# Research Papers — 2025-11 · bundle page 56 of 197 > Full-text markdown of papers #2751–2800 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/56 [← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/55.md) [Next bundle →](https://aipod.dev/papers/archive/2025-11/page/57.md) ### DELTA: Language Diffusion-based EEG-to-Text Architecture Authors: Mingyu Jeon, Hyobin Kim Published: 2025-11-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.21746v1 Electroencephalogram (EEG)-to-text remains challenging due to high-dimensional noise, subject variability, and error accumulation in autoregressive decoding. We introduce DELTA, which pairs a Residual Vector Quantization (RVQ) EEG tokenizer with a masked language diffusion model (LLaDA). RVQ discretizes continuous EEG into multi-layer tokens to reduce noise and individual differences, while LLaDA reconstructs sentences via non-sequential denoising. On ZuCo, DELTA improves semantic alignment by up to 5.37 points over autoregressive baselines, achieving BLEU-1 21.9 and ROUGE-1 F 17.2 under word-level conditions. These results enable reliable text generation from small EEG-text datasets and point toward scalable multimodal EEG-language models. --- ### A Lightweight Approach to Detection of AI-Generated Texts Using Stylometric Features Authors: Sergey K. Aityan, William Claster, Karthik Sai Emani, Sohni Rais, Thy Tran Published: 2025-11-22 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.21744v2 A growing number of AI-generated texts raise serious concerns. Most existing approaches to AI-generated text detection rely on fine-tuning large transformer models or building ensembles, which are computationally expensive and often provide limited generalization across domains. Existing lightweight alternatives achieved significantly lower accuracy on large datasets. We introduce NEULIF, a lightweight approach that achieves best performance in the lightweight detector class, that does not require extensive computational power and provides high detection accuracy. In our approach, a text is first decomposed into stylometric and readability features which are then used for classification by a compact Convolutional Neural Network (CNN) or Random Forest (RF). Evaluated and tested on the Kaggle AI vs. Human corpus, our models achieve 97% accuracy (~ 0.95 F1) for CNN and 95% accuracy (~ 0.94 F1) for the Random Forest, demonstrating high precision and recall, with ROC-AUC scores of 99.5% and 95%, respectively. The CNN (~ 25 MB) and Random Forest (~ 10.6 MB) models are orders of magnitude smaller than transformer-based ensembles and can be run efficiently on standard CPU devices, without sacrificing accuracy. This study also highlights the potential of such models for broader applications across languages, domains, and streaming contexts, showing that simplicity, when guided by structural insights, can rival complexity in AI-generated content detection. --- ### Scaling Competence, Shrinking Reasoning: Cognitive Signatures in Language Model Learning Authors: Mukul Singh, Ananya Singha, Arjun Radhakrishna, Sumit Gulwani Published: 2025-11-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.21743v1 We analyze reasoning in language models during task-specific fine-tuning and draws parallel between reasoning tokens--intermediate steps generated while solving problem and the human working memory. Drawing from cognitive science, we align training dynamics with the Four Stages of Competence: models initially produce incorrect outputs without reasoning, then begin reasoning (but still fail), eventually reason effectively, and finally solve tasks without explicit reasoning. We find that reasoning token length expands as performance improves, peaks at the stage of conscious competence, then declines as the model internalizes the task. Notably, after training, models retain performance even when reasoning is removed--suggesting it scaffolded learning but is no longer needed. This progression offers actionable insights: reasoning token dynamics can serve as a signal for diagnosing training stage, identifying convergence, and guiding early stopping. We propose metrics to track this trajectory and argue that reasoning behavior is valuable for understanding and optimizing reasoning model training. --- ### The Human Brain as a Combinatorial Complex Authors: Valentina Sánchez, Çiçek Güven, Koen Haak, Theodore Papamarkou, Gonzalo Nápoles, Marie Šafář Postma Published: 2025-11-22 Categories: q-bio.NC, cs.LG arXiv: https://arxiv.org/abs/2511.20692v2 We propose a framework for constructing combinatorial complexes (CCs) from fMRI time series data that captures both pairwise and higher-order neural interactions through information-theoretic measures, bridging topological deep learning and network neuroscience. Current graph-based representations of brain networks systematically miss the higher-order dependencies that characterize neural complexity, where information processing often involves synergistic interactions that cannot be decomposed into pairwise relationships. Unlike topological lifting approaches that map relational structures into higher-order domains, our method directly constructs CCs from statistical dependencies in the data. Our CCs generalize graphs by incorporating higher-order cells that represent collective dependencies among brain regions, naturally accommodating the multi-scale, hierarchical nature of neural processing. The framework constructs data-driven combinatorial complexes using O-information and S-information measures computed from fMRI signals, preserving both pairwise connections and higher-order cells (e.g., triplets, quadruplets) based on synergistic dependencies. Using NetSim simulations as a controlled proof-of-concept dataset, we demonstrate our CC construction pipeline and show how both pairwise and higher-order dependencies in neural time series can be quantified and represented within a unified structure. This work provides a framework for brain network representation that preserves fundamental higher-order structure invisible to traditional graph methods, and enables the application of topological deep learning (TDL) architectures to neural data. --- ### LLMs-Powered Accurate Extraction, Querying and Intelligent Management of Literature derived 2D Materials Data Authors: Lijun Shang, Yadong Yu, Wenqiang Kang, Jian Zhou, Dongyue Gao, Pan Xiang, Zhe Liu, Mengyan Dai, Zhonglu Guo, Zhimei Sun Published: 2025-11-22 Categories: cs.CL, cond-mat.mtrl-sci, cs.DB arXiv: https://arxiv.org/abs/2511.20691v1 Two-dimensional (2D) materials have showed widespread applications in energy storage and conversion owning to their unique physicochemical, and electronic properties. Most of the valuable information for the materials, such as their properties and preparation methods, is included in the published research papers. However, due to the dispersion of synthe --- ### Quality analysis and evaluation prediction of RAG retrieval based on machine learning algorithms Authors: Ruoxin Zhang, Zhizhao Wen, Chao Wang, Chenchen Tang, Puyang Xu, Yifan Jiang Published: 2025-11-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.19481v1 With the rapid evolution of large language models, retrieval enhanced generation technology has been widely used due to its ability to integrate external knowledge to improve output accuracy. However, the performance of the system is highly dependent on the quality of the retrieval module. If the retrieval results have low relevance to user needs or contain noisy information, it will directly lead to distortion of the generated content. In response to the performance bottleneck of existing models in processing tabular features, this paper proposes an XGBoost machine learning regression model based on feature engineering and particle swarm optimization. Correlation analysis shows that answer_quality is positively correlated with doc_delevance by 0.66, indicating that document relevance has a significant positive effect on answer quality, and improving document relevance may enhance answer quality; The strong negative correlations between semantic similarity, redundancy, and diversity were -0.89 and -0.88, respectively, indicating a tradeoff between semantic similarity, redundancy, and diversity. In other words, as the former two increased, diversity significantly decreased. The experimental results comparing decision trees, AdaBoost, etc. show that the VMD PSO BiLSTM model is superior in all evaluation indicators, with significantly lower MSE, RMSE, MAE, and MAPE compared to the comparison model. The R2 value is higher, indicating that its prediction accuracy, stability, and data interpretation ability are more outstanding. This achievement provides an effective path for optimizing the retrieval quality and improving the generation effect of RAG system, and has important value in promoting the implementation and application of related technologies. --- ### Exploiting the Experts: Unauthorized Compression in MoE-LLMs Authors: Pinaki Prasad Guha Neogi, Ahmad Mohammadshirazi, Dheeraj Kulshrestha, Rajiv Ramnath Published: 2025-11-22 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.19480v1 Mixture-of-Experts (MoE) architectures are increasingly adopted in large language models (LLMs) for their scalability and efficiency. However, their modular structure introduces a unique vulnerability: adversaries can attempt to compress or repurpose models by pruning experts and cheaply fine-tuning the remainder, effectively bypassing licensing and security constraints. In this paper, we systematically study the prunability of MoE-LLMs under task-specific usage. We first develop an expert attribution framework that identifies the subset of experts most responsible for a given task, then evaluate the performance trade-offs of pruning and re-aligning these experts using active learning-driven fine-tuning. Our findings reveal a critical knowledge loss--recovery trade-off: while certain experts can be isolated to retain task accuracy, significant degradation occurs without targeted re-alignment. Based on this analysis, we propose defense strategies that aim to make MoE models harder to compress and fine-tune without authorization, including entangled expert training and selective fine-tuning protocols that resist unauthorized adaptation. By positioning expert pruning as both a threat vector and a defense target, this work highlights the dual-use nature of MoE modularity and provides the first systematic evaluation framework for secure specialization of MoE-LLMs. --- ### Federated Learning Framework for Scalable AI in Heterogeneous HPC and Cloud Environments Authors: Sangam Ghimire, Paribartan Timalsina, Nirjal Bhurtel, Bishal Neupane, Bigyan Byanju Shrestha, Subarna Bhattarai, Prajwal Gaire, Jessica Thapa, Sudan Jha Published: 2025-11-22 Categories: cs.DC, cs.LG arXiv: https://arxiv.org/abs/2511.19479v1 As the demand grows for scalable and privacy-aware AI systems, Federated Learning (FL) has emerged as a promising solution, allowing decentralized model training without moving raw data. At the same time, the combination of high-performance computing (HPC) and cloud infrastructure offers vast computing power but introduces new complexities, especially when dealing with heterogeneous hardware, communication limits, and non-uniform data. In this work, we present a federated learning framework built to run efficiently across mixed HPC and cloud environments. Our system addresses key challenges such as system heterogeneity, communication overhead, and resource scheduling, while maintaining model accuracy and data privacy. Through experiments on a hybrid testbed, we demonstrate strong performance in terms of scalability, fault tolerance, and convergence, even under non-Independent and Identically Distributed (non-IID) data distributions and varied hardware. These results highlight the potential of federated learning as a practical approach to building scalable Artificial Intelligence (AI) systems in modern, distributed computing settings. --- ### A Multi-Stage Deep Learning Framework with PKCP-MixUp Augmentation for Pediatric Liver Tumor Diagnosis Using Multi-Phase Contrast-Enhanced CT Authors: Wanqi Wang, Chun Yang, Jianbo Shao, Yaokai Zhang, Xuehua Peng, Jin Sun, Chao Xiong, Long Lu, Lianting Hu Published: 2025-11-22 Categories: eess.IV, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2511.19478v3 Pediatric liver tumors are one of the most common solid tumors in pediatrics, with differentiation of benign or malignant status and pathological classification critical for clinical treatment. While pathological examination is the gold standard, the invasive biopsy has notable limitations: the highly vascular pediatric liver and fragile tumor tissue raise complication risks such as bleeding; additionally, young children with poor compliance require anesthesia for biopsy, increasing medical costs or psychological trauma. Although many efforts have been made to utilize AI in clinical settings, most researchers have overlooked its importance in pediatric liver tumors. To establish a non-invasive examination procedure, we developed a multi-stage deep learning (DL) framework for automated pediatric liver tumor diagnosis using multi-phase contrast-enhanced CT. Two retrospective and prospective cohorts were enrolled. We established a novel PKCP-MixUp data augmentation method to address data scarcity and class imbalance. We also trained a tumor detection model to extract ROIs, and then set a two-stage diagnosis pipeline with three backbones with ROI-masked images. Our tumor detection model has achieved high performance (mAP=0.871), and the first stage classification model between benign and malignant tumors reached an excellent performance (AUC=0.989). Final diagnosis models also exhibited robustness, including benign subtype classification (AUC=0.915) and malignant subtype classification (AUC=0.979). We also conducted multi-level comparative analyses, such as ablation studies on data and training pipelines, as well as Shapley-Value and CAM interpretability analyses. This framework fills the pediatric-specific DL diagnostic gap, provides actionable insights for CT phase selection and model design, and paves the way for precise, accessible pediatric liver tumor diagnosis. --- ### FAST: Topology-Aware Frequency-Domain Distribution Matching for Coreset Selection Authors: Jin Cui, Boran Zhao, Jiajun Xu, Jiaqi Guo, Shuo Guan, Pengju Ren Published: 2025-11-22 Categories: stat.ML, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.19476v3 Coreset selection compresses large datasets into compact, representative subsets, reducing the energy and computational burden of training deep neural networks. Existing methods are either: (i) DNN-based, which are tied to model-specific parameters and introduce architectural bias; or (ii) DNN-free, which rely on heuristics lacking theoretical guarantees. Neither approach explicitly constrains distributional equivalence, largely because continuous distribution matching is considered inapplicable to discrete sampling. Moreover, prevalent metrics (e.g., MSE, KL, CE, MMD) cannot accurately capture higher-order moment discrepancies, leading to suboptimal coresets. In this work, we propose FAST, the first DNN-free distribution-matching coreset selection framework that formulates the coreset selection task as a graph-constrained optimization problem grounded in spectral graph theory and employs the Characteristic Function Distance (CFD) to capture full distributional information in the frequency domain. We further discover that naive CFD suffers from a "vanishing phase gradient" issue in medium and high-frequency regions; to address this, we introduce an Attenuated Phase-Decoupled CFD. Furthermore, for better convergence, we design a Progressive Discrepancy-Aware Sampling strategy that progressively schedules frequency selection from low to high, preserving global structure before refining local details and enabling accurate matching with fewer frequencies while avoiding overfitting. Extensive experiments demonstrate that FAST significantly outperforms state-of-the-art coreset selection methods across all evaluated benchmarks, achieving an average accuracy gain of 9.12%. Compared to other baseline coreset methods, it reduces power consumption by 96.57% and achieves a 2.2x average speedup, underscoring its high performance and energy efficiency. --- ### Tracking and Segmenting Anything in Any Modality Authors: Tianlu Zhang, Qiang Zhang, Guiguang Ding, Jungong Han Published: 2025-11-22 Categories: cs.CV, cs.AI, cs.MM arXiv: https://arxiv.org/abs/2511.19475v1 Tracking and segmentation play essential roles in video understanding, providing basic positional information and temporal association of objects within video sequences. Despite their shared objective, existing approaches often tackle these tasks using specialized architectures or modality-specific parameters, limiting their generalization and scalability. Recent efforts have attempted to unify multiple tracking and segmentation subtasks from the perspectives of any modality input or multi-task inference. However, these approaches tend to overlook two critical challenges: the distributional gap across different modalities and the feature representation gap across tasks. These issues hinder effective cross-task and cross-modal knowledge sharing, ultimately constraining the development of a true generalist model. To address these limitations, we propose a universal tracking and segmentation framework named SATA, which unifies a broad spectrum of tracking and segmentation subtasks with any modality input. Specifically, a Decoupled Mixture-of-Expert (DeMoE) mechanism is presented to decouple the unified representation learning task into the modeling process of cross-modal shared knowledge and specific information, thus enabling the model to maintain flexibility while enhancing generalization. Additionally, we introduce a Task-aware Multi-object Tracking (TaMOT) pipeline to unify all the task outputs as a unified set of instances with calibrated ID information, thereby alleviating the degradation of task-specific knowledge during multi-task training. SATA demonstrates superior performance on 18 challenging tracking and segmentation benchmarks, offering a novel perspective for more generalizable video understanding. --- ### Pistachio: Towards Synthetic, Balanced, and Long-Form Video Anomaly Benchmarks Authors: Jie Li, Hongyi Cai, Mingkang Dong, Muxin Pu, Shan You, Fei Wang, Tao Huang Published: 2025-11-22 Categories: cs.CV, cs.AI, cs.MM arXiv: https://arxiv.org/abs/2511.19474v7 Automatically detecting abnormal events in videos is crucial for modern autonomous systems, yet existing Video Anomaly Detection (VAD) benchmarks lack the scene diversity, balanced anomaly coverage, and temporal complexity needed to reliably assess real-world performance. Meanwhile, the community is increasingly moving toward Video Anomaly Understanding (VAU), which requires deeper semantic and causal reasoning but remains difficult to benchmark due to the heavy manual annotation effort it demands. In this paper, we introduce Pistachio, a new VAD/VAU benchmark constructed entirely through a controlled, generation-based pipeline. By leveraging recent advances in video generation models, Pistachio provides precise control over scenes, anomaly types, and temporal narratives, effectively eliminating the biases and limitations of Internet-collected datasets. Our pipeline integrates scene-conditioned anomaly assignment, multi-step storyline generation, and a temporally consistent long-form synthesis strategy that produces coherent 41-second videos with minimal human intervention. Extensive experiments demonstrate the scale, diversity, and complexity of Pistachio, revealing new challenges for existing methods and motivating future research on dynamic and multi-event anomaly understanding. --- ### WavefrontDiffusion: Dynamic Decoding Schedule for Improved Reasoning Authors: Haojin Yang, Rui Hu, Zequn Sun, Rui Zhou, Yujun Cai, Yiwei Wang Published: 2025-11-22 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.19473v3 Diffusion Language Models (DLMs) have shown strong potential for text generation and are becoming a competitive alternative to autoregressive models. The denoising strategy plays an important role in determining the quality of their outputs. Mainstream denoising strategies include Standard Diffusion and BlockDiffusion. Standard Diffusion performs global denoising without restricting the update range, often finalizing incomplete context and causing premature end-of-sequence predictions. BlockDiffusion updates fixed-size blocks in a preset order, but its rigid structure can break apart coherent semantic units and disrupt reasoning. We present WavefrontDiffusion, a dynamic decoding approach that expands a wavefront of active tokens outward from finalized positions. This adaptive process follows the natural flow of semantic structure while keeping computational cost equal to block-based methods. Across four benchmarks in reasoning and code generation, WavefrontDiffusion achieves state-of-the-art performance while producing outputs with higher semantic fidelity, showing the value of adaptive scheduling for more coherent and efficient generation. --- ### PrefixGPT: Prefix Adder Optimization by a Generative Pre-trained Transformer Authors: Ruogu Ding, Xin Ning, Ulf Schlichtmann, Weikang Qian Published: 2025-11-22 Categories: cs.LG, cs.AI, cs.AR arXiv: https://arxiv.org/abs/2511.19472v2 Prefix adders are widely used in compute-intensive applications for their high speed. However, designing optimized prefix adders is challenging due to strict design rules and an exponentially large design space. We introduce PrefixGPT, a generative pre-trained Transformer (GPT) that directly generates optimized prefix adders from scratch. Our approach represents an adder's topology as a two-dimensional coordinate sequence and applies a legality mask during generation, ensuring every design is valid by construction. PrefixGPT features a customized decoder-only Transformer architecture. The model is first pre-trained on a corpus of randomly synthesized valid prefix adders to learn design rules and then fine-tuned to navigate the design space for optimized design quality. Compared with existing works, PrefixGPT not only finds a new optimal design with a 7.7% improved area-delay product (ADP) but exhibits superior exploration quality, lowering the average ADP by up to 79.1%. This demonstrates the potential of GPT-style models to first master complex hardware design principles and then apply them for more efficient design optimization. --- ### Not Quite Anything: Overcoming SAMs Limitations for 3D Medical Imaging Authors: Keith Moore Published: 2025-11-22 Categories: eess.IV, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2511.19471v1 Foundation segmentation models such as SAM and SAM-2 perform well on natural images but struggle with brain MRIs where structures like the caudate and thalamus lack sharp boundaries and have low contrast. Rather than fine tune these models (for example MedSAM), we propose a compositional alternative where the foundation model output is treated as an additional input channel and passed alongside the MRI to highlight regions of interest. We generate SAM-2 prompts by using a lightweight 3D U-Net that was previously trained on MRI segmentation. The U-Net may have been trained on a different dataset, so its guesses are often imprecise but usually in the correct region. The edges of the resulting foundation model guesses are smoothed to improve alignment with the MRI. We also test prompt free segmentation using DINO attention maps in the same framework. This has-a architecture avoids modifying foundation weights and adapts to domain shift without retraining the foundation model. It reaches about 96 percent volume accuracy on basal ganglia segmentation, which is sufficient for our study of longitudinal volume change. The approach is fast, label efficient, and robust to out of distribution scans. We apply it to study inflammation linked changes in sudden onset pediatric OCD. --- ### Quantifying Modality Contributions via Disentangling Multimodal Representations Authors: Padegal Amit, Omkar Mahesh Kashyap, Namitha Rayasam, Nidhi Shekhar, Surabhi Narayan Published: 2025-11-22 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2511.19470v1 Quantifying modality contributions in multimodal models remains a challenge, as existing approaches conflate the notion of contribution itself. Prior work relies on accuracy-based approaches, interpreting performance drops after removing a modality as indicative of its influence. However, such outcome-driven metrics fail to distinguish whether a modality is inherently informative or whether its value arises only through interaction with other modalities. This distinction is particularly important in cross-attention architectures, where modalities influence each other's representations. In this work, we propose a framework based on Partial Information Decomposition (PID) that quantifies modality contributions by decomposing predictive information in internal embeddings into unique, redundant, and synergistic components. To enable scalable, inference-only analysis, we develop an algorithm based on the Iterative Proportional Fitting Procedure (IPFP) that computes layer and dataset-level contributions without retraining. This provides a principled, representation-level view of multimodal behavior, offering clearer and more interpretable insights than outcome-based metrics. --- ### Towards a future space-based, highly scalable AI infrastructure system design Authors: Blaise Agüera y Arcas, Travis Beals, Maria Biggs, Jessica V. Bloom, Thomas Fischbacher, Konstantin Gromov, Urs Köster, Rishiraj Pravahan, James Manyika Published: 2025-11-22 Categories: cs.DC, cs.ET, cs.LG, physics.space-ph arXiv: https://arxiv.org/abs/2511.19468v2 If AI is a foundational general-purpose technology, we should anticipate that demand for AI compute -- and energy -- will continue to grow. The Sun is by far the largest energy source in our solar system, and thus it warrants consideration how future AI infrastructure could most efficiently tap into that power. This work explores a scalable compute system for machine learning in space, using fleets of satellites equipped with solar arrays, inter-satellite links using free-space optics, and Google tensor processing unit (TPU) accelerator chips. To facilitate high-bandwidth, low-latency inter-satellite communication, the satellites would be flown in close proximity. We illustrate the basic approach to formation flight via an 81-satellite cluster of 1 km radius, and describe an approach for using high-precision ML-based models to control large-scale constellations. Trillium TPUs are radiation tested. They survive a total ionizing dose equivalent to a 5 year mission life without permanent failures, and are characterized for bit-flip errors. Launch costs are a critical part of overall system cost; a learning curve analysis suggests launch to low-Earth orbit (LEO) may reach $\lesssim$\$200/kg by the mid-2030s. --- ### A Novel and Practical Universal Adversarial Perturbations against Deep Reinforcement Learning based Intrusion Detection Systems Authors: H. Zhang, L. Zhang, G. Epiphaniou, C. Maple Published: 2025-11-22 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2511.18223v1 Intrusion Detection Systems (IDS) play a vital role in defending modern cyber physical systems against increasingly sophisticated cyber threats. Deep Reinforcement Learning-based IDS, have shown promise due to their adaptive and generalization capabilities. However, recent studies reveal their vulnerability to adversarial attacks, including Universal Adversarial Perturbations (UAPs), which can deceive models with a single, input-agnostic perturbation. In this work, we propose a novel UAP attack against Deep Reinforcement Learning (DRL)-based IDS under the domain-specific constraints derived from network data rules and feature relationships. To the best of our knowledge, there is no existing study that has explored UAP generation for the DRL-based IDS. In addition, this is the first work that focuses on developing a UAP against a DRL-based IDS under realistic domain constraints based on not only the basic domain rules but also mathematical relations between the features. Furthermore, we enhance the evasion performance of the proposed UAP, by introducing a customized loss function based on the Pearson Correlation Coefficient, and we denote it as Customized UAP. To the best of our knowledge, this is also the first work using the PCC value in the UAP generation, even in the broader context. Four additional established UAP baselines are implemented for a comprehensive comparison. Experimental results demonstrate that our proposed Customized UAP outperforms two input-dependent attacks including Fast Gradient Sign Method (FGSM), Basic Iterative Method (BIM), and four UAP baselines, highlighting its effectiveness for real-world adversarial scenarios. --- ### Using MLIR Transform to Design Sliced Convolution Algorithm Authors: Victor Ferrari, Marcio Pereira, Lucas Alvarenga, Gustavo Leite, Guido Araujo Published: 2025-11-22 Categories: cs.CV, cs.LG, cs.PF arXiv: https://arxiv.org/abs/2511.18222v1 This paper proposes SConvTransform, a Transform dialect extension that provides operations for optimizing 2D convolutions in MLIR. Its main operation, SConvOp, lowers Linalg convolutions into tiled and packed generic operations through a fully declarative transformation pipeline. The process is guided by a Convolution Slicing Analysis that determines tile sizes and data layout strategies based on input and filter shapes, as well as target architecture parameters. SConvOp handles edge cases by splitting irregular regions and adjusting affine maps where needed. All packing and tiling operations are derived from a parametric set of affine equations, enabling reusable and analyzable transformations. Although functional correctness was the primary goal of this work, the experimental evaluation demonstrates the effectiveness of SConvTransform, achieving good enough performance across different target architectures. Future work will focus on optimizing performance and porting to other target devices. When applied to standard convolution configurations, the generated code achieves up to 60% of peak performance on ARM SME and 67% on Intel AVX512. These results validate the benefit of combining static shape analysis with structured tiling and packing strategies within the MLIR Transform dialect. Furthermore, the modular design of SConvTransform facilitates integration with future extensions, enabling continued optimization of convolution workloads through MLIR's extensible compilation infrastructure. --- ### Enhancing Large Language Models for Automated Homework Assessment in Undergraduate Circuit Analysis Authors: Liangliang Chen, Huiru Xie, Zhihao Qin, Yiming Guo, Jacqueline Rohde, Ying Zhang Published: 2025-11-22 Categories: cs.CY, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2511.18221v1 This research full paper presents an enhancement pipeline for large language models (LLMs) in assessing homework for an undergraduate circuit analysis course, aiming to improve LLMs' capacity to provide personalized support to electrical engineering students. Existing evaluations have demonstrated that GPT-4o possesses promising capabilities in assessing student homework in this domain. Building on these findings, we enhance GPT-4o's performance through multi-step prompting, contextual data augmentation, and the incorporation of targeted hints. These strategies effectively address common errors observed in GPT-4o's responses when using simple prompts, leading to a substantial improvement in assessment accuracy. Specifically, the correct response rate for GPT-4o increases from 74.71% to 97.70% after applying the enhanced prompting and augmented data on entry-level circuit analysis topics. This work lays a foundation for the effective integration of LLMs into circuit analysis instruction and, more broadly, into engineering education. --- ### Deep Gaussian Process Proximal Policy Optimization Authors: Matthijs van der Lende, Juan Cardenas-Cartagena Published: 2025-11-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.18214v2 Uncertainty estimation for Reinforcement Learning (RL) is a critical component in control tasks where agents must balance safe exploration and efficient learning. While deep neural networks have enabled breakthroughs in RL, they often lack calibrated uncertainty estimates. We introduce Deep Gaussian Process Proximal Policy Optimization (GPPO), a scalable, model-free actor-critic algorithm that leverages Deep Gaussian Processes (DGPs) to approximate both the policy and value function. GPPO maintains competitive performance with respect to Proximal Policy Optimization on standard high-dimensional continuous control benchmarks while providing well-calibrated uncertainty estimates that can inform safer and more effective exploration. --- ### Typing Reinvented: Towards Hands-Free Input via sEMG Authors: Kunwoo Lee, Dhivya Sreedhar, Pushkar Saraf, Chaeeun Lee, Kateryna Shapovalenko Published: 2025-11-22 Categories: cs.HC, cs.LG arXiv: https://arxiv.org/abs/2511.18213v1 We explore surface electromyography (sEMG) as a non-invasive input modality for mapping muscle activity to keyboard inputs, targeting immersive typing in next-generation human-computer interaction (HCI). This is especially relevant for spatial computing and virtual reality (VR), where traditional keyboards are impractical. Using attention-based architectures, we significantly outperform the existing convolutional baselines, reducing online generic CER from 24.98% -> 20.34% and offline personalized CER from 10.86% -> 10.10%, while remaining fully causal. We further incorporate a lightweight decoding pipeline with language-model-based correction, demonstrating the feasibility of accurate, real-time muscle-driven text input for future wearable and spatial interfaces. --- ### Large-Scale Pre-training Enables Multimodal AI Differentiation of Radiation Necrosis from Brain Metastasis Progression on Routine MRI Authors: Ahmed Gomaa, Annette Schwarz, Ludwig Singer, Arnd Dörfler, Matthias Stefan May, Pluvio Stephan, Ishita Sheth, Juliane Szkitsak, Katharina Breininger, Yixing Huang, Benjamin Frey, Oliver Schnell et al. Published: 2025-11-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18208v1 Background: Differentiating radiation necrosis (RN) from tumor progression after stereotactic radiosurgery (SRS) remains a critical challenge in brain metastases. While histopathology represents the gold standard, its invasiveness limits feasibility. Conventional supervised deep learning approaches are constrained by scarce biopsy-confirmed training data. Self-supervised learning (SSL) overcomes this by leveraging the growing availability of large-scale unlabeled brain metastases imaging datasets. Methods: In a two-phase deep learning strategy inspired by the foundation model paradigm, a Vision Transformer (ViT) was pre-trained via SSL on 10,167 unlabeled multi-source T1CE MRI sub-volumes. The pre-trained ViT was then fine-tuned for RN classification using a two-channel input (T1CE MRI and segmentation masks) on the public MOLAB dataset (n=109) using 20% of datasets as same-center held-out test set. External validation was performed on a second-center test cohort (n=28). Results: The self-supervised model achieved an AUC of 0.916 on the same-center test set and 0.764 on the second center test set, surpassing the fully supervised ViT (AUC 0.624/0.496; p=0.001/0.008) and radiomics (AUC 0.807/0.691; p=0.005/0.014). Multimodal integration further improved performance (AUC 0.947/0.821; p=0.073/0.001). Attention map visualizations enabled interpretability showing the model focused on clinically relevant lesion subregions. Conclusion: Large-scale pre-training on increasingly available unlabeled brain metastases datasets substantially improves AI model performance. A two-phase multimodal deep learning strategy achieved high accuracy in differentiating radiation necrosis from tumor progression using only routine T1CE MRI and standard clinical data, providing an interpretable, clinically accessible solution that warrants further validation. --- ### ProHD: Projection-Based Hausdorff Distance Approximation Authors: Jiuzhou Fu, Luanzheng Guo, Nathan R. Tallent, Dongfang Zhao Published: 2025-11-22 Categories: cs.IR, cs.LG arXiv: https://arxiv.org/abs/2511.18207v1 The Hausdorff distance (HD) is a robust measure of set dissimilarity, but computing it exactly on large, high-dimensional datasets is prohibitively expensive. We propose \textbf{ProHD}, a projection-guided approximation algorithm that dramatically accelerates HD computation while maintaining high accuracy. ProHD identifies a small subset of candidate "extreme" points by projecting the data onto a few informative directions (such as the centroid axis and top principal components) and computing the HD on this subset. This approach guarantees an underestimate of the true HD with a bounded additive error and typically achieves results within a few percent of the exact value. In extensive experiments on image, physics, and synthetic datasets (up to two million points in $D=256$), ProHD runs 10--100$\times$ faster than exact algorithms while attaining 5--20$\times$ lower error than random sampling-based approximations. Our method enables practical HD calculations in scenarios like large vector databases and streaming data, where quick and reliable set distance estimation is needed. --- ### Generating Synthetic Human Blastocyst Images for In-Vitro Fertilization Blastocyst Grading Authors: Pavan Narahari, Suraj Rajendran, Lorena Bori, Jonas E. Malmsten, Qiansheng Zhan, Zev Rosenwaks, Nikica Zaninovic, Iman Hajirasouliha Published: 2025-11-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18204v1 The success of in vitro fertilization (IVF) at many clinics relies on the accurate morphological assessment of day 5 blastocysts, a process that is often subjective and inconsistent. While artificial intelligence can help standardize this evaluation, models require large, diverse, and balanced datasets, which are often unavailable due to data scarcity, natural class imbalance, and privacy constraints. Existing generative embryo models can mitigate these issues but face several limitations, such as poor image quality, small training datasets, non-robust evaluation, and lack of clinically relevant image generation for effective data augmentation. Here, we present the Diffusion Based Imaging Model for Artificial Blastocysts (DIA) framework, a set of latent diffusion models trained to generate high-fidelity, novel day 5 blastocyst images. Our models provide granular control by conditioning on Gardner-based morphological categories and z-axis focal depth. We rigorously evaluated the models using FID, a memorization metric, an embryologist Turing test, and three downstream classification tasks. Our results show that DIA models generate realistic images that embryologists could not reliably distinguish from real images. Most importantly, we demonstrated clear clinical value. Augmenting an imbalanced dataset with synthetic images significantly improved classification accuracy (p < 0.05). Also, adding synthetic images to an already large, balanced dataset yielded statistically significant performance gains, and synthetic data could replace up to 40% of real data in some cases without a statistically significant loss in accuracy. DIA provides a robust solution for mitigating data scarcity and class imbalance in embryo datasets. By generating novel, high-fidelity, and controllable synthetic images, our models can improve the performance, fairness, and standardization of AI embryo assessment tools. --- ### InfiniBench: Infinite Benchmarking for Visual Spatial Reasoning with Customizable Scene Complexity Authors: Haoming Wang, Qiyao Xue, Wei Gao Published: 2025-11-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18200v2 Modern vision-language models (VLMs) are expected to have abilities of spatial reasoning with diverse scene complexities, but evaluating such abilities is difficult due to the lack of benchmarks that are not only diverse and scalable but also fully customizable. Existing benchmarks offer limited customizability over the scene complexity and are incapable of isolating and analyzing specific VLM failure modes under distinct spatial conditions. To address this gap, instead of individually presenting benchmarks for different scene complexities, in this paper we present InfiniBench, a fully automated, customizable and user-friendly benchmark generator that can synthesize a theoretically infinite variety of 3D scenes with parameterized control on scene complexity. InfiniBench uniquely translates scene descriptions in natural language into photo-realistic videos with complex and physically plausible 3D layouts. This is achieved through three key innovations: 1) a LLM-based agentic framework that iteratively refines procedural scene constraints from scene descriptions; 2) a flexible cluster-based layout optimizer that generates dense and cluttered scenes previously intractable for procedural methods; and 3) a task-aware camera trajectory optimization method that renders scenes into videos with full object coverage as VLM input. Experiments demonstrate that InfiniBench outperforms state-of-the-art procedural and LLM-based 3D generation methods in prompt fidelity and physical plausibility, especially in high-complexity scenarios. We further showcased the usefulness of InfiniBench, by generating benchmarks for representative spatial reasoning tasks including measurement, perspective-taking and spatiotemporal tracking. --- ### Improving Forecasts of Suicide Attempts for Patients with Little Data Authors: Genesis Hang, Annie Chen, Hope Neveux, Matthew K. Nock, Yaniv Yacoby Published: 2025-11-22 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2511.18199v2 Ecological Momentary Assessment (EMA) studies provide real-time data on suicidal thoughts and behaviors, but forecasting suicide attempts remains challenging: attempts are rare, and the pathways patients take to them are heterogeneous. Here, we investigate a cohort of patients from an EMA study with recorded suicide-related events. We show that a single model fit to all patients forecasts poorly, while idiographic (per-patient) models show improvement but overfit for those with little data. Based on this result, one may hypothesize that patients should be partitioned into subgroups---this way, similar patients' data can be pooled together to improve forecasts. However, we show that grouping patients at random already improves forecasts, with performance increasing monotonically with the number of groups. Moreover, we show that grouping patients by demographics yields worse forecasts than random groupings. From these results, we hypothesize that patient similarity is continuous, rather than discrete, and must be inferred from the data. This motivated us to use Latent Variable Multiple Output Gaussian Processes (LVMOGPs), adapted to our data. Preliminary results show that, even without careful kernel design, LVMOGPs already match the strongest baseline models on most metrics, and their latent spaces yield a similarity between patients that we can inspect directly. Because the cohort is conditioned on the outcome and the splits are not temporal, we read these results as evidence that idiographic structure exists and can be recovered, not as deployable forecasting performance---an area for future work. --- ### Linear Algebraic Approaches to Neuroimaging Data Compression: A Comparative Analysis of Matrix and Tensor Decomposition Methods for High-Dimensional Medical Images Authors: Jaeho Kim, Daniel David, Ana Vizitiv Published: 2025-11-22 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2511.18197v1 This paper evaluates Tucker decomposition and Singular Value Decomposition (SVD) for compressing neuroimaging data. Tucker decomposition preserves multi-dimensional relationships, achieving superior reconstruction fidelity and perceptual similarity. SVD excels in extreme compression but sacrifices fidelity. The results highlight Tucker decomposition's suitability for applications requiring the preservation of structural and temporal relationships. --- ### Agent-as-a-Graph: Knowledge Graph-Based Tool and Agent Retrieval for LLM Multi-Agent Systems Authors: Faheem Nizar, Elias Lumer, Anmol Gulati, Pradeep Honaganahalli Basavaraju, Vamse Kumar Subbiah Published: 2025-11-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.18194v1 Recent advances in Large Language Model Multi-Agent Systems enable scalable orchestration and retrieval of specialized, parallelized subagents, each equipped with hundreds or thousands of Model Context Protocol (MCP) servers and tools. However, existing agent, MCP, and retrieval methods typically match queries against a single agent description, obscuring fine-grained tool capabilities of each agent, resulting in suboptimal agent selection. We introduce Agent-as-a-Graph retrieval, a knowledge graph retrieval augmented generation approach that represents both tools and their parent agents as nodes and edges in a knowledge graph. During retrieval, i) relevant agents and tool nodes are first retrieved through vector search, ii) we apply a type-specific weighted reciprocal rank fusion (wRRF) for reranking tools and agents, and iii) parent agents are traversed in the knowledge graph for the final set of agents. We evaluate Agent-as-a-Graph on the LiveMCPBenchmark, achieving 14.9% and 14.6% improvements in Recall@5 and nDCG@5 over prior state-of-the-art retrievers, and 2.4% improvements in wRRF optimizations. --- ### ARIAL: An Agentic Framework for Document VQA with Precise Answer Localization Authors: Ahmad Mohammadshirazi, Pinaki Prasad Guha Neogi, Dheeraj Kulshrestha, Rajiv Ramnath Published: 2025-11-22 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.18192v2 Document Visual Question Answering (VQA) requires models to not only extract accurate textual answers but also precisely localize them within document images, a capability critical for interpretability in high-stakes applications. However, existing systems achieve strong textual accuracy while producing unreliable spatial grounding, or sacrifice performance for interpretability. We present ARIAL (Agentic Reasoning for Interpretable Answer Localization), a modular framework that orchestrates specialized tools through an LLM-based planning agent to achieve both precise answer extraction and reliable spatial grounding. ARIAL decomposes Document VQA into structured subtasks: OCR-based text extraction with TrOCR, retrieval-augmented context selection using semantic search, answer generation via a fine-tuned Gemma 3-27B model, and explicit bounding-box localization through text-to-region alignment. This modular architecture produces transparent reasoning traces, enabling tool-level auditability and independent component optimization. We evaluate ARIAL on four benchmarks (DocVQA, FUNSD, CORD, and SROIE) using both textual accuracy (ANLS) and spatial precision (mAP at IoU 0.50 to 0.95). ARIAL achieves state-of-the-art results across all datasets: 88.7 ANLS and 50.1 mAP on DocVQA, 90.0 ANLS and 50.3 mAP on FUNSD, 85.5 ANLS and 60.2 mAP on CORD, and 93.1 ANLS on SROIE, surpassing the previous best method (DLaVA) by +2.8 ANLS and +3.9 mAP on DocVQA. Our work demonstrates how agentic orchestration of specialized tools can simultaneously improve performance and interpretability, providing a pathway toward trustworthy, explainable document AI systems. --- ### Accelerating Time Series Foundation Models with Speculative Decoding Authors: Pranav Subbaraman, Fang Sun, Jinxi Yu, Yue Yao, Huacong Tang, Xiao Luo, Yizhou Sun Published: 2025-11-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.18191v2 Time series forecasting drives operational decisions under tight latency budgets, and autoregressive time series foundation models (TSFMs) increasingly deliver the most accurate forecasts. That accuracy is paid for at inference, since a horizon of $H$ steps takes $\lceil H / P\rceil$ sequential forward passes of a large model, so latency grows with exactly the long horizons these models are prized for. Yet a far cheaper model predicts most next patches nearly as well as the large one, and causal models can verify a block of future patches in one parallel pass even though they generate them one at a time. These are precisely the conditions under which speculative decoding thrives in LLMs, but its ingredients are all defined over discrete vocabularies. We therefore develop speculative decoding for continuous patch autoregression. A cheap draft proposes $K$ future patches, and the target verifies all of them in a single causal pass, accepting each by a log-domain Gaussian likelihood-ratio test and correcting the first rejection with its own prediction. We prove that the accelerated output stays within a squared-error radius of target-only decoding set by an acceptance temperature, and that throughput follows a capped-geometric law that makes speedups predictable before deployment. The method delivers up to $3.0 \times$ inference speedup at accuracy between target and draft across five TSFM families, and we characterize which architectures admit single-pass verification and when speculation does not pay. --- ### Early Lung Cancer Diagnosis from Virtual Follow-up LDCT Generation via Correlational Autoencoder and Latent Flow Matching Authors: Yutong Wu, Yifan Wang, Qining Zhang, Chuan Zhou, Lei Ying Published: 2025-11-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18185v1 Lung cancer is one of the most commonly diagnosed cancers, and early diagnosis is critical because the survival rate declines sharply once the disease progresses to advanced stages. However, achieving an early diagnosis remains challenging, particularly in distinguishing subtle early signals of malignancy from those of benign conditions. In clinical practice, a patient with a high risk may need to undergo an initial baseline and several annual follow-up examinations (e.g., CT scans) before receiving a definitive diagnosis, which can result in missing the optimal treatment. Recently, Artificial Intelligence (AI) methods have been increasingly used for early diagnosis of lung cancer, but most existing algorithms focus on radiomic features extraction from single early-stage CT scans. Inspired by recent advances in diffusion models for image generation, this paper proposes a generative method, named CorrFlowNet, which creates a virtual, one-year follow-up CT scan after the initial baseline scan. This virtual follow-up would allow for an early detection of malignant/benign nodules, reducing the need to wait for clinical follow-ups. During training, our approach employs a correlational autoencoder to encode both early baseline and follow-up CT images into a latent space that captures the dynamics of nodule progression as well as the correlations between them, followed by a flow matching algorithm on the latent space with a neural ordinary differential equation. An auxiliary classifier is used to further enhance the diagnostic accuracy. Evaluations on a real clinical dataset show our method can significantly improve downstream lung nodule risk assessment compared with existing baseline models. Moreover, its diagnostic accuracy is comparable with real clinical CT follow-ups, highlighting its potential to improve cancer diagnosis. --- ### The Workflow as Medium: A Framework for Navigating Human-AI Co-Creation Authors: Lee Ackerman Published: 2025-11-22 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2511.18182v1 This paper introduces the Creative Intelligence Loop (CIL), a novel socio-technical framework for responsible human-AI co-creation. Rooted in the 'Workflow as Medium' paradigm, the CIL proposes a disciplined structure for dynamic human-AI collaboration, guiding the strategic integration of diverse AI teammates who function as collaborators while the human remains the final arbiter for ethical alignment and creative integrity. The CIL was empirically demonstrated through the practice-led creation of two graphic novellas, investigating how AI could serve as an effective creative colleague within a subjective medium lacking objective metrics. The process required navigating multifaceted challenges including AI's 'jagged frontier' of capabilities, sycophancy, and attention-scarce feedback environments. This prompted iterative refinement of teaming practices, yielding emergent strategies: a multi-faceted critique system integrating adversarial AI roles to counter sycophancy, and prioritizing 'feedback-ready' concrete artifacts to elicit essential human critique. The resulting graphic novellas analyze distinct socio-technical governance failures: 'The Steward' examines benevolent AI paternalism in smart cities, illustrating how algorithmic hubris can erode freedom; 'Fork the Vote' probes democratic legitimacy by comparing centralized AI opacity with emergent collusion in federated networks. This work contributes a self-improving framework for responsible human-AI co-creation and two graphic novellas designed to foster AI literacy and dialogue through accessible narrative analysis of AI's societal implications. --- ### MOMA-AC: A preference-driven actor-critic framework for continuous multi-objective multi-agent reinforcement learning Authors: Adam Callaghan, Karl Mason, Patrick Mannion Published: 2025-11-22 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.18181v1 This paper addresses a critical gap in Multi-Objective Multi-Agent Reinforcement Learning (MOMARL) by introducing the first dedicated inner-loop actor-critic framework for continuous state and action spaces: Multi-Objective Multi-Agent Actor-Critic (MOMA-AC). Building on single-objective, single-agent algorithms, we instantiate this framework with Twin Delayed Deep Deterministic Policy Gradient (TD3) and Deep Deterministic Policy Gradient (DDPG), yielding MOMA-TD3 and MOMA-DDPG. The framework combines a multi-headed actor network, a centralised critic, and an objective preference-conditioning architecture, enabling a single neural network to encode the Pareto front of optimal trade-off policies for all agents across conflicting objectives in a continuous MOMARL setting. We also outline a natural test suite for continuous MOMARL by combining a pre-existing multi-agent single-objective physics simulator with its multi-objective single-agent counterpart. Evaluating cooperative locomotion tasks in this suite, we show that our framework achieves statistically significant improvements in expected utility and hypervolume relative to outer-loop and independent training baselines, while demonstrating stable scalability as the number of agents increases. These results establish our framework as a foundational step towards robust, scalable multi-objective policy learning in continuous multi-agent domains. --- ### Bayesian Calibration of Engine-out NOx Models for Engine-to-Engine Transferability Authors: Shrenik Zinage, Peter Meckl, Ilias Bilionis Published: 2025-11-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.18178v2 Accurate prediction of engine-out NOx is essential for meeting stringent emissions regulations and optimizing engine performance. Traditional approaches rely on models trained on data from a small number of engines, which can be insufficient in generalizing across an entire population of engines due to sensor biases and variations in input conditions. In real world applications, these models require tuning or calibration to maintain acceptable error tolerance when applied to other engines. This highlights the need for models that can adapt with minimal adjustments to accommodate engine-to-engine variability and sensor discrepancies. While previous studies have explored machine learning methods for predicting engine-out NOx, these approaches often fail to generalize reliably across different engines and operating environments. To address these issues, we propose a Bayesian calibration framework that combines Gaussian processes (GP) with approximate Bayesian computation to infer and correct sensor biases. Starting with a pre-trained model developed using nominal engine data, our method identifies engine specific sensor biases and recalibrates predictions accordingly. By incorporating these inferred biases, our approach generates posterior predictive distributions for engine-out NOx on unseen test data, achieving high accuracy without retraining the model. Our results demonstrate that this transferable modeling approach significantly improves the accuracy of predictions compared to conventional non-adaptive GP models, effectively addressing engine-to-engine variability and improving model generalizability. --- ### Rethinking Retrieval: From Traditional Retrieval Augmented Generation to Agentic and Non-Vector Reasoning Systems in the Financial Domain for Large Language Models Authors: Elias Lumer, Matt Melich, Olivia Zino, Elena Kim, Sara Dieter, Pradeep Honaganahalli Basavaraju, Vamse Kumar Subbiah, James A. Burke, Roberto Hernandez Published: 2025-11-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.18177v1 Recent advancements in Retrieval-Augmented Generation (RAG) have enabled Large Language Models to answer financial questions using external knowledge bases of U.S. SEC filings, earnings reports, and regulatory documents. However, existing work lacks systematic comparison of vector-based and non-vector RAG architectures for financial documents, and the empirical impact of advanced RAG techniques on retrieval accuracy, answer quality, latency, and cost remain unclear. We present the first systematic evaluation comparing vector-based agentic RAG using hybrid search and metadata filtering against hierarchical node-based systems that traverse document structure without embeddings. We evaluate two enhancement techniques applied to the vector-based architecture, i) cross-encoder reranking for retrieval precision, and ii) small-to-big chunk retrieval for context completeness. Across 1,200 SEC 10-K, 10-Q, and 8-K filings on a 150-question benchmark, we measure retrieval metrics (MRR, Recall@5), answer quality through LLM-as-a-judge pairwise comparisons, latency, and preprocessing costs. Vector-based agentic RAG achieves a 68% win rate over hierarchical node-based systems with comparable latency (5.2 compared to 5.98 seconds). Cross-encoder reranking achieves a 59% absolute improvement at optimal parameters (10, 5) for MRR@5. Small-to-big retrieval achieves a 65% win rate over baseline chunking with only 0.2 seconds additional latency. Our findings reveal that applying advanced RAG techniques to financial Q&A systems improves retrieval accuracy, answer quality, and has cost-performance tradeoffs to be considered in production. --- ### Unified Spherical Frontend: Learning Rotation-Equivariant Representations of Spherical Images from Any Camera Authors: Mukai Yu, Mosam Dabhi, Liuyue Xie, Sebastian Scherer, László A. Jeni Published: 2025-11-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18174v2 Modern perception increasingly relies on fisheye, panoramic, and other wide field-of-view (FoV) cameras, yet most pipelines still apply planar CNNs designed for pinhole imagery on 2D grids, where pixel-space neighborhoods misrepresent physical adjacency and models are sensitive to global rotations. Traditional spherical CNNs partially address this mismatch but require costly spherical harmonic transform that constrains resolution and efficiency. We present Unified Spherical Frontend (USF), a distortion-free lens-agnostic framework that transforms images from any calibrated camera onto the unit sphere via ray-direction correspondences, and performs spherical resampling, convolution, and pooling canonically in the spatial domain. USF is modular: projection, location sampling, value interpolation, and resolution control are fully decoupled. Its configurable distance-only convolution kernels offer rotation-equivariance, mirroring translation-equivariance in planar CNNs while avoiding harmonic transforms entirely. We compare multiple standard planar backbones with their spherical counterparts across classification, detection, and segmentation tasks on synthetic (Spherical MNIST) and real-world (PANDORA, Stanford 2D-3D-S) datasets, and stress-test robustness to extreme lens distortions, varying FoV, and arbitrary rotations. USF scales efficiently to high-resolution spherical imagery and maintains less than 1% performance drop under random test-time rotations without training-time rotational augmentation, and enables zero-shot generalization to any unseen (wide-FoV) lenses with minimal performance degradation. --- ### EgoControl: Controllable Egocentric Video Generation via 3D Full-Body Poses Authors: Enrico Pallotta, Sina Mokhtarzadeh Azar, Lars Doorenbos, Serdar Ozsoy, Umar Iqbal, Juergen Gall Published: 2025-11-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18173v1 Egocentric video generation with fine-grained control through body motion is a key requirement towards embodied AI agents that can simulate, predict, and plan actions. In this work, we propose EgoControl, a pose-controllable video diffusion model trained on egocentric data. We train a video prediction model to condition future frame generation on explicit 3D body pose sequences. To achieve precise motion control, we introduce a novel pose representation that captures both global camera dynamics and articulated body movements, and integrate it through a dedicated control mechanism within the diffusion process. Given a short sequence of observed frames and a sequence of target poses, EgoControl generates temporally coherent and visually realistic future frames that align with the provided pose control. Experimental results demonstrate that EgoControl produces high-quality, pose-consistent egocentric videos, paving the way toward controllable embodied video simulation and understanding. --- ### MEDIC: a network for monitoring data quality in collider experiments Authors: Juvenal Bassa, Arghya Chattopadhyay, Sudhir Malik, Mario Escabi Rivera Published: 2025-11-22 Categories: hep-ex, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.18172v2 Data Quality Monitoring (DQM) is a crucial component of particle physics experiments and ensures that the recorded data is of the highest quality, and suitable for subsequent physics analysis. Due to the extreme environmental conditions, unprecedented data volumes, and the sheer scale and complexity of the detectors, DQM orchestration has become a very challenging task. Therefore, the use of Machine Learning (ML) to automate anomaly detection, improve efficiency, and reduce human error in the process of collecting high-quality data is unavoidable. Since DQM relies on real experimental data, it is inherently tied to the specific detector substructure and technology in operation. In this work, a simulation-driven approach to DQM is proposed, enabling the study and development of data-quality methodologies in a controlled environment. Using a modified version of Delphes -- a fast, multi-purpose detector simulation -- the preliminary realization of a framework is demonstrated which leverages ML to identify detector anomalies as well as localize the malfunctioning components responsible. We introduce MEDIC (Monitoring for Event Data Integrity and Consistency), a neural network designed to learn detector behavior and perform DQM tasks to look for potential faults. Although the present implementation adopts a simplified setup for computational ease, where large detector regions are deliberately deactivated to mimic faults, this work represents an initial step toward a comprehensive ML-based DQM framework. The encouraging results underline the potential of simulation-driven studies as a foundation for developing more advanced, data-driven DQM systems for future particle detectors. --- ### BPMN to PDDL: Translating Business Workflows for AI Planning Authors: Jasper Nie, Christian Muise, Victoria Armstrong Published: 2025-11-22 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.18171v1 Business Process Model and Notation (BPMN) is a widely used standard for modelling business processes. While automated planning has been proposed as a method for simulating and reasoning about BPMN workflows, most implementations remain incomplete or limited in scope. This project builds upon prior theoretical work to develop a functional pipeline that translates BPMN 2.0 diagrams into PDDL representations suitable for planning. The system supports core BPMN constructs, including tasks, events, sequence flows, and gateways, with initial support for parallel and inclusive gateway behaviour. Using a non-deterministic planner, we demonstrate how to generate and evaluate valid execution traces. Our implementation aims to bridge the gap between theory and practical tooling, providing a foundation for further exploration of translating business processes into well-defined plans. --- ### Sparse Polyak with optimal thresholding operators for high-dimensional M-estimation Authors: Tianqi Qiao, Marie Maros Published: 2025-11-22 Categories: stat.ML, cs.LG, math.OC arXiv: https://arxiv.org/abs/2511.18167v1 We propose and analyze a variant of Sparse Polyak for high dimensional M-estimation problems. Sparse Polyak proposes a novel adaptive step-size rule tailored to suitably estimate the problem's curvature in the high-dimensional setting, guaranteeing that the algorithm's performance does not deteriorate when the ambient dimension increases. However, convergence guarantees can only be obtained by sacrificing solution sparsity and statistical accuracy. In this work, we introduce a variant of Sparse Polyak that retains its desirable scaling properties with respect to the ambient dimension while obtaining sparser and more accurate solutions. --- ### Towards a General Framework for HTN Modeling with LLMs Authors: Israel Puerta-Merino, Carlos Núñez-Molina, Pablo Mesejo, Juan Fernández-Olivares Published: 2025-11-22 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2511.18165v1 The use of Large Language Models (LLMs) for generating Automated Planning (AP) models has been widely explored; however, their application to Hierarchical Planning (HP) is still far from reaching the level of sophistication observed in non-hierarchical architectures. In this work, we try to address this gap. We present two main contributions. First, we propose L2HP, an extension of L2P (a library to LLM-driven PDDL models generation) that support HP model generation and follows a design philosophy of generality and extensibility. Second, we apply our framework to perform experiments where we compare the modeling capabilities of LLMs for AP and HP. On the PlanBench dataset, results show that parsing success is limited but comparable in both settings (around 36\%), while syntactic validity is substantially lower in the hierarchical case (1\% vs. 20\% of instances). These findings underscore the unique challenges HP presents for LLMs, highlighting the need for further research to improve the quality of generated HP models. --- ### Nested Unfolding Network for Real-World Concealed Object Segmentation Authors: Chunming He, Rihan Zhang, Dingming Zhang, Fengyang Xiao, Deng-Ping Fan, Sina Farsiu Published: 2025-11-22 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.18164v1 Deep unfolding networks (DUNs) have recently advanced concealed object segmentation (COS) by modeling segmentation as iterative foreground-background separation. However, existing DUN-based methods (RUN) inherently couple background estimation with image restoration, leading to conflicting objectives and requiring pre-defined degradation types, which are unrealistic in real-world scenarios. To address this, we propose the nested unfolding network (NUN), a unified framework for real-world COS. NUN adopts a DUN-in-DUN design, embedding a degradation-resistant unfolding network (DeRUN) within each stage of a segmentation-oriented unfolding network (SODUN). This design decouples restoration from segmentation while allowing mutual refinement. Guided by a vision-language model (VLM), DeRUN dynamically infers degradation semantics and restores high-quality images without explicit priors, whereas SODUN performs reversible estimation to refine foreground and background. Leveraging the multi-stage nature of unfolding, NUN employs image-quality assessment to select the best DeRUN outputs for subsequent stages, naturally introducing a self-consistency loss that enhances robustness. Extensive experiments show that NUN achieves a leading place on both clean and degraded benchmarks. Code will be released. --- ### Matching-Based Few-Shot Semantic Segmentation Models Are Interpretable by Design Authors: Pasquale De Marinis, Uzay Kaymak, Rogier Brussee, Gennaro Vessio, Giovanna Castellano Published: 2025-11-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18163v1 Few-Shot Semantic Segmentation (FSS) models achieve strong performance in segmenting novel classes with minimal labeled examples, yet their decision-making processes remain largely opaque. While explainable AI has advanced significantly in standard computer vision tasks, interpretability in FSS remains virtually unexplored despite its critical importance for understanding model behavior and guiding support set selection in data-scarce scenarios. This paper introduces the first dedicated method for interpreting matching-based FSS models by leveraging their inherent structural properties. Our Affinity Explainer approach extracts attribution maps that highlight which pixels in support images contribute most to query segmentation predictions, using matching scores computed between support and query features at multiple feature levels. We extend standard interpretability evaluation metrics to the FSS domain and propose additional metrics to better capture the practical utility of explanations in few-shot scenarios. Comprehensive experiments on FSS benchmark datasets, using different models, demonstrate that our Affinity Explainer significantly outperforms adapted standard attribution methods. Qualitative analysis reveals that our explanations provide structured, coherent attention patterns that align with model architectures and and enable effective model diagnosis. This work establishes the foundation for interpretable FSS research, enabling better model understanding and diagnostic for more reliable few-shot segmentation systems. The source code is publicly available at https://github.com/pasqualedem/AffinityExplainer. --- ### Vector Arithmetic in Concept and Token Subspaces Authors: Sheridan Feucht, Byron Wallace, David Bau Published: 2025-11-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.18162v1 In order to predict the next token, LLMs must represent semantic and surface-level information about the current word. Previous work identified two types of attention heads that disentangle this information: (i) Concept induction heads, which copy word meanings, and (ii) Token induction heads, which copy literal token representations (Feucht et al., 2025). We show that these heads can be used to identify subspaces of model activations that exhibit coherent semantic structure in Llama-2-7b. Specifically, when we transform hidden states using the attention weights of concept heads, we are able to more accurately perform parallelogram arithmetic (Mikolov et al., 2013) on the resulting hidden states, e.g., showing that "Athens" - "Greece" + "China" = "Beijing". This transformation allows for much higher nearest-neighbor accuracy (80%) than direct use of raw hidden states (47%). Analogously, we show that token heads allow for transformations that reveal surface-level word information in hidden states, allowing for operations like "coding" - "code" + "dance" = "dancing". --- ### Bringing Stability to Diffusion: Decomposing and Reducing Variance of Training Masked Diffusion Models Authors: Mengni Jia, Mengyu Zhou, Yihao Liu, Xiaoxi Jiang, Guanjun Jiang Published: 2025-11-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.18159v2 Masked diffusion models (MDMs) are a promising alternative to autoregressive models (ARMs), but they suffer from inherently much higher training variance. High variance leads to noisier gradient estimates and unstable optimization, so even equally strong pretrained MDMs and ARMs that are competitive at initialization often diverge after task-specific training, with MDMs falling far behind. There has been no theoretical explanation or systematic solution. We derive the first decomposition of MDM training variance into three sources: (A) masking pattern noise, (B) masking rate noise, and (C) data noise, while ARMs are only affected by (C). This explains the fundamental training gap. Building on this foundation, we design six variance-reduction methods, including two core methods: (1) P-POTS, a Pareto-optimal t sampler that minimizes training variance by sampling harder t values more often with appropriately smaller update steps, and (2) MIRROR, which uses negatively correlated samples to reduce (A). Experiments show that compared to standard MDM training, our methods improve accuracy by 7-8% on complex reasoning tasks, while simultaneously reducing run-to-run variability to near ARM levels, substantially narrowing the gap with strong ARM baselines; in most settings, even the best baseline runs remain below the worst run of our method. --- ### LocaGen: Low-Overhead Indoor Localization Through Spatial Augmentation Authors: Abdelrahman Abdelmotlb, Abdallah Taman, Sherif Mostafa, Moustafa Youssef Published: 2025-11-22 Categories: cs.LG, cs.NI arXiv: https://arxiv.org/abs/2511.18158v1 Indoor localization systems commonly rely on fingerprinting, which requires extensive survey efforts to obtain location-tagged signal data, limiting their real-world deployability. Recent approaches that attempt to reduce this overhead either suffer from low representation ability, mode collapse issues, or require the effort of collecting data at all target locations. We present LocaGen, a novel spatial augmentation framework that significantly reduces fingerprinting overhead by generating high-quality synthetic data at completely unseen locations. LocaGen leverages a conditional diffusion model guided by a novel spatially aware optimization strategy to synthesize realistic fingerprints at unseen locations using only a subset of seen locations. To further improve our diffusion model performance, LocaGen augments seen location data based on domain-specific heuristics and strategically selects the seen and unseen locations using a novel density-based approach that ensures robust coverage. Our extensive evaluation on a real-world WiFi fingerprinting dataset shows that LocaGen maintains the same localization accuracy even with 30% of the locations unseen and achieves up to 28% improvement in accuracy over state-of-the-art augmentation methods. --- ### scipy.spatial.transform: Differentiable Framework-Agnostic 3D Transformations in Python Authors: Martin Schuck, Alexander von Rohr, Angela P. Schoellig Published: 2025-11-22 Categories: cs.LG, cs.RO arXiv: https://arxiv.org/abs/2511.18157v2 Three-dimensional rigid-body transforms, i.e. rotations and translations, are central to modern differentiable machine learning pipelines in robotics, vision, and simulation. However, numerically robust and mathematically correct implementations, particularly on SO(3), are error-prone due to issues such as axis conventions, normalizations, composition consistency and subtle errors that only appear in edge cases. SciPy's spatial$.$transform module is a rigorously tested Python implementation. However, it historically only supported NumPy, limiting adoption in GPU-accelerated and autodiff-based workflows. We present a complete overhaul of SciPy's spatial$.$transform functionality that makes it compatible with any array library implementing the Python array API, including JAX, PyTorch, and CuPy. The revised implementation preserves the established SciPy interface while enabling GPU/TPU execution, JIT compilation, vectorized batching, and differentiation via native autodiff of the chosen backend. We demonstrate how this foundation supports differentiable scientific computing through two case studies: (i) scalability of 3D transforms and rotations and (ii) a JAX drone simulation that leverages SciPy's Rotation for accurate integration of rotational dynamics. Our contributions have been merged into SciPy main and will ship in the next release, providing a framework-agnostic, production-grade basis for 3D spatial math in differentiable systems and ML. --- ### A Coordinated Dual-Arm Framework for Delicate Snap-Fit Assemblies Authors: Shreyas Kumar, Barat S, Debojit Das, Yug Desai, Siddhi Jain, Rajesh Kumar, Harish J. Palanthandalam-Madapusi Published: 2025-11-22 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2511.18153v1 Delicate snap-fit assemblies, such as inserting a lens into an eye-wear frame or during electronics assembly, demand timely engagement detection and rapid force attenuation to prevent overshoot-induced component damage or assembly failure. We address these challenges with two key contributions. First, we introduce SnapNet, a lightweight neural network that detects snap-fit engagement from joint-velocity transients in real-time, showing that reliable detection can be achieved using proprioceptive signals without external sensors. Second, we present a dynamical-systems-based dual-arm coordination framework that integrates SnapNet driven detection with an event-triggered impedance modulation, enabling accurate alignment and compliant insertion during delicate snap-fit assemblies. Experiments across diverse geometries on a heterogeneous bimanual platform demonstrate high detection accuracy (over 96% recall) and up to a 30% reduction in peak impact forces compared to standard impedance control. --- ### UnfoldLDM: Degradation-Aware Unfolding with Iterative Latent Diffusion Priors for Blind Image Restoration Authors: Chunming He, Rihan Zhang, Zheng Chen, Bowen Yang, Chengyu Fang, Yunlong Lin, Yulun Zhang, Fengyang Xiao, Sina Farsiu Published: 2025-11-22 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.18152v3 Deep unfolding networks (DUNs) combine the interpretability of model-based methods with the learning ability of deep networks, yet remain limited for blind image restoration (BIR). Existing DUNs suffer from: (1) \textbf{Degradation-specific dependency}, as their optimization frameworks are tied to a known degradation model, making them unsuitable for BIR tasks; and (2) \textbf{Over-smoothing bias}, resulting from the direct feeding of gradient descent outputs, dominated by low-frequency content, into the proximal term, suppressing fine textures. To overcome these issues, we propose UnfoldLDM to integrate DUNs with latent diffusion model (LDM) for BIR. In each stage, UnfoldLDM employs a multi-granularity degradation-aware (MGDA) module as the gradient descent step. MGDA models BIR as an unknown degradation estimation problem and estimates both the holistic degradation matrix and its decomposed forms, enabling robust degradation removal. For the proximal step, we design a degradation-resistant LDM (DR-LDM) to extract compact degradation-invariant priors from the MGDA output. Guided by this prior, an over-smoothing correction transformer (OCFormer) explicitly recovers high-frequency components and enhances texture details. This unique combination ensures the final result is degradation-free and visually rich. Experiments show that our UnfoldLDM achieves a leading place on various BIR tasks and benefits downstream tasks. Moreover, our design is compatible with existing DUN-based methods, serving as a plug-and-play framework. Code will be released. ---