations, reducing detection robustness and reliability. To fully understand an attack's progression and impact, security analysts need systems that can generate accurate, human-like narratives of the entire attack. To address these challenges, we introduce OCR-APT, a system for APT detection and reconstruction of human-like attack stories. OCR-APT uses Graph Neural Networks (GNNs) for subgraph anomaly detection, learning behavior patterns around nodes rather than fragile attributes such as file paths or IPs. This approach leads to a more robust anomaly detection. It then iterates over detected subgraphs using Large Language Models (LLMs) to reconstruct multi-stage attack stories. Each stage is validated before proceeding, reducing hallucinations and ensuring an interpretable final report. Our evaluations on the DARPA TC3, OpTC, and NODLINK datasets show that OCR-APT outperforms state-of-the-art systems in both detection accuracy and alert interpretability. Moreover, OCR-APT reconstructs human-like reports that comprehensively capture the attack story.

---

### MAGPIE: A benchmark for Multi-AGent contextual PrIvacy Evaluation

Authors: Gurusha Juneja, Jayanth Naga Sai Pasupulati, Alon Albalak, Wenyue Hua, William Yang Wang
Published: 2025-10-16
Categories: cs.CR, cs.CL
arXiv: https://arxiv.org/abs/2510.15186v1

A core challenge for autonomous LLM agents in collaborative settings is balancing robust privacy understanding and preservation alongside task efficacy. Existing privacy benchmarks only focus on simplistic, single-turn interactions where private information can be trivially omitted without affecting task outcomes. In this paper, we introduce MAGPIE (Multi-AGent contextual PrIvacy Evaluation), a novel benchmark of 200 high-stakes tasks designed to evaluate privacy understanding and preservation in multi-agent collaborative, non-adversarial scenarios. MAGPIE integrates private information as essential for task resolution, forcing agents to balance effective collaboration with strategic information control. Our evaluation reveals that state-of-the-art agents, including GPT-5 and Gemini 2.5-Pro, exhibit significant privacy leakage, with Gemini 2.5-Pro leaking up to 50.7% and GPT-5 up to 35.1% of the sensitive information even when explicitly instructed not to. Moreover, these agents struggle to achieve consensus or task completion and often resort to undesirable behaviors such as manipulation and power-seeking (e.g., Gemini 2.5-Pro demonstrating manipulation in 38.2% of the cases). These findings underscore that current LLM agents lack robust privacy understanding and are not yet adequately aligned to simultaneously preserve privacy and maintain effective collaboration in complex environments.

---

### An Advanced Two-Stage Model with High Sensitivity and Generalizability for Prediction of Hip Fracture Risk Using Multiple Datasets

Authors: Shuo Sun, Meiling Zhou, Chen Zhao, Joyce H. Keyak, Nancy E. Lane, Jeffrey D. Deng, Kuan-Jui Su, Hui Shen, Hong-Wen Deng, Kui Zhang, Weihua Zhou
Published: 2025-10-16
Categories: cs.LG, physics.med-ph
arXiv: https://arxiv.org/abs/2510.15179v1

Hip fractures are a major cause of disability, mortality, and healthcare burden in older adults, underscoring the need for early risk assessment. However, commonly used tools such as the DXA T-score and FRAX often lack sensitivity and miss individuals at high risk, particularly those without prior fractures or with osteopenia. To address this limitation, we propose a sequential two-stage model that integrates clinical and imaging information to improve prediction accuracy. Using data from the Osteoporotic Fractures in Men Study (MrOS), the Study of Osteoporotic Fractures (SOF), and the UK Biobank, Stage 1 (Screening) employs clinical, demographic, and functional variables to estimate baseline risk, while Stage 2 (Imaging) incorporates DXA-derived features for refinement. The model was rigorously validated through internal and external testing, showing consistent performance and adaptability across cohorts. Compared to T-score and FRAX, the two-stage framework achieved higher sensitivity and reduced missed cases, offering a cost-effective and personalized approach for early hip fracture risk assessment. Keywords: Hip Fracture, Two-Stage Model, Risk Prediction, Sensitivity, DXA, FRAX

---

### Finding geodesics with the Deep Ritz method

Authors: Conor Rowan
Published: 2025-10-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.15177v2

Geodesic problems involve computing trajectories between prescribed initial and final states to minimize a user-defined measure of distance, cost, or energy. They arise throughout physics and engineering -- for instance, in determining optimal paths through complex environments, modeling light propagation in refractive media, and the study of spacetime trajectories in control theory and general relativity. Despite their ubiquity, the scientific machine learning (SciML) community has given relatively little attention to investigating its methods in the context of these problems. In this work, we argue that given their simple geometry, variational structure, and natural nonlinearity, geodesic problems are particularly well-suited for the Deep Ritz method. We substantiate this claim with four numerical examples drawn from path planning, optics, solid mechanics, and generative modeling. Our goal is not to provide an exhaustive study of geodesic problems, but rather to identify a promising application of the Deep Ritz method and a fruitful direction for future SciML research.

---

### A simple mean field model of feature learning

Authors: Niclas Göring, Chris Mingard, Yoonsoo Nam, Ard Louis
Published: 2025-10-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.15174v1

Feature learning (FL), where neural networks adapt their internal representations during training, remains poorly understood. Using methods from statistical physics, we derive a tractable, self-consistent mean-field (MF) theory for the Bayesian posterior of two-layer non-linear networks trained with stochastic gradient Langevin dynamics (SGLD). At infinite width, this theory reduces to kernel ridge regression, but at finite width it predicts a symmetry breaking phase transition where networks abruptly align with target functions. While the basic MF theory provides theoretical insight into the emergence of FL in the finite-width regime, semi-quantitatively predicting the onset of FL with noise or sample size, it substantially underestimates the improvements in generalisation after the transition. We trace this discrepancy to a key mechanism absent from the plain MF description: \textit{self-reinforcing input feature selection}. Incorporating this mechanism into the MF theory allows us to quantitatively match the learning curves of SGLD-trained networks and provides mechanistic insight into FL.

---

### Policy Transfer for Continuous-Time Reinforcement Learning: A (Rough) Differential Equation Approach

Authors: Xin Guo, Zijiu Lyu
Published: 2025-10-16
Categories: cs.LG, math.OC
arXiv: https://arxiv.org/abs/2510.15165v3

This paper studies policy transfer, one of the well-known transfer learning techniques adopted in large language models, for continuous-time reinforcement learning problems. In the case of continuous-time linear-quadratic systems with Shannon's entropy regularization, we fully exploit the Gaussian structure of their optimal policy and the stability of their associated Riccati equations. In the general case where the system has possibly non-linear and bounded dynamics, the key technical component is the stability of diffusion SDEs which is established by invoking the rough path theory. Our work provides the first theoretical proof of policy transfer for continuous-time RL: an optimal policy learned for one RL problem can be used to initialize to search for a near-optimal policy for another closely related RL problem, while achieving (at least) the same rate of convergence for the original algorithm. As a byproduct of our analysis, we derive the stability of a concrete class of continuous-time score-based diffusion models via their connection with LQRs. To illustrate the benefit of policy transfer for RL, we propose a novel policy learning algorithm for continuous-time LQRs, which achieves global linear convergence and local super-linear convergence.

---

### Hyperparameter Optimization and Reproducibility in Deep Learning Model Training

Authors: Usman Afzaal, Ziyu Su, Usama Sajjad, Hao Lu, Mostafa Rezapour, Metin Nafi Gurcan, Muhammad Khalid Khan Niazi
Published: 2025-10-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.15164v2

Reproducibility remains a critical challenge in foundation model training for histopathology, often hindered by software randomness, hardware non-determinism, and inconsistent hyperparameter reporting. To investigate these issues, we trained a CLIP model on the QUILT-1M dataset and systematically evaluated the impact of different hyperparameter settings and augmentation strategies across three downstream histopathology datasets (PatchCamelyon, LC25000-Lung, and LC25000-Colon). Despite variability across runs, we identified clear trends: RandomResizedCrop values of 0.7-0.8 outperformed more aggressive (0.6) or conservative (0.9) settings, distributed training without local loss improved stability, and learning rates below 5.0e-5 consistently degraded performance across all datasets. The LC25000 (Colon) dataset consistently provided the most reproducible benchmark. These findings highlight that reproducibility in computational pathology depends not only on transparent documentation but also on carefully chosen experimental configurations, and we provide practical rules to guide future efforts in developing reproducible foundation models for digital pathology.

---

### Train a Unified Multimodal Data Quality Classifier with Synthetic Data

Authors: Weizhi Wang, Rongmei Lin, Shiyang Li, Colin Lockard, Ritesh Sarkhel, Sanket Lokegaonkar, Jingbo Shang, Xifeng Yan, Nasser Zalmout, Xian Li
Published: 2025-10-16
Categories: cs.CV, cs.CL
arXiv: https://arxiv.org/abs/2510.15162v1

The Multimodal Large Language Models (MLLMs) are continually pre-trained on a mixture of image-text caption data and interleaved document data, while the high-quality data filtering towards image-text interleaved document data is under-explored. We propose to train an efficient MLLM as a Unified Mulitmodal Data Quality Classifier to Filter both high-quality image-text caption and interleaved data (UniFilter). To address the challenge of collecting diverse labeled multimodal data, we introduce a semi-synthetic approach that leverages readily available raw images and generates corresponding text across four quality levels. This method enables efficient creation of sample-score pairs for both caption and interleaved document data to train UniFilter. We apply UniFilter to curate high-quality caption data from DataComp caption dataset and interleaved data from the OBELICS image-text interleaved dataset. MLLMs pre-trained on the filtered data demonstrate significantly enhanced capabilities compared to those trained on baseline-filtered data, achieving stronger zero-shot reasoning and in-context learning capabilities. After visual supervised fine-tuning, these UniFilter-induced MLLMs achieve stronger performance on various benchmarks, highlighting the downstream benefits of high-quality multimodal pre-training. We release the synthetic training data used for training UniFilter, the UniFilter model checkpoints, and the high-quality interleaved document subset OBELICS-HQ, curated by UniFilter, to the community for reproduction and further development.

---

### XModBench: Benchmarking Cross-Modal Capabilities and Consistency in Omni-Language Models

Authors: Xingrui Wang, Jiang Liu, Chao Huang, Xiaodong Yu, Ze Wang, Ximeng Sun, Jialian Wu, Alan Yuille, Emad Barsoum, Zicheng Liu
Published: 2025-10-16
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.15148v2

Omni-modal large language models (OLLMs) aim to unify audio, vision, and text understanding within a single framework. While existing benchmarks primarily evaluate general cross-modal question-answering ability, it remains unclear whether OLLMs achieve modality-invariant reasoning or exhibit modality-specific biases. We introduce XModBench, a large-scale tri-modal benchmark explicitly designed to measure cross-modal consistency. XModBench comprises 60,828 multiple-choice questions spanning five task families and systematically covers all six modality compositions in question-answer pairs, enabling fine-grained diagnosis of an OLLM's modality-invariant reasoning, modality disparity, and directional imbalance. Experiments show that even the strongest model, Gemini 2.5 Pro, (i) struggles with spatial and temporal reasoning, achieving less than 60% accuracy, (ii) reveals persistent modality disparities, with performance dropping substantially when the same semantic content is conveyed through audio rather than text, and (iii) shows systematic directional imbalance, exhibiting lower consistency when vision serves as context compared to text. These findings indicate that current OLLMs remain far from truly modality-invariant reasoning and position XModBench as a fundamental diagnostic tool for evaluating and improving cross-modal competence. All data and evaluation tools will be available at https://xingruiwang.github.io/projects/XModBench/.

---

### HugAgent: A Human Simulation Benchmark for Individual-Level Reasoning

Authors: Chance Jiajie Li, Zhenze Mo, Yuhan Tang, Ao Qu, Jiayi Wu, Kaiya Ivy Zhao, Yulu Gan, Jie Fan, Jiangbo Yu, Hang Jiang, Paul Pu Liang, Jinhua Zhao et al.
Published: 2025-10-16
Categories: cs.AI, cs.CL, cs.CY
arXiv: https://arxiv.org/abs/2510.15144v4

Simulating human reasoning in open-ended tasks has long been a central aspiration in AI and cognitive science. While large language models now approximate human responses at scale, they remain tuned to population-level consensus, often erasing the individuality of reasoning styles and belief trajectories. To advance the vision of more human-like reasoning in machines, we introduce HugAgent (HUman-Grounded AGENT Benchmark), which rethinks human reasoning simulation along three dimensions: (i) from averaged to individualized reasoning, (ii) from behavioral mimicry to cognitive alignment, and (iii) from vignette-based to open-ended data. The benchmark evaluates whether a model can predict a specific person's behavioral responses and the underlying reasoning dynamics in out-of-distribution scenarios, given partial evidence of their prior views. HugAgent combines structured questionnaires with semi-structured think-aloud interviews to collect ecologically valid belief states, belief updates, and reasoning traces from human participants. Our experiments reveal a clear asymmetry: models recover a person's belief state from their own context reasonably well, but struggle to predict belief updates under intervention. Cross-person and cross-domain controls trace this gap to associative matching within a topic rather than identity-consistent reasoning, suggesting that progress requires better-calibrated change detection, not simply more context. We scope the benchmark to self-reported belief reasoning in three policy domains: healthcare, surveillance, and zoning. The benchmark, along with its complete data collection pipeline and companion chatbot, is open-sourced as HugAgent (https://github.com/jajamoa/HugAgent) and TraceYourThinking (https://github.com/jajamoa/trace-your-thinking).

---

### Manifold Dimension Estimation via Local Graph Structure

Authors: Zelong Bi, Pierre Lafaye de Micheaux
Published: 2025-10-16
Categories: stat.ML, cs.LG, stat.AP
arXiv: https://arxiv.org/abs/2510.15141v6

Most existing manifold dimension estimators rely on the assumption that the underlying manifold is locally flat within the neighborhoods under consideration. More recently, curvature-adjusted principal component analysis (CA-PCA) has emerged as a powerful alternative by explicitly accounting for the manifold's curvature. Motivated by these ideas, we propose a manifold dimension estimation framework that captures the local graph structure of the manifold through regression on local PCA coordinates. Within this framework, we introduce two representative estimators: quadratic embedding (QE) and total least squares (TLS). Experiments on both synthetic and real-world datasets demonstrate that these methods perform competitively with, and often outperform, state-of-the-art approaches.

---

### Fourier Transform Multiple Instance Learning for Whole Slide Image Classification

Authors: Anthony Bilic, Guangyu Sun, Ming Li, Md Sanzid Bin Hossain, Yu Tian, Wei Zhang, Laura Brattain, Dexter Hadley, Chen Chen
Published: 2025-10-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.15138v2

Whole Slide Image (WSI) classification relies on Multiple Instance Learning (MIL) with spatial patch features, yet existing methods struggle to capture global dependencies due to the immense size of WSIs and the local nature of patch embeddings. This limitation hinders the modeling of coarse structures essential for robust diagnostic prediction. We propose Fourier Transform Multiple Instance Learning (FFT-MIL), a framework that augments MIL with a frequency-domain branch to provide compact global context. Low-frequency crops are extracted from WSIs via the Fast Fourier Transform and processed through a modular FFT-Block composed of convolutional layers and Min-Max normalization to mitigate the high variance of frequency data. The learned global frequency feature is fused with spatial patch features through lightweight integration strategies, enabling compatibility with diverse MIL architectures. FFT-MIL was evaluated across six state-of-the-art MIL methods on three public datasets (BRACS, LUAD, and IMP). Integration of the FFT-Block improved macro F1 scores by an average of 3.51% and AUC by 1.51%, demonstrating consistent gains across architectures and datasets. These results establish frequency-domain learning as an effective and efficient mechanism for capturing global dependencies in WSI classification, complementing spatial features and advancing the scalability and accuracy of MIL-based computational pathology.

---

### Predicting the Unpredictable: Reproducible BiLSTM Forecasting of Incident Counts in the Global Terrorism Database (GTD)

Authors: Oluwasegun Adegoke
Published: 2025-10-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.15136v1

We study short-horizon forecasting of weekly terrorism incident counts using the Global Terrorism Database (GTD, 1970--2016). We build a reproducible pipeline with fixed time-based splits and evaluate a Bidirectional LSTM (BiLSTM) against strong classical anchors (seasonal-naive, linear/ARIMA) and a deep LSTM-Attention baseline. On the held-out test set, the BiLSTM attains RMSE 6.38, outperforming LSTM-Attention (9.19; +30.6\%) and a linear lag-regression baseline (+35.4\% RMSE gain), with parallel improvements in MAE and MAPE. Ablations varying temporal memory, training-history length, spatial grain, lookback size, and feature groups show that models trained on long historical data generalize best; a moderate lookback (20--30 weeks) provides strong context; and bidirectional encoding is critical for capturing both build-up and aftermath patterns within the window. Feature-group analysis indicates that short-horizon structure (lagged counts and rolling statistics) contributes most, with geographic and casualty features adding incremental lift. We release code, configs, and compact result tables, and provide a data/ethics statement documenting GTD licensing and research-only use. Overall, the study offers a transparent, baseline-beating reference for GTD incident forecasting.

---

### FarsiMCQGen: a Persian Multiple-choice Question Generation Framework

Authors: Mohammad Heydari Rad, Rezvan Afari, Saeedeh Momtazi
Published: 2025-10-16
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.15134v1

Multiple-choice questions (MCQs) are commonly used in educational testing, as they offer an efficient means of evaluating learners' knowledge. However, generating high-quality MCQs, particularly in low-resource languages such as Persian, remains a significant challenge. This paper introduces FarsiMCQGen, an innovative approach for generating Persian-language MCQs. Our methodology combines candidate generation, filtering, and ranking techniques to build a model that generates answer choices resembling those in real MCQs. We leverage advanced methods, including Transformers and knowledge graphs, integrated with rule-based approaches to craft credible distractors that challenge test-takers. Our work is based on data from Wikipedia, which includes general knowledge questions. Furthermore, this study introduces a novel Persian MCQ dataset comprising 10,289 questions. This dataset is evaluated by different state-of-the-art large language models (LLMs). Our results demonstrate the effectiveness of our model and the quality of the generated dataset, which has the potential to inspire further research on MCQs.

---

### A Simple Method for PMF Estimation on Large Supports

Authors: Alex Shtoff
Published: 2025-10-16
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.15132v1

We study nonparametric estimation of a probability mass function (PMF) on a large discrete support, where the PMF is multi-modal and heavy-tailed. The core idea is to treat the empirical PMF as a signal on a line graph and apply a data-dependent low-pass filter. Concretely, we form a symmetric tri-diagonal operator, the path graph Laplacian perturbed with a diagonal matrix built from the empirical PMF, then compute the eigenvectors, corresponding to the smallest feq eigenvalues. Projecting the empirical PMF onto this low dimensional subspace produces a smooth, multi-modal estimate that preserves coarse structure while suppressing noise. A light post-processing step of clipping and re-normalizing yields a valid PMF. Because we compute the eigenpairs of a symmetric tridiagonal matrix, the computation is reliable and runs time and memory proportional to the support times the dimension of the desired low-dimensional supspace. We also provide a practical, data-driven rule for selecting the dimension based on an orthogonal-series risk estimate, so the method "just works" with minimal tuning. On synthetic and real heavy-tailed examples, the approach preserves coarse structure while suppressing sampling noise, compares favorably to logspline and Gaussian-KDE baselines in the intended regimes. However, it has known failure modes (e.g., abrupt discontinuities). The method is short to implement, robust across sample sizes, and suitable for automated pipelines and exploratory analysis at scale because of its reliability and speed.

---

### Towards Error Centric Intelligence I, Beyond Observational Learning

Authors: Marcus A. Thomas
Published: 2025-10-16
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.15128v1

We argue that progress toward AGI is theory limited rather than data or scale limited. Building on the critical rationalism of Popper and Deutsch, we challenge the Platonic Representation Hypothesis. Observationally equivalent worlds can diverge under interventions, so observational adequacy alone cannot guarantee interventional competence. We begin by laying foundations, definitions of knowledge, learning, intelligence, counterfactual competence and AGI, and then analyze the limits of observational learning that motivate an error centric shift. We recast the problem as three questions about how explicit and implicit errors evolve under an agent's actions, which errors are unreachable within a fixed hypothesis space, and how conjecture and criticism expand that space. From these questions we propose Causal Mechanics, a mechanisms first program in which hypothesis space change is a first class operation and probabilistic structure is used when useful rather than presumed. We advance structural principles that make error discovery and correction tractable, including a differential Locality and Autonomy Principle for modular interventions, a gauge invariant form of Independent Causal Mechanisms for separability, and the Compositional Autonomy Principle for analogy preservation, together with actionable diagnostics. The aim is a scaffold for systems that can convert unreachable errors into reachable ones and correct them.

---

### Inferring Relative Consequences of Mechanical Ventilation from Observational Data Using Game-Based Comparisons

Authors: David J. Albers, Tell D. Bennett, Jana de Wiljes, George Hripcsak, Bradford J. Smith, Peter D. Sottile, J. N. Stroh
Published: 2025-10-16
Categories: q-bio.QM, cs.LG, math.OC
arXiv: https://arxiv.org/abs/2510.15127v4

Identifying the effects of mechanical ventilation (MV) protocols in critical care requires analyzing data from heterogeneous patient-ventilator systems in the clinical decision-making environment. Multiscale interactions among these coupled components generate a high-dimensional state space that remains sparsely sampled despite extensive data collection. Analysis of existing data is essential for understanding current respiratory management practices and generating testable hypotheses about improvement. The scale and complexity of available data motivate the use of reinforcement learning (RL) to explore data-consistent counterfactual trajectories. However, formulating RL in practical applications requires a spatiotemporally dependent reward process that defines state-to-consequence relationships, their context dependence, and the delays over which consequences emerge. These poorly understood elements are not known \emph{a priori} and inferred from data via hypotheses. To that end, categorized observed states are contrasted according to their relative consequences by solving a game-based inverse problem that identifies a comparison model required for downstream probabilistic and stochastic methods such as reinforcement learning for seeking MV optimization and personalization. The inverted-game inference is validated on synthetic data to reveal potential caveats before proceeding to real-world ICU data applications that expose complexities of the data-generating process. Clinical data applications revealed that both breath-type consequences and their relative ordering are inherently context- and time-dependent, varying across patient subgroups, time, and comparison quantities, and effect timescale. The discussion includes potential developments toward a state transition model for simulating the effects of MV management actions using empirical data and game-inferred comparisons.

---

### Iterative Topic Taxonomy Induction with LLMs: A Case Study of Electoral Advertising

Authors: Alexander Brady, Tunazzina Islam
Published: 2025-10-16
Categories: cs.CL, cs.AI, cs.CY, cs.LG, cs.SI
arXiv: https://arxiv.org/abs/2510.15125v3

Social media platforms play a pivotal role in shaping political discourse, but the scale and rapid evolution of online content make systematic analysis difficult. We introduce an end-to-end framework for inducing an interpretable topic taxonomy from unlabeled text corpora. The framework combines embedding-based clustering with iterative large language model (LLM) inference to construct a topic taxonomy without requiring predefined labels or seed topics. It first synthesizes candidate topics from document clusters and then uses the resulting taxonomy to assign consistent topic labels across clusters. We evaluate the approach through a case study of political advertising ahead of the 2024 U.S. presidential election. We use the induced taxonomy to support downstream analyses of issue prevalence, moral framing, advertising spend, and demographic exposure patterns. These results suggest that iterative taxonomy construction can provide a scalable and interpretable approach to organizing large unlabeled text corpora while supporting substantive downstream analysis.

---

### Procedural Game Level Design with Deep Reinforcement Learning

Authors: Miraç Buğra Özkan
Published: 2025-10-16
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.15120v1

Procedural content generation (PCG) has become an increasingly popular technique in game development, allowing developers to generate dynamic, replayable, and scalable environments with reduced manual effort. In this study, a novel method for procedural level design using Deep Reinforcement Learning (DRL) within a Unity-based 3D environment is proposed. The system comprises two agents: a hummingbird agent, acting as a solver, and a floating island agent, responsible for generating and placing collectible objects (flowers) on the terrain in a realistic and context-aware manner. The hummingbird is trained using the Proximal Policy Optimization (PPO) algorithm from the Unity ML-Agents toolkit. It learns to navigate through the terrain efficiently, locate flowers, and collect them while adapting to the ever-changing procedural layout of the island. The island agent is also trained using the Proximal Policy Optimization (PPO) algorithm. It learns to generate flower layouts based on observed obstacle positions, the hummingbird's initial state, and performance feedback from previous episodes. The interaction between these agents leads to emergent behavior and robust generalization across various environmental configurations. The results demonstrate that the approach not only produces effective and efficient agent behavior but also opens up new opportunities for autonomous game level design driven by machine learning. This work highlights the potential of DRL in enabling intelligent agents to both generate and solve content in virtual environments, pushing the boundaries of what AI can contribute to creative game development processes.

---

### Deep generative priors for 3D brain analysis

Authors: Ana Lawry Aguila, Dina Zemlyanker, You Cheng, Sudeshna Das, Daniel C. Alexander, Oula Puonti, Annabel Sorby-Adams, W. Taylor Kimberly, Juan Eugenio Iglesias
Published: 2025-10-16
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.15119v2

Diffusion models have recently emerged as powerful generative models in medical imaging. However, it remains a major challenge to combine these data-driven models with domain knowledge to guide brain imaging problems. In neuroimaging, Bayesian inverse problems have long provided a successful framework for inference tasks, where incorporating domain knowledge of the imaging process enables robust performance without requiring extensive training data. However, the anatomical modeling component of these approaches typically relies on classical mathematical priors that often fail to capture the complex structure of brain anatomy. In this work, we present the first general-purpose application of diffusion models as priors for solving a wide range of medical imaging inverse problems. Our approach leverages a score-based diffusion prior trained extensively on diverse brain MRI data, paired with flexible forward models that capture common image processing tasks such as super-resolution, bias field correction, inpainting, and combinations thereof. We further demonstrate how our framework can refine outputs from existing deep learning methods to improve anatomical fidelity. Experiments on heterogeneous clinical and research MRI data show that our method achieves state-of-the-art performance producing consistent, high-quality solutions without requiring paired training datasets. These results highlight the potential of diffusion priors as versatile tools for brain MRI analysis.

---

### Polarization based direction of arrival estimation using a radio interferometric array

Authors: Sarod Yatawatta
Published: 2025-10-16
Categories: astro-ph.IM, cs.LG
arXiv: https://arxiv.org/abs/2510.15116v2

Direction of arrival (DOA) estimation is mostly performed using specialized arrays that have carefully designed receiver spacing and layouts to match the operating frequency range. In contrast, radio interferometric arrays are designed to optimally sample the Fourier space data for making high quality images of the sky. Therefore, using existing radio interferometric arrays (with arbitrary geometry and wide frequency variation) for DOA estimation is practically infeasible except by using images made by such interferometers. In this paper, we focus on low cost DOA estimation without imaging, using a subset of a radio interferometric array, using a fraction of the data collected by the full array, and, enabling early determination of DOAs. The proposed method is suitable for transient and low duty cycle source detection. Moreover, the proposed method is an ideal follow-up step to online radio frequency interference (RFI) mitigation, enabling the early estimation of the DOA of the detected RFI.

---

### Measuring the Effect of Disfluency in Multilingual Knowledge Probing Benchmarks

Authors: Kirill Semenov, Rico Sennrich
Published: 2025-10-16
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.15115v1

For multilingual factual knowledge assessment of LLMs, benchmarks such as MLAMA use template translations that do not take into account the grammatical and semantic information of the named entities inserted in the sentence. This leads to numerous instances of ungrammaticality or wrong wording of the final prompts, which complicates the interpretation of scores, especially for languages that have a rich morphological inventory. In this work, we sample 4 Slavic languages from the MLAMA dataset and compare the knowledge retrieval scores between the initial (templated) MLAMA dataset and its sentence-level translations made by Google Translate and ChatGPT. We observe a significant increase in knowledge retrieval scores, and provide a qualitative analysis for possible reasons behind it. We also make an additional analysis of 5 more languages from different families and see similar patterns. Therefore, we encourage the community to control the grammaticality of highly multilingual datasets for higher and more interpretable results, which is well approximated by whole sentence translation with neural MT or LLM systems. The dataset and all related code is published at the Github repository: https://github.com/ZurichNLP/Fluent-mLAMA.

---

### DLER: Doing Length pEnalty Right - Incentivizing More Intelligence per Token via Reinforcement Learning

Authors: Shih-Yang Liu, Xin Dong, Ximing Lu, Shizhe Diao, Mingjie Liu, Min-Hung Chen, Hongxu Yin, Yu-Chiang Frank Wang, Kwang-Ting Cheng, Yejin Choi, Jan Kautz, Pavlo Molchanov
Published: 2025-10-16
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.15110v1

Reasoning language models such as OpenAI-o1, DeepSeek-R1, and Qwen achieve strong performance via extended chains of thought but often generate unnecessarily long outputs. Maximizing intelligence per token--accuracy relative to response length--remains an open problem. We revisit reinforcement learning (RL) with the simplest length penalty--truncation--and show that accuracy degradation arises not from the lack of sophisticated penalties but from inadequate RL optimization. We identify three key challenges: (i) large bias in advantage estimation, (ii) entropy collapse, and (iii) sparse reward signal. We address them with Doing Length pEnalty Right (DLER), a training recipe combining batch-wise reward normalization, higher clipping, dynamic sampling, and a simple truncation length penalty. DLER achieves state-of-the-art accuracy--efficiency trade-offs, cutting output length by over 70 percent while surpassing all previous baseline accuracy. It also improves test-time scaling: compared to DeepSeek-R1-7B, DLER-7B generates multiple concise responses in parallel with 28 percent higher accuracy and lower latency. We further introduce Difficulty-Aware DLER, which adaptively tightens truncation on easier questions for additional efficiency gains. We also propose an update-selective merging method that preserves baseline accuracy while retaining the concise reasoning ability of the DLER model, which is useful for scenarios where RL training data is scarce.

---

### Targeted Attacks and Defenses for Distributed Federated Learning in Vehicular Networks

Authors: Utku Demir, Tugba Erpek, Yalin E. Sagduyu, Sastry Kompella, Mengran Xue
Published: 2025-10-16
Categories: cs.NI, cs.AI, cs.DC, cs.LG, eess.SP
arXiv: https://arxiv.org/abs/2510.15109v1

In emerging networked systems, mobile edge devices such as ground vehicles and unmanned aerial system (UAS) swarms collectively aggregate vast amounts of data to make machine learning decisions such as threat detection in remote, dynamic, and infrastructure-constrained environments where power and bandwidth are scarce. Federated learning (FL) addresses these constraints and privacy concerns by enabling nodes to share local model weights for deep neural networks instead of raw data, facilitating more reliable decision-making than individual learning. However, conventional FL relies on a central server to coordinate model updates in each learning round, which imposes significant computational burdens on the central node and may not be feasible due to the connectivity constraints. By eliminating dependence on a central server, distributed federated learning (DFL) offers scalability, resilience to node failures, learning robustness, and more effective defense strategies. Despite these advantages, DFL remains vulnerable to increasingly advanced and stealthy cyberattacks. In this paper, we design sophisticated targeted training data poisoning and backdoor (Trojan) attacks, and characterize the emerging vulnerabilities in a vehicular network. We analyze how DFL provides resilience against such attacks compared to individual learning and present effective defense mechanisms to further strengthen DFL against the emerging cyber threats.

---

### PoTS: Proof-of-Training-Steps for Backdoor Detection in Large Language Models

Authors: Issam Seddik, Sami Souihi, Mohamed Tamaazousti, Sara Tucci Piergiovanni
Published: 2025-10-16
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2510.15106v1

As Large Language Models (LLMs) gain traction across critical domains, ensuring secure and trustworthy training processes has become a major concern. Backdoor attacks, where malicious actors inject hidden triggers into training data, are particularly insidious and difficult to detect. Existing post-training verification solutions like Proof-of-Learning are impractical for LLMs due to their requirement for full retraining, lack of robustness against stealthy manipulations, and inability to provide early detection during training. Early detection would significantly reduce computational costs. To address these limitations, we introduce Proof-of-Training Steps, a verification protocol that enables an independent auditor (Alice) to confirm that an LLM developer (Bob) has followed the declared training recipe, including data batches, architecture, and hyperparameters. By analyzing the sensitivity of the LLMs' language modeling head (LM-Head) to input perturbations, our method can expose subtle backdoor injections or deviations in training. Even with backdoor triggers in up to 10 percent of the training data, our protocol significantly reduces the attacker's ability to achieve a high attack success rate (ASR). Our method enables early detection of attacks at the injection step, with verification steps being 3x faster than training steps. Our results highlight the protocol's potential to enhance the accountability and security of LLM development, especially against insider threats.

---

### TGT: Text-Grounded Trajectories for Locally Controlled Video Generation

Authors: Guofeng Zhang, Angtian Wang, Jacob Zhiyuan Fang, Liming Jiang, Haotian Yang, Bo Liu, Yiding Yang, Guang Chen, Longyin Wen, Alan Yuille, Chongyang Ma
Published: 2025-10-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.15104v1

Text-to-video generation has advanced rapidly in visual fidelity, whereas standard methods still have limited ability to control the subject composition of generated scenes. Prior work shows that adding localized text control signals, such as bounding boxes or segmentation masks, can help. However, these methods struggle in complex scenarios and degrade in multi-object settings, offering limited precision and lacking a clear correspondence between individual trajectories and visual entities as the number of controllable objects increases. We introduce Text-Grounded Trajectories (TGT), a framework that conditions video generation on trajectories paired with localized text descriptions. We propose Location-Aware Cross-Attention (LACA) to integrate these signals and adopt a dual-CFG scheme to separately modulate local and global text guidance. In addition, we develop a data processing pipeline that produces trajectories with localized descriptions of tracked entities, and we annotate two million high quality video clips to train TGT. Together, these components enable TGT to use point trajectories as intuitive motion handles, pairing each trajectory with text to control both appearance and motion. Extensive experiments show that TGT achieves higher visual quality, more accurate text alignment, and improved motion controllability compared with prior approaches. Website: https://textgroundedtraj.github.io.

---

### Continual Learning via Sparse Memory Finetuning

Authors: Jessy Lin, Luke Zettlemoyer, Gargi Ghosh, Wen-Tau Yih, Aram Markosyan, Vincent-Pierre Berges, Barlas Oğuz
Published: 2025-10-16
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.15103v1

Modern language models are powerful, but typically static after deployment. A major obstacle to building models that continually learn over time is catastrophic forgetting, where updating on new data erases previously acquired capabilities. Motivated by the intuition that mitigating forgetting is challenging because trainable parameters are shared across all tasks, we investigate whether sparse parameter updates can enable learning without catastrophic forgetting. We introduce sparse memory finetuning, leveraging memory layer models (Berges et al., 2024), which are sparsely updated by design. By updating only the memory slots that are highly activated by a new piece of knowledge relative to usage on pretraining data, we reduce interference between new knowledge and the model's existing capabilities. We evaluate learning and forgetting compared to full finetuning and parameter-efficient finetuning with LoRA on two question answering tasks. We find that sparse memory finetuning learns new knowledge while exhibiting substantially less forgetting: while NaturalQuestions F1 drops by 89% after full finetuning on new facts and 71% with LoRA, sparse memory finetuning yields only an 11% drop with the same level of new knowledge acquisition. Our results suggest sparsity in memory layers offers a promising path toward continual learning in large language models.

---

### Operator Flow Matching for Timeseries Forecasting

Authors: Yolanne Yi Ran Lee, Kyriakos Flouris
Published: 2025-10-16
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.15101v1

Forecasting high-dimensional, PDE-governed dynamics remains a core challenge for generative modeling. Existing autoregressive and diffusion-based approaches often suffer cumulative errors and discretisation artifacts that limit long, physically consistent forecasts. Flow matching offers a natural alternative, enabling efficient, deterministic sampling. We prove an upper bound on FNO approximation error and propose TempO, a latent flow matching model leveraging sparse conditioning with channel folding to efficiently process 3D spatiotemporal fields using time-conditioned Fourier layers to capture multi-scale modes with high fidelity. TempO outperforms state-of-the-art baselines across three benchmark PDE datasets, and spectral analysis further demonstrates superior recovery of multi-scale dynamics, while efficiency studies highlight its parameter- and memory-light design compared to attention-based or convolutional regressors.

---

### OpenEstimate: Evaluating LLMs on Reasoning Under Uncertainty with Real-World Data

Authors: Alana Renda, Jillian Ross, Michael Cafarella, Jacob Andreas
Published: 2025-10-16
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.15096v2

Real-world settings where language models (LMs) are deployed -- in domains spanning healthcare, finance, and other forms of knowledge work -- require models to grapple with incomplete information and reason under uncertainty. Yet most LM evaluations focus on problems with well-defined answers and success criteria. This gap exists in part because natural problems involving uncertainty are difficult to construct: given that LMs have access to most of the same knowledge as humans, it is non-trivial to design questions for which LMs will struggle to produce correct answers, but which humans can answer reliably. As a result, LM performance on reasoning under uncertainty remains poorly characterized. To address this gap, we introduce OpenEstimate, an extensible, multi-domain benchmark for evaluating LMs on numerical estimation tasks that require models to synthesize significant amounts of background information and express predictions as probabilistic priors. We assess these priors for accuracy and calibration, quantifying their usefulness relative to samples from the true distribution of interest. Across six frontier LMs, we find that LM-elicited priors are often inaccurate and overconfident. Performance improves modestly depending on how uncertainty is elicited from the model, but is largely unaffected by changes in sampling strategy, reasoning effort, or prompt design. The OpenEstimate benchmark thus offers a challenging evaluation for frontier LMs and a platform for developing models that are better at probabilistic estimation and reasoning under uncertainty.

---

### Beyond Outcome-Based Imperfect-Recall: Higher-Resolution Abstractions for Imperfect-Information Games

Authors: Yanchang Fu, Qiyue Yin, Shengda Liu, Pei Xu, Kaiqi Huang
Published: 2025-10-16
Categories: cs.GT, cs.AI
arXiv: https://arxiv.org/abs/2510.15094v1

Hand abstraction is crucial for scaling imperfect-information games (IIGs) such as Texas Hold'em, yet progress is limited by the lack of a formal task model and by evaluations that require resource-intensive strategy solving. We introduce signal observation ordered games (SOOGs), a subclass of IIGs tailored to hold'em-style games that cleanly separates signal from player action sequences, providing a precise mathematical foundation for hand abstraction. Within this framework, we define a resolution bound-an information-theoretic upper bound on achievable performance under a given signal abstraction. Using the bound, we show that mainstream outcome-based imperfect-recall algorithms suffer substantial losses by arbitrarily discarding historical information; we formalize this behavior via potential-aware outcome Isomorphism (PAOI) and prove that PAOI characterizes their resolution bound. To overcome this limitation, we propose full-recall outcome isomorphism (FROI), which integrates historical information to raise the bound and improve policy quality. Experiments on hold'em-style benchmarks confirm that FROI consistently outperforms outcome-based imperfect-recall baselines. Our results provide a unified formal treatment of hand abstraction and practical guidance for designing higher-resolution abstractions in IIGs.

---

### Fast spectral separation method for kinetic equation with anisotropic non-stationary collision operator retaining micro-model fidelity

Authors: Yue Zhao, Huan Lei
Published: 2025-10-16
Categories: math.NA, physics.comp-ph, stat.ML
arXiv: https://arxiv.org/abs/2510.15093v2

We present a generalized, data-driven collisional operator for one-component plasmas, learned from molecular dynamics simulations, to extend the collisional kinetic model beyond the weakly coupled regime. The proposed operator features an anisotropic, non-stationary collision kernel that accounts for particle correlations typically neglected in classical Landau formulations. To enable efficient numerical evaluation, we develop a fast spectral separation method that represents the kernel as a low-rank tensor product of univariate basis functions. This formulation admits an $O(N \log N)$ algorithm via fast Fourier transforms and preserves key physical properties, including discrete conservation laws and the H-theorem, through a structure-preserving central difference discretization. Numerical experiments demonstrate that the proposed model accurately captures plasma dynamics in the moderately coupled regime beyond the standard Landau model while maintaining high computational efficiency and structure-preserving properties.

---

### DMRetriever: A Family of Models for Improved Text Retrieval in Disaster Management

Authors: Kai Yin, Xiangjue Dong, Chengkai Liu, Allen Lin, Lingfeng Shi, Ali Mostafavi, James Caverlee
Published: 2025-10-16
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2510.15087v2

Effective and efficient access to relevant information is essential for disaster management. However, no retrieval model is specialized for disaster management, and existing general-domain models fail to handle the varied search intents inherent to disaster management scenarios, resulting in inconsistent and unreliable performance. To this end, we introduce DMRetriever, the first series of dense retrieval models (33M to 7.6B) tailored for this domain. It is trained through a novel three-stage framework of bidirectional attention adaptation, unsupervised contrastive pre-training, and difficulty-aware progressive instruction fine-tuning, using high-quality data generated through an advanced data refinement pipeline. Comprehensive experiments demonstrate that DMRetriever achieves state-of-the-art (SOTA) performance across all six search intents at every model scale. Moreover, DMRetriever is highly parameter-efficient, with 596M model outperforming baselines over 13.3 X larger and 33M model exceeding baselines with only 7.6% of their parameters. All codes, data, and checkpoints are available at https://github.com/KaiYin97/DMRETRIEVER

---