# Research Papers — 2025-10 · bundle page 89 of 217 > Full-text markdown of papers #4401–4450 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/89 [← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/88.md) [Next bundle →](https://aipod.dev/papers/archive/2025-10/page/90.md) ### Self-Supervised Learning to Fly using Efficient Semantic Segmentation and Metric Depth Estimation for Low-Cost Autonomous UAVs Authors: Sebastian Mocanu, Emil Slusanschi, Marius Leordeanu Published: 2025-10-18 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2510.16624v1 This paper presents a vision-only autonomous flight system for small UAVs operating in controlled indoor environments. The system combines semantic segmentation with monocular depth estimation to enable obstacle avoidance, scene exploration, and autonomous safe landing operations without requiring GPS or expensive sensors such as LiDAR. A key innovation is an adaptive scale factor algorithm that converts non-metric monocular depth predictions into accurate metric distance measurements by leveraging semantic ground plane detection and camera intrinsic parameters, achieving a mean distance error of 14.4 cm. The approach uses a knowledge distillation framework where a color-based Support Vector Machine (SVM) teacher generates training data for a lightweight U-Net student network (1.6M parameters) capable of real-time semantic segmentation. For more complex environments, the SVM teacher can be replaced with a state-of-the-art segmentation model. Testing was conducted in a controlled 5x4 meter laboratory environment with eight cardboard obstacles simulating urban structures. Extensive validation across 30 flight tests in a real-world environment and 100 flight tests in a digital-twin environment demonstrates that the combined segmentation and depth approach increases the distance traveled during surveillance and reduces mission time while maintaining 100% success rates. The system is further optimized through end-to-end learning, where a compact student neural network learns complete flight policies from demonstration data generated by our best-performing method, achieving an 87.5% autonomous mission success rate. This work advances practical vision-based drone navigation in structured environments, demonstrating solutions for metric depth estimation and computational efficiency challenges that enable deployment on resource-constrained platforms. --- ### Feedback Lunch: Learned Feedback Codes for Secure Communications Authors: Yingyao Zhou, Natasha Devroye, Onur Günlü Published: 2025-10-18 Categories: cs.IT, cs.AI, cs.CR, cs.LG, eess.SP arXiv: https://arxiv.org/abs/2510.16620v4 We consider reversely-degraded secure-communication channels, for which the secrecy capacity is zero if there is no channel feedback. Specifically, we focus on a seeded modular code design for the block-fading Gaussian wiretap channel with channel-output feedback, combining universal hash functions for security and learned feedback-based codes for reliability. The trade-off between communication reliability and information leakage is studied, illustrating that feedback enables agreeing on a secret key shared between legitimate parties, overcoming the security advantage of the eavesdropper. Our findings motivate code designs for sensing-assisted secure communications in the context of integrated sensing and communication (ISAC). --- ### Count Counts: Motivating Exploration in LLM Reasoning with Count-based Intrinsic Rewards Authors: Xuan Zhang, Ruixiao Li, Zhijian Zhou, Long Li, Yulei Qin, Ke Li, Xing Sun, Xiaoyu Tan, Chao Qu, Yuan Qi Published: 2025-10-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.16614v2 Reinforcement Learning (RL) has become a compelling way to strengthen the multi step reasoning ability of Large Language Models (LLMs). However, prevalent RL paradigms still lean on sparse outcome-based rewards and limited exploration, which often drives LLMs toward repetitive and suboptimal reasoning patterns. In this paper, we study the central question of how to design exploration for LLM reasoning and introduce MERCI (Motivating Exploration in LLM Reasoning with Count-based Intrinsic Rewards), a novel RL algorithm that augments policy optimization with a principled intrinsic reward. Building on the idea of count-based exploration, MERCI leverages a lightweight Coin Flipping Network (CFN) to estimate the pseudo count and further epistemic uncertainty over reasoning trajectories, and converts them into an intrinsic reward that values novelty while preserving the learning signal from task rewards. We integrate MERCI into some advanced RL frameworks like Group Relative Policy Optimization (GRPO). Experiments on complex reasoning benchmarks demonstrate that MERCI encourages richer and more varied chains of thought, significantly improves performance over strong baselines, and helps the policy escape local routines to discover better solutions. It indicates that our targeted intrinsic motivation can make exploration reliable for language model reasoning. --- ### Accelerated Learning on Large Scale Screens using Generative Library Models Authors: Eli N. Weinstein, Andrei Slabodkin, Mattia G. Gollub, Elizabeth B. Wood Published: 2025-10-18 Categories: stat.ML, cs.LG, q-bio.BM arXiv: https://arxiv.org/abs/2510.16612v1 Biological machine learning is often bottlenecked by a lack of scaled data. One promising route to relieving data bottlenecks is through high throughput screens, which can experimentally test the activity of $10^6-10^{12}$ protein sequences in parallel. In this article, we introduce algorithms to optimize high throughput screens for data creation and model training. We focus on the large scale regime, where dataset sizes are limited by the cost of measurement and sequencing. We show that when active sequences are rare, we maximize information gain if we only collect positive examples of active sequences, i.e. $x$ with $y>0$. We can correct for the missing negative examples using a generative model of the library, producing a consistent and efficient estimate of the true $p(y | x)$. We demonstrate this approach in simulation and on a large scale screen of antibodies. Overall, co-design of experiments and inference lets us accelerate learning dramatically. --- ### A Deep Learning Framework for Real-Time Image Processing in Medical Diagnostics: Enhancing Accuracy and Speed in Clinical Applications Authors: Melika Filvantorkaman, Maral Filvan Torkaman Published: 2025-10-18 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2510.16611v1 Medical imaging plays a vital role in modern diagnostics; however, interpreting high-resolution radiological data remains time-consuming and susceptible to variability among clinicians. Traditional image processing techniques often lack the precision, robustness, and speed required for real-time clinical use. To overcome these limitations, this paper introduces a deep learning framework for real-time medical image analysis designed to enhance diagnostic accuracy and computational efficiency across multiple imaging modalities, including X-ray, CT, and MRI. The proposed system integrates advanced neural network architectures such as U-Net, EfficientNet, and Transformer-based models with real-time optimization strategies including model pruning, quantization, and GPU acceleration. The framework enables flexible deployment on edge devices, local servers, and cloud infrastructures, ensuring seamless interoperability with clinical systems such as PACS and EHR. Experimental evaluations on public benchmark datasets demonstrate state-of-the-art performance, achieving classification accuracies above 92%, segmentation Dice scores exceeding 91%, and inference times below 80 milliseconds. Furthermore, visual explanation tools such as Grad-CAM and segmentation overlays enhance transparency and clinical interpretability. These results indicate that the proposed framework can substantially accelerate diagnostic workflows, reduce clinician workload, and support trustworthy AI integration in time-critical healthcare environments. --- ### Prior Knowledge Makes It Possible: From Sublinear Graph Algorithms to LLM Test-Time Methods Authors: Avrim Blum, Daniel Hsu, Cyrus Rashtchian, Donya Saless Published: 2025-10-18 Categories: cs.LG, cs.AI, cs.CC, cs.DS arXiv: https://arxiv.org/abs/2510.16609v3 Test-time augmentation, such as Retrieval-Augmented Generation (RAG) or tool use, critically depends on an interplay between a model's parametric knowledge and externally retrieved information. However, the theoretical underpinnings of this relationship remain poorly understood. Specifically, it is not clear how much pre-training knowledge is required to answer queries with a small number of augmentation steps, which is a desirable property in practice. To address this question, we formulate multi-step reasoning as an $s$-$t$ connectivity problem on a knowledge graph. We represent a model's pre-training parametric knowledge as a partial, potentially noisy subgraph. We view augmentation as querying an oracle for true edges that augment the model's knowledge. Then, we characterize the necessary and sufficient number of augmentation steps for the model to generate an accurate answer given partial prior knowledge. One key result shows a phase transition: if the prior knowledge graph over $n$ vertices is disconnected into small components, then finding a path via augmentation is inefficient and requires $Ω(\sqrt{n})$ queries. On the other hand, once the density of correct knowledge surpasses a threshold, forming a giant component, we can find paths with an expected constant number of queries. --- ### Asymptotically Stable Quaternion-valued Hopfield-structured Neural Network with Periodic Projection-based Supervised Learning Rules Authors: Tianwei Wang, Xinhui Ma, Wei Pang Published: 2025-10-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.16607v3 Motivated by the geometric advantages of quaternions in representing rotations and postures, we propose a quaternion-valued supervised learning Hopfield-structured neural network (QSHNN) with a fully connected structure inspired by the classic Hopfield neural network (HNN). Starting from a continuous-time dynamical model of HNNs, we extend the formulation to the quaternionic domain and establish the existence and uniqueness of fixed points with asymptotic stability. For the learning rules, we introduce a periodic projection strategy that modifies standard gradient descent by periodically projecting each 4*4 block of the weight matrix onto the closest quaternionic structure in the least-squares sense. This approach preserves both convergence and quaternionic consistency throughout training. Benefiting from this rigorous mathematical foundation, the experimental model implementation achieves high accuracy, fast convergence, and strong reliability across randomly generated target sets. Moreover, the evolution trajectories of the QSHNN exhibit well-bounded curvature, i.e., sufficient smoothness, which is crucial for applications such as control systems or path planning modules in robotic arms, where joint postures are parameterized by quaternion neurons. Beyond these application scenarios, the proposed model offers a practical implementation framework and a general mathematical methodology for designing neural networks under hypercomplex or non-commutative algebraic structures. --- ### Fine-tuning of Large Language Models for Constituency Parsing Using a Sequence to Sequence Approach Authors: Francisco Jose Cortes Delgado, Eduardo Martinez Gracia, Rafael Valencia Garcia Published: 2025-10-18 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.16604v1 Recent advances in natural language processing with large neural models have opened new possibilities for syntactic analysis based on machine learning. This work explores a novel approach to phrase-structure analysis by fine-tuning large language models (LLMs) to translate an input sentence into its corresponding syntactic structure. The main objective is to extend the capabilities of MiSintaxis, a tool designed for teaching Spanish syntax. Several models from the Hugging Face repository were fine-tuned using training data generated from the AnCora-ES corpus, and their performance was evaluated using the F1 score. The results demonstrate high accuracy in phrase-structure analysis and highlight the potential of this methodology. --- ### Uncertain Knowledge Graph Completion via Semi-Supervised Confidence Distribution Learning Authors: Tianxing Wu, Shutong Zhu, Jingting Wang, Ning Xu, Guilin Qi, Haofen Wang Published: 2025-10-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.16601v2 Uncertain knowledge graphs (UKGs) associate each triple with a confidence score to provide more precise knowledge representations. Recently, since real-world UKGs suffer from the incompleteness, uncertain knowledge graph (UKG) completion attracts more attention, aiming to complete missing triples and confidences. Current studies attempt to learn UKG embeddings to solve this problem, but they neglect the extremely imbalanced distributions of triple confidences. This causes that the learnt embeddings are insufficient to high-quality UKG completion. Thus, in this paper, to address the above issue, we propose a new semi-supervised Confidence Distribution Learning (ssCDL) method for UKG completion, where each triple confidence is transformed into a confidence distribution to introduce more supervision information of different confidences to reinforce the embedding learning process. ssCDL iteratively learns UKG embedding by relational learning on labeled data (i.e., existing triples with confidences) and unlabeled data with pseudo labels (i.e., unseen triples with the generated confidences), which are predicted by meta-learning to augment the training data and rebalance the distribution of triple confidences. Experiments on two UKG datasets demonstrate that ssCDL consistently outperforms state-of-the-art baselines in different evaluation metrics. --- ### VisionSelector: End-to-End Learnable Visual Token Compression for Efficient Multimodal LLMs Authors: Jiaying Zhu, Yurui Zhu, Xin Lu, Wenrui Yan, Dong Li, Kunlin Liu, Xueyang Fu, Zheng-Jun Zha Published: 2025-10-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.16598v2 Multimodal Large Language Models (MLLMs) encounter significant computational and memory bottlenecks from the massive number of visual tokens generated by high-resolution images or multi-image inputs. Previous token compression techniques are often constrained by heuristic rules that risk discarding critical information. They may suffer from biases, such as attention sinks, that lead to sharp performance drops under aggressive compression ratios. To address these limitations, we reformulate token compression as a lightweight plug-and-play framework and turn it into an end-to-end learnable decision process. Specifically, we propose VisionSelector, a scorer module decoupled from the MLLM backbone that incorporates a differentiable Top-K mechanism and a curriculum annealing strategy to bridge the training-inference gap, enabling efficient and adaptive token selection across various compression rates. Remarkably lightweight with only 12.85M trainable parameters, VisionSelector demonstrates generalization across various compression rates and adaptively identifies critical tokens. This leads to superior performance across the evaluated compression budgets, evidenced by preserving 100% performance on MME with a 30% retention budget, outperforming representative heuristic baselines by 12.14 percentage points at a 10% retention budget, and doubling prefill speed. Our code is available at https://github.com/JulietChoo/VisionSelector . --- ### SHIELD: Suppressing Hallucinations In LVLM Encoders via Bias and Vulnerability Defense Authors: Yiyang Huang, Liang Shi, Yitian Zhang, Yi Xu, Yun Fu Published: 2025-10-18 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2510.16596v2 Large Vision-Language Models (LVLMs) excel in diverse cross-modal tasks. However, object hallucination, where models produce plausible but inaccurate object descriptions, remains a significant challenge. In contrast to previous work focusing on LLM components, this paper is the first to trace LVLM hallucinations to visual encoders and identifies three key issues: statistical bias, inherent bias, and vulnerability. To address these challenges, we propose SHIELD, a training-free framework that mitigates hallucinations through three strategies: re-weighting visual tokens to reduce statistical bias, introducing noise-derived tokens to counter inherent bias, and applying adversarial attacks with contrastive decoding to address vulnerability. Experiments demonstrate that SHIELD effectively mitigates object hallucinations across diverse benchmarks and LVLM families. Moreover, SHIELD achieves strong performance on the general LVLM benchmark, highlighting its broad applicability. Code is available at https://github.com/hukcc/SHIELD. --- ### Symmetry and Generalisation in Neural Approximations of Renormalisation Transformations Authors: Cassidy Ashworth, Pietro Liò, Francesco Caso Published: 2025-10-18 Categories: cs.LG, cond-mat.stat-mech, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2510.16591v1 Deep learning models have proven enormously successful at using multiple layers of representation to learn relevant features of structured data. Encoding physical symmetries into these models can improve performance on difficult tasks, and recent work has motivated the principle of parameter symmetry breaking and restoration as a unifying mechanism underlying their hierarchical learning dynamics. We evaluate the role of parameter symmetry and network expressivity in the generalisation behaviour of neural networks when learning a real-space renormalisation group (RG) transformation, using the central limit theorem (CLT) as a test case map. We consider simple multilayer perceptrons (MLPs) and graph neural networks (GNNs), and vary weight symmetries and activation functions across architectures. Our results reveal a competition between symmetry constraints and expressivity, with overly complex or overconstrained models generalising poorly. We analytically demonstrate this poor generalisation behaviour for certain constrained MLP architectures by recasting the CLT as a cumulant recursion relation and making use of an established framework to propagate cumulants through MLPs. We also empirically validate an extension of this framework from MLPs to GNNs, elucidating the internal information processing performed by these more complex models. These findings offer new insight into the learning dynamics of symmetric networks and their limitations in modelling structured physical transformations. --- ### Atom-anchored LLMs speak Chemistry: A Retrosynthesis Demonstration Authors: Alan Kai Hassen, Andrius Bernatavicius, Antonius P. A. Janssen, Mike Preuss, Gerard J. P. van Westen, Djork-Arné Clevert Published: 2025-10-18 Categories: cs.LG, cs.AI, q-bio.BM arXiv: https://arxiv.org/abs/2510.16590v2 Applications of machine learning in chemistry are often limited by the scarcity and expense of labeled data, restricting traditional supervised methods. In this work, we introduce a framework for molecular reasoning using general-purpose Large Language Models (LLMs) that operates without requiring task-specific model training. Our method anchors chain-of-thought reasoning to the molecular structure by using unique atomic identifiers. First, the LLM performs a zero-shot task to identify relevant fragments and their associated chemical labels or transformation classes. In an optional second step, this position-aware information is used in a few-shot task with provided class examples to predict the chemical transformation. We apply our framework to single-step retrosynthesis, a task where LLMs have previously underperformed. Across academic benchmarks and expert-validated drug discovery molecules, our work enables LLMs to achieve high success rates in identifying chemically plausible reaction sites ($\geq90\%$), named reaction classes ($\geq40\%$), and final reactants ($\geq74\%$). Ultimately, our work establishes a general blueprint for applying LLMs to challenges where molecular reasoning and molecular transformations are key, positioning atom-anchored LLMs as a powerful solution for data-scarce chemistry domains. --- ### Copy-Augmented Representation for Structure Invariant Template-Free Retrosynthesis Authors: Jiaxi Zhuang, Yu Zhang, Aimin Zhou, Ying Qian Published: 2025-10-18 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2510.16588v1 Retrosynthesis prediction is fundamental to drug discovery and chemical synthesis, requiring the identification of reactants that can produce a target molecule. Current template-free methods struggle to capture the structural invariance inherent in chemical reactions, where substantial molecular scaffolds remain unchanged, leading to unnecessarily large search spaces and reduced prediction accuracy. We introduce C-SMILES, a novel molecular representation that decomposes traditional SMILES into element-token pairs with five special tokens, effectively minimizing editing distance between reactants and products. Building upon this representation, we incorporate a copy-augmented mechanism that dynamically determines whether to generate new tokens or preserve unchanged molecular fragments from the product. Our approach integrates SMILES alignment guidance to enhance attention consistency with ground-truth atom mappings, enabling more chemically coherent predictions. Comprehensive evaluation on USPTO-50K and large-scale USPTO-FULL datasets demonstrates significant improvements: 67.2% top-1 accuracy on USPTO-50K and 50.8% on USPTO-FULL, with 99.9% validity in generated molecules. This work establishes a new paradigm for structure-aware molecular generation with direct applications in computational drug discovery. --- ### Multi-Marginal Schrödinger Bridge Matching Authors: Byoungwoo Park, Juho Lee Published: 2025-10-18 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2510.16587v2 Understanding the continuous evolution of populations from discrete temporal snapshots is a critical research challenge, particularly in fields like developmental biology and systems medicine where longitudinal tracking of individual entities is often impossible. Such trajectory inference is vital for unraveling the mechanisms of dynamic processes. While Schrödinger Bridge (SB) offer a potent framework, their traditional application to pairwise time points can be insufficient for systems defined by multiple intermediate snapshots. This paper introduces Multi-Marginal Schrödinger Bridge Matching (MSBM), a novel algorithm specifically designed for the multi-marginal SB problem. MSBM extends iterative Markovian fitting (IMF) to effectively handle multiple marginal constraints. This technique ensures robust enforcement of all intermediate marginals while preserving the continuity of the learned global dynamics across the entire trajectory. Empirical validations on synthetic data and real-world single-cell RNA sequencing datasets demonstrate the competitive or superior performance of MSBM in capturing complex trajectories and respecting intermediate distributions, all with notable computational efficiency. --- ### Can Knowledge-Graph-based Retrieval Augmented Generation Really Retrieve What You Need? Authors: Junchi Yu, Yujie Liu, Jindong Gu, Philip Torr, Dongzhan Zhou Published: 2025-10-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.16582v1 Retrieval-Augmented Generation (RAG) based on knowledge graphs (KGs) enhances large language models (LLMs) by providing structured and interpretable external knowledge. However, existing KG-based RAG methods struggle to retrieve accurate and diverse information from text-rich KGs for complex real-world queries. Process Reward Models (PRMs) offer a way to align the retrieval process of KG-based RAG with query-specific knowledge requirements, but they heavily rely on process-level supervision signals that are expensive and hard to obtain on KGs. To address this challenge, we propose GraphFlow, a framework that efficiently retrieves accurate and diverse knowledge required for real-world queries from text-rich KGs. GraphFlow employs a transition-based flow matching objective to jointly optimize a retrieval policy and a flow estimator. The flow estimator factorizes the reward of the retrieval outcome into the intermediate retrieval states. Such reward factorization guides the retrieval policy to retrieve candidates from KGs in proportion to their reward. This allows GraphFlow to explore high-quality regions of KGs that yield diverse and relevant results. We evaluate GraphFlow on the STaRK benchmark, which includes real-world queries from multiple domains over text-rich KGs. GraphFlow outperforms strong KG-RAG baselines, including GPT-4o, by 10% on average in hit rate and recall. It also shows strong generalization to unseen KGs, demonstrating its effectiveness and robustness. --- ### Patronus: Safeguarding Text-to-Image Models against White-Box Adversaries Authors: Xinfeng Li, Shengyuan Pang, Jialin Wu, Jiangyi Deng, Huanlong Zhong, Yanjiao Chen, Jie Zhang, Wenyuan Xu Published: 2025-10-18 Categories: cs.CR, cs.CV arXiv: https://arxiv.org/abs/2510.16581v1 Text-to-image (T2I) models, though exhibiting remarkable creativity in image generation, can be exploited to produce unsafe images. Existing safety measures, e.g., content moderation or model alignment, fail in the presence of white-box adversaries who know and can adjust model parameters, e.g., by fine-tuning. This paper presents a novel defensive framework, named Patronus, which equips T2I models with holistic protection to defend against white-box adversaries. Specifically, we design an internal moderator that decodes unsafe input features into zero vectors while ensuring the decoding performance of benign input features. Furthermore, we strengthen the model alignment with a carefully designed non-fine-tunable learning mechanism, ensuring the T2I model will not be compromised by malicious fine-tuning. We conduct extensive experiments to validate the intactness of the performance on safe content generation and the effectiveness of rejecting unsafe content generation. Results also confirm the resilience of Patronus against various fine-tuning attacks by white-box adversaries. --- ### AI-Generated Text Detection in Low-Resource Languages: A Case Study on Urdu Authors: Muhammad Ammar, Hadiya Murad Hadi, Usman Majeed Butt Published: 2025-10-18 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.16573v1 Large Language Models (LLMs) are now capable of generating text that closely resembles human writing, making them powerful tools for content creation, but this growing ability has also made it harder to tell whether a piece of text was written by a human or by a machine. This challenge becomes even more serious for languages like Urdu, where there are very few tools available to detect AI-generated text. To address this gap, we propose a novel AI-generated text detection framework tailored for the Urdu language. A balanced dataset comprising 1,800 humans authored, and 1,800 AI generated texts, sourced from models such as Gemini, GPT-4o-mini, and Kimi AI was developed. Detailed linguistic and statistical analysis was conducted, focusing on features such as character and word counts, vocabulary richness (Type Token Ratio), and N-gram patterns, with significance evaluated through t-tests and MannWhitney U tests. Three state-of-the-art multilingual transformer models such as mdeberta-v3-base, distilbert-base-multilingualcased, and xlm-roberta-base were fine-tuned on this dataset. The mDeBERTa-v3-base achieved the highest performance, with an F1-score 91.29 and accuracy of 91.26% on the test set. This research advances efforts in contesting misinformation and academic misconduct in Urdu-speaking communities and contributes to the broader development of NLP tools for low resource languages. --- ### Ripple Effect Protocol: Coordinating Agent Populations Authors: Ayush Chopra, Aman Sharma, Feroz Ahmad, Luca Muscariello, Vijoy Pandey, Ramesh Raskar Published: 2025-10-18 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2510.16572v1 Modern AI agents can exchange messages using protocols such as A2A and ACP, yet these mechanisms emphasize communication over coordination. As agent populations grow, this limitation produces brittle collective behavior, where individually smart agents converge on poor group outcomes. We introduce the Ripple Effect Protocol (REP), a coordination protocol in which agents share not only their decisions but also lightweight sensitivities - signals expressing how their choices would change if key environmental variables shifted. These sensitivities ripple through local networks, enabling groups to align faster and more stably than with agent-centric communication alone. We formalize REP's protocol specification, separating required message schemas from optional aggregation rules, and evaluate it across scenarios with varying incentives and network topologies. Benchmarks across three domains: (i) supply chain cascades (Beer Game), (ii) preference aggregation in sparse networks (Movie Scheduling), and (iii) sustainable resource allocation (Fishbanks) show that REP improves coordination accuracy and efficiency over A2A by 41 to 100%, while flexibly handling multimodal sensitivity signals from LLMs. By making coordination a protocol-level capability, REP provides scalable infrastructure for the emerging Internet of Agents --- ### Hallucination Benchmark for Speech Foundation Models Authors: Alkis Koudounas, Moreno La Quatra, Manuel Giollo, Sabato Marco Siniscalchi, Elena Baralis Published: 2025-10-18 Categories: cs.CL, cs.SD, eess.AS arXiv: https://arxiv.org/abs/2510.16567v1 Hallucinations in automatic speech recognition (ASR) systems refer to fluent and coherent transcriptions produced by neural ASR models that are completely unrelated to the underlying acoustic input (i.e., the speech signal). While similar to conventional decoding errors in potentially compromising the usability of transcriptions for downstream applications, hallucinations can be more detrimental due to their preservation of syntactically and semantically plausible structure. This apparent coherence can mislead subsequent processing stages and introduce serious risks, particularly in critical domains such as healthcare and law. Conventional evaluation metrics are primarily centered on error-based metrics and fail to distinguish between phonetic inaccuracies and hallucinations. Consequently, there is a critical need for new evaluation frameworks that can effectively identify and assess models with a heightened propensity for generating hallucinated content. To this end, we introduce SHALLOW, the first benchmark framework that systematically categorizes and quantifies hallucination phenomena in ASR along four complementary axes: lexical, phonetic, morphological, and semantic. We define targeted metrics within each category to produce interpretable profiles of model behavior. Through evaluation across various architectures and speech domains, we have found that SHALLOW metrics correlate strongly with word error rate (WER) when recognition quality is high (i.e., low WER). Still, this correlation weakens substantially as WER increases. SHALLOW, therefore, captures fine-grained error patterns that WER fails to distinguish under degraded and challenging conditions. Our framework supports specific diagnosis of model weaknesses and provides feedback for model improvement beyond what aggregate error rates can offer. --- ### Language over Content: Tracing Cultural Understanding in Multilingual Large Language Models Authors: Seungho Cho, Changgeon Ko, Eui Jun Hwang, Junmyeong Lee, Huije Lee, Jong C. Park Published: 2025-10-18 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.16565v2 Large language models (LLMs) are increasingly used across diverse cultural contexts, making accurate cultural understanding essential. Prior evaluations have mostly focused on output-level performance, obscuring the factors that drive differences in responses, while studies using circuit analysis have covered few languages and rarely focused on culture. In this work, we trace LLMs' internal cultural understanding mechanisms by measuring activation path overlaps when answering semantically equivalent questions under two conditions: varying the target country while fixing the question language, and varying the question language while fixing the country. We also use same-language country pairs to disentangle language from cultural aspects. Results show that internal paths overlap more for same-language, cross-country questions than for cross-language, same-country questions, indicating strong language-specific patterns. Notably, the South Korea-North Korea pair exhibits low overlap and high variability, showing that linguistic similarity does not guarantee aligned internal representation. --- ### BuildArena: A Physics-Aligned Interactive Benchmark of LLMs for Engineering Construction Authors: Tian Xia, Tianrun Gao, Wenhao Deng, Long Wei, Xiaowei Qian, Chenglei Yu, Tailin Wu Published: 2025-10-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.16559v7 Engineering construction automation aims to transform natural language specifications into physically viable structures, requiring complex integrated reasoning under strict physical constraints. While modern LLMs possess broad knowledge and strong reasoning capabilities that make them promising candidates for this domain, their construction competencies remain largely unevaluated. To address this gap, we introduce BuildArena, the first physics-aligned interactive benchmark designed for language-driven engineering construction. Technically, it contributes to the community in two aspects: (1) an extendable task design strategy spanning static and dynamic mechanics across multiple difficulty tiers; (2) a 3D Spatial Geometric Computation Library for supporting construction based on language instructions. On nine frontier LLMs and three additional open-weight models, BuildArena comprehensively evaluates their capabilities for language-driven and physics-grounded construction automation. We release the code at https://github.com/AI4Science-WestlakeU/BuildArena to benefit construction automation in engineering applications. --- ### A First Look at the Security Issues in the Model Context Protocol Ecosystem Authors: Xiaofan Li, Xing Gao Published: 2025-10-18 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2510.16558v2 The Model Context Protocol (MCP) has emerged as a standard for connecting large language models (LLMs) with external tools. However, this MCP ecosystem introduces new security risks across hosts, servers, and registries. In this paper, we present the first cross-entity security study of MCP under a two-stage attack surface. At the registry-level, weak vetting and ownership checks allow adversarial or hijacked servers to enter hosts. After integration, attacker-controlled tool metadata can shape LLM reasoning and induce attacker-intended operations, which hosts execute without independent verification. Code-level vulnerabilities (e.g., code injection) are not required but can amplify attacker-controlled parameters into exploitation. We analyze 67,057 servers across six public registries and identify widespread conditions enabling server hijacking and invocation manipulation. We further implement MCPInspect, a pre-integration analysis tool that detects misleading tool metadata and exploitable code vulnerabilities, identifying 833 vulnerable servers and 18 with suspicious descriptions. --- ### Fit for Purpose? Deepfake Detection in the Real World Authors: Guangyu Lin, Li Lin, Christina P. Walker, Daniel S. Schiff, Shu Hu Published: 2025-10-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.16556v2 The rapid proliferation of AI-generated content, driven by advances in generative adversarial networks, diffusion models, and multimodal large language models, has made the creation and dissemination of synthetic media effortless, heightening the risks of misinformation, particularly political deepfakes that distort truth and undermine trust in political institutions. In turn, governments, research institutions, and industry have strongly promoted deepfake detection initiatives as solutions. Yet, most existing models are trained and validated on synthetic, laboratory-controlled datasets, limiting their generalizability to the kinds of real-world political deepfakes circulating on social platforms that affect the public. In this work, we introduce the first systematic benchmark based on the Political Deepfakes Incident Database, a curated collection of real-world political deepfakes shared on social media since 2018. Our study includes a systematic evaluation of state-of-the-art deepfake detectors across academia, government, and industry. We find that the detectors from academia and government perform relatively poorly. While paid detection tools achieve relatively higher performance than free-access models, all evaluated detectors struggle to generalize effectively to authentic political deepfakes, and are vulnerable to simple manipulations, especially in the video domain. Results urge the need for politically contextualized deepfake detection frameworks to better safeguard the public in real-world settings. --- ### Urban-R1: Reinforced MLLMs Mitigate Geospatial Biases for Urban General Intelligence Authors: Qiongyan Wang, Xingchen Zou, Yutian Jiang, Haomin Wen, Jiaheng Wei, Qingsong Wen, Yuxuan Liang Published: 2025-10-18 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.16555v1 Rapid urbanization intensifies the demand for Urban General Intelligence (UGI), referring to AI systems that can understand and reason about complex urban environments. Recent studies have built urban foundation models using supervised fine-tuning (SFT) of LLMs and MLLMs, yet these models exhibit persistent geospatial bias, producing regionally skewed predictions and limited generalization. To this end, we propose Urban-R1, a reinforcement learning-based post-training framework that aligns MLLMs with the objectives of UGI. Urban-R1 adopts Group Relative Policy Optimization (GRPO) to optimize reasoning across geographic groups and employs urban region profiling as a proxy task to provide measurable rewards from multimodal urban data. Extensive experiments across diverse regions and tasks show that Urban-R1 effectively mitigates geo-bias and improves cross-region generalization, outperforming both SFT-trained and closed-source models. Our results highlight reinforcement learning alignment as a promising pathway toward equitable and trustworthy urban intelligence. --- ### LANPO: Bootstrapping Language and Numerical Feedback for Reinforcement Learning in LLMs Authors: Ang Li, Yifei Wang, Zhihang Yuan, Stefanie Jegelka, Yisen Wang Published: 2025-10-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.16552v1 Reinforcement learning in large language models (LLMs) often relies on scalar rewards, a practice that discards valuable textual rationale buried in the rollouts, forcing the model to explore \textit{de novo} with each attempt and hindering sample efficiency. While LLMs can uniquely learn from language feedback provided in-context, naively integrating on-line experiences into RL training presents a paradox: feedback from the same problem risks information leakage and memorization, while feedback from different problems often leads to behavior collapse due to irrelevant context. To resolve this tension, we propose \textbf{Language-And-Numerical Policy Optimization (LANPO)}, a framework that cleanly separates the roles of feedback: language guides exploration, while numerical rewards drive optimization. LANPO builds a dynamic experience pool from past trials and introduces two principles to ensure feedback is effective: \emph{Reward-Agnostic Reflection} for safe intra-sample self-correction and \emph{Relevant Abstraction} to distill generalizable lessons from inter-sample experiences. Across mathematical reasoning benchmarks, LANPO enables 7B and 14B models to significantly outperform strong baselines trained with GRPO in test accuracy. Our work provides a robust method for integrating historical experiences into the LLM RL loop, creating more effective and data-efficient learning agents. --- ### From Reviews to Actionable Insights: An LLM-Based Approach for Attribute and Feature Extraction Authors: Khaled Boughanmi, Kamel Jedidi, Nour Jedidi Published: 2025-10-18 Categories: stat.ML, cs.LG, econ.EM arXiv: https://arxiv.org/abs/2510.16551v3 This research proposes a systematic, large language model (LLM) approach for extracting product and service attributes, features, and associated sentiments from customer reviews. Grounded in marketing theory, the framework distinguishes perceptual attributes from actionable features, producing interpretable and managerially actionable insights. We apply the methodology to 20,000 Yelp reviews of Starbucks stores and evaluate eight prompt variants on a random subset of reviews. Model performance is assessed through agreement with human annotations and predictive validity for customer ratings. Results show high consistency between LLMs and human coders and strong predictive validity, confirming the reliability of the approach. Human coders required a median of six minutes per review, whereas the LLM processed each in two seconds, delivering comparable insights at a scale unattainable through manual coding. Managerially, the analysis identifies attributes and features that most strongly influence customer satisfaction and their associated sentiments, enabling firms to pinpoint "joy points," address "pain points," and design targeted interventions. We demonstrate how structured review data can power an actionable marketing dashboard that tracks sentiment over time and across stores, benchmarks performance, and highlights high-leverage features for improvement. Simulations indicate that enhancing sentiment for key service features could yield 1-2% average revenue gains per store. --- ### ReviewGuard: Enhancing Deficient Peer Review Detection via LLM-Driven Data Augmentation Authors: Haoxuan Zhang, Ruochi Li, Sarthak Shrestha, Shree Harshini Mamidala, Revanth Putta, Arka Krishan Aggarwal, Ting Xiao, Junhua Ding, Haihua Chen Published: 2025-10-18 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.16549v2 Peer review serves as the gatekeeper of science, yet the surge in submissions and widespread adoption of large language models (LLMs) in scholarly evaluation present unprecedented challenges. While recent work has focused on using LLMs to improve review efficiency, unchecked deficient reviews from both human experts and AI systems threaten to systematically undermine academic integrity. To address this issue, we introduce ReviewGuard, an automated system for detecting and categorizing deficient reviews through a four-stage LLM-driven framework: data collection from ICLR and NeurIPS on OpenReview, GPT-4.1 annotation with human validation, synthetic data augmentation yielding 6,634 papers with 24,657 real and 46,438 synthetic reviews, and fine-tuning of encoder-based models and open-source LLMs. Feature analysis reveals that deficient reviews exhibit lower rating scores, higher self-reported confidence, reduced structural complexity, and more negative sentiment than sufficient reviews. AI-generated text detection shows dramatic increases in AI-authored reviews since ChatGPT's emergence. Mixed training with synthetic and real data substantially improves detection performance - for example, Qwen 3-8B achieves recall of 0.6653 and F1 of 0.7073, up from 0.5499 and 0.5606 respectively. This study presents the first LLM-driven system for detecting deficient peer reviews, providing evidence to inform AI governance in peer review. Code, prompts, and data are available at https://github.com/haoxuan-unt2024/ReviewGuard --- ### NeurIPT: Foundation Model for Neural Interfaces Authors: Zitao Fang, Chenxuan Li, Hongting Zhou, Shuyang Yu, Guodong Du, Ashwaq Qasem, Yang Lu, Jing Li, Junsong Zhang, Sim Kuan Goh Published: 2025-10-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.16548v1 Electroencephalography (EEG) has wide-ranging applications, from clinical diagnosis to brain-computer interfaces (BCIs). With the increasing volume and variety of EEG data, there has been growing interest in establishing foundation models (FMs) to scale up and generalize neural decoding. Despite showing early potential, applying FMs to EEG remains challenging due to substantial inter-subject, inter-task, and inter-condition variability, as well as diverse electrode configurations across recording setups. To tackle these open challenges, we propose NeurIPT, a foundation model developed for diverse EEG-based Neural Interfaces with a Pre-trained Transformer by capturing both homogeneous and heterogeneous spatio-temporal characteristics inherent in EEG signals. Temporally, we introduce Amplitude-Aware Masked Pretraining (AAMP), masking based on signal amplitude rather than random intervals, to learn robust representations across varying signal intensities beyond local interpolation. Moreover, this temporal representation is enhanced by a Progressive Mixture-of-Experts (PMoE) architecture, where specialized expert subnetworks are progressively introduced at deeper layers, adapting effectively to the diverse temporal characteristics of EEG signals. Spatially, NeurIPT leverages the 3D physical coordinates of electrodes, enabling effective transfer of embedding across varying EEG settings, and develops Intra-Inter Lobe Pooling (IILP) during fine-tuning to efficiently exploit regional brain features. Empirical evaluations across eight downstream BCI datasets, via fine-tuning, demonstrated NeurIPT consistently achieved state-of-the-art performance, highlighting its broad applicability and robust generalization. Our work pushes forward the state of FMs in EEG and offers insights into scalable and generalizable neural information processing systems. --- ### Predicting life satisfaction using machine learning and explainable AI Authors: Alif Elham Khan, Mohammad Junayed Hasan, Humayra Anjum, Nabeel Mohammed, Sifat Momen Published: 2025-10-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.16547v1 Life satisfaction is a crucial facet of human well-being. Hence, research on life satisfaction is incumbent for understanding how individuals experience their lives and influencing interventions targeted at enhancing mental health and well-being. Life satisfaction has traditionally been measured using analog, complicated, and frequently error-prone methods. These methods raise questions concerning validation and propagation. However, this study demonstrates the potential for machine learning algorithms to predict life satisfaction with a high accuracy of 93.80% and a 73.00% macro F1-score. The dataset comes from a government survey of 19000 people aged 16-64 years in Denmark. Using feature learning techniques, 27 significant questions for assessing contentment were extracted, making the study highly reproducible, simple, and easily interpretable. Furthermore, clinical and biomedical large language models (LLMs) were explored for predicting life satisfaction by converting tabular data into natural language sentences through mapping and adding meaningful counterparts, achieving an accuracy of 93.74% and macro F1-score of 73.21%. It was found that life satisfaction prediction is more closely related to the biomedical domain than the clinical domain. Ablation studies were also conducted to understand the impact of data resampling and feature selection techniques on model performance. Moreover, the correlation between primary determinants with different age brackets was analyzed, and it was found that health condition is the most important determinant across all ages. This study demonstrates how machine learning, large language models and XAI can jointly contribute to building trust and understanding in using AI to investigate human behavior, with significant ramifications for academics and professionals working to quantify and comprehend subjective well-being. --- ### Watch Where You Move: Region-aware Dynamic Aggregation and Excitation for Gait Recognition Authors: Binyuan Huang, Yongdong Luo, Xianda Guo, Xiawu Zheng, Zheng Zhu, Jiahui Pan, Chengju Zhou Published: 2025-10-18 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2510.16541v1 Deep learning-based gait recognition has achieved great success in various applications. The key to accurate gait recognition lies in considering the unique and diverse behavior patterns in different motion regions, especially when covariates affect visual appearance. However, existing methods typically use predefined regions for temporal modeling, with fixed or equivalent temporal scales assigned to different types of regions, which makes it difficult to model motion regions that change dynamically over time and adapt to their specific patterns. To tackle this problem, we introduce a Region-aware Dynamic Aggregation and Excitation framework (GaitRDAE) that automatically searches for motion regions, assigns adaptive temporal scales and applies corresponding attention. Specifically, the framework includes two core modules: the Region-aware Dynamic Aggregation (RDA) module, which dynamically searches the optimal temporal receptive field for each region, and the Region-aware Dynamic Excitation (RDE) module, which emphasizes the learning of motion regions containing more stable behavior patterns while suppressing attention to static regions that are more susceptible to covariates. Experimental results show that GaitRDAE achieves state-of-the-art performance on several benchmark datasets. --- ### Enhancing Compositional Reasoning in CLIP via Reconstruction and Alignment of Text Descriptions Authors: Jihoon Kwon, Kyle Min, Jy-yong Sohn Published: 2025-10-18 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2510.16540v1 Despite recent advances, vision-language models trained with standard contrastive objectives still struggle with compositional reasoning -- the ability to understand structured relationships between visual and linguistic elements. This shortcoming is largely due to the tendency of the text encoder to focus on individual words rather than their relations, a limitation reinforced by contrastive training that primarily aligns words with visual objects. In this paper, we introduce REconstruction and Alignment of text Descriptions (READ), a fine-tuning method designed to enhance compositional reasoning by adding two auxiliary objectives to the contrastive learning: (1) a token-level reconstruction objective, where a frozen pre-trained decoder reconstructs alternative captions based on the embedding of the original caption; and (2) a sentence-level alignment objective, which explicitly aligns paraphrased sentences in the embedding space. We show that READ-CLIP, a model derived by applying the READ method to the pre-trained CLIP model, achieves the state-of-the-art performance across five major compositional reasoning benchmarks, outperforming the strongest conventional fine-tuning baseline by up to 4.1%. Furthermore, applying the READ to existing CLIP variants (including NegCLIP and FSC-CLIP) also improves performance on these benchmarks. Quantitative and qualitative analyses reveal that our proposed objectives -- reconstruction and alignment -- offer complementary benefits: the former encourages the encoder to capture relationships between words within a caption, while the latter ensures consistent representations for paraphrases expressed with different wording. --- ### Few-Label Multimodal Modeling of SNP Variants and ECG Phenotypes Using Large Language Models for Cardiovascular Risk Stratification Authors: Niranjana Arun Menon, Yulong Li, Iqra Farooq, Sara Ahmed, Muhammad Awais, Imran Razzak Published: 2025-10-18 Categories: q-bio.QM, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.16536v1 Cardiovascular disease (CVD) risk stratification remains a major challenge due to its multifactorial nature and limited availability of high-quality labeled datasets. While genomic and electrophysiological data such as SNP variants and ECG phenotypes are increasingly accessible, effectively integrating these modalities in low-label settings is non-trivial. This challenge arises from the scarcity of well-annotated multimodal datasets and the high dimensionality of biological signals, which limit the effectiveness of conventional supervised models. To address this, we present a few-label multimodal framework that leverages large language models (LLMs) to combine genetic and electrophysiological information for cardiovascular risk stratification. Our approach incorporates a pseudo-label refinement strategy to adaptively distill high-confidence labels from weakly supervised predictions, enabling robust model fine-tuning with only a small set of ground-truth annotations. To enhance the interpretability, we frame the task as a Chain of Thought (CoT) reasoning problem, prompting the model to produce clinically relevant rationales alongside predictions. Experimental results demonstrate that the integration of multimodal inputs, few-label supervision, and CoT reasoning improves robustness and generalizability across diverse patient profiles. Experimental results using multimodal SNP variants and ECG-derived features demonstrated comparable performance to models trained on the full dataset, underscoring the promise of LLM-based few-label multimodal modeling for advancing personalized cardiovascular care. --- ### Hey Pentti, We Did It Again!: Differentiable vector-symbolic types that prove polynomial termination Authors: Eilene Tomkins-Flanagan, Connor Hanley, Mary A. Kelly Published: 2025-10-18 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.16533v1 We present a typed computer language, Doug, in which all typed programs may be proved to halt in polynomial time, encoded in a vector-symbolic architecture (VSA). Doug is just an encoding of the light linear functional programming language (LLFPL) described by (Schimanski2009, ch. 7). The types of Doug are encoded using a slot-value encoding scheme based on holographic declarative memory (HDM; Kelly, 2020). The terms of Doug are encoded using a variant of the Lisp VSA defined by (Flanagan, 2024). Doug allows for some points on the embedding space of a neural network to be interpreted as types, where the types of nearby points are similar both in structure and content. Types in Doug are therefore learnable by a neural network. Following (Chollet, 2019), (Card, 1983), and (Newell, 1981), we view skill as the application of a procedure, or program of action, that causes a goal to be satisfied. Skill acquisition may therefore be expressed as program synthesis. Using Doug, we hope to describe a form of learning of skilled behaviour that follows a human-like pace of skill acquisition (i.e., substantially faster than brute force; Heathcote, 2000), exceeding the efficiency of all currently existing approaches (Kaplan, 2020; Jones, 2021; Chollet, 2024). Our approach brings us one step closer to modeling human mental representations, as they must actually exist in the brain, and those representations' acquisition, as they are actually learned. --- ### Realizing LLMs' Causal Potential Requires Science-Grounded, Novel Benchmarks Authors: Ashutosh Srivastava, Lokesh Nagalapatti, Gautam Jajoo, Aniket Vashishtha, Parameswari Krishnamurthy, Amit Sharma Published: 2025-10-18 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2510.16530v1 Recent claims of strong performance by Large Language Models (LLMs) on causal discovery are undermined by a key flaw: many evaluations rely on benchmarks likely included in pretraining corpora. Thus, apparent success suggests that LLM-only methods, which ignore observational data, outperform classical statistical approaches. We challenge this narrative by asking: Do LLMs truly reason about causal structure, and how can we measure it without memorization concerns? Can they be trusted for real-world scientific discovery? We argue that realizing LLMs' potential for causal analysis requires two shifts: (P.1) developing robust evaluation protocols based on recent scientific studies to guard against dataset leakage, and (P.2) designing hybrid methods that combine LLM-derived knowledge with data-driven statistics. To address P.1, we encourage evaluating discovery methods on novel, real-world scientific studies. We outline a practical recipe for extracting causal graphs from recent publications released after an LLM's training cutoff, ensuring relevance and preventing memorization while capturing both established and novel relations. Compared to benchmarks like BNLearn, where LLMs achieve near-perfect accuracy, they perform far worse on our curated graphs, underscoring the need for statistical grounding. Supporting P.2, we show that using LLM predictions as priors for the classical PC algorithm significantly improves accuracy over both LLM-only and purely statistical methods. We call on the community to adopt science-grounded, leakage-resistant benchmarks and invest in hybrid causal discovery methods suited to real-world inquiry. --- ### DIV-Nav: Open-Vocabulary Spatial Relationships for Multi-Object Navigation Authors: Jesús Ortega-Peimbert, Finn Lukas Busch, Timon Homberger, Quantao Yang, Olov Andersson Published: 2025-10-18 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2510.16518v2 Advances in open-vocabulary semantic mapping and object navigation have enabled robots to perform an informed search of their environment for an arbitrary object. However, such zero-shot object navigation is typically designed for simple queries with an object name like "television" or "blue rug". Here, we consider more complex free-text queries with spatial relationships, such as "find the remote on the table" while still leveraging robustness of a semantic map. We present DIV-Nav, a real-time navigation system that efficiently addresses this problem through a series of relaxations: i) Decomposing natural language instructions with complex spatial constraints into simpler object-level queries on a semantic map, ii) computing the Intersection of individual semantic belief maps to identify regions where all objects co-exist, and iii) Validating the discovered objects against the original, complex spatial constrains via a LVLM. We further investigate how to adapt the frontier exploration objectives of online semantic mapping to such spatial search queries to more effectively guide the search process. We validate our system through extensive experiments on the MultiON benchmark and real-world deployment on a Boston Dynamics Spot robot using a Jetson Orin AGX. More details and videos are available at https://anonsub42.github.io/reponame/ --- ### Image Categorization and Search via a GAT Autoencoder and Representative Models Authors: Duygu Sap, Martin Lotz, Connor Mattinson Published: 2025-10-18 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2510.16514v1 We propose a method for image categorization and retrieval that leverages graphs and a graph attention network (GAT)-based autoencoder. Our approach is representative-centric, that is, we execute the categorization and retrieval process via the representative models we construct for the images and image categories. We utilize a graph where nodes represent images (or their representatives) and edges capture similarity relationships. GAT highlights important features and relationships between images, enabling the autoencoder to construct context-aware latent representations that capture the key features of each image relative to its neighbors. We obtain category representatives from these embeddings and categorize a query image by comparing its representative to the category representatives. We then retrieve the most similar image to the query image within its identified category. We demonstrate the effectiveness of our representative-centric approach through experiments with both the GAT autoencoders and standard feature-based techniques. --- ### eDCF: Estimating Intrinsic Dimension using Local Connectivity Authors: Dhruv Gupta, Aditya Nagarsekar, Vraj Shah, Sujith Thomas Published: 2025-10-18 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2510.16513v1 Modern datasets often contain high-dimensional features exhibiting complex dependencies. To effectively analyze such data, dimensionality reduction methods rely on estimating the dataset's intrinsic dimension (id) as a measure of its underlying complexity. However, estimating id is challenging due to its dependence on scale: at very fine scales, noise inflates id estimates, while at coarser scales, estimates stabilize to lower, scale-invariant values. This paper introduces a novel, scalable, and parallelizable method called eDCF, which is based on Connectivity Factor (CF), a local connectivity-based metric, to robustly estimate intrinsic dimension across varying scales. Our method consistently matches leading estimators, achieving comparable values of mean absolute error (MAE) on synthetic benchmarks with noisy samples. Moreover, our approach also attains higher exact intrinsic dimension match rates, reaching up to 25.0% compared to 16.7% for MLE and 12.5% for TWO-NN, particularly excelling under medium to high noise levels and large datasets. Further, we showcase our method's ability to accurately detect fractal geometries in decision boundaries, confirming its utility for analyzing realistic, structured data. --- ### Structured Temporal Causality for Interpretable Multivariate Time Series Anomaly Detection Authors: Dongchan Cho, Jiho Han, Keumyeong Kang, Minsang Kim, Honggyu Ryu, Namsoon Jung Published: 2025-10-18 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2510.16511v1 Real-world multivariate time series anomalies are rare and often unlabeled. Additionally, prevailing methods rely on increasingly complex architectures tuned to benchmarks, detecting only fragments of anomalous segments and overstating performance. In this paper, we introduce OracleAD, a simple and interpretable unsupervised framework for multivariate time series anomaly detection. OracleAD encodes each variable's past sequence into a single causal embedding to jointly predict the present time point and reconstruct the input window, effectively modeling temporal dynamics. These embeddings then undergo a self-attention mechanism to project them into a shared latent space and capture spatial relationships. These relationships are not static, since they are modeled by a property that emerges from each variable's temporal dynamics. The projected embeddings are aligned to a Stable Latent Structure (SLS) representing normal-state relationships. Anomalies are identified using a dual scoring mechanism based on prediction error and deviation from the SLS, enabling fine-grained anomaly diagnosis at each time point and across individual variables. Since any noticeable SLS deviation originates from embeddings that violate the learned temporal causality of normal data, OracleAD directly pinpoints the root-cause variables at the embedding level. OracleAD achieves state-of-the-art results across multiple real-world datasets and evaluation protocols, while remaining interpretable through SLS. --- ### A Bayesian Framework for Symmetry Inference in Chaotic Attractors Authors: Ziad Ghanem, Chang Hyunwoong, Preskella Mrad Published: 2025-10-18 Categories: stat.ML, math.DS arXiv: https://arxiv.org/abs/2510.16509v1 Detecting symmetry from data is a fundamental problem in signal analysis, providing insight into underlying structure and constraints. When data emerge as trajectories of dynamical systems, symmetries encode structural properties of the dynamics that enable model reduction, principled comparison across conditions, and detection of regime changes. While recent optimal transport methods provide practical tools for data-driven symmetry detection in this setting, they rely on deterministic thresholds and lack uncertainty quantification, limiting robustness to noise and ability to resolve hierarchical symmetry structures. We present a Bayesian framework that formulates symmetry detection as probabilistic model selection over a lattice of candidate subgroups, using a Gibbs posterior constructed from Wasserstein distances between observed data and group-transformed copies. We establish three theoretical guarantees: $(i)$ a Bayesian Occam's razor favoring minimal symmetry consistent with data, $(ii)$ conjugation equivariance ensuring frame-independence, and $(iii)$ stability bounds under perturbations for robustness to noise. Posterior inference is performed via Metropolis-Hastings sampling and numerical experiments on equivariant dynamical systems and synthetic point clouds demonstrate accurate symmetry recovery under high noise and small sample sizes. An application to human gait dynamics reveals symmetry changes induced by mechanical constraints, demonstrating the framework's utility for statistical inference in biomechanical and dynamical systems. --- ### OOS-DSD: Improving Out-of-stock Detection in Retail Images using Auxiliary Tasks Authors: Franko Šikić, Sven Lončarić Published: 2025-10-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.16508v1 Out-of-stock (OOS) detection is a very important retail verification process that aims to infer the unavailability of products in their designated areas on the shelf. In this paper, we introduce OOS-DSD, a novel deep learning-based method that advances OOS detection through auxiliary learning. In particular, we extend a well-established YOLOv8 object detection architecture with additional convolutional branches to simultaneously detect OOS, segment products, and estimate scene depth. While OOS detection and product segmentation branches are trained using ground truth data, the depth estimation branch is trained using pseudo-labeled annotations produced by the state-of-the-art (SOTA) depth estimation model Depth Anything V2. Furthermore, since the aforementioned pseudo-labeled depth estimates display relative depth, we propose an appropriate depth normalization procedure that stabilizes the training process. The experimental results show that the proposed method surpassed the performance of the SOTA OOS detection methods by 1.8% of the mean average precision (mAP). In addition, ablation studies confirm the effectiveness of auxiliary learning and the proposed depth normalization procedure, with the former increasing mAP by 3.7% and the latter by 4.2%. --- ### PRISMM-Bench: A Benchmark of Peer-Review Grounded Multimodal Inconsistencies Authors: Lukas Selch, Yufang Hou, M. Jehanzeb Mirza, Sivan Doveh, James Glass, Rogerio Feris, Wei Lin Published: 2025-10-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.16505v3 Large Multimodal Models (LMMs) are increasingly applied to scientific research, yet it remains unclear whether they can reliably understand and reason over the multimodal complexity of papers. A central challenge lies in detecting and resolving inconsistencies across text, figures, tables, and equations, issues that are often subtle, domain-specific, and ultimately undermine clarity, reproducibility, and trust. Existing benchmarks overlook this issue, either isolating single modalities or relying on synthetic errors that fail to capture real-world complexity. We introduce PRISMM-Bench (Peer-Review-sourced Inconsistency Set for Multimodal Models), the first benchmark grounded in real reviewer-flagged inconsistencies in scientific papers. Through a multi-stage pipeline of review mining, LLM-assisted filtering and human verification, we curate 384 inconsistencies from 353 papers. Based on this set, we design three tasks, namely inconsistency identification, remedy and pair matching, which assess a model's capacity to detect, correct, and reason over inconsistencies across different modalities. Furthermore, to address the notorious problem of choice-only shortcuts in multiple-choice evaluation, where models exploit answer patterns without truly understanding the question, we further introduce structured JSON-based answer representations that minimize linguistic biases by reducing reliance on superficial stylistic cues. We benchmark 21 leading LMMs, including large open-weight models (GLM-4.5V 106B, InternVL3 78B) and proprietary models (Gemini 2.5 Pro, GPT-5 with high reasoning). Results reveal strikingly low performance (27.8-53.9\%), underscoring the challenge of multimodal scientific reasoning and motivating progress towards trustworthy scientific assistants. --- ### Automated Composition of Agents: A Knapsack Approach for Agentic Component Selection Authors: Michelle Yuan, Khushbu Pahwa, Shuaichen Chang, Mustafa Kaba, Jiarong Jiang, Xiaofei Ma, Yi Zhang, Monica Sunkara Published: 2025-10-18 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.16499v2 Designing effective agentic systems requires the seamless composition and integration of agents, tools, and models within dynamic and uncertain environments. Most existing methods rely on static, semantic retrieval approaches for tool or agent discovery. However, effective reuse and composition of existing components remain challenging due to incomplete capability descriptions and the limitations of retrieval methods. Component selection suffers because the decisions are not based on capability, cost, and real-time utility. To address these challenges, we introduce a structured, automated framework for agentic system composition that is inspired by the knapsack problem. Our framework enables a composer agent to systematically identify, select, and assemble an optimal set of agentic components by jointly considering performance, budget constraints, and compatibility. By dynamically testing candidate components and modeling their utility in real-time, our approach streamlines the assembly of agentic systems and facilitates scalable reuse of resources. Empirical evaluation with Claude 3.5 Sonnet across five benchmarking datasets shows that our online-knapsack-based composer consistently lies on the Pareto frontier, achieving higher success rates at significantly lower component costs compared to our baselines. In the single-agent setup, the online knapsack composer shows a success rate improvement of up to 31.6% in comparison to the retrieval baselines. In multi-agent systems, the online knapsack composer increases success rate from 37% to 87% when agents are selected from an agent inventory of 100+ agents. The substantial performance gap confirms the robust adaptability of our method across diverse domains and budget constraints. --- ### Edge-Based Speech Transcription and Synthesis for Kinyarwanda and Swahili Languages Authors: Pacome Simon Mbonimpa, Diane Tuyizere, Azizuddin Ahmed Biyabani, Ozan K. Tonguz Published: 2025-10-18 Categories: cs.DC, cs.LG arXiv: https://arxiv.org/abs/2510.16497v1 This paper presents a novel framework for speech transcription and synthesis, leveraging edge-cloud parallelism to enhance processing speed and accessibility for Kinyarwanda and Swahili speakers. It addresses the scarcity of powerful language processing tools for these widely spoken languages in East African countries with limited technological infrastructure. The framework utilizes the Whisper and SpeechT5 pre-trained models to enable speech-to-text (STT) and text-to-speech (TTS) translation. The architecture uses a cascading mechanism that distributes the model inference workload between the edge device and the cloud, thereby reducing latency and resource usage, benefiting both ends. On the edge device, our approach achieves a memory usage compression of 9.5% for the SpeechT5 model and 14% for the Whisper model, with a maximum memory usage of 149 MB. Experimental results indicate that on a 1.7 GHz CPU edge device with a 1 MB/s network bandwidth, the system can process a 270-character text in less than a minute for both speech-to-text and text-to-speech transcription. Using real-world survey data from Kenya, it is shown that the cascaded edge-cloud architecture proposed could easily serve as an excellent platform for STT and TTS transcription with good accuracy and response time. --- ### Check Yourself Before You Wreck Yourself: Selectively Quitting Improves LLM Agent Safety Authors: Vamshi Krishna Bonagiri, Ponnurangam Kumaragurum, Khanh Nguyen, Benjamin Plaut Published: 2025-10-18 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.16492v4 As Large Language Model (LLM) agents increasingly operate in complex environments with real-world consequences, their safety becomes critical. While uncertainty quantification is well-studied for single-turn tasks, multi-turn agentic scenarios with real-world tool access present unique challenges where uncertainties and ambiguities compound, leading to severe or catastrophic risks beyond traditional text generation failures. We propose using "quitting" as a simple yet effective behavioral mechanism for LLM agents to recognize and withdraw from situations where they lack confidence. Leveraging the ToolEmu framework, we conduct a systematic evaluation of quitting behavior across 12 state-of-the-art LLMs. Our results demonstrate a highly favorable safety-helpfulness trade-off: agents prompted to quit with explicit instructions improve safety by an average of +0.39 on a 0-3 scale across all models (+0.64 for proprietary models), while maintaining a negligible average decrease of -0.03 in helpfulness. Our analysis demonstrates that simply adding explicit quit instructions proves to be a highly effective safety mechanism that can immediately be deployed in existing agent systems, and establishes quitting as an effective first-line defense mechanism for autonomous agents in high-stakes applications. --- ### NP-Engine: Empowering Optimization Reasoning in Large Language Models with Verifiable Synthetic NP Problems Authors: Xiaozhe Li, Xinyu Fang, Shengyuan Ding, Linyang Li, Haodong Duan, Qingwen Liu, Kai Chen Published: 2025-10-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.16476v1 Large Language Models (LLMs) have shown strong reasoning capabilities, with models like OpenAI's O-series and DeepSeek R1 excelling at tasks such as mathematics, coding, logic, and puzzles through Reinforcement Learning with Verifiable Rewards (RLVR). However, their ability to solve more complex optimization problems - particularly NP-hard tasks - remains underexplored. To bridge this gap, we propose NP-ENGINE, the first comprehensive framework for training and evaluating LLMs on NP-hard problems. NP-ENGINE covers 10 tasks across five domains, each equipped with (i) a controllable instance generator, (ii) a rule-based verifier, and (iii) a heuristic solver that provides approximate optimal solutions as ground truth. This generator-verifier-heuristic pipeline enables scalable and verifiable RLVR training under hierarchical difficulties. We also introduce NP-BENCH, a benchmark derived from NP-ENGINE-DATA, specifically designed to evaluate LLMs' ability to tackle NP-hard level reasoning problems, focusing not only on feasibility but also on solution quality. Additionally, we present QWEN2.5-7B-NP, a model trained via zero-RLVR with curriculum learning on Qwen2.5-7B-Instruct, which significantly outperforms GPT-4o on NP-BENCH and achieves SOTA performance with the same model size. Beyond in-domain tasks, we demonstrate that RLVR training on NP-ENGINE-DATA enables strong out-of-domain (OOD) generalization to reasoning tasks (logic, puzzles, math, and knowledge), as well as non-reasoning tasks such as instruction following. We also observe a scaling trend: increasing task diversity improves OOD generalization. These findings suggest that task-rich RLVR training is a promising direction for advancing LLM's reasoning ability, revealing new insights into the scaling laws of RLVR. --- ### SCALAR: Self-Calibrating Adaptive Latent Attention Representation Learning Authors: Farwa Abbas, Hussain Ahmad, Claudia Szabo Published: 2025-10-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.16474v1 High-dimensional, heterogeneous data with complex feature interactions pose significant challenges for traditional predictive modeling approaches. While Projection to Latent Structures (PLS) remains a popular technique, it struggles to model complex non-linear relationships, especially in multivariate systems with high-dimensional correlation structures. This challenge is further compounded by simultaneous interactions across multiple scales, where local processing fails to capture crossgroup dependencies. Additionally, static feature weighting limits adaptability to contextual variations, as it ignores sample-specific relevance. To address these limitations, we propose a novel method that enhances predictive performance through novel architectural innovations. Our architecture introduces an adaptive kernel-based attention mechanism that processes distinct feature groups separately before integration, enabling capture of local patterns while preserving global relationships. Experimental results show substantial improvements in performance metrics, compared to the state-of-the-art methods across diverse datasets. --- ### Declarative Techniques for NL Queries over Heterogeneous Data Authors: Elham Khabiri, Jeffrey O. Kephart, Fenno F. Heath, Srideepika Jayaraman, Fateh A. Tipu, Yingjie Li, Dhruv Shah, Achille Fokoue, Anu Bhamidipaty Published: 2025-10-18 Categories: cs.DB, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2510.16470v1 In many industrial settings, users wish to ask questions in natural language, the answers to which require assembling information from diverse structured data sources. With the advent of Large Language Models (LLMs), applications can now translate natural language questions into a set of API calls or database calls, execute them, and combine the results into an appropriate natural language response. However, these applications remain impractical in realistic industrial settings because they do not cope with the data source heterogeneity that typifies such environments. In this work, we simulate the heterogeneity of real industry settings by introducing two extensions of the popular Spider benchmark dataset that require a combination of database and API calls. Then, we introduce a declarative approach to handling such data heterogeneity and demonstrate that it copes with data source heterogeneity significantly better than state-of-the-art LLM-based agentic or imperative code generation systems. Our augmented benchmarks are available to the research community. --- ### ReviewSense: Transforming Customer Review Dynamics into Actionable Business Insights Authors: Siddhartha Krothapalli, Kartikey Singh Bhandari, Tridib Kumar Das, Praveen Kumar, Naveen Suravarpu, Pratik Narang Published: 2025-10-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.16466v2 As customer feedback becomes increasingly central to strategic growth, the ability to derive actionable insights from unstructured reviews is essential. While traditional AI-driven systems excel at predicting user preferences, far less work has focused on transforming customer reviews into prescriptive, business-facing recommendations. This paper introduces ReviewSense, a novel prescriptive decision support framework that leverages advanced large language models (LLMs) to transform customer reviews into targeted, actionable business recommendations. By identifying key trends, recurring issues, and specific concerns within customer sentiments, ReviewSense extends beyond preference-based systems to provide businesses with deeper insights for sustaining growth and enhancing customer loyalty. The novelty of this work lies in integrating clustering, LLM adaptation, and expert-driven evaluation into a unified, business-facing pipeline. Preliminary manual evaluations indicate strong alignment between the model's recommendations and business objectives, highlighting its potential for driving data-informed decision-making. This framework offers a new perspective on AI-driven sentiment analysis, demonstrating its value in refining business strategies and maximizing the impact of customer feedback. --- ### HGC-Avatar: Hierarchical Gaussian Compression for Streamable Dynamic 3D Avatars Authors: Haocheng Tang, Ruoke Yan, Xinhui Yin, Qi Zhang, Xinfeng Zhang, Siwei Ma, Wen Gao, Chuanmin Jia Published: 2025-10-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.16463v1 Recent advances in 3D Gaussian Splatting (3DGS) have enabled fast, photorealistic rendering of dynamic 3D scenes, showing strong potential in immersive communication. However, in digital human encoding and transmission, the compression methods based on general 3DGS representations are limited by the lack of human priors, resulting in suboptimal bitrate efficiency and reconstruction quality at the decoder side, which hinders their application in streamable 3D avatar systems. We propose HGC-Avatar, a novel Hierarchical Gaussian Compression framework designed for efficient transmission and high-quality rendering of dynamic avatars. Our method disentangles the Gaussian representation into a structural layer, which maps poses to Gaussians via a StyleUNet-based generator, and a motion layer, which leverages the SMPL-X model to represent temporal pose variations compactly and semantically. This hierarchical design supports layer-wise compression, progressive decoding, and controllable rendering from diverse pose inputs such as video sequences or text. Since people are most concerned with facial realism, we incorporate a facial attention mechanism during StyleUNet training to preserve identity and expression details under low-bitrate constraints. Experimental results demonstrate that HGC-Avatar provides a streamable solution for rapid 3D avatar rendering, while significantly outperforming prior methods in both visual quality and compression efficiency. ---