# Research Papers — 2025-10 · bundle page 194 of 217

> Full-text markdown of papers #9651–9700 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/194
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/193.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/195.md)

### Efficient Surgical Robotic Instrument Pose Reconstruction in Real World Conditions Using Unified Feature Detection

Authors: Zekai Liang, Kazuya Miyata, Xiao Liang, Florian Richter, Michael C. Yip
Published: 2025-10-03
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2510.03532v1

Accurate camera-to-robot calibration is essential for any vision-based robotic control system and especially critical in minimally invasive surgical robots, where instruments conduct precise micro-manipulations. However, MIS robots have long kinematic chains and partial visibility of their degrees of freedom in the camera, which introduces challenges for conventional camera-to-robot calibration methods that assume stiff robots with good visibility. Previous works have investigated both keypoint-based and rendering-based approaches to address this challenge in real-world conditions; however, they often struggle with consistent feature detection or have long inference times, neither of which are ideal for online robot control. In this work, we propose a novel framework that unifies the detection of geometric primitives (keypoints and shaft edges) through a shared encoding, enabling efficient pose estimation via projection geometry. This architecture detects both keypoints and edges in a single inference and is trained on large-scale synthetic data with projective labeling. This method is evaluated across both feature detection and pose estimation, with qualitative and quantitative results demonstrating fast performance and state-of-the-art accuracy in challenging surgical environments.

---

### Fine-Tuning on Noisy Instructions: Effects on Generalization and Performance

Authors: Ahmed Alajrami, Xingwei Tan, Nikolaos Aletras
Published: 2025-10-03
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.03528v2

Instruction-tuning plays a vital role in enhancing the task-solving abilities of large language models (LLMs), improving their usability in generating helpful responses on various tasks. However, previous work has demonstrated that they are sensitive to minor variations in instruction phrasing. In this paper, we explore whether introducing perturbations in instruction-tuning data can enhance LLMs' resistance against noisy instructions. We focus on how instruction-tuning with perturbations, such as removing stop words or shuffling words, affects LLMs' performance on the original and perturbed versions of widely-used benchmarks (MMLU, BBH, GSM8K). We further assess learning dynamics and potential shifts in model behavior. Surprisingly, our results suggest that instruction-tuning on perturbed instructions can, in some cases, improve downstream performance. These findings highlight the importance of including perturbed instructions in instruction-tuning, which can make LLMs more resilient to noisy user inputs.

---

### Sample, Align, Synthesize: Graph-Based Response Synthesis with ConGrs

Authors: Sayan Ghosh, Shahzaib Saqib Warraich, Dhruv Tarsadiya, Gregory Yauney, Swabha Swayamdipta
Published: 2025-10-03
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.03527v1

Language models can be sampled multiple times to access the distribution underlying their responses, but existing methods cannot efficiently synthesize rich epistemic signals across different long-form responses. We introduce Consensus Graphs (ConGrs), a flexible DAG-based data structure that represents shared information, as well as semantic variation in a set of sampled LM responses to the same prompt. We construct ConGrs using a light-weight lexical sequence alignment algorithm from bioinformatics, supplemented by the targeted usage of a secondary LM judge. Further, we design task-dependent decoding methods to synthesize a single, final response from our ConGr data structure. Our experiments show that synthesizing responses from ConGrs improves factual precision on two biography generation tasks by up to 31% over an average response and reduces reliance on LM judges by more than 80% compared to other methods. We also use ConGrs for three refusal-based tasks requiring abstention on unanswerable queries and find that abstention rate is increased by up to 56%. We apply our approach to the MATH and AIME reasoning tasks and find an improvement over self-verification and majority vote baselines by up to 6 points of accuracy. We show that ConGrs provide a flexible method for capturing variation in LM responses and using the epistemic signals provided by response variation to synthesize more effective responses.

---

### Identifying Financial Risk Information Using RAG with a Contrastive Insight

Authors: Ali Elahi
Published: 2025-10-03
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.03521v1

In specialized domains, humans often compare new problems against similar examples, highlight nuances, and draw conclusions instead of analyzing information in isolation. When applying reasoning in specialized contexts with LLMs on top of a RAG, the pipeline can capture contextually relevant information, but it is not designed to retrieve comparable cases or related problems. While RAG is effective at extracting factual information, its outputs in specialized reasoning tasks often remain generic, reflecting broad facts rather than context-specific insights. In finance, it results in generic risks that are true for the majority of companies. To address this limitation, we propose a peer-aware comparative inference layer on top of RAG. Our contrastive approach outperforms baseline RAG in text generation metrics such as ROUGE and BERTScore in comparison with human-generated equity research and risk.

---

### Certifiable Safe RLHF: Semantic Grounding and Fixed Penalty Constraint Optimization for Safer LLM Alignment

Authors: Kartik Pandit, Sourav Ganguly, Arnesh Banerjee, Shaahin Angizi, Arnob Ghosh
Published: 2025-10-03
Categories: cs.LG, cs.AI, eess.SY
arXiv: https://arxiv.org/abs/2510.03520v2

Ensuring safety is a foundational requirement for large language models (LLMs). Achieving an appropriate balance between enhancing the utility of model outputs and mitigating their potential for harm is a complex and persistent challenge. Contemporary approaches frequently formalize this problem within the framework of Constrained Markov Decision Processes (CMDPs) and employ established CMDP optimization techniques. However, these methods exhibit two notable limitations. First, their reliance on reward and cost functions renders performance highly sensitive to the underlying scoring mechanism, which must capture semantic meaning rather than being triggered by superficial keywords. Second, CMDP-based training entails tuning dual-variable, a process that is both computationally expensive and does not provide any provable safety guarantee for a fixed dual variable that can be exploitable through adversarial jailbreaks. To overcome these limitations, we introduce Certifiable Safe-RLHF (CS-RLHF) that introduces a cost model trained on a large-scale corpus to assign semantically grounded safety scores. In contrast to the lagrangian-based approach, CS-RLHF adopts a rectified penalty-based formulation. This design draws on the theory of exact penalty functions in constrained optimization, wherein constraint satisfaction is enforced directly through a suitably chosen penalty term. With an appropriately scaled penalty, feasibility of the safety constraints can be guaranteed at the optimizer, eliminating the need for dual-variable updates. Empirical evaluation demonstrates that CS-RLHF outperforms state-of-the-art LLM model responses rendering at-least 5 times efficient against nominal and jail-breaking prompts

---

### TS-Reasoner: Aligning Time Series Foundation Models with LLM Reasoning

Authors: Fangxu Yu, Hongyu Zhao, Tianyi Zhou
Published: 2025-10-03
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.03519v3

Time series reasoning is crucial to decision-making in diverse domains, including finance, energy, and scientific discovery. While existing time series foundation models (TSFMs) can capture low-level dynamic patterns and provide accurate forecasting, further analysis usually requires additional background knowledge and sophisticated reasoning, which are lacking in most TSFMs but can be achieved through Large Language Models (LLMs). On the other hand, without expensive post-training, LLMs often struggle with the numerical understanding of time series data. Although it is intuitive to integrate the two types of models, developing effective training recipes that align the two modalities for reasoning tasks is still an open challenge. To this end, we propose TS-Reasoner that aligns the latent representations of TSFMs with the textual inputs of LLMs for downstream understanding/reasoning tasks. Specifically, we propose a simple yet effective method to curate diverse, synthetic pairs of time series and textual captions for alignment training. We then develop a two-stage training recipe that applies instruction fine-tuning after the alignment pretraining. Unlike existing works that train an LLM to take time series as inputs, we leverage a pretrained TSFM and freeze it during training. Experiments on several benchmarks demonstrate that TS-Reasoner not only outperforms a wide range of open-source LLMs, Vision-Language Models (VLMs), and Time Series LLMs of comparable scale, but also does so with remarkable data efficiency, e.g., using less than half the training data.

---

### RAPID: An Efficient Reinforcement Learning Algorithm for Small Language Models

Authors: Lianghuan Huang, Sagnik Anupam, Insup Lee, Shuo Li, Osbert Bastani
Published: 2025-10-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.03515v1

Reinforcement learning (RL) has emerged as a promising strategy for finetuning small language models (SLMs) to solve targeted tasks such as math and coding. However, RL algorithms tend to be resource-intensive, taking a significant amount of time to train. We propose RAPID, a novel RL algorithm that can substantially reduce the running time of RL. Our key insight is that RL tends to be costly due to the need to perform both inference and backpropagation during training. To maximize use of computational resources, our algorithm performs inference in large batches, and then performs off-policy policy gradient updates in mini-batches. For off-policy updates, we incorporate group advantage estimation into the policy gradient algorithm, and derive an importance weighted estimator to correct for the bias arising from off-policy learning. Our experiments demonstrate that our algorithm can reduce running time by 11%-34% on three benchmarks compared to state-of-the-art RL algorithms while maintaining similar or better accuracy.

---

### Red Lines and Grey Zones in the Fog of War: Benchmarking Legal Risk, Moral Harm, and Regional Bias in Large Language Model Military Decision-Making

Authors: Toby Drinkall
Published: 2025-10-03
Categories: cs.CY, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.03514v1

As military organisations consider integrating large language models (LLMs) into command and control (C2) systems for planning and decision support, understanding their behavioural tendencies is critical. This study develops a benchmarking framework for evaluating aspects of legal and moral risk in targeting behaviour by comparing LLMs acting as agents in multi-turn simulated conflict. We introduce four metrics grounded in International Humanitarian Law (IHL) and military doctrine: Civilian Target Rate (CTR) and Dual-use Target Rate (DTR) assess compliance with legal targeting principles, while Mean and Max Simulated Non-combatant Casualty Value (SNCV) quantify tolerance for civilian harm. We evaluate three frontier models, GPT-4o, Gemini-2.5, and LLaMA-3.1, through 90 multi-agent, multi-turn crisis simulations across three geographic regions. Our findings reveal that off-the-shelf LLMs exhibit concerning and unpredictable targeting behaviour in simulated conflict environments. All models violated the IHL principle of distinction by targeting civilian objects, with breach rates ranging from 16.7% to 66.7%. Harm tolerance escalated through crisis simulations with MeanSNCV increasing from 16.5 in early turns to 27.7 in late turns. Significant inter-model variation emerged: LLaMA-3.1 selected an average of 3.47 civilian strikes per simulation with MeanSNCV of 28.4, while Gemini-2.5 selected 0.90 civilian strikes with MeanSNCV of 17.6. These differences indicate that model selection for deployment constitutes a choice about acceptable legal and moral risk profiles in military operations. This work seeks to provide a proof-of-concept of potential behavioural risks that could emerge from the use of LLMs in Decision Support Systems (AI DSS) as well as a reproducible benchmarking framework with interpretable metrics for standardising pre-deployment testing.

---

### A Lightweight Federated Learning Approach for Privacy-Preserving Botnet Detection in IoT

Authors: Taha M. Mahmoud, Naima Kaabouch
Published: 2025-10-03
Categories: cs.LG, cs.CR, cs.DC
arXiv: https://arxiv.org/abs/2510.03513v1

The rapid growth of the Internet of Things (IoT) has expanded opportunities for innovation but also increased exposure to botnet-driven cyberattacks. Conventional detection methods often struggle with scalability, privacy, and adaptability in resource-constrained IoT environments. To address these challenges, we present a lightweight and privacy-preserving botnet detection framework based on federated learning. This approach enables distributed devices to collaboratively train models without exchanging raw data, thus maintaining user privacy while preserving detection accuracy. A communication-efficient aggregation strategy is introduced to reduce overhead, ensuring suitability for constrained IoT networks. Experiments on benchmark IoT botnet datasets demonstrate that the framework achieves high detection accuracy while substantially reducing communication costs. These findings highlight federated learning as a practical path toward scalable, secure, and privacy-aware intrusion detection for IoT ecosystems.

---

### Platonic Transformers: A Solid Choice For Equivariance

Authors: Mohammad Mohaiminul Islam, Rishabh Anand, David R. Wessels, Friso de Kruiff, Thijs P. Kuipers, Rex Ying, Clara I. Sánchez, Sharvaree Vadgama, Georg Bökman, Erik J. Bekkers
Published: 2025-10-03
Categories: cs.CV, cs.AI, cs.LG, eess.IV
arXiv: https://arxiv.org/abs/2510.03511v3

While widespread, Transformers lack inductive biases for geometric symmetries common in science and computer vision. Existing equivariant methods often sacrifice the efficiency and flexibility that make Transformers so effective through complex, computationally intensive designs. We introduce the Platonic Transformer to resolve this trade-off. By defining attention relative to reference frames from the Platonic solid symmetry groups, our method induces a principled weight-sharing scheme. This enables combined equivariance to continuous translations and Platonic symmetries, while preserving the exact architecture and computational cost of a standard Transformer. Furthermore, we show that this attention is formally equivalent to a dynamic group convolution, which reveals that the model learns adaptive geometric filters and enables a highly scalable, linear-time convolutional variant. Across diverse benchmarks in computer vision (CIFAR-10), 3D point clouds (ScanObjectNN), and molecular property prediction (QM9, OMol25), the Platonic Transformer achieves competitive performance by leveraging these geometric constraints at no additional cost.

---

### Task-Level Contrastiveness for Cross-Domain Few-Shot Learning

Authors: Kristi Topollai, Anna Choromanska
Published: 2025-10-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.03509v1

Few-shot classification and meta-learning methods typically struggle to generalize across diverse domains, as most approaches focus on a single dataset, failing to transfer knowledge across various seen and unseen domains. Existing solutions often suffer from low accuracy, high computational costs, and rely on restrictive assumptions. In this paper, we introduce the notion of task-level contrastiveness, a novel approach designed to address issues of existing methods. We start by introducing simple ways to define task augmentations, and thereafter define a task-level contrastive loss that encourages unsupervised clustering of task representations. Our method is lightweight and can be easily integrated within existing few-shot/meta-learning algorithms while providing significant benefits. Crucially, it leads to improved generalization and computational efficiency without requiring prior knowledge of task domains. We demonstrate the effectiveness of our approach through different experiments on the MetaDataset benchmark, where it achieves superior performance without additional complexity.

---

### D2 Actor Critic: Diffusion Actor Meets Distributional Critic

Authors: Lunjun Zhang, Shuo Han, Hanrui Lyu, Bradly C Stadie
Published: 2025-10-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.03508v3

We introduce D2AC, a new model-free reinforcement learning (RL) algorithm designed to train expressive diffusion policies online effectively. At its core is a policy improvement objective that avoids the high variance of typical policy gradients and the complexity of backpropagation through time. This stable learning process is critically enabled by our second contribution: a robust distributional critic, which we design through a fusion of distributional RL and clipped double Q-learning. The resulting algorithm is highly effective, achieving state-of-the-art performance on a benchmark of eighteen hard RL tasks, including Humanoid, Dog, and Shadow Hand domains, spanning both dense-reward and goal-conditioned RL scenarios. Beyond standard benchmarks, we also evaluate a biologically motivated predator-prey task to examine the behavioral robustness and generalization capacity of our approach. Code: https://github.com/d2ac-actor-critic/d2ac-public

---

### Composite Optimization with Error Feedback: the Dual Averaging Approach

Authors: Yuan Gao, Anton Rodomanov, Jeremy Rack, Sebastian Stich
Published: 2025-10-03
Categories: math.OC, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.03507v1

Communication efficiency is a central challenge in distributed machine learning training, and message compression is a widely used solution. However, standard Error Feedback (EF) methods (Seide et al., 2014), though effective for smooth unconstrained optimization with compression (Karimireddy et al., 2019), fail in the broader and practically important setting of composite optimization, which captures, e.g., objectives consisting of a smooth loss combined with a non-smooth regularizer or constraints. The theoretical foundation and behavior of EF in the context of the general composite setting remain largely unexplored. In this work, we consider composite optimization with EF. We point out that the basic EF mechanism and its analysis no longer stand when a composite part is involved. We argue that this is because of a fundamental limitation in the method and its analysis technique. We propose a novel method that combines Dual Averaging with EControl (Gao et al., 2024), a state-of-the-art variant of the EF mechanism, and achieves for the first time a strong convergence analysis for composite optimization with error feedback. Along with our new algorithm, we also provide a new and novel analysis template for inexact dual averaging method, which might be of independent interest. We also provide experimental results to complement our theoretical findings.

---

### OneFlow: Concurrent Mixed-Modal and Interleaved Generation with Edit Flows

Authors: John Nguyen, Marton Havasi, Tariq Berrada, Luke Zettlemoyer, Ricky T. Q. Chen
Published: 2025-10-03
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.03506v3

We present OneFlow, the first non-autoregressive multimodal model that enables variable-length and concurrent mixed-modal generation. Unlike autoregressive models that enforce rigid causal ordering between text and image generation, OneFlow combines an insertion-based Edit Flow for discrete text tokens with Flow Matching for image latents. OneFlow enables concurrent text-image synthesis with hierarchical sampling that prioritizes content over grammar. Through controlled experiments across model sizes from 1B to 8B, we demonstrate that OneFlow outperforms autoregressive baselines on both generation and understanding tasks while using up to 50% fewer training FLOPs. OneFlow surpasses both autoregressive and diffusion-based approaches while unlocking new capabilities for concurrent generation, iterative refinement, and natural reasoning-like generation.

---

### ALHD: A Large-Scale and Multigenre Benchmark Dataset for Arabic LLM-Generated Text Detection

Authors: Ali Khairallah, Arkaitz Zubiaga
Published: 2025-10-03
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.03502v2

We introduce ALHD, the first large-scale comprehensive Arabic dataset explicitly designed to distinguish between human- and LLM-generated texts. ALHD spans three genres (news, social media, reviews), covering both MSA and dialectal Arabic, and contains over 400K balanced samples generated by three leading LLMs and originated from multiple human sources, which enables studying generalizability in Arabic LLM-genearted text detection. We provide rigorous preprocessing, rich annotations, and standardized balanced splits to support reproducibility. In addition, we present, analyze and discuss benchmark experiments using our new dataset, in turn identifying gaps and proposing future research directions. Benchmarking across traditional classifiers, BERT-based models, and LLMs (zero-shot and few-shot) demonstrates that fine-tuned BERT models achieve competitive performance, outperforming LLM-based models. Results are however not always consistent, as we observe challenges when generalizing across genres; indeed, models struggle to generalize when they need to deal with unseen patterns in cross-genre settings, and these challenges are particularly prominent when dealing with news articles, where LLM-generated texts resemble human texts in style, which opens up avenues for future research. ALHD establishes a foundation for research related to Arabic LLM-detection and mitigating risks of misinformation, academic dishonesty, and cyber threats.

---

### Real-Time Threaded Houbara Detection and Segmentation for Wildlife Conservation using Mobile Platforms

Authors: Lyes Saad Saoud, Loic Lesobre, Enrico Sorato, Irfan Hussain
Published: 2025-10-03
Categories: cs.CV, cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2510.03501v1

Real-time animal detection and segmentation in natural environments are vital for wildlife conservation, enabling non-invasive monitoring through remote camera streams. However, these tasks remain challenging due to limited computational resources and the cryptic appearance of many species. We propose a mobile-optimized two-stage deep learning framework that integrates a Threading Detection Model (TDM) to parallelize YOLOv10-based detection and MobileSAM-based segmentation. Unlike prior YOLO+SAM pipelines, our approach improves real-time performance by reducing latency through threading. YOLOv10 handles detection while MobileSAM performs lightweight segmentation, both executed concurrently for efficient resource use. On the cryptic Houbara Bustard, a conservation-priority species, our model achieves mAP50 of 0.9627, mAP75 of 0.7731, mAP95 of 0.7178, and a MobileSAM mIoU of 0.7421. YOLOv10 operates at 43.7 ms per frame, confirming real-time readiness. We introduce a curated Houbara dataset of 40,000 annotated images to support model training and evaluation across diverse conditions. The code and dataset used in this study are publicly available on GitHub at https://github.com/LyesSaadSaoud/mobile-houbara-detseg. For interactive demos and additional resources, visit https://lyessaadsaoud.github.io/LyesSaadSaoud-Threaded-YOLO-SAM-Houbara.

---

### AgentHub: A Registry for Discoverable, Verifiable, and Reproducible AI Agents

Authors: Erik Pautsch, Tanmay Singla, Parv Kumar, Wenxin Jiang, Huiyun Peng, Behnaz Hassanshahi, Konstantin Läufer, George K. Thiruvathukal, James C. Davis
Published: 2025-10-03
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2510.03495v2

LLM-based agents are rapidly proliferating, yet the infrastructure for discovering, evaluating, and governing them remains fragmented compared to mature ecosystems like software package registries (e.g., npm) and model hubs (e.g., Hugging Face). Existing efforts typically address naming, distribution, or protocol descriptors, but stop short of providing a registry layer that makes agents discoverable, comparable, and governable under automated reuse. We present AgentHub, a registry layer and accompanying research agenda for agent sharing that targets discovery and workflow integration, trust and security, openness and governance, ecosystem interoperability, lifecycle transparency, and capability clarity with evidence. We describe a reference prototype that implements a canonical manifest with publish-time validation, version-bound evidence records linked to auditable artifacts, and an append-only lifecycle event log whose states are respected by default in search and resolution. We also provide initial discovery results using an LLM-as-judge recommendation pipeline, showing how structured contracts and evidence improve intent-accurate retrieval beyond keyword-driven discovery. AgentHub aims to provide a common substrate for building reliable, reusable agent ecosystems.

---

### Trajectory Data Suffices for Statistically Efficient Policy Evaluation in Fixed-Horizon Offline RL with Linear $q^π$-Realizability and Concentrability

Authors: Volodymyr Tkachuk, Csaba Szepesvári, Xiaoqi Tan
Published: 2025-10-03
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.03494v2

We study finite-horizon offline reinforcement learning (RL) with function approximation for both policy evaluation and policy optimization. Prior work established that statistically efficient learning is impossible for either of these problems when the only assumptions are that the data has good coverage (concentrability) and the state-action value function of every policy is linearly realizable ($q^π$-realizability) (Foster et al., 2021). Recently, Tkachuk et al. (2024) gave a statistically efficient learner for policy optimization, if in addition the data is assumed to be given as trajectories. In this work we present a statistically efficient learner for policy evaluation under the same assumptions. Further, we show that the sample complexity of the learner used by Tkachuk et al. (2024) for policy optimization can be improved by a tighter analysis.

---

### SEER: The Span-based Emotion Evidence Retrieval Benchmark

Authors: Aneesha Sampath, Oya Aran, Emily Mower Provost
Published: 2025-10-03
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.03490v2

We introduce the SEER (Span-based Emotion Evidence Retrieval) Benchmark to test Large Language Models' (LLMs) ability to identify the specific spans of text that express emotion. Unlike traditional emotion recognition tasks that assign a single label to an entire sentence, SEER targets the underexplored task of emotion evidence detection: pinpointing which exact phrases convey emotion. This span-level approach is crucial for applications like empathetic dialogue and clinical support, which need to know how emotion is expressed, not just what the emotion is. SEER includes two tasks: identifying emotion evidence within a single sentence, and identifying evidence across a short passage of five consecutive sentences. It contains new annotations for both emotion and emotion evidence on 1200 real-world sentences. We evaluate 14 open-source LLMs and find that, while some models approach average human performance on single-sentence inputs, their accuracy degrades in longer passages. Our error analysis reveals key failure modes, including overreliance on emotion keywords and false positives in neutral text.

---

### Reasoning-based Anomaly Detection Framework: A Real-time, Scalable, and Automated Approach to Anomaly Detection Across Domains

Authors: Anupam Panwar, Himadri Pal, Jiali Chen, Kyle Cho, Riddick Jiang, Miao Zhao, Rajiv Krishnamurthy
Published: 2025-10-03
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.03486v1

Detecting anomalies in large, distributed systems presents several challenges. The first challenge arises from the sheer volume of data that needs to be processed. Flagging anomalies in a high-throughput environment calls for a careful consideration of both algorithm and system design. The second challenge comes from the heterogeneity of time-series datasets that leverage such a system in production. In practice, anomaly detection systems are rarely deployed for a single use case. Typically, there are several metrics to monitor, often across several domains (e.g. engineering, business and operations). A one-size-fits-all approach rarely works, so these systems need to be fine-tuned for every application - this is often done manually. The third challenge comes from the fact that determining the root-cause of anomalies in such settings is akin to finding a needle in a haystack. Identifying (in real time) a time-series dataset that is associated causally with the anomalous time-series data is a very difficult problem. In this paper, we describe a unified framework that addresses these challenges. Reasoning based Anomaly Detection Framework (RADF) is designed to perform real time anomaly detection on very large datasets. This framework employs a novel technique (mSelect) that automates the process of algorithm selection and hyper-parameter tuning for each use case. Finally, it incorporates a post-detection capability that allows for faster triaging and root-cause determination. Our extensive experiments demonstrate that RADF, powered by mSelect, surpasses state-of-the-art anomaly detection models in AUC performance for 5 out of 9 public benchmarking datasets. RADF achieved an AUC of over 0.85 for 7 out of 9 datasets, a distinction unmatched by any other state-of-the-art model.

---

### Learning Efficient Guardrails for Compliance

Authors: Xiaofei Wen, Wenjie Jacky Mo, Yanan Xie, Peng Qi, Muhao Chen
Published: 2025-10-03
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.03485v2

Autonomous web agents are increasingly deployed for long-horizon tasks, yet their ability to adhere to real-world policies remains critically underexplored compared to standard safety objectives. To address this gap, we introduce PolicyGuardBench, a benchmark of 60k policy-trajectory pairs designed to evaluate compliance through both full-trajectory and novel prefix-based violation detection tasks. Using this dataset, we train PolicyGuard, a lightweight guardrail model that achieves strong detection accuracy while maintaining high inference efficiency. Notably, our model demonstrates robust generalization capabilities, preserving high performance even on unseen domains. These contributions establish a comprehensive framework for studying policy compliance, showing that accurate and generalizable guardrails are feasible at small scales.

---

### DuPLUS: Dual-Prompt Vision-Language Framework for Universal Medical Image Segmentation and Prognosis

Authors: Numan Saeed, Tausifa Jan Saleem, Fadillah Maani, Muhammad Ridzuan, Hu Wang, Mohammad Yaqub
Published: 2025-10-03
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.03483v1

Deep learning for medical imaging is hampered by task-specific models that lack generalizability and prognostic capabilities, while existing 'universal' approaches suffer from simplistic conditioning and poor medical semantic understanding. To address these limitations, we introduce DuPLUS, a deep learning framework for efficient multi-modal medical image analysis. DuPLUS introduces a novel vision-language framework that leverages hierarchical semantic prompts for fine-grained control over the analysis task, a capability absent in prior universal models. To enable extensibility to other medical tasks, it includes a hierarchical, text-controlled architecture driven by a unique dual-prompt mechanism. For segmentation, DuPLUS is able to generalize across three imaging modalities, ten different anatomically various medical datasets, encompassing more than 30 organs and tumor types. It outperforms the state-of-the-art task specific and universal models on 8 out of 10 datasets. We demonstrate extensibility of its text-controlled architecture by seamless integration of electronic health record (EHR) data for prognosis prediction, and on a head and neck cancer dataset, DuPLUS achieved a Concordance Index (CI) of 0.69. Parameter-efficient fine-tuning enables rapid adaptation to new tasks and modalities from varying centers, establishing DuPLUS as a versatile and clinically relevant solution for medical image analysis. The code for this work is made available at: https://anonymous.4open.science/r/DuPLUS-6C52

---

### How to Set $β_1, β_2$ in Adam: An Online Learning Perspective

Authors: Quan Nguyen
Published: 2025-10-03
Categories: cs.LG, math.OC
arXiv: https://arxiv.org/abs/2510.03478v2

While Adam is one of the most effective optimizer for training large-scale machine learning models, a theoretical understanding of how to optimally set its momentum factors, $β_1$ and $β_2$, remains largely incomplete. Prior works have shown that Adam can be seen as an instance of Follow-the-Regularized-Leader (FTRL), one of the most important class of algorithms in online learning. The prior analyses in these works required setting $β_1 = \sqrt{β_2}$, which does not cover the more practical cases with $β_1 \neq \sqrt{β_2}$. We derive novel, more general analyses that hold for both $β_1 \geq \sqrt{β_2}$ and $β_1 \leq \sqrt{β_2}$. In both cases, our results strictly generalize the existing bounds. Furthermore, we show that our bounds are tight in the worst case. We also prove that setting $β_1 = \sqrt{β_2}$ is optimal for an oblivious adversary, but sub-optimal for an non-oblivious adversary.

---

### Destination-to-Chutes Task Mapping Optimization for Multi-Robot Coordination in Robotic Sorting Systems

Authors: Yulun Zhang, Alexandre O. G. Barbosa, Federico Pecora, Jiaoyang Li
Published: 2025-10-03
Categories: cs.RO, cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2510.03472v1

We study optimizing a destination-to-chutes task mapping to improve throughput in Robotic Sorting Systems (RSS), where a team of robots sort packages on a sortation floor by transporting them from induct workstations to eject chutes based on their shipping destinations (e.g. Los Angeles or Pittsburgh). The destination-to-chutes task mapping is used to determine which chutes a robot can drop its package. Finding a high-quality task mapping is challenging because of the complexity of a real-world RSS. First, optimizing task mapping is interdependent with robot target assignment and path planning. Second, chutes will be CLOSED for a period of time once they receive sufficient packages to allow for downstream processing. Third, task mapping quality directly impacts the downstream processing, as scattered chutes for the same destination increase package handling time. In this paper, we first formally define task mappings and the problem of Task Mapping Optimization (TMO). We then present a simulator of RSS to evaluate task mappings. We then present a simple TMO method based on the Evolutionary Algorithm and Mixed Integer Linear Programming, demonstrating the advantage of our optimized task mappings over the greedily generated ones in various RSS setups with different map sizes, numbers of chutes, and destinations. Finally, we use Quality Diversity algorithms to analyze the throughput of a diverse set of task mappings. Our code is available online at https://github.com/lunjohnzhang/tmo_public.

---

### On residual network depth

Authors: Benoit Dherin, Michael Munn
Published: 2025-10-03
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.03470v2

Deep residual architectures, such as ResNet and the Transformer, have enabled models of unprecedented depth, yet a formal understanding of why depth is so effective remains an open question. A popular intuition, following Veit et al. (2016), is that these residual networks behave like ensembles of many shallower models. Our key finding is an explicit analytical formula that verifies this ensemble perspective, proving that increasing network depth is mathematically equivalent to expanding the size of this implicit ensemble. Furthermore, our expansion reveals a hierarchical ensemble structure in which the combinatorial growth of computation paths leads to an explosion in the output signal, explaining the historical necessity of normalization layers in training deep models. This insight offers a first principles explanation for the historical dependence on normalization layers and sheds new light on a family of successful normalization-free techniques like SkipInit and Fixup. However, while these previous approaches infer scaling factors through optimizer analysis or a heuristic analogy to Batch Normalization, our work offers the first explanation derived directly from the network's inherent functional structure. Specifically, our Residual Expansion Theorem reveals that scaling each residual module provides a principled solution to taming the combinatorial explosion inherent to these architectures. We further show that this scaling acts as a capacity controls that also implicitly regularizes the model's complexity.

---

### Bridging LLM Planning Agents and Formal Methods: A Case Study in Plan Verification

Authors: Keshav Ramani, Vali Tawosi, Salwa Alamir, Daniel Borrajo
Published: 2025-10-03
Categories: cs.AI, cs.LO
arXiv: https://arxiv.org/abs/2510.03469v2

We introduce a novel framework for evaluating the alignment between natural language plans and their expected behavior by converting them into Kripke structures and Linear Temporal Logic (LTL) using Large Language Models (LLMs) and performing model checking. We systematically evaluate this framework on a simplified version of the PlanBench plan verification dataset and report on metrics like Accuracy, Precision, Recall and F1 scores. Our experiments demonstrate that GPT-5 achieves excellent classification performance (F1 score of 96.3%) while almost always producing syntactically perfect formal representations that can act as guarantees. However, the synthesis of semantically perfect formal models remains an area for future exploration.

---

### Searching for the Most Human-like Emergent Language

Authors: Brendon Boldt, David Mortensen
Published: 2025-10-03
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.03467v1

In this paper, we design a signalling game-based emergent communication environment to generate state-of-the-art emergent languages in terms of similarity to human language. This is done with hyperparameter optimization, using XferBench as the objective function. XferBench quantifies the statistical similarity of emergent language to human language by measuring its suitability for deep transfer learning to human language. Additionally, we demonstrate the predictive power of entropy on the transfer learning performance of emergent language as well as corroborate previous results on the entropy-minimization properties of emergent communication systems. Finally, we report generalizations regarding what hyperparameters produce more realistic emergent languages, that is, ones which transfer better to human language.

---

### Optimal Regularization Under Uncertainty: Distributional Robustness and Convexity Constraints

Authors: Oscar Leong, Eliza O'Reilly, Yong Sheng Soh
Published: 2025-10-03
Categories: math.OC, math.MG, math.ST, stat.ML
arXiv: https://arxiv.org/abs/2510.03464v1

Regularization is a central tool for addressing ill-posedness in inverse problems and statistical estimation, with the choice of a suitable penalty often determining the reliability and interpretability of downstream solutions. While recent work has characterized optimal regularizers for well-specified data distributions, practical deployments are often complicated by distributional uncertainty and the need to enforce structural constraints such as convexity. In this paper, we introduce a framework for distributionally robust optimal regularization, which identifies regularizers that remain effective under perturbations of the data distribution. Our approach leverages convex duality to reformulate the underlying distributionally robust optimization problem, eliminating the inner maximization and yielding formulations that are amenable to numerical computation. We show how the resulting robust regularizers interpolate between memorization of the training distribution and uniform priors, providing insights into their behavior as robustness parameters vary. For example, we show how certain ambiguity sets, such as those based on the Wasserstein-1 distance, naturally induce regularity in the optimal regularizer by promoting regularizers with smaller Lipschitz constants. We further investigate the setting where regularizers are required to be convex, formulating a convex program for their computation and illustrating their stability with respect to distributional shifts. Taken together, our results provide both theoretical and computational foundations for designing regularizers that are reliable under model uncertainty and structurally constrained for robust deployment.

---

### ALMAS: an Autonomous LLM-based Multi-Agent Software Engineering Framework

Authors: Vali Tawosi, Keshav Ramani, Salwa Alamir, Xiaomo Liu
Published: 2025-10-03
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2510.03463v2

Multi-agent Large Language Model (LLM) systems have been leading the way in applied LLM research across a number of fields. One notable area is software development, where researchers have advanced the automation of code implementation, code testing, code maintenance, inter alia, using LLM agents. However, software development is a multifaceted environment that extends beyond just code. As such, a successful LLM system must factor in multiple stages of the software development life-cycle (SDLC). In this paper, we propose a vision for ALMAS, an Autonomous LLM-based Multi-Agent Software Engineering framework, which follows the above SDLC philosophy such that it may work within an agile software development team to perform several tasks end-to-end. ALMAS aligns its agents with agile roles, and can be used in a modular fashion to seamlessly integrate with human developers and their development environment. We showcase the progress towards ALMAS through our published works and a use case demonstrating the framework, where ALMAS is able to seamlessly generate an application and add a new feature.

---

### Omni-Embed-Nemotron: A Unified Multimodal Retrieval Model for Text, Image, Audio, and Video

Authors: Mengyao Xu, Wenfei Zhou, Yauhen Babakhin, Gabriel Moreira, Ronay Ak, Radek Osmulski, Bo Liu, Even Oldridge, Benedikt Schifferer
Published: 2025-10-03
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.03458v1

We present Omni-Embed-Nemotron, a unified multimodal retrieval embedding model developed to handle the increasing complexity of real-world information needs. While Retrieval-Augmented Generation (RAG) has significantly advanced language models by incorporating external knowledge, existing text-based retrievers rely on clean, structured input and struggle with the visually and semantically rich content found in real-world documents such as PDFs, slides, or videos. Recent work such as ColPali has shown that preserving document layout using image-based representations can improve retrieval quality. Building on this, and inspired by the capabilities of recent multimodal models such as Qwen2.5-Omni, we extend retrieval beyond text and images to also support audio and video modalities. Omni-Embed-Nemotron enables both cross-modal (e.g., text - video) and joint-modal (e.g., text - video+audio) retrieval using a single model. We describe the architecture, training setup, and evaluation results of Omni-Embed-Nemotron, and demonstrate its effectiveness in text, image, and video retrieval.

---

### PEaRL: Pathway-Enhanced Representation Learning for Gene and Pathway Expression Prediction from Histology

Authors: Sejuti Majumder, Saarthak Kapse, Moinak Bhattacharya, Xuan Xu, Alisa Yurovsky, Prateek Prasanna
Published: 2025-10-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.03455v1

Integrating histopathology with spatial transcriptomics (ST) provides a powerful opportunity to link tissue morphology with molecular function. Yet most existing multimodal approaches rely on a small set of highly variable genes, which limits predictive scope and overlooks the coordinated biological programs that shape tissue phenotypes. We present PEaRL (Pathway Enhanced Representation Learning), a multimodal framework that represents transcriptomics through pathway activation scores computed with ssGSEA. By encoding biologically coherent pathway signals with a transformer and aligning them with histology features via contrastive learning, PEaRL reduces dimensionality, improves interpretability, and strengthens cross-modal correspondence. Across three cancer ST datasets (breast, skin, and lymph node), PEaRL consistently outperforms SOTA methods, yielding higher accuracy for both gene- and pathway-level expression prediction (up to 58.9 percent and 20.4 percent increase in Pearson correlation coefficient compared to SOTA). These results demonstrate that grounding transcriptomic representation in pathways produces more biologically faithful and interpretable multimodal models, advancing computational pathology beyond gene-level embeddings.

---

### A Qualitative Comparative Evaluation of Cognitive and Generative Theories

Authors: Paul S. Rosenbloom
Published: 2025-10-03
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.03453v1

Evaluation is a critical activity associated with any theory. Yet this has proven to be an exceptionally challenging activity for theories based on cognitive architectures. For an overlapping set of reasons, evaluation can also be challenging for theories based on generative neural architectures. This dual challenge is approached here by leveraging a broad perspective on theory evaluation to yield a wide-ranging, albeit qualitative, comparison of whole-mind-oriented cognitive and generative architectures and the full systems that are based on these architectures.

---

### Denoising of Two-Phase Optically Sectioned Structured Illumination Reconstructions Using Encoder-Decoder Networks

Authors: Allison Davis, Yezhi Shen, Xiaoyu Ji, Fengqing Zhu
Published: 2025-10-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.03452v1

Structured illumination (SI) enhances image resolution and contrast by projecting patterned light onto a sample. In two-phase optical-sectioning SI (OS-SI), reduced acquisition time introduces residual artifacts that conventional denoising struggles to suppress. Deep learning offers an alternative to traditional methods; however, supervised training is limited by the lack of clean, optically sectioned ground-truth data. We investigate encoder-decoder networks for artifact reduction in two-phase OS-SI, using synthetic training pairs formed by applying real artifact fields to synthetic images. An asymmetrical denoising autoencoder (DAE) and a U-Net are trained on the synthetic data, then evaluated on real OS-SI images. Both networks improve image clarity, with each excelling against different artifact types. These results demonstrate that synthetic training enables supervised denoising of OS-SI images and highlight the potential of encoder-decoder networks to streamline reconstruction workflows.

---

### The Argument is the Explanation: Structured Argumentation for Trust in Agents

Authors: Ege Cakar, Per Ola Kristensson
Published: 2025-10-03
Categories: cs.LG, cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2510.03442v1

Humans are black boxes -- we cannot observe their neural processes, yet society functions by evaluating verifiable arguments. AI explainability should follow this principle: stakeholders need verifiable reasoning chains, not mechanistic transparency. We propose using structured argumentation to provide a level of explanation and verification neither interpretability nor LLM-generated explanation is able to offer. Our pipeline achieves state-of-the-art 94.44 macro F1 on the AAEC published train/test split (5.7 points above prior work) and $0.81$ macro F1, $\sim$0.07 above previous published results with comparable data setups, for Argumentative MicroTexts relation classification, converting LLM text into argument graphs and enabling verification at each inferential step. We demonstrate this idea on multi-agent risk assessment using the Structured What-If Technique, where specialized agents collaborate transparently to carry out risk assessment otherwise achieved by humans alone. Using Bipolar Assumption-Based Argumentation, we capture support/attack relationships, thereby enabling automatic hallucination detection via fact nodes attacking arguments. We also provide a verification mechanism that enables iterative refinement through test-time feedback without retraining. For easy deployment, we provide a Docker container for the fine-tuned AMT model, and the rest of the code with the Bipolar ABA Python package on GitHub.

---

### Spatial-ViLT: Enhancing Visual Spatial Reasoning through Multi-Task Learning

Authors: Chashi Mahiul Islam, Oteo Mamo, Samuel Jacob Chacko, Xiuwen Liu, Weikuan Yu
Published: 2025-10-03
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.03441v1

Vision-language models (VLMs) have advanced multimodal reasoning but still face challenges in spatial reasoning for 3D scenes and complex object configurations. To address this, we introduce SpatialViLT, an enhanced VLM that integrates spatial features like depth maps, 3D coordinates, and edge maps through a multi-task learning framework. This approach enriches multimodal embeddings with spatial understanding. We propose two variants: SpatialViLT and MaskedSpatialViLT, focusing on full and masked object regions, respectively. Additionally, SpatialEnsemble combines both approaches, achieving state-of-the-art accuracy. Our models excel in spatial reasoning categories such as directional, topological, and proximity relations, as demonstrated on the challenging Visual Spatial Reasoning (VSR) dataset. This work represents a significant step in enhancing the spatial intelligence of AI systems, crucial for advanced multimodal understanding and real-world applications.

---

### Morpheme Induction for Emergent Language

Authors: Brendon Boldt, David Mortensen
Published: 2025-10-03
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.03439v1

We introduce CSAR, an algorithm for inducing morphemes from emergent language corpora of parallel utterances and meanings. It is a greedy algorithm that (1) weights morphemes based on mutual information between forms and meanings, (2) selects the highest-weighted pair, (3) removes it from the corpus, and (4) repeats the process to induce further morphemes (i.e., Count, Select, Ablate, Repeat). The effectiveness of CSAR is first validated on procedurally generated datasets and compared against baselines for related tasks. Second, we validate CSAR's performance on human language data to show that the algorithm makes reasonable predictions in adjacent domains. Finally, we analyze a handful of emergent languages, quantifying linguistic characteristics like degree of synonymy and polysemy.

---

### Scalable Ground Station Selection for Large LEO Constellations

Authors: Grace Ra Kim, Duncan Eddy, Vedant Srinivas, Mykel J. Kochenderfer
Published: 2025-10-03
Categories: cs.NI, cs.AI, eess.SY
arXiv: https://arxiv.org/abs/2510.03438v1

Effective ground station selection is critical for low Earth orbiting (LEO) satellite constellations to minimize operational costs, maximize data downlink volume, and reduce communication gaps between access windows. Traditional ground station selection typically begins by choosing from a fixed set of locations offered by Ground Station-as-a-Service (GSaaS) providers, which helps reduce the problem scope to optimizing locations over existing infrastructure. However, finding a globally optimal solution for stations using existing mixed-integer programming methods quickly becomes intractable at scale, especially when considering multiple providers and large satellite constellations. To address this issue, we introduce a scalable, hierarchical framework that decomposes the global selection problem into single-satellite, short time-window subproblems. Optimal station choices from each subproblem are clustered to identify consistently high-value locations across all decomposed cases. Cluster-level sets are then matched back to the closest GSaaS candidate sites to produce a globally feasible solution. This approach enables scalable coordination while maintaining near-optimal performance. We evaluate our method's performance on synthetic Walker-Star test cases (1-10 satellites, 1-10 stations), achieving solutions within 95% of the global IP optimum for all test cases. Real-world evaluations on Capella Space (5 satellites), ICEYE (40), and Planet's Flock (96) show that while exact IP solutions fail to scale, our framework continues to deliver high-quality site selections.

---

### Consistent Kernel Change-Point Detection under m-Dependence for Text Segmentation

Authors: Jairo Diaz-Rodriguez, Mumin Jia
Published: 2025-10-03
Categories: cs.LG, cs.CL, stat.ML
arXiv: https://arxiv.org/abs/2510.03437v2

Kernel change-point detection (KCPD) has become a widely used tool for identifying structural changes in complex data. While existing theory establishes consistency under independence assumptions, real-world sequential data such as text exhibits strong dependencies. We establish new guarantees for KCPD under $m$-dependent data: specifically, we prove consistency in the number of detected change points and weak consistency in their locations under mild additional assumptions. We perform an LLM-based simulation that generates synthetic $m$-dependent text to validate the asymptotics. To complement these results, we present the first comprehensive empirical study of KCPD for text segmentation with modern embeddings. Across diverse text datasets, KCPD with text embeddings outperforms baselines in standard text segmentation metrics. We demonstrate through a case study on Taylor Swift's tweets that KCPD not only provides strong theoretical and simulated reliability but also practical effectiveness for text segmentation tasks.

---

### Paris: A Decentralized Trained Open-Weight Diffusion Model

Authors: Zhiying Jiang, Raihan Seraj, Marcos Villagra, Bidhan Roy
Published: 2025-10-03
Categories: cs.GR, cs.DC, cs.LG
arXiv: https://arxiv.org/abs/2510.03434v3

We present Paris, the first publicly released diffusion model pre-trained entirely through decentralized computation. Paris demonstrates that high-quality text-to-image generation can be achieved without centrally coordinated infrastructure. Paris is open for research and commercial use. Paris required implementing our Distributed Diffusion Training framework from scratch. The model consists of 8 expert diffusion models (129M-605M parameters each) trained in complete isolation with no gradient, parameter, or intermediate activation synchronization. Rather than requiring synchronized gradient updates across thousands of GPUs, we partition data into semantically coherent clusters where each expert independently optimizes its subset while collectively approximating the full distribution. A lightweight transformer router dynamically selects appropriate experts at inference, achieving generation quality comparable to centrally coordinated baselines. Eliminating synchronization enables training on heterogeneous hardware without specialized interconnects. Empirical validation confirms that Paris's decentralized training maintains generation quality while removing the dedicated GPU cluster requirement for large-scale diffusion models. Paris achieves this using 14$\times$ less training data and 16$\times$ less compute than the prior decentralized baseline.

---

### LHGEL: Large Heterogeneous Graph Ensemble Learning using Batch View Aggregation

Authors: Jiajun Shen, Yufei Jin, Yi He, Xingquan Zhu
Published: 2025-10-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.03432v1

Learning from large heterogeneous graphs presents significant challenges due to the scale of networks, heterogeneity in node and edge types, variations in nodal features, and complex local neighborhood structures. This paper advocates for ensemble learning as a natural solution to this problem, whereby training multiple graph learners under distinct sampling conditions, the ensemble inherently captures different aspects of graph heterogeneity. Yet, the crux lies in combining these learners to meet global optimization objective while maintaining computational efficiency on large-scale graphs. In response, we propose LHGEL, an ensemble framework that addresses these challenges through batch sampling with three key components, namely batch view aggregation, residual attention, and diversity regularization. Specifically, batch view aggregation samples subgraphs and forms multiple graph views, while residual attention adaptively weights the contributions of these views to guide node embeddings toward informative subgraphs, thereby improving the accuracy of base learners. Diversity regularization encourages representational disparity across embedding matrices derived from different views, promoting model diversity and ensemble robustness. Our theoretical study demonstrates that residual attention mitigates gradient vanishing issues commonly faced in ensemble learning. Empirical results on five real heterogeneous networks validate that our LHGEL approach consistently outperforms its state-of-the-art competitors by substantial margin. Codes and datasets are available at https://github.com/Chrisshen12/LHGEL.

---

### Application of a Virtual Imaging Framework for Investigating a Deep Learning-Based Reconstruction Method for 3D Quantitative Photoacoustic Computed Tomography

Authors: Refik Mert Cam, Seonyeong Park, Umberto Villa, Mark A. Anastasio
Published: 2025-10-03
Categories: physics.med-ph, cs.AI, eess.SP
arXiv: https://arxiv.org/abs/2510.03431v1

Quantitative photoacoustic computed tomography (qPACT) is a promising imaging modality for estimating physiological parameters such as blood oxygen saturation. However, developing robust qPACT reconstruction methods remains challenging due to computational demands, modeling difficulties, and experimental uncertainties. Learning-based methods have been proposed to address these issues but remain largely unvalidated. Virtual imaging (VI) studies are essential for validating such methods early in development, before proceeding to less-controlled phantom or in vivo studies. Effective VI studies must employ ensembles of stochastically generated numerical phantoms that accurately reflect relevant anatomy and physiology. Yet, most prior VI studies for qPACT relied on overly simplified phantoms. In this work, a realistic VI testbed is employed for the first time to assess a representative 3D learning-based qPACT reconstruction method for breast imaging. The method is evaluated across subject variability and physical factors such as measurement noise and acoustic aberrations, offering insights into its strengths and limitations.

---

### Generalized Orders of Magnitude for Scalable, Parallel, High-Dynamic-Range Computation

Authors: Franz A. Heinsen, Leo Kozachkov
Published: 2025-10-03
Categories: cs.LG, cs.AI, math.NA
arXiv: https://arxiv.org/abs/2510.03426v2

Many domains, from deep learning to finance, require compounding real numbers over long sequences, often leading to catastrophic numerical underflow or overflow. We introduce generalized orders of magnitude (GOOMs), a principled extension of traditional orders of magnitude that incorporates floating-point numbers as a special case, and which in practice enables stable computation over significantly larger dynamic ranges of real numbers than previously possible. We implement GOOMs, along with an efficient custom parallel prefix scan, to support native execution on parallel hardware such as GPUs. We demonstrate that our implementation of GOOMs outperforms traditional approaches with three representative experiments, all of which were previously considered impractical or impossible, and now become possible and practical: (1) compounding real matrix products far beyond standard floating-point limits; (2) estimating spectra of Lyapunov exponents in parallel, orders of magnitude faster than with previous methods, applying a novel selective-resetting method to prevent state colinearity; and (3) capturing long-range dependencies in deep recurrent neural networks with non-diagonal recurrent states, computed in parallel via a prefix scan, without requiring any form of stabilization. Our results show that our implementation of GOOMs, combined with efficient parallel scanning, offers a scalable and numerically robust alternative to conventional floating-point numbers for high-dynamic-range applications.

---

### Memory-Efficient Backpropagation for Fine-Tuning LLMs on Resource-Constrained Mobile Devices

Authors: Congzheng Song, Xinyu Tang
Published: 2025-10-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.03425v1

Fine-tuning large language models (LLMs) with backpropagation\textemdash even for a subset of parameters such as LoRA\textemdash can be much more memory-consuming than inference and is often deemed impractical for resource-constrained mobile devices. Alternative methods, such as zeroth-order optimization (ZO), can greatly reduce the memory footprint but come at the cost of significantly slower model convergence (10$\times$ to 100$\times$ more steps than backpropagation). We propose a memory-efficient implementation of backpropagation (MeBP) on mobile devices that provides better trade-off between memory usage and compute time, while converging faster and achieving better performance than the ZO baseline. We verify the effectiveness of MeBP on an iPhone 15 Pro Max and show that various LLMs, ranging from 0.5B to 4B parameters, can be fine-tuned using less than 1GB of memory. We release an example of the MeBP implementation at https://github.com/apple/ml-mebp.

---

### Multi-task Neural Diffusion Processes

Authors: Joseph Rawson, Domniki Ladopoulou, Petros Dellaportas
Published: 2025-10-03
Categories: cs.LG, cs.AI, stat.AP, stat.ML
arXiv: https://arxiv.org/abs/2510.03419v3

Neural diffusion processes provide a scalable, non-Gaussian approach to modelling distributions over functions, but existing formulations are limited to single-task inference and do not capture dependencies across related tasks. We propose multi-task neural diffusion processes (MT-NDPs), an extension that incorporates a task encoder to enable task-conditioned probabilistic regression and few-shot adaptation across related functions. The task encoder extracts a low-dimensional representation from context observations and conditions the diffusion model on this representation, allowing information sharing across tasks while accommodating variable-sized context sets and preserving permutation invariance with respect to the ordering of context observations. We evaluate MT-NDPs through synthetic experiments and two real-world applications involving wind turbine data and school examination outcomes. The results demonstrate improved predictive accuracy relative to single-task diffusion baselines when context observations are available, alongside competitive performance against neural-process and Gaussian-process alternatives. In the wind-energy application, MT-NDPs achieve the lowest average coverage error among the evaluated models at larger context sizes, demonstrating improved predictive uncertainty calibration. Overall, our findings highlight the potential of task-conditioned diffusion models for uncertainty-aware multi-task regression and few-shot adaptation to previously unseen tasks.

---

### LegalWiz: A Multi-Agent Generation Framework for Contradiction Detection in Legal Documents

Authors: Ananya Mantravadi, Shivali Dalmia, Olga Pospelova, Abhishek Mukherji, Nand Dave, Anudha Mittal
Published: 2025-10-03
Categories: cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2510.03418v2

Retrieval-Augmented Generation (RAG) integrates large language models (LLMs) with external sources, but unresolved contradictions in retrieved evidence often lead to hallucinations and legally unsound outputs. Benchmarks currently used for contradiction detection lack domain realism, cover only limited conflict types, and rarely extend beyond single-sentence pairs, making them unsuitable for legal applications. Controlled generation of documents with embedded contradictions is therefore essential: it enables systematic stress-testing of models, ensures coverage of diverse conflict categories, and provides a reliable basis for evaluating contradiction detection and resolution. We present a multi-agent contradiction-aware benchmark framework for the legal domain that generates synthetic legal-style documents, injects six structured contradiction types, and models both self- and pairwise inconsistencies. Automated contradiction mining is combined with human-in-the-loop validation to guarantee plausibility and fidelity. This benchmark offers one of the first structured resources for contradiction-aware evaluation in legal RAG pipelines, supporting more consistent, interpretable, and trustworthy systems.

---

### NEXUS: Network Exploration for eXploiting Unsafe Sequences in Multi-Turn LLM Jailbreaks

Authors: Javad Rafiei Asl, Sidhant Narula, Mohammad Ghasemigol, Eduardo Blanco, Daniel Takabi
Published: 2025-10-03
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2510.03417v2

Large Language Models (LLMs) have revolutionized natural language processing but remain vulnerable to jailbreak attacks, especially multi-turn jailbreaks that distribute malicious intent across benign exchanges and bypass alignment mechanisms. Existing approaches often explore the adversarial space poorly, rely on hand-crafted heuristics, or lack systematic query refinement. We present NEXUS (Network Exploration for eXploiting Unsafe Sequences), a modular framework for constructing, refining, and executing optimized multi-turn attacks. NEXUS comprises: (1) ThoughtNet, which hierarchically expands a harmful intent into a structured semantic network of topics, entities, and query chains; (2) a feedback-driven Simulator that iteratively refines and prunes these chains through attacker-victim-judge LLM collaboration using harmfulness and semantic-similarity benchmarks; and (3) a Network Traverser that adaptively navigates the refined query space for real-time attacks. This pipeline uncovers stealthy, high-success adversarial paths across LLMs. On several closed-source and open-source LLMs, NEXUS increases attack success rate by 2.1% to 19.4% over prior methods. Code: https://github.com/inspire-lab/NEXUS

---

### Training Variation of Physically-Informed Deep Learning Models

Authors: Ashley Lenau, Dennis Dimiduk, Stephen R. Niezgoda
Published: 2025-10-03
Categories: cs.LG, cond-mat.mtrl-sci
arXiv: https://arxiv.org/abs/2510.03416v1

A successful deep learning network is highly dependent not only on the training dataset, but the training algorithm used to condition the network for a given task. The loss function, dataset, and tuning of hyperparameters all play an essential role in training a network, yet there is not much discussion on the reliability or reproducibility of a training algorithm. With the rise in popularity of physics-informed loss functions, this raises the question of how reliable one's loss function is in conditioning a network to enforce a particular boundary condition. Reporting the model variation is needed to assess a loss function's ability to consistently train a network to obey a given boundary condition, and provides a fairer comparison among different methods. In this work, a Pix2Pix network predicting the stress fields of high elastic contrast composites is used as a case study. Several different loss functions enforcing stress equilibrium are implemented, with each displaying different levels of variation in convergence, accuracy, and enforcing stress equilibrium across many training sessions. Suggested practices in reporting model variation are also shared.

---

### LLMs Lean on Priors, Not Programming Language Semantics

Authors: Aditya Thimmaiah, Jiyang Zhang, Jayanth Srinivasa, Junyi Jessy Li, Milos Gligoric
Published: 2025-10-03
Categories: cs.PL, cs.AI, cs.CL, cs.SE
arXiv: https://arxiv.org/abs/2510.03415v3

Recent work asks whether large language models (LLMs) condition their reasoning on explicit rules rather than statistical regularities from pretraining. Program execution provides a canonical instance: formal semantics define behavior through symbolic transition rules that can be systematically altered under distribution shift. We investigate whether LLMs can condition their reasoning on formal semantics through program execution and introduce PLSemanticsBench, pairing featherweight C programs with two semantic systems -- small-step operational semantics and K semantics -- and probing four capabilities: composing rules for final states, selecting rules when state is unmutated, sustaining such conditioning over long traces, and following supplied rules under novel semantics. To decouple semantic reasoning from syntactic familiarity, we redefine familiar operators to induce symbol-meaning conflict and introduce novel symbols defined only through the supplied rules, and stress-test models on Human-Written, LLM-Translated, and Fuzzer-Generated splits with increasing structural complexity. Across 11 frontier LLMs, strong final-state accuracy under standard semantics (up to 90%) drops sharply -- by as much as 40--60% points -- under semantic mutations and increasing structural complexity. Only a handful of models achieve non-zero long-horizon conditioning accuracy, and even the best systems reach just 35%. Together, these results suggest that contemporary LLMs often rely on pretrained lexical associations rather than systematically conditioning on supplied formal rules. PLSemanticsBench is publicly available at https://EngineeringSoftware.github.io/PLSemanticsBench.

---

### Report of the 2025 Workshop on Next-Generation Ecosystems for Scientific Computing: Harnessing Community, Software, and AI for Cross-Disciplinary Team Science

Authors: Lois Curfman McInnes, Dorian Arnold, Prasanna Balaprakash, Mike Bernhardt, Beth Cerny, Anshu Dubey, Roscoe Giles, Denice Ward Hood, Mary Ann Leung, Vanessa Lopez-Marrero, Paul Messina, Olivia B. Newton et al.
Published: 2025-10-03
Categories: cs.CE, cs.AI
arXiv: https://arxiv.org/abs/2510.03413v2

This report summarizes insights from the 2025 Workshop on Next-Generation Ecosystems for Scientific Computing: Harnessing Community, Software, and AI for Cross-Disciplinary Team Science, which convened more than 40 experts from national laboratories, academia, industry, and community organizations to chart a path toward more powerful, sustainable, and collaborative scientific software ecosystems. To address urgent challenges at the intersection of high-performance computing (HPC), AI, and scientific software, participants envisioned agile, robust ecosystems built through socio-technical co-design--the intentional integration of social and technical components as interdependent parts of a unified strategy. This approach combines advances in AI, HPC, and software with new models for cross-disciplinary collaboration, training, and workforce development. Key recommendations include building modular, trustworthy AI-enabled scientific software systems; enabling scientific teams to integrate AI systems into their workflows while preserving human creativity, trust, and scientific rigor; and creating innovative training pipelines that keep pace with rapid technological change. Pilot projects were identified as near-term catalysts, with initial priorities focused on hybrid AI/HPC infrastructure, cross-disciplinary collaboration and pedagogy, responsible AI guidelines, and prototyping of public-private partnerships. This report presents a vision of next-generation ecosystems for scientific computing where AI, software, hardware, and human expertise are interwoven to drive discovery, expand access, strengthen the workforce, and accelerate scientific progress.

---

### LegalSim: Multi-Agent Simulation of Legal Systems for Discovering Procedural Exploits

Authors: Sanket Badhe
Published: 2025-10-03
Categories: cs.MA, cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2510.03405v1

We present LegalSim, a modular multi-agent simulation of adversarial legal proceedings that explores how AI systems can exploit procedural weaknesses in codified rules. Plaintiff and defendant agents choose from a constrained action space (for example, discovery requests, motions, meet-and-confer, sanctions) governed by a JSON rules engine, while a stochastic judge model with calibrated grant rates, cost allocations, and sanction tendencies resolves outcomes. We compare four policies: PPO, a contextual bandit with an LLM, a direct LLM policy, and a hand-crafted heuristic; Instead of optimizing binary case outcomes, agents are trained and evaluated using effective win rate and a composite exploit score that combines opponent-cost inflation, calendar pressure, settlement pressure at low merit, and a rule-compliance margin. Across configurable regimes (e.g., bankruptcy stays, inter partes review, tax procedures) and heterogeneous judges, we observe emergent ``exploit chains'', such as cost-inflating discovery sequences and calendar-pressure tactics that remain procedurally valid yet systemically harmful. Evaluation via cross-play and Bradley-Terry ratings shows, PPO wins more often, the bandit is the most consistently competitive across opponents, the LLM trails them, and the heuristic is weakest. The results are stable in judge settings, and the simulation reveals emergent exploit chains, motivating red-teaming of legal rule systems in addition to model-level testing.

---