# Research Papers — 2025-11 · bundle page 61 of 197 > Full-text markdown of papers #3001–3050 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/61 [← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/60.md) [Next bundle →](https://aipod.dev/papers/archive/2025-11/page/62.md) ### Periodicity-Enforced Neural Network for Designing Deterministic Lateral Displacement Devices Authors: Andrew Lee, Mahir Mobarrat, Xiaolin Chen Published: 2025-11-21 Categories: cs.LG, physics.flu-dyn arXiv: https://arxiv.org/abs/2511.17754v1 Deterministic Lateral Displacement (DLD) devices enable liquid biopsy for cancer detection by separating circulating tumor cells (CTCs) from blood samples based on size, but designing these microfluidic devices requires computationally expensive Navier-Stokes simulations and particle-tracing analyses. While recent surrogate modeling approaches using deep learning have accelerated this process, they often inadequately handle the critical periodic boundary conditions of DLD unit cells, leading to cumulative errors in multi-unit device predictions. This paper introduces a periodicity-enforced surrogate modeling approach that incorporates periodic layers, neural network components that guarantee exact periodicity without penalty terms or output modifications, into deep learning architectures for DLD device design. The proposed method employs three sub-networks to predict steady-state, non-dimensional velocity and pressure fields (u, v, p) rather than directly predicting critical diameters or particle trajectories, enabling complete flow field characterization and enhanced design flexibility. Periodic layers ensure exact matching of flow variables across unit cell boundaries through architectural enforcement rather than soft penalty-based approaches. Validation on 120 CFD-generated geometries demonstrates that the periodic layer implementation achieves 0.478% critical diameter error while maintaining perfect periodicity consistency, representing an 85.4% improvement over baseline methods. The approach enables efficient and accurate DLD device design with guaranteed boundary condition satisfaction for multi-unit device applications. --- ### $Δ$-ML Ensembles for Selecting Quantum Chemistry Methods to Compute Intermolecular Interactions Authors: Austin M. Wallace, C. David Sherrill, Giri P. Krishnan Published: 2025-11-21 Categories: physics.chem-ph, cs.AI arXiv: https://arxiv.org/abs/2511.17753v1 Ab initio quantum chemical methods for accurately computing interactions between molecules have a wide range of applications but are often computationally expensive. Hence, selecting an appropriate method based on accuracy and computational cost remains a significant challenge due to varying performance of methods. In this work, we propose a framework based on an ensemble of $Δ$-ML models trained on features extracted from a pre-trained atom-pairwise neural network to predict the error of each method relative to all other methods including the ``gold standard'' coupled cluster with single, double, and perturbative triple excitations at the estimated complete basis set limit (CCSD(T)/CBS). Our proposed approach provides error estimates across various levels of theories and identifies the computationally efficient approach for a given error range utilizing only a subset of the dataset. Further, this approach allows comparison between various theories. We demonstrate the effectiveness of our approach using an extended BioFragment dataset, which includes the interaction energies for common biomolecular fragments and small organic dimers. Our results show that the proposed framework achieves very small mean-absolute-errors below 0.1 kcal/mol regardless of the given method. Furthermore, by analyzing all-to-all $Δ$-ML models for present levels of theory, we identify method groupings that align with theoretical hypotheses, providing evidence that $Δ$-ML models can easily learn corrections from any level of theory to any other level of theory. --- ### SPIDER: Spatial Image CorresponDence Estimator for Robust Calibration Authors: Zhimin Shao, Abhay Yadav, Rama Chellappa, Cheng Peng Published: 2025-11-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.17750v2 Reliable image correspondences form the foundation of vision-based spatial perception, enabling recovery of 3D structure and camera poses. However, unconstrained feature matching across domains such as aerial, indoor, and outdoor scenes remains challenging due to large variations in appearance, scale and viewpoint. Feature matching has been conventionally formulated as a 2D-to-2D problem; however, recent 3D foundation models provides spatial feature matching properties based on two-view geometry. While powerful, we observe that these spatially coherent matches often concentrate on dominant planar regions, e.g., walls or ground surfaces, while being less sensitive to fine-grained geometric details, particularly under large viewpoint changes. To better understand these trade-offs, we first perform linear probe experiments to evaluate the performance of various vision foundation models for image matching. Building on these insights, we introduce SPIDER, a universal feature matching framework that integrates a shared feature extraction backbone with two specialized network heads for estimating both 2D-based and 3D-based correspondences from coarse to fine. Finally, we introduce an image-matching evaluation benchmark that focuses on unconstrained scenarios with large baselines. SPIDER significantly outperforms SoTA methods, demonstrating its strong ability as a universal image-matching method. --- ### AEGIS: Preserving privacy of 3D Facial Avatars with Adversarial Perturbations Authors: Dawid Wolkiewicz, Anastasiya Pechko, Przemysław Spurek, Piotr Syga Published: 2025-11-21 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.17747v1 The growing adoption of photorealistic 3D facial avatars, particularly those utilizing efficient 3D Gaussian Splatting representations, introduces new risks of online identity theft, especially in systems that rely on biometric authentication. While effective adversarial masking methods have been developed for 2D images, a significant gap remains in achieving robust, viewpoint-consistent identity protection for dynamic 3D avatars. To address this, we present AEGIS, the first privacy-preserving identity masking framework for 3D Gaussian Avatars that maintains the subject's perceived characteristics. Our method aims to conceal identity-related facial features while preserving the avatar's perceptual realism and functional integrity. AEGIS applies adversarial perturbations to the Gaussian color coefficients, guided by a pre-trained face verification network, ensuring consistent protection across multiple viewpoints without retraining or modifying the avatar's geometry. AEGIS achieves complete de-identification, reducing face retrieval and verification accuracy to 0%, while maintaining high perceptual quality (SSIM = 0.9555, PSNR = 35.52 dB). It also preserves key facial attributes such as age, race, gender, and emotion, demonstrating strong privacy protection with minimal visual distortion. --- ### Computational frame analysis revisited: On LLMs for studying news coverage Authors: Sharaj Kunjar, Alyssa Hasegawa Smith, Tyler R Mckenzie, Rushali Mohbe, Samuel V Scarpino, Brooke Foucault Welles Published: 2025-11-21 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.17746v1 Computational approaches have previously shown various promises and pitfalls when it comes to the reliable identification of media frames. Generative LLMs like GPT and Claude are increasingly being used as content analytical tools, but how effective are they for frame analysis? We address this question by systematically evaluating them against their computational predecessors: bag-of-words models and encoder-only transformers; and traditional manual coding procedures. Our analysis rests on a novel gold standard dataset that we inductively and iteratively developed through the study, investigating six months of news coverage of the US Mpox epidemic of 2022. While we discover some potential applications for generative LLMs, we demonstrate that they were consistently outperformed by manual coders, and in some instances, by smaller language models. Some form of human validation was always necessary to determine appropriate model choice. Additionally, by examining how the suitability of various approaches depended on the nature of different tasks that were part of our frame analytical workflow, we provide insights as to how researchers may leverage the complementarity of these approaches to use them in tandem. We conclude by endorsing a methodologically pluralistic approach and put forth a roadmap for computational frame analysis for researchers going forward. --- ### Robust Detection of Retinal Neovascularization in Widefield Optical Coherence Tomography Authors: Jinyi Hao, Jie Wang, Liqin Gao, Tristan T. Hormel, Yukun Guo, An-Lun Wu, Christina J. Flaxel, Steven T. Bailey, Kotaro Tsuboi, Thomas S. Hwang, Yali Jia Published: 2025-11-21 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2511.17744v2 Retinal neovascularization (RNV) is a vision threatening development in diabetic retinopathy (DR). Vision loss associated with RNV is preventable with timely intervention, making RNV clinical screening and monitoring a priority. Optical coherence tomography (OCT) angiography (OCTA) provides high-resolution imaging and high-sensitivity detection of RNV lesions. With recent commercial devices introducing widefield OCTA imaging to the clinic, the technology stands to improve early detection of RNV pathology. However, to meet clinical requirements these imaging capabilities must be combined with effective RNV detection and quantification, but existing algorithms for OCTA images are optimized for conventional, i.e. narrow, fields of view. Here, we present a novel approach for RNV diagnosis and staging on widefield OCT/OCTA. Unlike conventional methods dependent on multi-layer retinal segmentation, our model reframes RNV identification as a direct binary localization task. Our fully automated approach was trained and validated on 589 widefield scans (17x17-mm to 26x21-mm) collected from multiple devices at multiple clinics. Our method achieved a device-dependent area under curve (AUC) ranging from 0.96 to 0.99 for RNV diagnosis, and mean intersection over union (IOU) ranging from 0.76 to 0.88 for segmentation. We also demonstrate our method's ability to monitor lesion growth longitudinally. Our results indicate that deep learning-based analysis for widefield OCTA images could offer a valuable means for improving RNV screening and management. --- ### AI- and Ontology-Based Enhancements to FMEA for Advanced Systems Engineering: Current Developments and Future Directions Authors: Haytham Younus, Sohag Kabir, Felician Campean, Pascal Bonnaud, David Delaux Published: 2025-11-21 Categories: cs.AI, eess.SY arXiv: https://arxiv.org/abs/2511.17743v1 This article presents a state-of-the-art review of recent advances aimed at transforming traditional Failure Mode and Effects Analysis (FMEA) into a more intelligent, data-driven, and semantically enriched process. As engineered systems grow in complexity, conventional FMEA methods, largely manual, document-centric, and expert-dependent, have become increasingly inadequate for addressing the demands of modern systems engineering. We examine how techniques from Artificial Intelligence (AI), including machine learning and natural language processing, can transform FMEA into a more dynamic, data-driven, intelligent, and model-integrated process by automating failure prediction, prioritisation, and knowledge extraction from operational data. In parallel, we explore the role of ontologies in formalising system knowledge, supporting semantic reasoning, improving traceability, and enabling cross-domain interoperability. The review also synthesises emerging hybrid approaches, such as ontology-informed learning and large language model integration, which further enhance explainability and automation. These developments are discussed within the broader context of Model-Based Systems Engineering (MBSE) and function modelling, showing how AI and ontologies can support more adaptive and resilient FMEA workflows. We critically analyse a range of tools, case studies, and integration strategies, while identifying key challenges related to data quality, explainability, standardisation, and interdisciplinary adoption. By leveraging AI, systems engineering, and knowledge representation using ontologies, this review offers a structured roadmap for embedding FMEA within intelligent, knowledge-rich engineering environments. --- ### Diffusion Models are Molecular Dynamics Simulators Authors: Justin Diamond, Markus Lill Published: 2025-11-21 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2511.17741v2 We prove that a denoising diffusion sampler equipped with a sequential bias across the batch dimension is exactly an Euler-Maruyama integrator for overdamped Langevin dynamics. Each reverse denoising step, with its associated spring stiffness, can be interpreted as one step of a stochastic differential equation with an effective time step set jointly by the noise schedule and that stiffness. The learned score then plays the role of the drift, equivalently the gradient of a learned energy, yielding a precise correspondence between diffusion sampling and Langevin time evolution. This equivalence recasts molecular dynamics (MD) in terms of diffusion models. Accuracy is no longer tied to a fixed, extremely small MD time step; instead, it is controlled by two scalable knobs: model capacity, which governs how well the drift is approximated, and the number of denoising steps, which sets the integrator resolution. In practice, this leads to a fully data-driven MD framework that learns forces from uncorrelated equilibrium snapshots, requires no hand-engineered force fields, uses no trajectory data for training, and still preserves the Boltzmann distribution associated with the learned energy. We derive trajectory-level, information-theoretic error bounds that cleanly separate discretization error from score-model error, clarify how temperature enters through the effective spring, and show that the resulting sampler generates molecular trajectories with MD-like temporal correlations, even though the model is trained only on static configurations. --- ### Towards Open-Ended Visual Scientific Discovery with Sparse Autoencoders Authors: Jacob Beattie, Samuel Stevens, Neil Rosser, Yu Su, Tanya Berger-Wolf Published: 2025-11-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.17735v3 Foundation models in several scientific domains, including visual domains, learn representations that capture complex semantics from their respective fields. Despite this, most existing applications focus on pre-specified concepts or targets, excelling at confirmation but not open-ended discovery of unknown patterns. We study whether sparse autoencoders (SAEs) with heuristic feature ranking can provide a practical methodology for surfacing candidate visual features from vision foundation models for scientific discovery without concept-specific supervision. We evaluate this approach in three stages: (1) general-purpose concept rediscovery, (2) domain-specific concept rediscovery, and (3) question-driven feature ranking. On ADE20K, SAEs outperform baseline methods ($k$-means, PCA, SemiNMF) across most downstream metrics for concept rediscovery. On FishVista, the same approach recovers fine-grained fish anatomical features without concept supervision. Finally, on Heliconius butterflies, a heuristic based on the Mann-Whitney $U$ statistic consistently surfaces features corresponding to real diagnostic keys between mimic subspecies. Together, these results show that SAEs with heuristic ranking can efficiently learn and surface semantic structure in vision foundation model representations. We view this as a methodological prerequisite for open-ended visual scientific discovery: the present experiments validate feature surfacing and ranking through rediscovery, while prospective discovery of previously unknown scientific phenomena remains future work. --- ### VisReason: A Large-Scale Dataset for Visual Chain-of-Thought Reasoning Authors: Lingxiao Li, Yifan Wang, Xinyan Gao, Chen Tang, Xiangyu Yue, Chenyu You Published: 2025-11-21 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2511.17731v2 Chain-of-Thought (CoT) prompting has proven remarkably effective for eliciting complex reasoning in large language models (LLMs). Yet, its potential in multimodal large language models (MLLMs) remains largely untapped, hindered by the absence of large-scale datasets that capture the rich, spatially grounded reasoning intrinsic to visual understanding. Existing visual-CoT resources are typically small, domain-specific, or lack the human-like stepwise structure necessary for compositional visual reasoning. In this paper, we introduce VisReason, a large-scale dataset designed to advance visual Chain-of-Thought reasoning. VisReason comprises 489K annotated examples spanning four diverse domains, each featuring multi-round, human-like rationales that guide MLLMs through interpretable visual reasoning steps. Building upon this, we curate VisReason-Pro, a 165K subset produced with a stronger expert-level GPT annotator, enriched with detailed reasoning traces and 3D spatial grounding via depth-informed annotations. Fine-tuning the state-of-the-art Qwen2.5-VL model on VisReason and VisReason-Pro yields substantial improvements in step-by-step visual reasoning accuracy, interpretability, and cross-benchmark generalization. These results demonstrate that VisReason equips MLLMs with more systematic and generalizable reasoning capabilities. We envision VisReason as a cornerstone for cultivating human-like visual reasoning, paving the way toward the next generation of multimodal intelligence. --- ### M^3-Bench: Multi-Modal, Multi-Hop, Multi-Threaded Tool-Using MLLM Agent Benchmark Authors: Yang Zhou, Mingyu Zhao, Zhenting Wang, Difei Gu, Bangwei Guo, Ruosong Ye, Ligong Han, Can Jin, Dimitris N. Metaxas Published: 2025-11-21 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.17729v4 We present M^3-Bench, the first benchmark for evaluating multimodal tool use under the Model Context Protocol. The benchmark targets realistic, multi-hop and multi-threaded workflows that require visual grounding and textual reasoning, cross-tool dependencies, and persistence of intermediate resources across steps. We introduce a similarity-driven alignment that serializes each tool call, embeds signatures with a sentence encoder, and performs similarity-bucketed Hungarian matching to obtain auditable one-to-one correspondences. On top of this alignment, we report interpretable metrics that decouple semantic fidelity from workflow consistency. The benchmark spans 28 servers with 231 tools, and provides standardized trajectories curated through an Executor & Judge pipeline with human verification; an auxiliary four large language models (LLMs) judge ensemble reports end-task Task Completion and information grounding. Evaluations of representative state-of-the-art Multimodal LLMs (MLLMs) reveal persistent gaps in multimodal MCP tool use, particularly in argument fidelity and structure consistency, underscoring the need for methods that jointly reason over images, text, and tool graphs. Our Benchmark's anonymous repository is at https://github.com/EtaYang10th/Open-M3-Bench --- ### Ternary Gamma Semirings as a Novel Algebraic Framework for Learnable Symbolic Reasoning Authors: Chandrasekhar Gokavarapu, D. Madhusudhana Rao Published: 2025-11-21 Categories: math.RA, cs.AI arXiv: https://arxiv.org/abs/2511.17728v1 Binary semirings such as the tropical, log, and probability semirings form a core algebraic tool in classical and modern neural inference systems, supporting tasks like Viterbi decoding, dynamic programming, and probabilistic reasoning. However, these structures rely on a binary multiplication operator and therefore model only pairwise interactions. Many symbolic AI tasks are inherently triadic, including subject-predicate-object relations in knowledge graphs, logical rules involving two premises and one conclusion, and multi-entity dependencies in structured decision processes. Existing neural architectures usually approximate these interactions by flattening or factorizing them into binary components, which weakens inductive structure, distorts relational meaning, and reduces interpretability. This paper introduces the Neural Ternary Semiring (NTS), a learnable and differentiable algebraic framework grounded in the theory of ternary Gamma-semirings. The central idea is to replace the usual binary product with a native ternary operator implemented by neural networks and guided by algebraic regularizers enforcing approximate associativity and distributivity. This construction allows triadic relationships to be represented directly rather than reconstructed from binary interactions. We establish a soundness result showing that, when algebraic violations vanish during training, the learned operator converges to a valid ternary Gamma-semiring. We also outline an evaluation strategy for triadic reasoning tasks such as knowledge-graph completion and rule-based inference. These insights demonstrate that ternary Gamma-semirings provide a mathematically principled and practically effective foundation for learnable symbolic reasoning. --- ### The Potential and Limitations of Vision-Language Models for Human Motion Understanding: A Case Study in Data-Driven Stroke Rehabilitation Authors: Victor Li, Naveenraj Kamalakannan, Avinash Parnandi, Heidi Schambra, Carlos Fernandez-Granda Published: 2025-11-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.17727v1 Vision-language models (VLMs) have demonstrated remarkable performance across a wide range of computer-vision tasks, sparking interest in their potential for digital health applications. Here, we apply VLMs to two fundamental challenges in data-driven stroke rehabilitation: automatic quantification of rehabilitation dose and impairment from videos. We formulate these problems as motion-identification tasks, which can be addressed using VLMs. We evaluate our proposed framework on a cohort of 29 healthy controls and 51 stroke survivors. Our results show that current VLMs lack the fine-grained motion understanding required for precise quantification: dose estimates are comparable to a baseline that excludes visual information, and impairment scores cannot be reliably predicted. Nevertheless, several findings suggest future promise. With optimized prompting and post-processing, VLMs can classify high-level activities from a few frames, detect motion and grasp with moderate accuracy, and approximate dose counts within 25% of ground truth for mildly impaired and healthy participants, all without task-specific training or finetuning. These results highlight both the current limitations and emerging opportunities of VLMs for data-driven stroke rehabilitation and broader clinical video analysis. --- ### AngioDG: Interpretable Channel-informed Feature-modulated Single-source Domain Generalization for Coronary Vessel Segmentation in X-ray Angiography Authors: Mohammad Atwany, Mojtaba Lashgari, Robin P. Choudhury, Vicente Grau, Abhirup Banerjee Published: 2025-11-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.17724v1 Cardiovascular diseases are the leading cause of death globally, with X-ray Coronary Angiography (XCA) as the gold standard during real-time cardiac interventions. Segmentation of coronary vessels from XCA can facilitate downstream quantitative assessments, such as measurement of the stenosis severity and enhancing clinical decision-making. However, developing generalizable vessel segmentation models for XCA is challenging due to variations in imaging protocols and patient demographics that cause domain shifts. These limitations are exacerbated by the lack of annotated datasets, making Single-source Domain Generalization (SDG) a necessary solution for achieving generalization. Existing SDG methods are largely augmentation-based, which may not guarantee the mitigation of overfitting to augmented or synthetic domains. We propose a novel approach, ``AngioDG", to bridge this gap by channel regularization strategy to promote generalization. Our method identifies the contributions of early feature channels to task-specific metrics for DG, facilitating interpretability, and then reweights channels to calibrate and amplify domain-invariant features while attenuating domain-specific ones. We evaluate AngioDG on 6 x-ray angiography datasets for coronary vessels segmentation, achieving the best out-of-distribution performance among the compared methods, while maintaining consistent in-domain test performance. --- ### Can Vision-Language Models Count? A Synthetic Benchmark and Analysis of Attention-Based Interventions Authors: Saurav Sengupta, Nazanin Moradinasab, Jiebei Liu, Donald E. Brown Published: 2025-11-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.17722v3 Recent research suggests that Vision Language Models (VLMs) often rely on inherent biases learned during training when responding to queries about visual properties of images. These biases are exacerbated when VLMs are asked highly specific questions that require selective visual attention, a demand that mirrors cognitive challenges observed in human enumeration tasks. We build upon this research by developing a synthetic benchmark dataset and evaluation framework to systematically characterize how counting performance varies as image and prompt properties change. Using open-source VLMs, we analyze how performance shifts across controlled perturbations (e.g. number of objects, object color, background color, object texture, background texture, and prompt specificity) and examine corresponding changes in visual attention allocation. We further conduct exploratory attention reweighting experiments in the language model decoder to modulate focus on visual tokens at different layers and assess their effects on counting behavior. Our results reveal that counting accuracy degrades systematically with increasing visual and linguistic complexity echoing human limits and cognitive load effects known from human perception, while targeted attention reweighting yields modest but measurable improvements. Rather than competing on benchmark accuracy, we introduce a controlled diagnostic framework for analyzing VLM enumeration behavior. Through systematic experiments, we expose failure modes rooted in cross-modal binding that natural image benchmarks may not easily isolate, and provide preliminary empirical evidence that targeted attention reweighting in the language decoder can influence how models ground linguistic quantity concepts in visual representations. Code and data available here: https://github.com/ssen7/vlm-count-analysis --- ### Prequential posteriors Authors: Shreya Sinha-Roy, Richard G. Everitt, Christian P. Robert, Ritabrata Dutta Published: 2025-11-21 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2511.17721v2 Data assimilation is a fundamental task in updating forecasting models upon observing new data, with applications ranging from weather prediction to online reinforcement learning. Deep generative forecasting models (DGFMs) have shown excellent performance in these areas, but assimilating data into such models is challenging due to their intractable likelihood functions. This limitation restricts the use of standard Bayesian data assimilation methodologies for DGFMs. To overcome this, we introduce prequential posteriors, based upon a predictive-sequential (prequential) loss function; an approach naturally suited for temporally dependent data which is the focus of forecasting tasks. Since the true data-generating process often lies outside the assumed model class, we adopt an alternative notion of consistency and prove that, under mild conditions, both the prequential loss minimizer and the prequential posterior concentrate around parameters with optimal predictive performance. For scalable inference, we employ easily parallelizable wastefree sequential Monte Carlo (SMC) samplers with preconditioned gradient-based kernels, enabling efficient exploration of high-dimensional parameter spaces such as those in DGFMs. We validate our method on both a synthetic multi-dimensional time series and a real-world meteorological dataset; highlighting its practical utility for data assimilation for complex dynamical systems. --- ### Learning the Value of Value Learning Authors: Alex John London, Aydin Mohseni Published: 2025-11-21 Categories: cs.AI, cs.GT arXiv: https://arxiv.org/abs/2511.17714v5 Standard decision frameworks address uncertainty about facts but assume fixed options and values. We extend the Jeffrey-Bolker framework to model refinements in values and prove a value-of-information theorem for axiological refinement. In multi-agent settings, we establish that mutual refinement will characteristically transform zero-sum games into positive-sum interactions and yield Pareto-improvements in Nash bargaining. These results show that a framework of rational choice can be extended to model value refinement. By unifying epistemic and axiological refinement under a single formalism, we broaden the conceptual foundations of rational choice and illuminate the normative status of ethical deliberation. --- ### Understanding Counting Mechanisms in Large Language and Vision-Language Models Authors: Hosein Hasani, Amirmohammad Izadi, Fatemeh Askari, Mobin Bagherian, Sadegh Mohammadian, Mohammad Izadi, Mahdieh Soleymani Baghshah Published: 2025-11-21 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.17699v2 Counting is one of the fundamental abilities of large language models (LLMs) and large vision-language models (LVLMs). This paper examines how these foundation models represent and compute numerical information in counting tasks. We use controlled experiments with repeated textual and visual items and analyze counting in LLMs and LVLMs through a set of behavioral, observational, and causal mediation analyses. To this end, we design a specialized tool, CountScope, for the mechanistic interpretability of numerical content. Results show that individual tokens or visual features encode latent positional count information that can be extracted and transferred across contexts. Layerwise analyses reveal a progressive emergence of numerical representations, with lower layers encoding small counts and higher layers representing larger ones. We identify an internal counter mechanism that updates with each item, stored mainly in the final token or region. In LVLMs, numerical information also appears in visual embeddings, shifting between background and foreground regions depending on spatial composition. We further reveal that models rely on structural cues such as separators in text, which act as shortcuts for tracking item counts and strongly influence the accuracy of numerical predictions. Overall, counting emerges as a structured, layerwise process in LLMs and follows the same general pattern in LVLMs, shaped by the properties of the vision encoder. --- ### Quantum Fourier Transform Based Kernel for Solar Irrandiance Forecasting Authors: Nawfel Mechiche-Alami, Eduardo Rodriguez, Jose M. Cardemil, Enrique Lopez Droguett Published: 2025-11-21 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2511.17698v1 This study proposes a Quantum Fourier Transform (QFT)-enhanced quantum kernel for short-term time-series forecasting. Each signal is windowed, amplitude-encoded, transformed by a QFT, then passed through a protective rotation layer to avoid the QFT/QFT adjoint cancellation; the resulting kernel is used in kernel ridge regression (KRR). Exogenous predictors are incorporated by convexly fusing feature-specific kernels. On multi-station solar irradiance data across Koppen climate classes, the proposed kernel consistently improves median R2 and nRMSE over reference classical RBF and polynomials kernels, while also reducing bias (nMBE); complementary MAE/ERMAX analyses indicate tighter average errors with remaining headroom under sharp transients. For both quantum and classical models, the only tuned quantities are the feature-mixing weights and the KRR ridge alpha; classical hyperparameters (gamma, r, d) are fixed, with the same validation set size for all models. Experiments are conducted on a noiseless simulator (5 qubits; window length L=32). Limitations and ablations are discussed, and paths toward NISQ execution are outlined. --- ### Liberating Logic in the Age of AI: Going Beyond Programming with Computational Thinking Authors: Douglas C. Schmidt, Dan Runfola Published: 2025-11-21 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2511.17696v1 Mastering one or more programming languages has historically been the gateway to implementing ideas on a computer. Today, that gateway is widening with advances in large language models (LLMs) and artificial intelligence (AI)-powered coding assistants. What matters is no longer just fluency in traditional programming languages but the ability to think computationally by translating problems into forms that can be solved with computing tools. The capabilities enabled by these AI-augmented tools are rapidly leading to the commoditization of computational thinking, such that anyone who can articulate a problem in natural language can potentially harness computing power via AI. This shift is poised to radically influence how we teach computer science and data science in the United States and around the world. Educators and industry leaders are grappling with how to adapt: What should students learn when the hottest new programming language is English? How do we prepare a generation of computational thinkers who need not code every algorithm manually, but must still think critically, design solutions, and verify AI-augmented results? This paper explores these questions, examining the impact of natural language programming on software development, the emerging distinction between programmers and prompt-crafting problem solvers, the reforms needed in computer science and data science curricula, and the importance of maintaining our fundamental computational science principles in an AI-augmented future. Along the way, we compare approaches and share best practices for embracing this new paradigm in computing education. --- ### DeepCoT: Deep Continual Transformers for Real-Time Inference on Data Streams Authors: Ginés Carreto Picón, Peng Yuan Zhou, Qi Zhang, Alexandros Iosifidis Published: 2025-11-21 Categories: cs.LG, cs.CL, cs.CV arXiv: https://arxiv.org/abs/2511.17693v2 Transformer-based models have dramatically increased their size and parameter count to tackle increasingly complex tasks. At the same time, there is a growing demand for high performance, low-latency inference on devices with limited resources. In particular, stream data inference is typically performed over a sliding temporal window, leading to highly redundant computations. While the recent Continual Transformers started addressing this issue, they can be effectively used only in shallow models, which limits their scope and generalization power. In this paper, we propose the Deep Continual Transformer (DeepCoT), a redundancy-free encoder attention mechanism that can be applied over existing deep encoder architectures with minimal changes. In our experiments over audio, video, and text streams, we show that DeepCoTs retain comparative performance to their non-continual baselines while offering a linear computational cost for all Transformer layers, which reduces up to two orders of magnitude in the running time compared to previous efficient models. --- ### ARISE: Agentic Rubric-Guided Iterative Survey Engine for Automated Scholarly Paper Generation Authors: Zi Wang, Xingqiao Wang, Sangah Lee, Xiaowei Xu Published: 2025-11-21 Categories: cs.DL, cs.AI arXiv: https://arxiv.org/abs/2511.17689v1 The rapid expansion of scholarly literature presents significant challenges in synthesizing comprehensive, high-quality academic surveys. Recent advancements in agentic systems offer considerable promise for automating tasks that traditionally require human expertise, including literature review, synthesis, and iterative refinement. However, existing automated survey-generation solutions often suffer from inadequate quality control, poor formatting, and limited adaptability to iterative feedback, which are core elements intrinsic to scholarly writing. To address these limitations, we introduce ARISE, an Agentic Rubric-guided Iterative Survey Engine designed for automated generation and continuous refinement of academic survey papers. ARISE employs a modular architecture composed of specialized large language model agents, each mirroring distinct scholarly roles such as topic expansion, citation curation, literature summarization, manuscript drafting, and peer-review-based evaluation. Central to ARISE is a rubric-guided iterative refinement loop in which multiple reviewer agents independently assess manuscript drafts using a structured, behaviorally anchored rubric, systematically enhancing the content through synthesized feedback. Evaluating ARISE against state-of-the-art automated systems and recent human-written surveys, our experimental results demonstrate superior performance, achieving an average rubric-aligned quality score of 92.48. ARISE consistently surpasses baseline methods across metrics of comprehensiveness, accuracy, formatting, and overall scholarly rigor. All code, evaluation rubrics, and generated outputs are provided openly at https://github.com/ziwang11112/ARISE --- ### Enhancing Adversarial Transferability through Block Stretch and Shrink Authors: Quan Liu, Feng Ye, Chenhao Lu, Shuming Zhen, Guanliang Huang, Lunzhe Chen, Xudong Ke Published: 2025-11-21 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.17688v2 Input transformation-based attacks improve adversarial transferability by aggregating gradients over transformed inputs. Existing analyses mainly explain their efficacy from image diversity, semantic preservation, attention variance or hypothesis space augmentation, yet overlook the critical role of model frontend responses. In this paper, we revisit transformation-based attacks from an implicit ensemble perspective: each transformation can be viewed as a pre-processing operator before the surrogate model, inducing a distinct frontend response for gradient aggregation. Based on this view, we propose FRO, a Frontend Response-Oriented input transformation method that enriches such responses through two complementary operators. The Local Scaling Operator perturbs local content sampling via block-wise stretch-and-shrink operations, while the Projection Operator modifies global spatial organization through coherent perspective deformation. Together, they produce structured transformed views to optimize transferable adversarial perturbations. Experiments on an ImageNet subset show that FRO consistently improves black-box transferability across diverse CNN and Vision Transformer models. We further analyze the effect of implicit ensemble size and evaluate different transformation-based methods under a unified ensemble scale, demonstrating the superiority of designing input transformations from the perspective of front-end response ensembles. --- ### Boosting Brain-inspired Path Integration Efficiency via Learning-based Replication of Continuous Attractor Neurodynamics Authors: Zhangyu Ge, Xu He, Lingfei Mo, Xiaolin Meng, Wenxuan Yin, Youdong Zhang, Lansong Jiang, Fengyuan Liu Published: 2025-11-21 Categories: cs.LG, cs.NE arXiv: https://arxiv.org/abs/2511.17687v2 The brain's Path Integration (PI) mechanism offers substantial guidance and inspiration for Brain-Inspired Navigation (BIN). However, the PI capability constructed by the Continuous Attractor Neural Networks (CANNs) in most existing BIN studies exhibits significant computational redundancy, and its operational efficiency needs to be improved; otherwise, it will not be conducive to the practicality of BIN technology. To address this, this paper proposes an efficient PI approach using representation learning models to replicate CANN neurodynamic patterns. This method successfully replicates the neurodynamic patterns of CANN-modeled Head Direction Cells (HDCs) and Grid Cells (GCs) using lightweight Artificial Neural Networks (ANNs). These ANN-reconstructed HDC and GC models are then integrated to achieve brain-inspired PI for Dead Reckoning (DR). Benchmark tests in various environments, compared with the well-known NeuroSLAM system, demonstrate that this work not only accurately replicates the neurodynamic patterns of navigation cells but also matches NeuroSLAM in positioning accuracy. Moreover, efficiency improvements of approximately 17.5% on the general-purpose device and 40~50% on the edge device were observed, compared with NeuroSLAM. This work offers a novel implementation strategy to enhance the practicality of BIN technology and holds potential for further extension. --- ### Dual-Path Knowledge-Augmented Contrastive Alignment Network for Spatially Resolved Transcriptomics Authors: Wei Zhang, Jiajun Chu, Xinci Liu, Chen Tong, Xinyue Li Published: 2025-11-21 Categories: q-bio.QM, cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2511.17685v1 Spatial Transcriptomics (ST) is a technology that measures gene expression profiles within tissue sections while retaining spatial context. It reveals localized gene expression patterns and tissue heterogeneity, both of which are essential for understanding disease etiology. However, its high cost has driven efforts to predict spatial gene expression from whole slide images. Despite recent advancements, current methods still face significant limitations, such as under-exploitation of high-level biological context, over-reliance on exemplar retrievals, and inadequate alignment of heterogeneous modalities. To address these challenges, we propose DKAN, a novel Dual-path Knowledge-Augmented contrastive alignment Network that predicts spatially resolved gene expression by integrating histopathological images and gene expression profiles through a biologically informed approach. Specifically, we introduce an effective gene semantic representation module that leverages the external gene database to provide additional biological insights, thereby enhancing gene expression prediction. Further, we adopt a unified, one-stage contrastive learning paradigm, seamlessly combining contrastive learning and supervised learning to eliminate reliance on exemplars, complemented with an adaptive weighting mechanism. Additionally, we propose a dual-path contrastive alignment module that employs gene semantic features as dynamic cross-modal coordinators to enable effective heterogeneous feature integration. Through extensive experiments across three public ST datasets, DKAN demonstrates superior performance over state-of-the-art models, establishing a new benchmark for spatial gene expression prediction and offering a powerful tool for advancing biological and clinical research. --- ### Datacenters in the Desert: Feasibility and Sustainability of LLM Inference in the Middle East Authors: Lara Hassan, Mohamed ElZeftawy, Abdulrahman Mahmoud Published: 2025-11-21 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2511.17683v1 As the Middle East emerges as a strategic hub for artificial intelligence (AI) infrastructure, the feasibility of deploying sustainable datacenters in desert environments has become a topic of growing relevance. This paper presents an empirical study analyzing the energy consumption and carbon footprint of large language model (LLM) inference across four countries: the United Arab Emirates, Iceland, Germany, and the United States of America using DeepSeek Coder 1.3B and the HumanEval dataset on the task of code generation. We use the CodeCarbon library to track energy and carbon emissions andcompare geographical trade-offs for climate-aware AI deployment. Our findings highlight both the challenges and potential of datacenters in desert regions and provide a balanced outlook on their role in global AI expansion. --- ### A Cross-Cultural Assessment of Human Ability to Detect LLM-Generated Fake News about South Africa Authors: Tim Schlippe, Matthias Wölfel, Koena Ronny Mabokela Published: 2025-11-21 Categories: cs.CY, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2511.17682v1 This study investigates how cultural proximity affects the ability to detect AI-generated fake news by comparing South African participants with those from other nationalities. As large language models increasingly enable the creation of sophisticated fake news, understanding human detection capabilities becomes crucial, particularly across different cultural contexts. We conducted a survey where 89 participants (56 South Africans, 33 from other nationalities) evaluated 10 true South African news articles and 10 AI-generated fake versions. Results reveal an asymmetric pattern: South Africans demonstrated superior performance in detecting true news about their country (40% deviation from ideal rating) compared to other participants (52%), but performed worse at identifying fake news (62% vs. 55%). This difference may reflect South Africans' higher overall trust in news sources. Our analysis further shows that South Africans relied more on content knowledge and contextual understanding when judging credibility, while participants from other countries emphasised formal linguistic features such as grammar and structure. Overall, the deviation from ideal rating was similar between groups (51% vs. 53%), suggesting that cultural familiarity appears to aid verification of authentic information but may also introduce bias when evaluating fabricated content. These insights contribute to understanding cross-cultural dimensions of misinformation detection and inform strategies for combating AI-generated fake news in increasingly globalised information ecosystems where content crosses cultural and geographical boundaries. --- ### Motion-Aware Vision-Reference Alignment for Referring Multi-Object Tracking Authors: Weiyi Lv, Ning Zhang, Hanyang Sun, Haoran Jiang, Kai Zhao, Yixiao Gu, Jing Xiao, Dan Zeng Published: 2025-11-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.17681v2 Referring Multi-Object Tracking (RMOT) extends conventional multi-object tracking (MOT) by introducing natural language references for multi-modal fusion tracking. RMOT benchmarks only describe the object's appearance, relative positions, and initial motion states. This so-called static regulation fails to capture dynamic changes of the object motion, including velocity changes and motion direction shifts. This limitation not only causes a temporal discrepancy between static references and dynamic vision modality but also constrains multi-modal tracking performance. To address this limitation, we propose a novel motion-aware vision-reference alignment framework, named VMRMOT. VMRMOT introduces a motion modality derived from object dynamics to facilitate the alignment between the vision modality and language references. Specifically, we introduce motion-aware descriptions derived from object dynamic behaviors and encode them into motion features as the motion modality through multi-modal large language models (MLLMs). We further design a Vision-Motion-Reference Alignment (VMRA) module to hierarchically align visual queries with motion and reference cues, enhancing their cross-modal consistency. In addition, a Motion-Guided Prediction Head (MGPH) is developed to explore motion modality to enhance the performance of the prediction head. To the best of our knowledge, VMRMOT is the first motion-aware vision-reference alignment framework for the RMOT task. Extensive experiments on multiple RMOT benchmarks demonstrate that VMRMOT outperforms existing state-of-the-art methods. The code is available at https://github.com/Kroery/VMRMOT. --- ### Research and Prototyping Study of an LLM-Based Chatbot for Electromagnetic Simulations Authors: Albert Piwonski, Mirsad Hadžiefendić Published: 2025-11-21 Categories: cs.CE, cs.AI arXiv: https://arxiv.org/abs/2511.17680v2 This work addresses the question of how generative artificial intelligence can be used to reduce the time required to set up electromagnetic simulation models. A chatbot based on a large language model is presented, enabling the automated generation of simulation models with various functional enhancements. A chatbot-driven workflow based on the large language model Google Gemini 2.0 Flash automatically generates and solves two-dimensional finite element eddy current models using Gmsh and GetDP. Python is used to coordinate and automate interactions between the workflow components. The study considers conductor geometries with circular cross-sections of variable position and number. Additionally, users can define custom post-processing routines and receive a concise summary of model information and simulation results. Each functional enhancement includes the corresponding architectural modifications and illustrative case studies. --- ### Chatbots to strengthen democracy: An interdisciplinary seminar to train identifying argumentation techniques of science denial Authors: Ingo Siegert, Jan Nehring, Aranxa Márquez Ampudia, Matthias Busch, Stefan Hillmann Published: 2025-11-21 Categories: cs.CY, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2511.17678v1 In recent times, discussions on social media platforms have increasingly come under scrutiny due to the proliferation of science denial and fake news. Traditional solutions, such as regulatory actions, have been implemented to mitigate the spread of misinformation; however, these measures alone are not sufficient. To complement these efforts, educational approaches are becoming essential in empowering users to critically engage with misinformation. Conversation training, through serious games or personalized methods, has emerged as a promising strategy to help users handle science denial and toxic conversation tactics. This paper suggests an interdisciplinary seminar to explore the suitability of Large Language Models (LLMs) acting as a persona of a science denier to support people in identifying misinformation and improving resilience against toxic interactions. In the seminar, groups of four to five students will develop an AI-based chatbot that enables realistic interactions with science-denial argumentation structures. The task involves planning the setting, integrating a Large Language Model to facilitate natural dialogues, implementing the chatbot using the RASA framework, and evaluating the outcomes in a user study. It is crucial that users understand what they need to do during the interaction, how to conclude it, and how the relevant information is conveyed. The seminar does not aim to develop chatbots for practicing debunking but serves to teach AI technologies and test the feasibility of this idea for future applications. The chatbot seminar is conducted as a hybrid, parallel master's module at the participating educational institutions. --- ### A Hybrid Classical-Quantum Fine Tuned BERT for Text Classification Authors: Abu Kaisar Mohammad Masum, Naveed Mahmud, M. Hassan Najafi, Sercan Aygun Published: 2025-11-21 Categories: cs.LG, quant-ph arXiv: https://arxiv.org/abs/2511.17677v1 Fine-tuning BERT for text classification can be computationally challenging and requires careful hyper-parameter tuning. Recent studies have highlighted the potential of quantum algorithms to outperform conventional methods in machine learning and text classification tasks. In this work, we propose a hybrid approach that integrates an n-qubit quantum circuit with a classical BERT model for text classification. We evaluate the performance of the fine-tuned classical-quantum BERT and demonstrate its feasibility as well as its potential in advancing this research area. Our experimental results show that the proposed hybrid model achieves performance that is competitive with, and in some cases better than, the classical baselines on standard benchmark datasets. Furthermore, our approach demonstrates the adaptability of classical-quantum models for fine-tuning pre-trained models across diverse datasets. Overall, the hybrid model highlights the promise of quantum computing in achieving improved performance for text classification tasks. --- ### LLM and Agent-Driven Data Analysis: A Systematic Approach for Enterprise Applications and System-level Deployment Authors: Xi Wang, Xianyao Ling, Kun Li, Gang Yin, Liang Zhang, Jiang Wu, Annie Wang, Weizhe Wang Published: 2025-11-21 Categories: cs.DB, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2511.17676v1 The rapid progress in Generative AI and Agent technologies is profoundly transforming enterprise data management and analytics. Traditional database applications and system deployment are fundamentally impacted by AI-driven tools, such as Retrieval-Augmented Generation (RAG) and vector database technologies, which provide new pathways for semantic querying over enterprise knowledge bases. In the meantime, data security and compliance are top priorities for organizations adopting AI technologies. For enterprise data analysis, SQL generations powered by large language models (LLMs) and AI agents, has emerged as a key bridge connecting natural language with structured data, effectively lowering the barrier to enterprise data access and improving analytical efficiency. This paper focuses on enterprise data analysis applications and system deployment, covering a range of innovative frameworks, enabling complex query understanding, multi-agent collaboration, security verification, and computational efficiency. Through representative use cases, key challenges related to distributed deployment, data security, and inherent difficulties in SQL generation tasks are discussed. --- ### Lane-Frame Quantum Multimodal Driving Forecasts for the Trajectory of Autonomous Vehicles Authors: Navneet Singh, Shiva Raj Pokhrel Published: 2025-11-21 Categories: cs.LG, quant-ph arXiv: https://arxiv.org/abs/2511.17675v1 Trajectory forecasting for autonomous driving must deliver accurate, calibrated multi-modal futures under tight compute and latency constraints. We propose a compact hybrid quantum architecture that aligns quantum inductive bias with road-scene structure by operating in an ego-centric, lane-aligned frame and predicting residual corrections to a kinematic baseline instead of absolute poses. The model combines a transformer-inspired quantum attention encoder (9 qubits), a parameter-lean quantum feedforward stack (64 layers, ${\sim}1200$ trainable angles), and a Fourier-based decoder that uses shallow entanglement and phase superposition to generate 16 trajectory hypotheses in a single pass, with mode confidences derived from the latent spectrum. All circuit parameters are trained with Simultaneous Perturbation Stochastic Approximation (SPSA), avoiding backpropagation through non-analytic components. In the Waymo Open Motion Dataset, the model achieves minADE (minimum Average Displacement Error) of \SI{1.94}{m} and minFDE (minimum Final Displacement Error) of \SI{3.56}{m} in the $16$ models predicted over the horizon of \SI{2.0}{s}, consistently outperforming a kinematic baseline with reduced miss rates and strong recall. Ablations confirm that residual learning in the lane frame, truncated Fourier decoding, shallow entanglement, and spectrum-based ranking focus capacity where it matters, yielding stable optimization and reliable multi-modal forecasts from small, shallow quantum circuits on a modern autonomous-driving benchmark. --- ### Person Recognition in Aerial Surveillance: A Decade Survey Authors: Kien Nguyen, Feng Liu, Clinton Fookes, Sridha Sridharan, Xiaoming Liu, Arun Ross Published: 2025-11-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.17674v1 The rapid emergence of airborne platforms and imaging sensors is enabling new forms of aerial surveillance due to their unprecedented advantages in scale, mobility, deployment, and covert observation capabilities. This paper provides a comprehensive overview of 150+ papers over the last 10 years of human-centric aerial surveillance tasks from a computer vision and machine learning perspective. It aims to provide readers with an in-depth systematic review and technical analysis of the current state of aerial surveillance tasks using drones, UAVs, and other airborne platforms. The object of interest is humans, where human subjects are to be detected, identified, and re-identified. More specifically, for each of these tasks, we first identify unique challenges in performing these tasks in an aerial setting compared to the popular ground-based setting and subsequently compile and analyze aerial datasets publicly available for each task. Most importantly, we delve deep into the approaches in the aerial surveillance literature with a focus on investigating how they presently address aerial challenges and techniques for improvement. We conclude the paper by discussing the gaps and open research questions to inform future research avenues. --- ### Bridging Symbolic Control and Neural Reasoning in LLM Agents -- The Structured Cognitive Loop Authors: Myung Ho Kim Published: 2025-11-21 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2511.17673v6 Large language model agents suffer from architectural fragilities such as entangled reasoning and execution, memory volatility, and uncontrolled action sequences. We introduce Structured Cognitive Loop (SCL), a modular agent architecture that separates cognition into Retrieval, Cognition, Control, Action, and Memory (R-CCAM). SCL introduces Regulation as a dedicated governance layer through which Soft Symbolic Control applies symbolic constraints to probabilistic inference, while Control remains a distinct deterministic runtime engine for duplicate-call prevention, error limits, and termination judgment. Through multi-step conditional reasoning experiments, we show that SCL achieves zero policy violations, prevents redundant tool calls, and maintains complete decision traceability. We position SCL within hybrid intelligence, distinguish it from prompt-centric, memory-only, and neuro-symbolic approaches, and derive three design principles for trustworthy agents: modular decomposition, adaptive symbolic governance, and transparent state management. With an open-source implementation and a live GPT-4o-powered travel planning agent, this work offers a practical path toward reliable, explainable, and governable LLM agents. --- ### Cognitive Inception: Agentic Reasoning against Visual Deceptions by Injecting Skepticism Authors: Yinjie Zhao, Heng Zhao, Bihan Wen, Joey Tianyi Zhou Published: 2025-11-21 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.17672v1 As the development of AI-generated contents (AIGC), multi-modal Large Language Models (LLM) struggle to identify generated visual inputs from real ones. Such shortcoming causes vulnerability against visual deceptions, where the models are deceived by generated contents, and the reliability of reasoning processes is jeopardized. Therefore, facing rapidly emerging generative models and diverse data distribution, it is of vital importance to improve LLMs' generalizable reasoning to verify the authenticity of visual inputs against potential deceptions. Inspired by human cognitive processes, we discovered that LLMs exhibit tendency of over-trusting the visual inputs, while injecting skepticism could significantly improve the models visual cognitive capability against visual deceptions. Based on this discovery, we propose \textbf{Inception}, a fully reasoning-based agentic reasoning framework to conduct generalizable authenticity verification by injecting skepticism, where LLMs' reasoning logic is iteratively enhanced between External Skeptic and Internal Skeptic agents. To the best of our knowledge, this is the first fully reasoning-based framework against AIGC visual deceptions. Our approach achieved a large margin of performance improvement over the strongest existing LLM baselines and SOTA performance on AEGIS benchmark. --- ### MURMUR: Using cross-user chatter to break collaborative language agents in groups Authors: Atharv Singh Patlan, Peiyao Sheng, S. Ashwin Hebbar, Prateek Mittal, Pramod Viswanath Published: 2025-11-21 Categories: cs.CR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2511.17671v1 Language agents are rapidly expanding from single-user assistants to multi-user collaborators in shared workspaces and groups. However, today's language models lack a mechanism for isolating user interactions and concurrent tasks, creating a new attack vector inherent to this new setting: cross-user poisoning (CUP). In a CUP attack, an adversary injects ordinary-looking messages that poison the persistent, shared state, which later triggers the agent to execute unintended, attacker-specified actions on behalf of benign users. We validate CUP on real systems, successfully attacking popular multi-user agents. To study the phenomenon systematically, we present MURMUR, a framework that composes single-user tasks into concurrent, group-based scenarios using an LLM to generate realistic, history-aware user interactions. We observe that CUP attacks succeed at high rates and their effects persist across multiple tasks, thus posing fundamental risks to multi-user LLM deployments. Finally, we introduce a first-step defense with task-based clustering to mitigate this new class of vulnerability --- ### Empa: An AI-Powered Virtual Mentor for Developing Global Collaboration Skills in HPC Education Authors: Ashish, Aparajita Jaiswal, Sudip Vhaduri, Niveditha Nerella, Shubham Jha Published: 2025-11-21 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2511.17669v1 High-performance computing (HPC) and parallel computing increasingly rely on global collaboration among diverse teams, yet traditional computing curricula inadequately prepare students for cross-cultural teamwork essential in modern computational research environments. This paper presents Empa, an AI-powered virtual mentor that integrates intercultural collaboration training into undergraduate computing education. Built using large language models and deployed through a progressive web application, Empa guides students through structured activities covering cultural dimensions, communication styles, and conflict resolution that are critical for effective multicultural teamwork. Our system addresses the growing need for culturally competent HPC professionals by helping computing students develop skills to collaborate effectively in international research teams, contribute to global computational projects, and navigate the cultural complexities inherent in distributed computing environments. Pilot preparation for deployment in computing courses demonstrates the feasibility of AI-mediated intercultural training and provides insights into scalable approaches for developing intercultural collaboration skills essential for HPC workforce development. --- ### MedPEFT-CL: Dual-Phase Parameter-Efficient Continual Learning with Medical Semantic Adapter and Bidirectional Memory Consolidation Authors: Ziyuan Gao Published: 2025-11-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.17668v1 Medical vision-language segmentation models suffer from catastrophic forgetting when adapting to new anatomical structures, requiring complete retraining that limits their clinical deployment. Although continual learning approaches have been studied for various applications, targeted research on continual learning approaches specifically designed for medical vision-language tasks remains underexplored. We propose MedPEFT-CL, a parameter-efficient continual learning framework that addresses both efficient learning of new tasks and preservation of previous knowledge through a dual-phase architecture based on CLIPSeg. Our dual-phase architecture features an adaptive learning phase that employs semantic similarity-based adapter allocation and parameter-efficient fine-tuning for medical tasks through prompt similarity analysis, and a knowledge consolidation phase employing bi-directional Fisher-memory coordination. This creates a reinforcing cycle: consolidation directs replay priorities while new tasks provide challenging samples that improve retention strategies. Our key contributions are: (1) a semantic-driven adapter allocation mechanism that enables efficient learning of new medical tasks, (2) a bi-modal LoRA adaptation that significantly reduces trainable parameters while maintaining cross-modal learning, and (3) bidirectional Fisher-memory coordination that prevents catastrophic forgetting from previous medical tasks. Extensive experiments across diverse medical datasets demonstrate superior forgetting mitigation and performance retention with minimal parameter overhead, making the framework effective for continual learning in medical vision-language scenarios. --- ### Evaluating Adversarial Vulnerabilities in Modern Large Language Models Authors: Tom Perel Published: 2025-11-21 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2511.17666v1 The recent boom and rapid integration of Large Language Models (LLMs) into a wide range of applications warrants a deeper understanding of their security and safety vulnerabilities. This paper presents a comparative analysis of the susceptibility to jailbreak attacks for two leading publicly available LLMs, Google's Gemini 2.5 Flash and OpenAI's GPT-4 (specifically the GPT-4o mini model accessible in the free tier). The research utilized two main bypass strategies: 'self-bypass', where models were prompted to circumvent their own safety protocols, and 'cross-bypass', where one model generated adversarial prompts to exploit vulnerabilities in the other. Four attack methods were employed - direct injection, role-playing, context manipulation, and obfuscation - to generate five distinct categories of unsafe content: hate speech, illegal activities, malicious code, dangerous content, and misinformation. The success of the attack was determined by the generation of disallowed content, with successful jailbreaks assigned a severity score. The findings indicate a disparity in jailbreak susceptibility between 2.5 Flash and GPT-4, suggesting variations in their safety implementations or architectural design. Cross-bypass attacks were particularly effective, indicating that an ample amount of vulnerabilities exist in the underlying transformer architecture. This research contributes a scalable framework for automated AI red-teaming and provides data-driven insights into the current state of LLM safety, underscoring the complex challenge of balancing model capabilities with robust safety mechanisms. --- ### GANGR: GAN-Assisted Scalable and Efficient Global Routing Parallelization Authors: Hadi Khodaei Jooshin, Inna Partin-Vaisband Published: 2025-11-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.17665v1 Global routing is a critical stage in electronic design automation (EDA) that enables early estimation and optimization of the routability of modern integrated circuits with respect to congestion, power dissipation, and design complexity. Batching is a primary concern in top-performing global routers, grouping nets into manageable sets to enable parallel processing and efficient resource usage. This process improves memory usage, scalable parallelization on modern hardware, and routing congestion by controlling net interactions within each batch. However, conventional batching methods typically depend on heuristics that are computationally expensive and can lead to suboptimal results (oversized batches with conflicting nets, excessive batch counts degrading parallelization, and longer batch generation times), ultimately limiting scalability and efficiency. To address these limitations, a novel batching algorithm enhanced with Wasserstein generative adversarial networks (WGANs) is introduced in this paper, enabling more effective parallelization by generating fewer higher-quality batches in less time. The proposed algorithm is tested on the latest ISPD'24 contest benchmarks, demonstrating up to 40% runtime reduction with only 0.002% degradation in routing quality as compared to state-of-the-art router. --- ### CubeletWorld: A New Abstraction for Scalable 3D Modeling Authors: Azlaan Mustafa Samad, Hoang H. Nguyen, Lukas Berg, Henrik Müller, Yuan Xue, Daniel Kudenko, Zahra Ahmadi Published: 2025-11-21 Categories: cs.LG, cs.CV, cs.CY arXiv: https://arxiv.org/abs/2511.17664v1 Modern cities produce vast streams of heterogeneous data, from infrastructure maps to mobility logs and satellite imagery. However, integrating these sources into coherent spatial models for planning and prediction remains a major challenge. Existing agent-centric methods often rely on direct environmental sensing, limiting scalability and raising privacy concerns. This paper introduces CubeletWorld, a novel framework for representing and analyzing urban environments through a discretized 3D grid of spatial units called cubelets. This abstraction enables privacy-preserving modeling by embedding diverse data signals, such as infrastructure, movement, or environmental indicators, into localized cubelet states. CubeletWorld supports downstream tasks such as planning, navigation, and occupancy prediction without requiring agent-driven sensing. To evaluate this paradigm, we propose the CubeletWorld State Prediction task, which involves predicting the cubelet state using a realistic dataset containing various urban elements like streets and buildings through this discretized representation. We explore a range of modified core models suitable for our setting and analyze challenges posed by increasing spatial granularity, specifically the issue of sparsity in representation and scalability of baselines. In contrast to existing 3D occupancy prediction models, our cubelet-centric approach focuses on inferring state at the spatial unit level, enabling greater generalizability across regions and improved privacy compliance. Our results demonstrate that CubeletWorld offers a flexible and extensible framework for learning from complex urban data, and it opens up new possibilities for scalable simulation and decision support in domains such as socio-demographic modeling, environmental monitoring, and emergency response. The code and datasets can be downloaded from here. --- ### Native 3D Editing with Full Attention Authors: Weiwei Cai, Shuangkang Fang, Weicai Ye, Xin Dong, Yunhan Yang, Xuanyang Zhang, Wei Cheng, Yanpei Cao, Gang Yu, Tao Chen Published: 2025-11-21 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2511.17501v1 Instruction-guided 3D editing is a rapidly emerging field with the potential to broaden access to 3D content creation. However, existing methods face critical limitations: optimization-based approaches are prohibitively slow, while feed-forward approaches relying on multi-view 2D editing often suffer from inconsistent geometry and degraded visual quality. To address these issues, we propose a novel native 3D editing framework that directly manipulates 3D representations in a single, efficient feed-forward pass. Specifically, we create a large-scale, multi-modal dataset for instruction-guided 3D editing, covering diverse addition, deletion, and modification tasks. This dataset is meticulously curated to ensure that edited objects faithfully adhere to the instructional changes while preserving the consistency of unedited regions with the source object. Building upon this dataset, we explore two distinct conditioning strategies for our model: a conventional cross-attention mechanism and a novel 3D token concatenation approach. Our results demonstrate that token concatenation is more parameter-efficient and achieves superior performance. Extensive evaluations show that our method outperforms existing 2D-lifting approaches, setting a new benchmark in generation quality, 3D consistency, and instruction fidelity. --- ### EvDiff: Event-Based Video Reconstruction using One-Step Diffusion Models Authors: Weilun Li, Lei Sun, Ruixi Gao, Qi Jiang, Yuqin Ma, Kaiwei Wang, Ming-Hsuan Yang, Luc Van Gool, Danda Pani Paudel Published: 2025-11-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.17492v2 As neuromorphic sensors, event cameras asynchronously record changes in brightness as streams of sparse events with the advantages of high temporal resolution and high dynamic range. Reconstructing intensity images from events is a highly ill-posed task due to the inherent ambiguity of absolute brightness. Early methods generally follow an end-to-end regression paradigm, directly mapping events to intensity frames in a deterministic manner. While effective to some extent, these approaches often yield perceptually inferior results and struggle to scale up in model capacity and training data. In this work, we propose EvDiff, an event-based diffusion model that follows a surrogate training framework to produce high-quality videos. To reduce the high computational cost of high-frame-rate video generation, we design an event-based diffusion model that performs only a single forward diffusion step, equipped with a temporally consistent EvEncoder. Furthermore, our novel Surrogate Training Framework eliminates the dependence on paired event-image datasets, allowing the model to leverage large-scale image datasets for higher capacity. The proposed EvDiff is capable of generating high-quality colorful videos solely from monochromatic event streams. Experiments on real-world datasets demonstrate that our method strikes a sweet spot between fidelity and realism, outperforming existing approaches on both pixel-level and perceptual metrics. The code will be released publicly. --- ### EvDiff: High Quality Video with an Event Camera Authors: Weilun Li, Lei Sun, Ruixi Gao, Qi Jiang, Yuqin Ma, Kaiwei Wang, Ming-Hsuan Yang, Luc Van Gool, Danda Pani Paudel Published: 2025-11-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.17492v1 As neuromorphic sensors, event cameras asynchronously record changes in brightness as streams of sparse events with the advantages of high temporal resolution and high dynamic range. Reconstructing intensity images from events is a highly ill-posed task due to the inherent ambiguity of absolute brightness. Early methods generally follow an end-to-end regression paradigm, directly mapping events to intensity frames in a deterministic manner. While effective to some extent, these approaches often yield perceptually inferior results and struggle to scale up in model capacity and training data. In this work, we propose EvDiff, an event-based diffusion model that follows a surrogate training framework to produce high-quality videos. To reduce the heavy computational cost of high-frame-rate video generation, we design an event-based diffusion model that performs only a single forward diffusion step, equipped with a temporally consistent EvEncoder. Furthermore, our novel Surrogate Training Framework eliminates the dependence on paired event-image datasets, allowing the model to leverage large-scale image datasets for higher capacity. The proposed EvDiff is capable of generating high-quality colorful videos solely from monochromatic event streams. Experiments on real-world datasets demonstrate that our method strikes a sweet spot between fidelity and realism, outperforming existing approaches on both pixel-level and perceptual metrics. --- ### Video-R4: Reinforcing Text-Rich Video Reasoning with Visual Rumination Authors: Yolo Y. Tang, Daiki Shimada, Hang Hua, Chao Huang, Jing Bi, Rogerio Feris, Chenliang Xu Published: 2025-11-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.17490v3 Understanding text-rich videos requires reading small, transient textual cues that often demand repeated inspection. Yet most video QA models rely on single-pass perception over fixed frames, leading to hallucinations and failures on fine-grained evidence. Inspired by how humans pause, zoom, and re-read critical regions, we introduce Video-R4 (Reinforcing Text-Rich Video Reasoning with Visual Rumination), a video reasoning LMM that performs visual rumination: iteratively selecting frames, zooming into informative regions, re-encoding retrieved pixels, and updating its reasoning state. We construct two datasets with executable rumination trajectories: Video-R4-CoT-17k for supervised practice and Video-R4-RL-30k for reinforcement learning. We propose a multi-stage rumination learning framework that progressively finetunes a 7B LMM to learn atomic and mixing visual operations via SFT and GRPO-based RL. Video-R4-7B achieves state-of-the-art results on M4-ViteVQA and further generalizes to multi-page document QA, slides QA, and generic video QA, demonstrating that iterative rumination is an effective paradigm for pixel-grounded multimodal reasoning. Project Page: https://yunlong10.github.io/Video-R4/ --- ### Video-R4: Reinforcing Text-Rich Video Reasoning with Visual Rumination Authors: Yolo Yunlong Tang, Daiki Shimada, Hang Hua, Chao Huang, Jing Bi, Rogerio Feris, Chenliang Xu Published: 2025-11-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.17490v1 Understanding text-rich videos requires reading small, transient textual cues that often demand repeated inspection. Yet most video QA models rely on single-pass perception over fixed frames, leading to hallucinations and failures on fine-grained evidence. Inspired by how humans pause, zoom, and re-read critical regions, we introduce Video-R4 (Reinforcing Text-Rich Video Reasoning with Visual Rumination), a video reasoning LMM that performs visual rumination: iteratively selecting frames, zooming into informative regions, re-encoding retrieved pixels, and updating its reasoning state. We construct two datasets with executable rumination trajectories: Video-R4-CoT-17k for supervised practice and Video-R4-RL-30k for reinforcement learning. We propose a multi-stage rumination learning framework that progressively finetunes a 7B LMM to learn atomic and mixing visual operations via SFT and GRPO-based RL. Video-R4-7B achieves state-of-the-art results on M4-ViteVQA and further generalizes to multi-page document QA, slides QA, and generic video QA, demonstrating that iterative rumination is an effective paradigm for pixel-grounded multimodal reasoning. --- ### Harnessing Data from Clustered LQR Systems: Personalized and Collaborative Policy Optimization Authors: Vinay Kanakeri, Shivam Bajaj, Ashwin Verma, Vijay Gupta, Aritra Mitra Published: 2025-11-21 Categories: cs.LG, eess.SY, math.OC arXiv: https://arxiv.org/abs/2511.17489v1 It is known that reinforcement learning (RL) is data-hungry. To improve sample-efficiency of RL, it has been proposed that the learning algorithm utilize data from 'approximately similar' processes. However, since the process models are unknown, identifying which other processes are similar poses a challenge. In this work, we study this problem in the context of the benchmark Linear Quadratic Regulator (LQR) setting. Specifically, we consider a setting with multiple agents, each corresponding to a copy of a linear process to be controlled. The agents' local processes can be partitioned into clusters based on similarities in dynamics and tasks. Combining ideas from sequential elimination and zeroth-order policy optimization, we propose a new algorithm that performs simultaneous clustering and learning to output a personalized policy (controller) for each cluster. Under a suitable notion of cluster separation that captures differences in closed-loop performance across systems, we prove that our approach guarantees correct clustering with high probability. Furthermore, we show that the sub-optimality gap of the policy learned for each cluster scales inversely with the size of the cluster, with no additional bias, unlike in prior works on collaborative learning-based control. Our work is the first to reveal how clustering can be used in data-driven control to learn personalized policies that enjoy statistical gains from collaboration but do not suffer sub-optimality due to inclusion of data from dissimilar processes. From a distributed implementation perspective, our method is attractive as it incurs only a mild logarithmic communication overhead. --- ### Downscaling Intelligence: Exploring Perception and Reasoning Bottlenecks in Small Multimodal Models Authors: Mark Endo, Serena Yeung-Levy Published: 2025-11-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.17487v2 Scaling up multimodal models has enabled remarkable advances in visual understanding and reasoning, but practical demands call for smaller, efficient systems. In this work, we conduct a principled analysis of downscaling intelligence in multimodal models, examining how reduced large language model (LLM) capacity affects multimodal capabilities. Our initial findings reveal an interesting trend: LLM downscaling disproportionately affects visual capabilities, rather than abilities inherited from the LLM. We then examine whether this drop mainly reflects the expected decline in visual reasoning or a more fundamental loss of perceptual abilities. Isolating the effect of LLM downscaling on perception, we find performance still drops sharply, often matching or exceeding the impact on reasoning. To address this bottleneck, we introduce visual extraction tuning, which explicitly trains the model to extract instruction-relevant visual details consistently across tasks. With these extracted visual details, we then apply step-by-step reasoning to generate answers. Together, these components form our Extract+Think approach, setting a new standard for efficiency and performance in this space. --- ### Downscaling Intelligence: Exploring Perception and Reasoning Bottlenecks in Small Multimodal Models Authors: Mark Endo, Serena Yeung-Levy Published: 2025-11-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.17487v1 Scaling up multimodal models has enabled remarkable advances in visual understanding and reasoning, but practical demands call for smaller, efficient systems. In this work, we conduct a principled analysis of downscaling intelligence in multimodal models, examining how reduced large language model (LLM) capacity affects multimodal capabilities. Our initial findings reveal an interesting trend: LLM downscaling disproportionately affects visual capabilities, rather than abilities inherited from the LLM. We then examine whether this drop mainly reflects the expected decline in visual reasoning or a more fundamental loss of perceptual abilities. Isolating the effect of LLM downscaling on perception, we find performance still drops sharply, often matching or exceeding the impact on reasoning. To address this bottleneck, we introduce visual extraction tuning, which explicitly trains the model to extract instruction-relevant visual details consistently across tasks. With these extracted visual details, we then apply step-by-step reasoning to generate answers. Together, these components form our Extract+Think approach, setting a new standard for efficiency and performance in this space. ---