# Research Papers — 2025-11 · bundle page 173 of 197 > Full-text markdown of papers #8601–8650 of 9830 published in 2025-11, newest first. AI-readable mirrors of the full 9830-paper 2025-11 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2025-11/page/173 [← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/172.md) [Next bundle →](https://aipod.dev/papers/archive/2025-11/page/174.md) ### GRDD+: An Extended Greek Dialectal Dataset with Cross-Architecture Fine-tuning Evaluation Authors: Stergios Chatzikyriakidis, Dimitris Papadakis, Sevasti-Ioanna Papaioannou, Erofili Psaltaki Published: 2025-11-05 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.03772v3 We present an extended Greek Dialectal Dataset (GRDD+) 1that complements the existing GRDD dataset with more data from Cretan, Cypriot, Pontic and Northern Greek, while we add six new varieties: Greco-Corsican, Griko (Southern Italian Greek), Maniot, Heptanesian, Tsakonian, and Katharevusa Greek. The result is a dataset with total size 6,374,939 words and 10 varieties. This is the first dataset with such variation and size to date. We conduct a number of fine-tuning experiments to see the effect of good quality dialectal data on a number of LLMs. We fine-tune three model architectures (Llama-3-8B, Llama-3.1-8B, Krikri-8B) and compare the results to frontier models (Claude-3.7-Sonnet, Gemini-2.5, ChatGPT-5). --- ### Climbing the label tree: Hierarchy-preserving contrastive learning for medical imaging Authors: Alif Elham Khan Published: 2025-11-05 Categories: q-bio.QM, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.03771v1 Medical image labels are often organized by taxonomies (e.g., organ - tissue - subtype), yet standard self-supervised learning (SSL) ignores this structure. We present a hierarchy-preserving contrastive framework that makes the label tree a first-class training signal and an evaluation target. Our approach introduces two plug-in objectives: Hierarchy-Weighted Contrastive (HWC), which scales positive/negative pair strengths by shared ancestors to promote within-parent coherence, and Level-Aware Margin (LAM), a prototype margin that separates ancestor groups across levels. The formulation is geometry-agnostic and applies to Euclidean and hyperbolic embeddings without architectural changes. Across several benchmarks, including breast histopathology, the proposed objectives consistently improve representation quality over strong SSL baselines while better respecting the taxonomy. We evaluate with metrics tailored to hierarchy faithfulness: HF1 (hierarchical F1), H-Acc (tree-distance-weighted accuracy), and parent-distance violation rate. We also report top-1 accuracy for completeness. Ablations show that HWC and LAM are effective even without curvature, and combining them yields the most taxonomy-aligned representations. Taken together, these results provide a simple, general recipe for learning medical image representations that respect the label tree and advance both performance and interpretability in hierarchy-rich domains. --- ### Deep Learning-Driven Downscaling for Climate Risk Assessment of Projected Temperature Extremes in the Nordic Region Authors: Parthiban Loganathan, Elias Zea, Ricardo Vinuesa, Evelyn Otero Published: 2025-11-05 Categories: physics.geo-ph, cs.LG arXiv: https://arxiv.org/abs/2511.03770v1 Rapid changes and increasing climatic variability across the widely varied Koppen-Geiger regions of northern Europe generate significant needs for adaptation. Regional planning needs high-resolution projected temperatures. This work presents an integrative downscaling framework that incorporates Vision Transformer (ViT), Convolutional Long Short-Term Memory (ConvLSTM), and Geospatial Spatiotemporal Transformer with Attention and Imbalance-Aware Network (GeoStaNet) models. The framework is evaluated with a multicriteria decision system, Deep Learning-TOPSIS (DL-TOPSIS), for ten strategically chosen meteorological stations encompassing the temperate oceanic (Cfb), subpolar oceanic (Cfc), warm-summer continental (Dfb), and subarctic (Dfc) climate regions. Norwegian Earth System Model (NorESM2-LM) Coupled Model Intercomparison Project Phase 6 (CMIP6) outputs were bias-corrected during the 1951-2014 period and subsequently validated against earlier observations of day-to-day temperature metrics and diurnal range statistics. The ViT showed improved performance (Root Mean Squared Error (RMSE): 1.01 degrees C; R^2: 0.92), allowing for production of credible downscaled projections. Under the SSP5-8.5 scenario, the Dfc and Dfb climate zones are projected to warm by 4.8 degrees C and 3.9 degrees C, respectively, by 2100, with expansion in the diurnal temperature range by more than 1.5 degrees C. The Time of Emergence signal first appears in subarctic winter seasons (Dfc: approximately 2032), signifying an urgent need for adaptation measures. The presented framework offers station-based, high-resolution estimates of uncertainties and extremes, with direct uses for adaptation policy over high-latitude regions with fast environmental change. --- ### What's in Common? Multimodal Models Hallucinate When Reasoning Across Scenes Authors: Candace Ross, Florian Bordes, Adina Williams, Polina Kirichenko, Mark Ibrahim Published: 2025-11-05 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2511.03768v1 Multimodal language models possess a remarkable ability to handle an open-vocabulary's worth of objects. Yet the best models still suffer from hallucinations when reasoning about scenes in the real world, revealing a gap between their seemingly strong performance on existing perception benchmarks that are saturating and their reasoning in the real world. To address this gap, we build a novel benchmark of in-the-wild scenes that we call Common-O. With more than 10.5k examples using exclusively new images not found in web training data to avoid contamination, Common-O goes beyond just perception, inspired by cognitive tests for humans, to probe reasoning across scenes by asking "what's in common?". We evaluate leading multimodal language models, including models specifically trained to perform chain-of-thought reasoning. We find that perceiving objects in single images is tractable for most models, yet reasoning across scenes is very challenging even for the best models, including reasoning models. Despite saturating many leaderboards focusing on perception, the best performing model only achieves 35% on Common-O -- and on Common-O Complex, consisting of more complex scenes, the best model achieves only 1%. Curiously, we find models are more prone to hallucinate when similar objects are present in the scene, suggesting models may be relying on object co-occurrence seen during training. Among the models we evaluated, we found scale can provide modest improvements while models explicitly trained with multi-image inputs show bigger improvements, suggesting scaled multi-image training may offer promise. We make our benchmark publicly available to spur research into the challenge of hallucination when reasoning across scenes. --- ### LoRA-Edge: Tensor-Train-Assisted LoRA for Practical CNN Fine-Tuning on Edge Devices Authors: Hyunseok Kwak, Kyeongwon Lee, Jae-Jin Lee, Woojoo Lee Published: 2025-11-05 Categories: cs.CV, cs.AR arXiv: https://arxiv.org/abs/2511.03765v2 On-device fine-tuning of CNNs is essential to withstand domain shift in edge applications such as Human Activity Recognition (HAR), yet full fine-tuning is infeasible under strict memory, compute, and energy budgets. We present LoRA-Edge, a parameter-efficient fine-tuning (PEFT) method that builds on Low-Rank Adaptation (LoRA) with tensor-train assistance. LoRA-Edge (i) applies Tensor-Train Singular Value Decomposition (TT-SVD) to pre-trained convolutional layers, (ii) selectively updates only the output-side core with zero-initialization to keep the auxiliary path inactive at the start, and (iii) fuses the update back into dense kernels, leaving inference cost unchanged. This design preserves convolutional structure and reduces the number of trainable parameters by up to two orders of magnitude compared to full fine-tuning. Across diverse HAR datasets and CNN backbones, LoRA-Edge achieves accuracy within 4.7% of full fine-tuning while updating at most 1.49% of parameters, consistently outperforming prior parameter-efficient baselines under similar budgets. On a Jetson Orin Nano, TT-SVD initialization and selective-core training yield 1.4-3.8x faster convergence to target F1. LoRA-Edge thus makes structure-aligned, parameter-efficient on-device CNN adaptation practical for edge platforms. --- ### OptiMA: A Transaction-Based Framework with Throughput Optimization for Very Complex Multi-Agent Systems Authors: Umut Çalıkyılmaz, Nitin Nayak, Jinghua Groppe, Sven Groppe Published: 2025-11-05 Categories: cs.MA, cs.AI, cs.DB arXiv: https://arxiv.org/abs/2511.03761v1 In recent years, the research of multi-agent systems has taken a direction to explore larger and more complex models to fulfill sophisticated tasks. We point out two possible pitfalls that might be caused by increasing complexity; susceptibilities to faults, and performance bottlenecks. To prevent the former threat, we propose a transaction-based framework to design very complex multi-agent systems (VCMAS). To address the second threat, we offer to integrate transaction scheduling into the proposed framework. We implemented both of these ideas to develop the OptiMA framework and show that it is able to facilitate the execution of VCMAS with more than a hundred agents. We also demonstrate the effect of transaction scheduling on such a system by showing improvements up to more than 16\%. Furthermore, we also performed a theoretical analysis on the transaction scheduling problem and provided practical tools that can be used for future research on it. --- ### Leveraging LLM-based agents for social science research: insights from citation network simulations Authors: Jiarui Ji, Runlin Lei, Xuchen Pan, Zhewei Wei, Hao Sun, Yankai Lin, Xu Chen, Yongzheng Yang, Yaliang Li, Bolin Ding, Ji-Rong Wen Published: 2025-11-05 Categories: physics.soc-ph, cs.AI, cs.CY, cs.MA, cs.SI arXiv: https://arxiv.org/abs/2511.03758v3 The emergence of Large Language Models (LLMs) demonstrates their potential to encapsulate the logic and patterns inherent in human behavior simulation by leveraging extensive web data pre-training. However, the boundaries of LLM capabilities in social simulation remain unclear. To further explore the social attributes of LLMs, we introduce the CiteAgent framework, designed to generate citation networks based on human-behavior simulation with LLM-based agents. CiteAgent successfully captures predominant phenomena in real-world citation networks, including power-law distribution, citational distortion, and shrinking diameter. Building on this realistic simulation, we establish two LLM-based research paradigms in social science: LLM-SE (LLM-based Survey Experiment) and LLM-LE (LLM-based Laboratory Experiment). These paradigms facilitate rigorous analyses of citation network phenomena, allowing us to validate and challenge existing theories. Additionally, we extend the research scope of traditional science of science studies through idealized social experiments, with the simulation experiment results providing valuable insights for real-world academic environments. Our work demonstrates the potential of LLMs for advancing science of science research in social science. --- ### Laugh, Relate, Engage: Stylized Comment Generation for Short Videos Authors: Xuan Ouyang, Senan Wang, Bouzhou Wang, Siyuan Xiahou, Jinrong Zhou, Yuekang Li Published: 2025-11-05 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.03757v1 Short-video platforms have become a central medium in the modern Internet landscape, where efficient information delivery and strong interactivity are reshaping user engagement and cultural dissemination. Among the various forms of user interaction, comments play a vital role in fostering community participation and enabling content re-creation. However, generating comments that are both compliant with platform guidelines and capable of exhibiting stylistic diversity and contextual awareness remains a significant challenge. We introduce LOLGORITHM, a modular multi-agent system (MAS) designed for controllable short-video comment generation. The system integrates video segmentation, contextual and affective analysis, and style-aware prompt construction. It supports six distinct comment styles: puns (homophones), rhyming, meme application, sarcasm (irony), plain humor, and content extraction. Powered by a multimodal large language model (MLLM), LOLGORITHM directly processes video inputs and achieves fine-grained style control through explicit prompt markers and few-shot examples. To support development and evaluation, we construct a bilingual dataset using official APIs from Douyin (Chinese) and YouTube (English), covering five popular video genres: comedy skits, daily life jokes, funny animal clips, humorous commentary, and talk shows. Evaluation combines automated metrics originality, relevance, and style conformity with a large-scale human preference study involving 40 videos and 105 participants. Results show that LOLGORITHM significantly outperforms baseline models, achieving preference rates of over 90% on Douyin and 87.55% on YouTube. This work presents a scalable and culturally adaptive framework for stylized comment generation on short-video platforms, offering a promising path to enhance user engagement and creative interaction. --- ### Bifidelity Karhunen-Loève Expansion Surrogate with Active Learning for Random Fields Authors: Aniket Jivani, Cosmin Safta, Beckett Y. Zhou, Xun Huan Published: 2025-11-05 Categories: stat.ML, cs.LG, physics.flu-dyn, stat.AP arXiv: https://arxiv.org/abs/2511.03756v2 We present a bifidelity Karhunen--Loève expansion (KLE) surrogate model for field-valued quantities of interest (QoIs) under uncertain inputs. The QoIs considered here are scalar fields. The approach combines the spectral efficiency of the KLE with polynomial chaos expansions (PCEs) to preserve an explicit mapping between input uncertainties and output fields. By coupling inexpensive low-fidelity (LF) simulations that capture dominant response trends with a limited number of high-fidelity (HF) simulations that correct for systematic bias, the proposed method can enable accurate and computationally affordable surrogate construction. To further improve surrogate accuracy, we develop an active learning strategy that adaptively selects new HF evaluations based on the surrogate's generalization error, estimated via cross-validation and modeled using Gaussian process regression. New HF samples are then acquired by maximizing an expected improvement criterion, targeting regions of high surrogate error. The resulting BF-KLE-AL framework is demonstrated on three examples of increasing complexity: a one-dimensional analytical benchmark, a two-dimensional convection-diffusion system, and a three-dimensional turbulent round jet simulation based on Reynolds-averaged Navier--Stokes (RANS) and enhanced delayed detached-eddy simulations (EDDES). The experiments show that bifidelity gains depend on LF accuracy, discrepancy approximation, and the allocation of simulation cost. Active learning improves prediction over random sampling in several settings, while the cost-matched comparisons identify both favorable regimes and cases where an HF-only surrogate is more accurate. --- ### Disentangled Concepts Speak Louder Than Words: Explainable Video Action Recognition Authors: Jongseo Lee, Wooil Lee, Gyeong-Moon Park, Seong Tae Kim, Jinwoo Choi Published: 2025-11-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.03725v2 Effective explanations of video action recognition models should disentangle how movements unfold over time from the surrounding spatial context. However, existing methods based on saliency produce entangled explanations, making it unclear whether predictions rely on motion or spatial context. Language-based approaches offer structure but often fail to explain motions due to their tacit nature -- intuitively understood but difficult to verbalize. To address these challenges, we propose Disentangled Action aNd Context concept-based Explainable (DANCE) video action recognition, a framework that predicts actions through disentangled concept types: motion dynamics, objects, and scenes. We define motion dynamics concepts as human pose sequences. We employ a large language model to automatically extract object and scene concepts. Built on an ante-hoc concept bottleneck design, DANCE enforces prediction through these concepts. Experiments on four datasets -- KTH, Penn Action, HAA500, and UCF-101 -- demonstrate that DANCE significantly improves explanation clarity with competitive performance. We validate the superior interpretability of DANCE through a user study. Experimental results also show that DANCE is beneficial for model debugging, editing, and failure analysis. --- ### Outbidding and Outbluffing Elite Humans: Mastering Liar's Poker via Self-Play and Reinforcement Learning Authors: Richard Dewey, Janos Botyanszki, Ciamac C. Moallemi, Andrew T. Zheng Published: 2025-11-05 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2511.03724v3 AI researchers have long focused on poker-like games as a testbed for environments characterized by multi-player dynamics, imperfect information, and reasoning under uncertainty. While recent breakthroughs have matched elite human play at no-limit Texas hold'em, the multi-player dynamics are subdued: most hands converge quickly with only two players engaged through multiple rounds of bidding. In this paper, we present Solly, the first AI agent to achieve elite human play in reduced-format Liar's Poker, a game characterized by extensive multi-player engagement. We trained Solly using self-play with a model-free, actor-critic, deep reinforcement learning algorithm. Solly played at an elite human level as measured by win rate (won over 50% of hands) and equity (money won) in heads-up and multi-player Liar's Poker. Solly also outperformed large language models (LLMs), including those with reasoning abilities, on the same metrics. Solly developed novel bidding strategies, randomized play effectively, and was not easily exploitable by world-class human players. --- ### Grounded Misunderstandings in Asymmetric Dialogue: A Perspectivist Annotation Scheme for MapTask Authors: Nan Li, Albert Gatt, Massimo Poesio Published: 2025-11-05 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.03718v2 Collaborative dialogue relies on participants incrementally establishing common ground, yet in asymmetric settings they may believe they agree while referring to different entities. We introduce a perspectivist annotation scheme for the HCRC MapTask corpus (Anderson et al., 1991) that separately captures speaker and addressee grounded interpretations for each reference expression, enabling us to trace how understanding emerges, diverges, and repairs over time. Using a scheme-constrained LLM annotation pipeline, we obtain 13k annotated reference expressions with reliability estimates and analyze the resulting understanding states. The results show that full misunderstandings are rare once lexical variants are unified, but multiplicity discrepancies systematically induce divergences, revealing how apparent grounding can mask referential misalignment. Our framework provides both a resource and an analytic lens for studying grounded misunderstanding and for evaluating (V)LLMs' capacity to model perspective-dependent grounding in collaborative dialogue. --- ### Shrinking the Variance: Shrinkage Baselines for Reinforcement Learning with Verifiable Rewards Authors: Guanning Zeng, Zhaoyi Zhou, Daman Arora, Andrea Zanette Published: 2025-11-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.03710v2 Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a powerful paradigm for post-training large reasoning models (LRMs) using policy-gradient methods such as GRPO. To stabilize training, these methods typically center trajectory rewards by subtracting the empirical mean reward for each prompt. Statistically, this centering acts as a control variate (baseline), reducing the variance of the policy-gradient estimator. In practice, the mean reward is estimated using per-prompt empirical averages computed from the generations for each prompt in a batch. Motivated by Stein's paradox, we propose shrinkage estimators that combine per-prompt and across-prompt means to improve per-prompt mean estimation accuracy, especially in the low-generation regime typical of RLVR. Theoretically, we construct a shrinkage-based baseline that provably yields lower-variance policy-gradient estimators across algorithms. Our baseline is a drop-in replacement for standard per-prompt mean baselines and requires no additional hyperparameters or computation. Empirically, shrinkage baselines consistently outperform empirical-mean baselines, producing lower-variance gradient updates and improved training stability. --- ### The Adaptivity Barrier in Batched Nonparametric Bandits: Sharp Characterization of the Price of Unknown Margin Authors: Rong Jiang, Cong Ma Published: 2025-11-05 Categories: math.ST, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2511.03708v2 We study batched nonparametric contextual bandits under a margin condition when the margin parameter $α$ is unknown. To capture the statistical cost of this ignorance, we introduce the regret inflation criterion, defined as the ratio between the regret of an adaptive algorithm and that of an oracle knowing $α$. We show that the optimal regret inflation grows polynomially with the horizon $T$, with exponent given by the value of a convex optimization problem that depends on the dimension, smoothness, and number of batches $M$. Moreover, the minimizer of this optimization problem directly prescribes the batch allocation and exploration strategy of a rate-optimal algorithm. Building on this principle, we develop RoBIN (RObust batched algorithm with adaptive BINning), which achieves the optimal regret inflation up to polylogarithmic factors. These results reveal a new adaptivity barrier: under batching, adaptation to an unknown margin parameter inevitably incurs a polynomial penalty, sharply characterized by a variational problem. Remarkably, this barrier vanishes once the number of batches exceeds order $\log \log T$; with only a doubly logarithmic number of updates, one can recover the oracle regret rate up to polylogarithmic factors. --- ### Do Androids Dream of Unseen Puppeteers? Probing for a Conspiracy Tendencies in Large Language Models Authors: Francesco Corso, Francesco Pierri, Gianmarco De Francisci Morales Published: 2025-11-05 Categories: cs.CL, cs.CY arXiv: https://arxiv.org/abs/2511.03699v2 We investigate whether Large Language Models (LLMs) exhibit conspiratorial tendencies, whether they display socio-demographic biases in this domain, and how easily they can be conditioned into adopting conspiratorial perspectives. Conspiracy beliefs play a central role in the spread of misinformation and in shaping distrust toward institutions, making them an important testbed for assessing the social and psychological fidelity of LLMs and their potential to reproduce or reinforce harmful narratives. Although LLMs are often used as proxies for studying human behavior, it remains unclear whether they reproduce higher-order psychological constructs such as generalized conspiratorial beliefs. To bridge this research gap, we administer validated psychometric surveys measuring conspiratorial mindset to multiple models under different prompting and conditioning strategies. Our findings reveal that LLMs show partial agreement with elements of conspiracy belief, and conditioning with socio-demographic attributes produces uneven effects, exposing latent demographic biases. Moreover, targeted prompts can easily shift model responses toward conspiratorial directions, underscoring both the susceptibility of LLMs to manipulation and the potential risks of their deployment in sensitive contexts. These results highlight the importance of critically evaluating the psychological dimensions embedded in LLMs, both to advance computational social science and to inform possible mitigation strategies against harmful uses. --- ### AnaFlow: Agentic LLM-based Workflow for Reasoning-Driven Explainable and Sample-Efficient Analog Circuit Sizing Authors: Mohsen Ahmadzadeh, Kaichang Chen, Georges Gielen Published: 2025-11-05 Categories: cs.LG, cs.AI, cs.AR arXiv: https://arxiv.org/abs/2511.03697v1 Analog/mixed-signal circuits are key for interfacing electronics with the physical world. Their design, however, remains a largely handcrafted process, resulting in long and error-prone design cycles. While the recent rise of AI-based reinforcement learning and generative AI has created new techniques to automate this task, the need for many time-consuming simulations is a critical bottleneck hindering the overall efficiency. Furthermore, the lack of explainability of the resulting design solutions hampers widespread adoption of the tools. To address these issues, a novel agentic AI framework for sample-efficient and explainable analog circuit sizing is presented. It employs a multi-agent workflow where specialized Large Language Model (LLM)-based agents collaborate to interpret the circuit topology, to understand the design goals, and to iteratively refine the circuit's design parameters towards the target goals with human-interpretable reasoning. The adaptive simulation strategy creates an intelligent control that yields a high sample efficiency. The AnaFlow framework is demonstrated for two circuits of varying complexity and is able to complete the sizing task fully automatically, differently from pure Bayesian optimization and reinforcement learning approaches. The system learns from its optimization history to avoid past mistakes and to accelerate convergence. The inherent explainability makes this a powerful tool for analog design space exploration and a new paradigm in analog EDA, where AI agents serve as transparent design assistants. --- ### Behavior-Adaptive Q-Learning: A Unifying Framework for Offline-to-Online RL Authors: Lipeng Zu, Hansong Zhou, Xiaonan Zhang Published: 2025-11-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.03695v1 Offline reinforcement learning (RL) enables training from fixed data without online interaction, but policies learned offline often struggle when deployed in dynamic environments due to distributional shift and unreliable value estimates on unseen state-action pairs. We introduce Behavior-Adaptive Q-Learning (BAQ), a framework designed to enable a smooth and reliable transition from offline to online RL. The key idea is to leverage an implicit behavioral model derived from offline data to provide a behavior-consistency signal during online fine-tuning. BAQ incorporates a dual-objective loss that (i) aligns the online policy toward the offline behavior when uncertainty is high, and (ii) gradually relaxes this constraint as more confident online experience is accumulated. This adaptive mechanism reduces error propagation from out-of-distribution estimates, stabilizes early online updates, and accelerates adaptation to new scenarios. Across standard benchmarks, BAQ consistently outperforms prior offline-to-online RL approaches, achieving faster recovery, improved robustness, and higher overall performance. Our results demonstrate that implicit behavior adaptation is a principled and practical solution for reliable real-world policy deployment. --- ### Colorectal Cancer Histopathological Grading using Multi-Scale Federated Learning Authors: Md Ahasanul Arafath, Abhijit Kumar Ghosh, Md Rony Ahmed, Sabrin Afroz, Minhazul Hosen, Md Hasan Moon, Md Tanzim Reza, Md Ashad Alam Published: 2025-11-05 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2511.03693v1 Colorectal cancer (CRC) grading is a critical prognostic factor but remains hampered by inter-observer variability and the privacy constraints of multi-institutional data sharing. While deep learning offers a path to automation, centralized training models conflict with data governance regulations and neglect the diagnostic importance of multi-scale analysis. In this work, we propose a scalable, privacy-preserving federated learning (FL) framework for CRC histopathological grading that integrates multi-scale feature learning within a distributed training paradigm. Our approach employs a dual-stream ResNetRS50 backbone to concurrently capture fine-grained nuclear detail and broader tissue-level context. This architecture is integrated into a robust FL system stabilized using FedProx to mitigate client drift across heterogeneous data distributions from multiple hospitals. Extensive evaluation on the CRC-HGD dataset demonstrates that our framework achieves an overall accuracy of 83.5%, outperforming a comparable centralized model (81.6%). Crucially, the system excels in identifying the most aggressive Grade III tumors with a high recall of 87.5%, a key clinical priority to prevent dangerous false negatives. Performance further improves with higher magnification, reaching 88.0% accuracy at 40x. These results validate that our federated multi-scale approach not only preserves patient privacy but also enhances model performance and generalization. The proposed modular pipeline, with built-in preprocessing, checkpointing, and error handling, establishes a foundational step toward deployable, privacy-aware clinical AI for digital pathology. --- ### The OpenHands Software Agent SDK: A Composable and Extensible Foundation for Production Agents Authors: Xingyao Wang, Simon Rosenberg, Juan Michelini, Calvin Smith, Hoang Tran, Engel Nyst, Rohit Malhotra, Xuhui Zhou, Valerie Chen, Robert Brennan, Graham Neubig Published: 2025-11-05 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2511.03690v2 Agents are now used widely in the process of software development, but building production-ready software engineering agents is a complex task. Deploying software agents effectively requires flexibility in implementation and experimentation, reliable and secure execution, and interfaces for users to interact with agents. In this paper, we present the OpenHands Software Agent SDK, a toolkit for implementing software development agents that satisfy these desiderata. This toolkit is a complete architectural redesign of the agent components of the popular OpenHands framework for software development agents. To achieve flexibility, we design a simple interface for implementing agents that requires only a few lines of code in the default case, but is easily extensible to more complex full-featured agents with features such as custom tools, memory management, and more. For security and reliability, it delivers seamless local-to-remote execution portability, integrated REST/WebSocket services. For interaction with human users, it can connect directly to a variety of interfaces, such as visual workspaces (VSCode, VNC, browser), command-line interfaces, and APIs. Compared with existing SDKs from OpenAI, Claude and Google, OpenHands uniquely integrates native sandboxed execution, lifecycle control, model-agnostic multi-LLM routing, and built-in security analysis. We validate the architecture empirically: production deployment data shows that V1 substantially reduces system-attributable failures over V0 with negligible event-sourcing overhead, and evaluations across multiple models and benchmarks demonstrate strong agent performance. Put together, these elements allow the OpenHands Software Agent SDK to provide a practical foundation for prototyping, unlocking new classes of custom applications, and reliably deploying agents at scale. --- ### Structured Matrix Scaling for Multi-Class Calibration Authors: Eugène Berta, David Holzmüller, Michael I. Jordan, Francis Bach Published: 2025-11-05 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.03685v2 Post-hoc recalibration methods are widely used to ensure that classifiers provide faithful probability estimates. We argue that parametric recalibration functions based on logistic regression can be motivated from a simple theoretical setting for both binary and multiclass classification. This insight motivates the use of more expressive calibration methods beyond standard temperature scaling. For multi-class calibration however, a key challenge lies in the increasing number of parameters introduced by more complex models, often coupled with limited calibration data, which can lead to overfitting. Through extensive experiments, we demonstrate that the resulting bias-variance tradeoff can be effectively managed by structured regularization, robust preprocessing and efficient optimization. The resulting methods lead to substantial gains over existing logistic-based calibration techniques. We provide efficient and easy-to-use open-source implementations of our methods, making them an attractive alternative to common temperature, vector, and matrix scaling implementations. --- ### Simulation-Based Validation of an Integrated 4D/5D Digital-Twin Framework for Predictive Construction Control Authors: Atena Khoshkonesh, Mohsen Mohammadagha, Navid Ebrahimi Published: 2025-11-05 Categories: cs.CE, cs.AI, cs.LG, eess.SY arXiv: https://arxiv.org/abs/2511.03684v1 Persistent cost and schedule deviations remain a major challenge in the U.S. construction industry, revealing the limitations of deterministic CPM and static document-based estimating. This study presents an integrated 4D/5D digital-twin framework that couples Building Information Modeling (BIM) with natural-language processing (NLP)-based cost mapping, computer-vision (CV)-driven progress measurement, Bayesian probabilistic CPM updating, and deep-reinforcement-learning (DRL) resource-leveling. A nine-month case implementation on a Dallas-Fort Worth mid-rise project demonstrated measurable gains in accuracy and efficiency: 43% reduction in estimating labor, 6% reduction in overtime, and 30% project-buffer utilization, while maintaining an on-time finish at 128 days within P50-P80 confidence bounds. The digital-twin sandbox also enabled real-time "what-if" forecasting and traceable cost-schedule alignment through a 5D knowledge graph. Findings confirm that integrating AI-based analytics with probabilistic CPM and DRL enhances forecasting precision, transparency, and control resilience. The validated workflow establishes a practical pathway toward predictive, adaptive, and auditable construction management. --- ### Whisper Leak: a side-channel attack on Large Language Models Authors: Geoff McDonald, Jonathan Bar Or Published: 2025-11-05 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2511.03675v1 Large Language Models (LLMs) are increasingly deployed in sensitive domains including healthcare, legal services, and confidential communications, where privacy is paramount. This paper introduces Whisper Leak, a side-channel attack that infers user prompt topics from encrypted LLM traffic by analyzing packet size and timing patterns in streaming responses. Despite TLS encryption protecting content, these metadata patterns leak sufficient information to enable topic classification. We demonstrate the attack across 28 popular LLMs from major providers, achieving near-perfect classification (often >98% AUPRC) and high precision even at extreme class imbalance (10,000:1 noise-to-target ratio). For many models, we achieve 100% precision in identifying sensitive topics like "money laundering" while recovering 5-20% of target conversations. This industry-wide vulnerability poses significant risks for users under network surveillance by ISPs, governments, or local adversaries. We evaluate three mitigation strategies - random padding, token batching, and packet injection - finding that while each reduces attack effectiveness, none provides complete protection. Through responsible disclosure, we have collaborated with providers to implement initial countermeasures. Our findings underscore the need for LLM providers to address metadata leakage as AI systems handle increasingly sensitive information. --- ### DQN Performance with Epsilon Greedy Policies and Prioritized Experience Replay Authors: Daniel Perkins, Oscar J. Escobar, Luke Green Published: 2025-11-05 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.03670v1 We present a detailed study of Deep Q-Networks in finite environments, emphasizing the impact of epsilon-greedy exploration schedules and prioritized experience replay. Through systematic experimentation, we evaluate how variations in epsilon decay schedules affect learning efficiency, convergence behavior, and reward optimization. We investigate how prioritized experience replay leads to faster convergence and higher returns and show empirical results comparing uniform, no replay, and prioritized strategies across multiple simulations. Our findings illuminate the trade-offs and interactions between exploration strategies and memory management in DQN training, offering practical recommendations for robust reinforcement learning in resource-constrained settings. --- ### Addressing prior dependence in hierarchical Bayesian modeling for PTA data analysis I: Methodology and implementation Authors: Luigi D'amico, Eleonora Villa, Fatima Modica Bittordo, Aldo Barca, Francesco Alì, Massimo Meneghetti, Luca Naso Published: 2025-11-05 Categories: astro-ph.IM, astro-ph.CO, astro-ph.HE, stat.ML arXiv: https://arxiv.org/abs/2511.03667v1 Complex inference tasks, such as those encountered in Pulsar Timing Array (PTA) data analysis, rely on Bayesian frameworks. The high-dimensional parameter space and the strong interdependencies among astrophysical, pulsar noise, and nuisance parameters introduce significant challenges for efficient learning and robust inference. These challenges are emblematic of broader issues in decision science, where model over-parameterization and prior sensitivity can compromise both computational tractability and the reliability of the results. We address these issues in the framework of hierarchical Bayesian modeling by introducing a reparameterization strategy. Our approach employs Normalizing Flows (NFs) to decorrelate the parameters governing hierarchical priors from those of astrophysical interest. The use of NF-based mappings provides both the flexibility to realize the reparametrization and the tractability to preserve proper probability densities. We further adopt i-nessai, a flow-guided nested sampler, to accelerate exploration of complex posteriors. This unified use of NFs improves statistical robustness and computational efficiency, providing a principled methodology for addressing hierarchical Bayesian inference in PTA analysis. --- ### Part-Aware Bottom-Up Group Reasoning for Fine-Grained Social Interaction Detection Authors: Dongkeun Kim, Minsu Cho, Suha Kwak Published: 2025-11-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.03666v2 Social interactions often emerge from subtle, fine-grained cues such as facial expressions, gaze, and gestures. However, existing methods for social interaction detection overlook such nuanced cues and primarily rely on holistic representations of individuals. Moreover, they directly detect social groups without explicitly modeling the underlying interactions between individuals. These drawbacks limit their ability to capture localized social signals and introduce ambiguity when group configurations should be inferred from social interactions grounded in nuanced cues. In this work, we propose a part-aware bottom-up group reasoning framework for fine-grained social interaction detection. The proposed method infers social groups and their interactions using body part features and their interpersonal relations. Our model first detects individuals and enhances their features using part-aware cues, and then infers group configuration by associating individuals via similarity-based reasoning, which considers not only spatial relations but also subtle social cues that signal interactions, leading to more accurate group inference. Experiments on the NVI dataset demonstrate that our method outperforms prior methods, achieving the new state of the art, while additional results on the Café dataset further validate its generalizability to group activity understanding. --- ### A Lightweight 3D-CNN for Event-Based Human Action Recognition with Privacy-Preserving Potential Authors: Mehdi Sefidgar Dilmaghani, Francis Fowley, Peter Corcoran Published: 2025-11-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.03665v1 This paper presents a lightweight three-dimensional convolutional neural network (3DCNN) for human activity recognition (HAR) using event-based vision data. Privacy preservation is a key challenge in human monitoring systems, as conventional frame-based cameras capture identifiable personal information. In contrast, event cameras record only changes in pixel intensity, providing an inherently privacy-preserving sensing modality. The proposed network effectively models both spatial and temporal dynamics while maintaining a compact design suitable for edge deployment. To address class imbalance and enhance generalization, focal loss with class reweighting and targeted data augmentation strategies are employed. The model is trained and evaluated on a composite dataset derived from the Toyota Smart Home and ETRI datasets. Experimental results demonstrate an F1-score of 0.9415 and an overall accuracy of 94.17%, outperforming benchmark 3D-CNN architectures such as C3D, ResNet3D, and MC3_18 by up to 3%. These results highlight the potential of event-based deep learning for developing accurate, efficient, and privacy-aware human action recognition systems suitable for real-world edge applications. --- ### SHIELD: Securing Healthcare IoT with Efficient Machine Learning Techniques for Anomaly Detection Authors: Mahek Desai, Apoorva Rumale, Marjan Asadinia Published: 2025-11-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.03661v1 The integration of IoT devices in healthcare introduces significant security and reliability challenges, increasing susceptibility to cyber threats and operational anomalies. This study proposes a machine learning-driven framework for (1) detecting malicious cyberattacks and (2) identifying faulty device anomalies, leveraging a dataset of 200,000 records. Eight machine learning models are evaluated across three learning approaches: supervised learning (XGBoost, K-Nearest Neighbors (K- NN)), semi-supervised learning (Generative Adversarial Networks (GAN), Variational Autoencoders (VAE)), and unsupervised learning (One-Class Support Vector Machine (SVM), Isolation Forest, Graph Neural Networks (GNN), and Long Short-Term Memory (LSTM) Autoencoders). The comprehensive evaluation was conducted across multiple metrics like F1-score, precision, recall, accuracy, ROC-AUC, computational efficiency. XGBoost achieved 99\% accuracy with minimal computational overhead (0.04s) for anomaly detection, while Isolation Forest balanced precision and recall effectively. LSTM Autoencoders underperformed with lower accuracy and higher latency. For attack detection, KNN achieved near-perfect precision, recall, and F1-score with the lowest computational cost (0.05s), followed by VAE at 97% accuracy. GAN showed the highest computational cost with lowest accuracy and ROC-AUC. These findings enhance IoT-enabled healthcare security through effective anomaly detection strategies. By improving early detection of cyber threats and device failures, this framework has the potential to prevent data breaches, minimize system downtime, and ensure the continuous and safe operation of medical devices, ultimately safeguarding patient health and trust in IoT-driven healthcare solutions. --- ### ChiMDQA: Towards Comprehensive Chinese Document QA with Fine-grained Evaluation Authors: Jing Gao, Shutiao Luo, Yumeng Liu, Yuanming Li, Hongji Zeng Published: 2025-11-05 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.03656v1 With the rapid advancement of natural language processing (NLP) technologies, the demand for high-quality Chinese document question-answering datasets is steadily growing. To address this issue, we present the Chinese Multi-Document Question Answering Dataset(ChiMDQA), specifically designed for downstream business scenarios across prevalent domains including academic, education, finance, law, medical treatment, and news. ChiMDQA encompasses long-form documents from six distinct fields, consisting of 6,068 rigorously curated, high-quality question-answer (QA) pairs further classified into ten fine-grained categories. Through meticulous document screening and a systematic question-design methodology, the dataset guarantees both diversity and high quality, rendering it applicable to various NLP tasks such as document comprehension, knowledge extraction, and intelligent QA systems. Additionally, this paper offers a comprehensive overview of the dataset's design objectives, construction methodologies, and fine-grained evaluation system, supplying a substantial foundation for future research and practical applications in Chinese QA. The code and data are available at: https://anonymous.4open.science/r/Foxit-CHiMDQA/. --- ### Efficient and Private Property Testing via Indistinguishability Authors: Cynthia Dwork, Pranay Tankala Published: 2025-11-05 Categories: cs.CC, cs.DS, cs.LG arXiv: https://arxiv.org/abs/2511.03653v2 Given a small random sample of $n$-bit strings labeled by an unknown Boolean function, which properties of this function can be tested computationally efficiently? We show an equivalence between properties that are efficiently testable from few samples and properties with structured symmetry, which depend only on the function's average values on an efficiently computable partition of the domain. Without the efficiency constraint, a similar characterization in terms of unstructured symmetry was obtained by Blais and Yoshida (2019). We also give a function testing analogue of the classic characterization of testable graph properties in terms of regular partitions, as well as a sublinear time and differentially private algorithm to compute concise summaries of such partitions of graphs. Finally, we tighten a recent characterization of the computational indistinguishability of product distributions, which encompasses the related task of efficiently testing which of two candidate functions labeled the observed samples. Essential to our proofs is the following observation of independent interest: Every randomized Boolean function, no matter how complex, admits a supersimulator: a randomized polynomial-size circuit whose output on random inputs cannot be efficiently distinguished from reality with constant advantage, even by polynomially larger distinguishers. This surprising fact is implicit in a theorem of Dwork et al. (2021) in the context of algorithmic fairness, but its complexity-theoretic implications were not previously explored. We give a new proof of this lemma using an iteration technique from the graph regularity literature, and we observe that a subtle quantifier switch allows it to powerfully circumvent known barriers to improving the landmark complexity-theoretic regularity lemma of Trevisan, Tulsiani, and Vadhan (2009). --- ### Flying Robotics Art: ROS-based Drone Draws the Record-Breaking Mural Authors: Andrei A. Korigodskii, Oleg D. Kalachev, Artem E. Vasiunik, Matvei V. Urvantsev, Georgii E. Bondar Published: 2025-11-05 Categories: cs.RO, cs.CV, eess.SY arXiv: https://arxiv.org/abs/2511.03651v1 This paper presents the innovative design and successful deployment of a pioneering autonomous unmanned aerial system developed for executing the world's largest mural painted by a drone. Addressing the dual challenges of maintaining artistic precision and operational reliability under adverse outdoor conditions such as wind and direct sunlight, our work introduces a robust system capable of navigating and painting outdoors with unprecedented accuracy. Key to our approach is a novel navigation system that combines an infrared (IR) motion capture camera and LiDAR technology, enabling precise location tracking tailored specifically for largescale artistic applications. We employ a unique control architecture that uses different regulation in tangential and normal directions relative to the planned path, enabling precise trajectory tracking and stable line rendering. We also present algorithms for trajectory planning and path optimization, allowing for complex curve drawing and area filling. The system includes a custom-designed paint spraying mechanism, specifically engineered to function effectively amidst the turbulent airflow generated by the drone's propellers, which also protects the drone's critical components from paint-related damage, ensuring longevity and consistent performance. Experimental results demonstrate the system's robustness and precision in varied conditions, showcasing its potential for autonomous large-scale art creation and expanding the functional applications of robotics in creative fields. --- ### Signal Intensity-weighted coordinate channels improve learning stability and generalisation in 1D and 2D CNNs in localisation tasks on biomedical signals Authors: Vittal L. Rao Published: 2025-11-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.03645v1 Localisation tasks in biomedical data often require models to learn meaningful spatial or temporal relationships from signals with complex intensity distributions. A common strategy, exemplified by CoordConv layers, is to append coordinate channels to convolutional inputs, enabling networks to learn absolute positions. In this work, we propose a signal intensity-weighted coordinate representation that replaces the pure coordinate channels with channels scaled by local signal intensity. This modification embeds an intensity-position coupling directly in the input representation, introducing a simple and modality-agnostic inductive bias. We evaluate the approach on two distinct localisation problems: (i) predicting the time of morphological transition in 20-second, two-lead ECG signals, and (ii) regressing the coordinates of nuclear centres in cytological images from the SiPaKMeD dataset. In both cases, the proposed representation yields faster convergence and higher generalisation performance relative to conventional coordinate-channel approaches, demonstrating its effectiveness across both one-dimensional and two-dimensional biomedical signals. --- ### Explaining Human Choice Probabilities with Simple Vector Representations Authors: Peter A. V. DiBerardino, Britt Anderson Published: 2025-11-05 Categories: q-bio.NC, cs.AI arXiv: https://arxiv.org/abs/2511.03643v3 We formalize human choice behavior in a probabilistic hide-and-seek task. In our geometric construction, vectors represent participant choice frequencies as well as probability matching and maximizing strategies. We measured choice behavior not just in the well-studied scenario of pursuing an objective (seeking), but also the rarely studied scenario of avoiding consequences (hiding). We used our geometric construction to define the avoidance counterpart of probability matching, probability antimatching, as a vector reflection across the uniform distribution. Decomposing the behavior of participants when they were seeking into matching and maximizing components, we could mathematically derive the analogous antimatching and minimizing strategies for hiding. Participants did change their choice frequencies between hiding and seeking conditions. In both cases, we found that a linear combination of just two vectors did an excellent job of fitting participant choice frequencies: matching + maximizing for seeking, antimatching + minimizing for hiding. We could account for diversity in participant strategy usage by varying the coefficients of the two relevant basis strategy vectors. We successfully applied this model in scenarios of up to 7 rooms. We conclude that an apparent diversity of human conduct in stochastic environments can, in some cases, be explained by varying the weighting of two principle strategies: whether to match/antimatch or maximize/minimize. --- ### Watermarking Large Language Models in Europe: Interpreting the AI Act in Light of Technology Authors: Thomas Souverain Published: 2025-11-05 Categories: cs.CR, cs.AI, cs.CL, cs.CY arXiv: https://arxiv.org/abs/2511.03641v1 To foster trustworthy Artificial Intelligence (AI) within the European Union, the AI Act requires providers to mark and detect the outputs of their general-purpose models. The Article 50 and Recital 133 call for marking methods that are ''sufficiently reliable, interoperable, effective and robust''. Yet, the rapidly evolving and heterogeneous landscape of watermarks for Large Language Models (LLMs) makes it difficult to determine how these four standards can be translated into concrete and measurable evaluations. Our paper addresses this challenge, anchoring the normativity of European requirements in the multiplicity of watermarking techniques. Introducing clear and distinct concepts on LLM watermarking, our contribution is threefold. (1) Watermarking Categorisation: We propose an accessible taxonomy of watermarking methods according to the stage of the LLM lifecycle at which they are applied - before, during, or after training, and during next-token distribution or sampling. (2) Watermarking Evaluation: We interpret the EU AI Act's requirements by mapping each criterion with state-of-the-art evaluations on robustness and detectability of the watermark, and of quality of the LLM. Since interoperability remains largely untheorised in LLM watermarking research, we propose three normative dimensions to frame its assessment. (3) Watermarking Comparison: We compare current watermarking methods for LLMs against the operationalised European criteria and show that no approach yet satisfies all four standards. Encouraged by emerging empirical tests, we recommend further research into watermarking directly embedded within the low-level architecture of LLMs. --- ### Quantifying Weighted Morphological Content of Large-Scale Structures via Simulation-Based Inference Authors: M. H. Jalali Kanafi, S. M. S. Movahed Published: 2025-11-05 Categories: astro-ph.CO, cs.LG, physics.comp-ph arXiv: https://arxiv.org/abs/2511.03636v2 We perform a simulation-based forecasting analysis to compare the cosmological constraining power of higher-order summary statistics of the large-scale structure, the Minkowski Functionals (MFs) and a class weighted morphological measure known as the Conditional Moments of Derivatives (CMD), with that of the redshift-space halo power spectrum multipoles (PS), with a particular focus on their sensitivity to nonlinear and anisotropic features in redshift space. Our analysis relies on halo catalogs from the Big Sobol Sequence simulations at redshift $z=0.5$, employing a likelihood-free inference framework implemented via neural posterior estimation. At the fiducial Quijote cosmology and for a Gaussian smoothing scale of $R=15\,h^{-1}\mathrm{Mpc}$, CMD provide systematically tighter constraints than MFs. Combining MFs and CMD into a joint estimator improves the precision by $27\%^{+9\%}_{-5\%}$ for $σ_8$ and $26\%^{+7\%}_{-5\%}$ for $Ω_{\mathrm{m}}$ relative to MFs alone, highlighting the complementary anisotropy-sensitive information captured by the CMD in contrast to the scalar morphological content encapsulated by the MFs. We compare the combined statistic MFs+CMD with the PS at matched effective scales ($k_{\max}\simeq0.16\,h\,\mathrm{Mpc^{-1}}$) under three halo-selection conditions: all halos, fixed number density, and mass-selected ($M>3\times10^{13}\,h^{-1}M_\odot$). In the mass-selected configuration, the (weighted) morphological estimator outperforms the power spectrum by $45\%^{+20\%}_{-9\%}$ for $σ_8$ and $43\%^{+10\%}_{-7\%}$ for $Ω_{\mathrm{m}}$. We also extend the simulation-based forecast analysis across a continuous range of cosmological parameters and multiple smoothing scales for morphological measures. --- ### Towards Transparent Stance Detection: A Zero-Shot Approach Using Implicit and Explicit Interpretability Authors: Apoorva Upadhyaya, Wolfgang Nejdl, Marco Fisichella Published: 2025-11-05 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2511.03635v1 Zero-Shot Stance Detection (ZSSD) identifies the attitude of the post toward unseen targets. Existing research using contrastive, meta-learning, or data augmentation suffers from generalizability issues or lack of coherence between text and target. Recent works leveraging large language models (LLMs) for ZSSD focus either on improving unseen target-specific knowledge or generating explanations for stance analysis. However, most of these works are limited by their over-reliance on explicit reasoning, provide coarse explanations that lack nuance, and do not explicitly model the reasoning process, making it difficult to interpret the model's predictions. To address these issues, in our study, we develop a novel interpretable ZSSD framework, IRIS. We provide an interpretable understanding of the attitude of the input towards the target implicitly based on sequences within the text (implicit rationales) and explicitly based on linguistic measures (explicit rationales). IRIS considers stance detection as an information retrieval ranking task, understanding the relevance of implicit rationales for different stances to guide the model towards correct predictions without requiring the ground-truth of rationales, thus providing inherent interpretability. In addition, explicit rationales based on communicative features help decode the emotional and cognitive dimensions of stance, offering an interpretable understanding of the author's attitude towards the given target. Extensive experiments on the benchmark datasets of VAST, EZ-STANCE, P-Stance, and RFD using 50%, 30%, and even 10% training data prove the generalizability of our model, benefiting from the proposed architecture and interpretable design. --- ### nanoTabPFN: A Lightweight and Educational Reimplementation of TabPFN Authors: Alexander Pfefferle, Johannes Hog, Lennart Purucker, Frank Hutter Published: 2025-11-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.03634v2 Tabular foundation models such as TabPFN have revolutionized predictive machine learning for tabular data. At the same time, the driving factors of this revolution are hard to understand. Existing open-source tabular foundation models are implemented in complicated pipelines boasting over 10,000 lines of code, lack architecture documentation or code quality. In short, the implementations are hard to understand, not beginner-friendly, and complicated to adapt for new experiments. We introduce nanoTabPFN, a simplified and lightweight implementation of the TabPFN v2 architecture and a corresponding training loop that uses pre-generated training data. nanoTabPFN makes tabular foundation models more accessible to students and researchers alike. For example, restricted to a small data setting it achieves a performance comparable to traditional machine learning baselines within one minute of pre-training on a single GPU (160,000x faster than TabPFN v2 pretraining). This eliminated requirement of large computational resources makes pre-training tabular foundation models accessible for educational purposes. Our code is available at https://github.com/automl/nanoTabPFN. --- ### Neural Beamforming with Doppler-Aware Sparse Attention for High Mobility Environments Authors: Cemil Vahapoglu, Timothy J. O'Shea, Wan Liu, Sennur Ulukus Published: 2025-11-05 Categories: cs.IT, cs.LG, eess.SP arXiv: https://arxiv.org/abs/2511.03632v1 Beamforming has significance for enhancing spectral efficiency and mitigating interference in multi-antenna wireless systems, facilitating spatial multiplexing and diversity in dense and high mobility scenarios. Traditional beamforming techniques such as zero-forcing beamforming (ZFBF) and minimum mean square error (MMSE) beamforming experience performance deterioration under adverse channel conditions. Deep learning-based beamforming offers an alternative with nonlinear mappings from channel state information (CSI) to beamforming weights by improving robustness against dynamic channel environments. Transformer-based models are particularly effective due to their ability to model long-range dependencies across time and frequency. However, their quadratic attention complexity limits scalability in large OFDM grids. Recent studies address this issue through sparse attention mechanisms that reduce complexity while maintaining expressiveness, yet often employ patterns that disregard channel dynamics, as they are not specifically designed for wireless communication scenarios. In this work, we propose a Doppler-aware Sparse Neural Network Beamforming (Doppler-aware Sparse NNBF) model that incorporates a channel-adaptive sparse attention mechanism in a multi-user single-input multiple-output (MU-SIMO) setting. The proposed sparsity structure is configurable along 2D time-frequency axes based on channel dynamics and is theoretically proven to ensure full connectivity within p hops, where p is the number of attention heads. Simulation results under urban macro (UMa) channel conditions show that Doppler-aware Sparse NNBF significantly outperforms both a fixed-pattern baseline, referred to as Standard Sparse NNBF, and conventional beamforming techniques ZFBF and MMSE beamforming in high mobility scenarios, while maintaining structured sparsity with a controlled number of attended keys per query. --- ### Financial Management System for SMEs: Real-World Deployment of Accounts Receivable and Cash Flow Prediction Authors: Bartłomiej Małkus, Szymon Bobek, Grzegorz J. Nalepa Published: 2025-11-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.03631v2 Small and Medium Enterprises (SMEs), particularly freelancers and early-stage businesses, face unique financial management challenges due to limited resources, small customer bases, and constrained data availability. This paper presents the development and deployment of an integrated financial prediction system that combines accounts receivable prediction and cash flow forecasting specifically designed for SME operational constraints. Our system addresses the gap between enterprise-focused financial tools and the practical needs of freelancers and small businesses. The solution integrates two key components: a binary classification model for predicting invoice payment delays, and a multi-module cash flow forecasting model that handles incomplete and limited historical data. A prototype system has been implemented and deployed as a web application with integration into Cluee's platform, a startup providing financial management tools for freelancers, demonstrating practical feasibility for real-world SME financial management. --- ### LiveTradeBench: Seeking Real-World Alpha with Large Language Models Authors: Haofei Yu, Fenghai Li, Jiaxuan You Published: 2025-11-05 Categories: q-fin.TR, cs.AI, cs.CE, cs.CL arXiv: https://arxiv.org/abs/2511.03628v1 Large language models (LLMs) achieve strong performance across benchmarks--from knowledge quizzes and math reasoning to web-agent tasks--but these tests occur in static settings, lacking real dynamics and uncertainty. Consequently, they evaluate isolated reasoning or problem-solving rather than decision-making under uncertainty. To address this, we introduce LiveTradeBench, a live trading environment for evaluating LLM agents in realistic and evolving markets. LiveTradeBench follows three design principles: (i) Live data streaming of market prices and news, eliminating dependence on offline backtesting and preventing information leakage while capturing real-time uncertainty; (ii) a portfolio-management abstraction that extends control from single-asset actions to multi-asset allocation, integrating risk management and cross-asset reasoning; and (iii) multi-market evaluation across structurally distinct environments--U.S. stocks and Polymarket prediction markets--differing in volatility, liquidity, and information flow. At each step, an agent observes prices, news, and its portfolio, then outputs percentage allocations that balance risk and return. Using LiveTradeBench, we run 50-day live evaluations of 21 LLMs across families. Results show that (1) high LMArena scores do not imply superior trading outcomes; (2) models display distinct portfolio styles reflecting risk appetite and reasoning dynamics; and (3) some LLMs effectively leverage live signals to adapt decisions. These findings expose a gap between static evaluation and real-world competence, motivating benchmarks that test sequential decision making and consistency under live uncertainty. --- ### CLAX: Fast and Flexible Neural Click Models in JAX Authors: Philipp Hager, Onno Zoeter, Maarten de Rijke Published: 2025-11-05 Categories: cs.IR, cs.LG, cs.SE arXiv: https://arxiv.org/abs/2511.03620v1 CLAX is a JAX-based library that implements classic click models using modern gradient-based optimization. While neural click models have emerged over the past decade, complex click models based on probabilistic graphical models (PGMs) have not systematically adopted gradient-based optimization, preventing practitioners from leveraging modern deep learning frameworks while preserving the interpretability of classic models. CLAX addresses this gap by replacing EM-based optimization with direct gradient-based optimization in a numerically stable manner. The framework's modular design enables the integration of any component, from embeddings and deep networks to custom modules, into classic click models for end-to-end optimization. We demonstrate CLAX's efficiency by running experiments on the full Baidu-ULTR dataset comprising over a billion user sessions in $\approx$ 2 hours on a single GPU, orders of magnitude faster than traditional EM approaches. CLAX implements ten classic click models, serving both industry practitioners seeking to understand user behavior and improve ranking performance at scale and researchers developing new click models. CLAX is available at: https://github.com/philipphager/clax --- ### Towards Formalizing Reinforcement Learning Theory: A Robbins-Siegmund Approach Authors: Shangtong Zhang Published: 2025-11-05 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2511.03618v2 In this paper, we formalize the almost sure convergence of $Q$-learning and linear temporal difference (TD) learning with Markovian samples using the Lean 4 theorem prover based on the Mathlib library. $Q$-learning and linear TD are among the earliest and most influential reinforcement learning (RL) algorithms. The investigation of their convergence properties is not only a major research topic during the early development of the RL field but also receives significant attention nowadays. This paper formally verifies their almost sure convergence in a unified framework based on the Robbins-Siegmund theorem. The framework developed in this work can potentially be extended to convergence rates and other modes of convergence. This work thus makes an important step towards fully formalizing convergent RL results. The code is available at https://github.com/ShangtongZhang/rl-theory-in-lean. --- ### Visualization Biases MLLM's Decision Making in Network Data Tasks Authors: Timo Brand, Henry Förster, Stephen G. Kobourov, Jacob Miller Published: 2025-11-05 Categories: cs.GR, cs.AI arXiv: https://arxiv.org/abs/2511.03617v1 We evaluate how visualizations can influence the judgment of MLLMs about the presence or absence of bridges in a network. We show that the inclusion of visualization improves confidence over a structured text-based input that could theoretically be helpful for answering the question. On the other hand, we observe that standard visualization techniques create a strong bias towards accepting or refuting the presence of a bridge -- independently of whether or not a bridge actually exists in the network. While our results indicate that the inclusion of visualization techniques can effectively influence the MLLM's judgment without compromising its self-reported confidence, they also imply that practitioners must be careful of allowing users to include visualizations in generative AI applications so as to avoid undesired hallucinations. --- ### Going Beyond Expert Performance via Deep Implicit Imitation Reinforcement Learning Authors: Iason Chrysomallis, Georgios Chalkiadakis Published: 2025-11-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.03616v1 Imitation learning traditionally requires complete state-action demonstrations from optimal or near-optimal experts. These requirements severely limit practical applicability, as many real-world scenarios provide only state observations without corresponding actions and expert performance is often suboptimal. In this paper we introduce a deep implicit imitation reinforcement learning framework that addresses both limitations by combining deep reinforcement learning with implicit imitation learning from observation-only datasets. Our main algorithm, Deep Implicit Imitation Q-Network (DIIQN), employs an action inference mechanism that reconstructs expert actions through online exploration and integrates a dynamic confidence mechanism that adaptively balances expert-guided and self-directed learning. This enables the agent to leverage expert guidance for accelerated training while maintaining capacity to surpass suboptimal expert performance. We further extend our framework with a Heterogeneous Actions DIIQN (HA-DIIQN) algorithm to tackle scenarios where expert and agent possess different action sets, a challenge previously unaddressed in the implicit imitation learning literature. HA-DIIQN introduces an infeasibility detection mechanism and a bridging procedure identifying alternative pathways connecting agent capabilities to expert guidance when direct action replication is impossible. Our experimental results demonstrate that DIIQN achieves up to 130% higher episodic returns compared to standard DQN, while consistently outperforming existing implicit imitation methods that cannot exceed expert performance. In heterogeneous action settings, HA-DIIQN learns up to 64% faster than baselines, leveraging expert datasets unusable by conventional approaches. Extensive parameter sensitivity analysis reveals the framework's robustness across varying dataset sizes and hyperparameter configurations. --- ### A systematic review of relation extraction task since the emergence of Transformers Authors: Ringwald Celian, Gandon, Fabien, Faron Catherine, Michel Franck, Abi Akl Hanna Published: 2025-11-05 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.03610v2 This article presents a systematic review of relation extraction (RE) research since the advent of Transformer-based models. Using an automated framework to collect and annotate publications, we analyze 34 surveys, 64 datasets, and 104 models published between 2019 and 2024. The review highlights methodological advances, benchmark resources, and the integration of semantic web technologies. By consolidating results across multiple dimensions, the study identifies current trends, limitations, and open challenges, offering researchers and practitioners a comprehensive reference for understanding the evolution and future directions of RE. --- ### Vector-valued self-normalized concentration inequalities beyond sub-Gaussianity Authors: Diego Martinez-Taboada, Tomas Gonzalez, Aaditya Ramdas Published: 2025-11-05 Categories: stat.ML, cs.LG, math.ST arXiv: https://arxiv.org/abs/2511.03606v2 The study of self-normalized processes plays a crucial role in a wide range of applications, from sequential decision-making to econometrics. While the behavior of self-normalized concentration has been widely investigated for scalar-valued processes, vector-valued processes remain comparatively underexplored, especially outside of the sub-Gaussian framework. In this contribution, we provide concentration bounds for self-normalized processes with light tails beyond sub-Gaussianity (such as Bennett or Bernstein bounds). We illustrate the relevance of our results in the context of online linear regression, with applications in (kernelized) linear bandits. --- ### Step-Audio-EditX Technical Report Authors: Chao Yan, Boyong Wu, Peng Yang, Pengfei Tan, Guoqiang Hu, Li Xie, Yuxin Zhang, Xiangyu, Zhang, Fei Tian, Xuerui Yang, Xiangyu Zhang et al. Published: 2025-11-05 Categories: cs.CL, cs.AI, cs.HC, cs.SD, eess.AS arXiv: https://arxiv.org/abs/2511.03601v2 We present Step-Audio-EditX, the first open-source LLM-based audio model excelling at expressive and iterative audio editing encompassing emotion, speaking style, and paralinguistics alongside robust zero-shot text-to-speech (TTS) capabilities. Our core innovation lies in leveraging only large-margin synthetic data, which circumvents the need for embedding-based priors or auxiliary modules. This large-margin learning approach enables both iterative control and high expressivity across voices, and represents a fundamental pivot from the conventional focus on representation-level disentanglement. Evaluation results demonstrate that Step-Audio-EditX surpasses both MiniMax-2.6-hd and Doubao-Seed-TTS-2.0 in emotion editing and other fine-grained control tasks. --- ### Tensor-Efficient High-Dimensional Q-learning Authors: Junyi Wu, Dan Li Published: 2025-11-05 Categories: cs.LG, eess.SY arXiv: https://arxiv.org/abs/2511.03595v2 High-dimensional reinforcement learning(RL) faces challenges with complex calculations and low sample efficiency in large state-action spaces. Q-learning algorithms struggle particularly with the curse of dimensionality, where the number of state-action pairs grows exponentially with problem size. While neural network-based approaches like Deep Q-Networks have shown success, they do not explicitly exploit problem structure. Many high-dimensional control tasks exhibit low-rank structure in their value functions, and tensor-based methods using low-rank decomposition offer parameter-efficient representations. However, existing tensor-based Q-learning methods focus on representation fidelity without leveraging this structure for exploration. We propose Tensor-Efficient Q-Learning (TEQL), which represents the Q-function as a low-rank CP tensor over discretized state-action spaces and exploits the tensor structure for uncertainty-aware exploration. TEQL incorporates Error-Uncertainty Guided Exploration (EUGE), which combines tensor approximation error with visit counts to guide action selection, along with frequency-aware regularization to stabilize updates. Under matched parameter budgets, experiments on classic control tasks demonstrate that TEQL outperforms both matrix-based low-rank methods and deep RL baselines in sample efficiency, making it suitable for resource-constrained applications where sampling costs are high. --- ### Human Mesh Modeling for Anny Body Authors: Romain Brégier, Guénolé Fiche, Laura Bravo-Sánchez, Thomas Lucas, Matthieu Armando, Philippe Weinzaepfel, Grégory Rogez, Fabien Baradel Published: 2025-11-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.03589v3 Parametric body models provide the structural basis for many human-centric tasks, yet existing models often rely on costly 3D scans and learned shape spaces that are proprietary and demographically narrow. We introduce Anny, a simple, fully differentiable, and scan-free human body model grounded in anthropometric knowledge from the MakeHuman community. Anny defines a continuous, interpretable shape space, where phenotype parameters (e.g. gender, age, height, weight) control blendshapes spanning a wide range of human forms---across ages (from infants to elders), body types, and proportions. Calibrated using WHO population statistics, Anny provides realistic and demographically grounded human shape variation within a single unified model. We release the Anny body model and its code under the Apache 2.0 license. Thanks to its openness and semantic control, Anny serves as a versatile foundation for 3D human modeling---supporting millimeter-accurate scan fitting, controlled synthetic data generation, and Human Mesh Recovery (HMR). We further introduce Anny-One, a collection of 780k photorealistic images generated with Anny, showing that despite its simplicity, HMR models trained with Anny can match the performance of those trained with scan-based body models. --- ### PerfDojo: Automated ML Library Generation for Heterogeneous Architectures Authors: Andrei Ivanov, Siyuan Shen, Gioele Gottardo, Marcin Chrapek, Afif Boudaoud, Timo Schneider, Luca Benini, Torsten Hoefler Published: 2025-11-05 Categories: cs.PF, cs.AI arXiv: https://arxiv.org/abs/2511.03586v1 The increasing complexity of machine learning models and the proliferation of diverse hardware architectures (CPUs, GPUs, accelerators) make achieving optimal performance a significant challenge. Heterogeneity in instruction sets, specialized kernel requirements for different data types and model features (e.g., sparsity, quantization), and architecture-specific optimizations complicate performance tuning. Manual optimization is resource-intensive, while existing automatic approaches often rely on complex hardware-specific heuristics and uninterpretable intermediate representations, hindering performance portability. We introduce PerfLLM, a novel automatic optimization methodology leveraging Large Language Models (LLMs) and Reinforcement Learning (RL). Central to this is PerfDojo, an environment framing optimization as an RL game using a human-readable, mathematically-inspired code representation that guarantees semantic validity through transformations. This allows effective optimization without prior hardware knowledge, facilitating both human analysis and RL agent training. We demonstrate PerfLLM's ability to achieve significant performance gains across diverse CPU (x86, Arm, RISC-V) and GPU architectures. --- ### Learning Under Laws: A Constraint-Projected Neural PDE Solver that Eliminates Hallucinations Authors: Mainak Singha Published: 2025-11-05 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.03578v1 Neural networks can approximate solutions to partial differential equations, but they often break the very laws they are meant to model-creating mass from nowhere, drifting shocks, or violating conservation and entropy. We address this by training within the laws of physics rather than beside them. Our framework, called Constraint-Projected Learning (CPL), keeps every update physically admissible by projecting network outputs onto the intersection of constraint sets defined by conservation, Rankine-Hugoniot balance, entropy, and positivity. The projection is differentiable and adds only about 10% computational overhead, making it fully compatible with back-propagation. We further stabilize training with total-variation damping (TVD) to suppress small oscillations and a rollout curriculum that enforces consistency over long prediction horizons. Together, these mechanisms eliminate both hard and soft violations: conservation holds at machine precision, total-variation growth vanishes, and entropy and error remain bounded. On Burgers and Euler systems, CPL produces stable, physically lawful solutions without loss of accuracy. Instead of hoping neural solvers will respect physics, CPL makes that behavior an intrinsic property of the learning process. ---