# Research Papers — 2025-11 · bundle page 67 of 197 > Full-text markdown of papers #3301–3350 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/67 [← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/66.md) [Next bundle →](https://aipod.dev/papers/archive/2025-11/page/68.md) ### Predicting the Emergence of Induction Heads in Language Model Pretraining Authors: Tatsuya Aoyama, Ethan Gotlieb Wilcox, Nathan Schneider Published: 2025-11-21 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.16893v3 Specialized attention heads dubbed induction heads (IHs) have been argued to underlie the remarkable in-context learning capabilities of modern language models; yet, a precise characterization of their emergence, especially in the context of language modeling, remains wanting. In this study, we investigate the relationship between statistical properties of the training data and IH formation in both natural and synthetic training data settings. We show that: (1) a simple equation combining batch size and context size predicts the point at which IHs form and that this emergence point is agnostic to model size; (2) surface bigram repetition frequency and reliability strongly affect the formation of IHs, and we find an effective decision boundary in terms of these two values; (3) local dependency with high bigram repetition frequency and reliability is sufficient for IH formation, but categoriality and the shape of the marginal distribution appear to modulate IH formation near the decision boundary. --- ### Glass Surface Detection: Leveraging Reflection Dynamics in Flash/No-flash Imagery Authors: Tao Yan, Zeyu Wang, Hao Huang, Yiwei Lu, Ke Xu, Chunping Ge, Yinghui Wang, Xiaojun Chang, Rynson W. H. Lau Published: 2025-11-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.16887v5 Glass surfaces are ubiquitous in daily life, typically appearing colorless, transparent, and lacking distinctive features. These characteristics make glass surface detection a challenging computer vision task. Existing glass surface detection methods always rely on boundary cues (\textit{e.g.}, window and door frames) or reflection cues to locate glass surfaces, but they fail to fully exploit the intrinsic properties of the glass itself for accurate localization. We observed that in most real-world scenes, the illumination intensity in front of the glass surface differs from that behind it, which results in variations in the reflections visible on the glass surface. Specifically, when standing on the brighter side of the glass and applying a flash towards the darker side, existing reflections on the glass surface tend to disappear. Conversely, while standing on the darker side and applying a flash towards the brighter side, distinct reflections will appear on the glass surface. Based on this phenomenon, we propose \textit{NFGlassNet}, a novel method for glass surface detection that leverages the reflection dynamics present in flash/no-flash imagery. Specifically, we propose a Reflection Contrast Mining Module (RCMM) for extracting reflections, and a Reflection Guided Attention Module (RGAM) for fusing features from reflection and glass surface for accurate glass surface detection. For learning our network, we also construct a dataset consisting of $\sim$3.3$K$ no-flash and flash image pairs captured from various scenes with corresponding ground truth annotations. Extensive experiments demonstrate that our method outperforms the state-of-the-art methods. Our code, model, and dataset will be available upon acceptance of the manuscript. --- ### Latent Reasoning in TRMs is Secretly a Policy Improvement Operator Authors: Arip Asadulaev, Rayan Banerjee, Fakhri Karray, Martin Takac Published: 2025-11-21 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.16886v5 Recently, small models with latent recursion have obtained promising results on complex reasoning tasks. These results are typically explained by the theory that such recursion increases a networks depth, allowing it to compactly emulate the capacity of larger models. However, the performance of recursively added layers remains behind the capabilities of one pass models with the same feed-forward depth. This means that in the looped version, not every recursive step effectively contributes to depth. This raises the question: when and why does latent reasoning improve performance, and when does it result in dead compute? In our work, we demonstrate that latent recursive reasoning provides answer to this question. We show that latent recursive reasoning can be formalized as a policy improvement algorithm. Building on these insights, we propose to use a training schemes from reinforcement learning and diffusion methods for latent reasoning models. Using the Tiny Recursive Model as our testbed, we show that with our modifications we can avoid dead compute steps and reduce the total number of forward passes by 18x while maintaining performance. Broadly speaking, we show how a policy improvement perspective on recursive steps can explain model behavior and provide insights for further improvements. --- ### Improving Latent Reasoning in LLMs via Soft Concept Mixing Authors: Kang Wang, Xiangyu Duan, Tianyi Du Published: 2025-11-21 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.16885v1 Unlike human reasoning in abstract conceptual spaces, large language models (LLMs) typically reason by generating discrete tokens, which potentially limit their expressive power. The recent work Soft Thinking has shown that LLMs' latent reasoning via soft concepts is a promising direction, but LLMs are trained on discrete tokens. To reduce this gap between the soft concepts in reasoning and the discrete tokens in training, we propose Soft Concept Mixing (SCM), a soft concept aware training scheme that directly exposes the model to soft representations during training. Specifically, SCM constructs a soft concept vector by forming a probability-weighted average of embeddings. Then, this vector is mixed into the model's hidden states, which embody rich contextual information. Finally, the entire latent reasoning process is optimized with Reinforcement Learning (RL). Experiments on five reasoning benchmarks demonstrate that SCM improves the reasoning performance of LLMs, and simultaneously maintains a stable training dynamic. --- ### Generative AI in Sociological Research: State of the Discipline Authors: AJ Alvero, Dustin S. Stoltz, Oscar Stuhler, Marshall Taylor Published: 2025-11-21 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2511.16884v2 Generative artificial intelligence (GenAI) has garnered considerable attention for its potential utility in research and scholarship. A growing body of work in sociology and related fields demonstrates both the potential advantages and risks of GenAI, but these studies are largely proof-of-concept or specific audits of models and products. We know comparatively little about how sociologists actually use GenAI in their research practices and how they view its present and future role in the discipline. In this paper, we describe the current landscape of GenAI use in sociological research based on a survey of authors in 50 sociology journals. Our sample includes both computational sociologists and non-computational sociologists and their collaborators. We find that sociologists primarily use GenAI to assist with writing tasks: revising, summarizing, editing, and translating their own work. Respondents report that GenAI saves time and that they are curious about its capabilities, but they do not currently feel strong institutional or field-level pressure to adopt it. Overall, respondents are wary of GenAI's social and environmental impacts and express low levels of trust in its outputs, but many believe that GenAI tools will improve over the next several years. We do not find large differences between computational and non-computational scholars in terms of GenAI use, attitudes, and concern; nor do we find strong patterns by familiarity or frequency of use. We discuss what these findings suggest about the future of GenAI in sociology and highlight challenges for developing shared norms around its use in research practice. --- ### PersonalizedRouter: Personalized LLM Routing via Graph-based User Preference Modeling Authors: Zhongjie Dai, Tao Feng, Jiaxuan You Published: 2025-11-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.16883v1 The growing number of Large Language Models (LLMs) with diverse capabilities and response styles provides users with a wider range of choices, which presents challenges in selecting appropriate LLMs, as user preferences vary in terms of performance, cost, and response style. Current LLM selection methods typically optimize for a single fixed objective, such as performance, cost, or a trade-off between them, and fail to learn individual user preferences from interaction data. To address these limitations, we propose PersonalizedRouter, a graph-based framework that models diverse user profiles and performs personalized LLM selection by leveraging interaction data that includes task context, queries, candidate LLMs, and user decisions. To capture contextual information between user queries and optimal LLMs, PersonalizedRouter converts the interaction data into a heterogeneous graph, where the relationships between different types of nodes are represented by edges. To evaluate adaptability across users, we design two strategies: the multi-cost-efficiency simulation strategy and the LLM-as-a-Judge strategy. In addition, we construct PersonaRoute-Bench, a large-scale benchmark with 1,000 simulated users and 10 LLMs. Experimental results show that PersonalizedRouter significantly outperforms existing LLM selection methods and surpasses the strongest methods by a large margin of 15.38% and 9.83% under two simulation strategies. On the PersonaRoute-Bench with 1,000 users, it further surpasses the best methods by 16.19% and 59.69% while maintaining higher efficiency. Moreover, PersonalizedRouter demonstrates strong few-shot generalization, achieving 64.81% and 85.80% of the fully trained model's performance when adapting to new users and new LLMs. --- ### Aggregating Direct and Indirect Neighbors through Graph Linear Transformations Authors: Marshall Rosenhoover, Huaming Zhang Published: 2025-11-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.16871v2 Graph neural networks (GNN) typically rely on localized message passing, requiring increasing depth to capture long range dependencies. In this work, we introduce Graph Linear Transformations, a linear transformation that realizes direct and indirect feature mixing on graphs through a single, well-defined linear operator derived from the graph structure. By interpreting graphs as walk-summable Gaussian graphical models, we compute these transformations via Gaussian Belief Propagation, enabling each node to aggregate information from both direct and indirect neighbors without explicit enumeration of multi-hop paths. We show that different constructions of the underlying precision matrix induce distinct and interpretable propagation biases, ranging from selective edge-level interactions to uniform structural smoothing, and that Graph Linear Transformations can achieve competitive or superior performance compared to both local message-passing GNNs and dynamic neighborhood aggregation models across homophilic and heterophilic benchmark datasets. --- ### Align & Invert: Solving Inverse Problems with Diffusion and Flow-based Models via Representation Alignment Authors: Loukas Sfountouris, Giannis Daras, Paris Giampouras Published: 2025-11-21 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2511.16870v3 Enforcing alignment between the internal representations of diffusion or flow-based generative models and those of pretrained self-supervised encoders has recently been shown to provide a powerful inductive bias, improving both convergence and sample quality. In this work, we extend this idea to inverse problems, where pretrained generative models are employed as priors. We propose applying representation alignment (REPA) between diffusion or flow-based models and a DINOv2 visual encoder, to guide the reconstruction process at inference time. Although ground-truth signals are unavailable in inverse problems, we empirically show that aligning model representations of approximate target features can substantially enhance reconstruction quality and perceptual realism. We provide theoretical results showing (a) that REPA regularization can be viewed as a variational approach for minimizing a divergence measure in the DINOv2 embedding space, and (b) how under certain regularity assumptions REPA updates steer the latent diffusion states toward those of the clean image. These results offer insights into the role of REPA in improving perceptual fidelity. Finally, we demonstrate the generality of our approach by We integrate REPA into multiple state-of-the-art inverse problem solvers, and provide extensive experiments on super-resolution, box inpainting, Gaussian deblurring, and motion deblurring confirming that our method consistently improves reconstruction quality, while also providing efficiency gains reducing the number of required discretization steps. --- ### The Joint Gromov Wasserstein Objective for Multiple Object Matching Authors: Aryan Tajmir Riahi, Khanh Dao Duc Published: 2025-11-21 Categories: cs.CV, q-bio.BM arXiv: https://arxiv.org/abs/2511.16868v2 The Gromov-Wasserstein (GW) distance serves as a powerful tool for matching objects in metric spaces. However, its traditional formulation is constrained to pairwise matching between single objects, limiting its utility in scenarios and applications requiring multiple-to-one or multiple-to-multiple object matching. In this paper, we introduce the Joint Gromov-Wasserstein (JGW) objective and extend the original framework of GW to enable simultaneous matching between collections of objects. Our formulation provides a non-negative dissimilarity measure that identifies partially isomorphic distributions of mm-spaces, with point sampling convergence. We also show that the objective can be formulated and solved for point cloud representations by adapting traditional algorithms in Optimal Transport, including entropic regularization. Our benchmarking with other variants of GW for partial matching indicates superior performance in accuracy and computational efficiency of our method, while experiments on both synthetic and real-world datasets show its effectiveness for multiple shape matching, including geometric shapes and biomolecular complexes, suggesting promising applications for solving complex matching problems across diverse domains, including computer graphics and atomic model building for structural biology. --- ### Parts-Mamba: Augmenting Joint Context with Part-Level Scanning for Occluded Human Skeleton Authors: Tianyi Shen, Huijuan Xu, Nilesh Ahuja, Omesh Tickoo, Philip Shin, Vijaykrishnan Narayanan Published: 2025-11-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.16860v1 Skeleton action recognition involves recognizing human action from human skeletons. The use of graph convolutional networks (GCNs) has driven major advances in this recognition task. In real-world scenarios, the captured skeletons are not always perfect or complete because of occlusions of parts of the human body or poor communication quality, leading to missing parts in skeletons or videos with missing frames. In the presence of such non-idealities, existing GCN models perform poorly due to missing local context. To address this limitation, we propose Parts-Mamba, a hybrid GCN-Mamba model designed to enhance the ability to capture and maintain contextual information from distant joints. The proposed Parts-Mamba model effectively captures part-specific information through its parts-specific scanning feature and preserves non-neighboring joint context via a parts-body fusion module. Our proposed model is evaluated on the NTU RGB+D 60 and NTU RGB+D 120 datasets under different occlusion settings, achieving up to 12.9% improvement in accuracy. --- ### "Jutters" Authors: Meike Driessen, Selina Khan, Gonçalo Marcelino Published: 2025-11-20 Categories: cs.HC, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2601.11532v1 This project explores how we engage with AI-generated content through the lens of the jutter: Dutch coastal foragers who comb the shoreline after storms, gathering and repurposing what the sea leaves behind. Reflecting how our lives are increasingly shaped by AI-generated media, we create a beach-like installation that blends real shoreline debris with AI-transformed images and videos. Visitors are invited to explore this space as contemporary jutters, deciding what to keep and what to discard. In doing so, the project reimagines AI-imagery as material for reflection, encouraging a more discerning engagement with the content that drifts through our feeds. A video preview of the installation can be found at https://www.youtube.com/watch?v=L6319Ii7MT8. --- ### NOVAID: Natural-language Observability Visualization Assistant for ITOps Dashboard Widget Generation Authors: Pratik Mishra, Caner Gözübüyük, Seema Nagar, Prateeti Mohapatra, Raya Wittich, Arthur de Magalhaes Published: 2025-11-20 Categories: cs.HC, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2601.11531v1 Manual creation of IT monitoring dashboard widgets is slow, error-prone, and a barrier for both novice and expert users. We present NOVAID, an interactive chatbot that leverages Large Language Models (LLMs) to generate IT monitoring widgets directly from natural language queries. Unlike general natural language-to-visualization tools, NOVAID addresses IT operations-specific challenges: specialized widget types like SLO charts, dynamic API-driven data retrieval, and complex contextual filters. The system combines a domain-aware semantic parser, fuzzy entity matching, and schema completion to produce standardized widget JSON specifications. An interactive clarification loop ensures accuracy in underspecified queries. On a curated dataset of 271 realistic queries, NOVAID achieves promising accuracy (up to 94.10% in metric extraction) across multiple LLMs. A user study with IT engineers yielded a System Usability Scale score of 74.2 for NOVAID, indicating good usability. By bridging natural language intent with operational dashboards, NOVAID demonstrates clear potential and a path for deployment in enterprise ITOps monitoring platforms. --- ### The Linguistic Architecture of Reflective Thought: Evaluation of a Large Language Model as a Tool to Isolate the Formal Structure of Mentalization Authors: Stefano Epifani, Giuliano Castigliego, Laura Kecskemeti, Giuliano Razzicchia, Elisabeth Seiwald-Sonderegger Published: 2025-11-20 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.08945v1 Background: Mentalization integrates cognitive, affective, and intersubjective components. Large Language Models (LLMs) display an increasing ability to generate reflective texts, raising questions regarding the relationship between linguistic form and mental representation. This study assesses the extent to which a single LLM can reproduce the linguistic structure of mentalization according to the parameters of Mentalization-Based Treatment (MBT). Methods: Fifty dialogues were generated between human participants and an LLM configured in standard mode. Five psychiatrists trained in MBT, working under blinded conditions, evaluated the mentalization profiles produced by the model along the four MBT axes, assigning Likert-scale scores for evaluative coherence, argumentative coherence, and global quality. Inter-rater agreement was estimated using ICC(3,1). Results: Mean scores (3.63-3.98) and moderate standard deviations indicate a high level of structural coherence in the generated profiles. ICC values (0.60-0.84) show substantial-to-high agreement among raters. The model proved more stable in the Implicit-Explicit and Self-Other dimensions, while presenting limitations in the integration of internal states and external contexts. The profiles were coherent and clinically interpretable yet characterized by affective neutrality. --- ### A Multi-objective Optimization Approach for Feature Selection in Gentelligent Systems Authors: Mohammadhossein Ghahramani, Yan Qiao, NaiQi Wu, Mengchu Zhou Published: 2025-11-20 Categories: cs.NE, cs.AI arXiv: https://arxiv.org/abs/2512.05971v1 The integration of advanced technologies, such as Artificial Intelligence (AI), into manufacturing processes is attracting significant attention, paving the way for the development of intelligent systems that enhance efficiency and automation. This paper uses the term "Gentelligent system" to refer to systems that incorporate inherent component information (akin to genes in bioinformatics-where manufacturing operations are likened to chromosomes in this study) and automated mechanisms. By implementing reliable fault detection methods, manufacturers can achieve several benefits, including improved product quality, increased yield, and reduced production costs. To support these objectives, we propose a hybrid framework with a dominance-based multi-objective evolutionary algorithm. This mechanism enables simultaneous optimization of feature selection and classification performance by exploring Pareto-optimal solutions in a single run. This solution helps monitor various manufacturing operations, addressing a range of conflicting objectives that need to be minimized together. Manufacturers can leverage such predictive methods and better adapt to emerging trends. To strengthen the validation of our model, we incorporate two real-world datasets from different industrial domains. The results on both datasets demonstrate the generalizability and effectiveness of our approach. --- ### Memory-DD: A Low-Complexity Dendrite-Inspired Neuron for Temporal Prediction Tasks Authors: Dongjian Yang, Xiaoyuan Li, Chuanmei Xi, Ye Sun, Gang Liu Published: 2025-11-20 Categories: cs.NE, cs.AI arXiv: https://arxiv.org/abs/2512.04094v1 Dendrite-inspired neurons have been widely used in tasks such as image classification due to low computational complexity and fast inference speed. Temporal data prediction, as a key machine learning task, plays a key role in real-time scenarios such as sensor data analysis, financial forecasting, and urban traffic management. However, existing dendrite-inspired neurons are mainly designed for static data. Studies on capturing dynamic features and modeling long-term dependencies in temporal sequences remain limited. Efficient architectures specifically designed for temporal sequence prediction are still lacking. In this paper, we propose Memory-DD, a low-complexity dendrite-inspired neuron model. Memory-DD consists of two dendrite-inspired neuron groups that contain no nonlinear activation functions but can still realize nonlinear mappings. Compared with traditional neurons without dendritic functions, Memory-DD requires only two neuron groups to extract logical relationships between features in input sequences. This design effectively captures temporal dependencies and is suitable for both classification and regression tasks on sequence data. Experimental results show that Memory-DD achieves an average accuracy of 89.41% on 18 temporal classification benchmark datasets, outperforming LSTM by 4.25%. On 9 temporal regression datasets, it reaches comparable performance to LSTM, while using only 50% of the parameters and reducing computational complexity (FLOPs) by 27.7%. These results demonstrate that Memory-DD successfully extends the low-complexity advantages of dendrite-inspired neurons to temporal prediction, providing a low-complexity and efficient solution for time-series data processing. --- ### Statistical Arbitrage in Polish Equities Market Using Deep Learning Techniques Authors: Marek Adamczyk, Michał Dąbrowski Published: 2025-11-20 Categories: q-fin.ST, cs.AI arXiv: https://arxiv.org/abs/2512.02037v1 We study a systematic approach to a popular Statistical Arbitrage technique: Pairs Trading. Instead of relying on two highly correlated assets, we replace the second asset with a replication of the first using risk factor representations. These factors are obtained through Principal Components Analysis (PCA), exchange traded funds (ETFs), and, as our main contribution, Long Short Term Memory networks (LSTMs). Residuals between the main asset and its replication are examined for mean reversion properties, and trading signals are generated for sufficiently fast mean reverting portfolios. Beyond introducing a deep learning based replication method, we adapt the framework of Avellaneda and Lee (2008) to the Polish market. Accordingly, components of WIG20, mWIG40, and selected sector indices replace the original S&P500 universe, and market parameters such as the risk free rate and transaction costs are updated to reflect local conditions. We outline the full strategy pipeline: risk factor construction, residual modeling via the Ornstein Uhlenbeck process, and signal generation. Each replication technique is described together with its practical implementation. Strategy performance is evaluated over two periods: 2017-2019 and the recessive year 2020. All methods yield profits in 2017-2019, with PCA achieving roughly 20 percent cumulative return and an annualized Sharpe ratio of up to 2.63. Despite multiple adaptations, our conclusions remain consistent with those of the original paper. During the COVID-19 recession, only the ETF based approach remains profitable (about 5 percent annual return), while PCA and LSTM methods underperform. LSTM results, although negative, are promising and indicate potential for future optimization. --- ### Integration of LSTM Networks in Random Forest Algorithms for Stock Market Trading Predictions Authors: Juan C. King, Jose M. Amigo Published: 2025-11-20 Categories: q-fin.CP, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.02036v1 The aim of this paper is the analysis and selection of stock trading systems that combine different models with data of different nature, such as financial and microeconomic information. Specifically, based on previous work by the authors and applying advanced techniques of Machine Learning and Deep Learning, our objective is to formulate trading algorithms for the stock market with empirically tested statistical advantages, thus improving results published in the literature. Our approach integrates Long Short-Term Memory (LSTM) networks with algorithms based on decision trees, such as Random Forest and Gradient Boosting. While the former analyze price patterns of financial assets, the latter are fed with economic data of companies. Numerical simulations of algorithmic trading with data from international companies and 10-weekday predictions confirm that an approach based on both fundamental and technical variables can outperform the usual approaches, which do not combine those two types of variables. In doing so, Random Forest turned out to be the best performer among the decision trees. We also discuss how the prediction performance of such a hybrid approach can be boosted by selecting the technical variables. --- ### CONFIDE: Hallucination Assessment for Reliable Biomolecular Structure Prediction and Design Authors: Zijun Gao, Mutian He, Shijia Sun, Hanqun Cao, Jingjie Zhang, Zihao Luo, Xiaorui Wang, Xiaojun Yao, Chang-Yu Hsieh, Chunbin Gu, Pheng Ann Heng Published: 2025-11-20 Categories: q-bio.BM, cs.AI arXiv: https://arxiv.org/abs/2512.02033v1 Reliable evaluation of protein structure predictions remains challenging, as metrics like pLDDT capture energetic stability but often miss subtle errors such as atomic clashes or conformational traps reflecting topological frustration within the protein folding energy landscape. We present CODE (Chain of Diffusion Embeddings), a self evaluating metric empirically found to quantify topological frustration directly from the latent diffusion embeddings of the AlphaFold3 series of structure predictors in a fully unsupervised manner. Integrating this with pLDDT, we propose CONFIDE, a unified evaluation framework that combines energetic and topological perspectives to improve the reliability of AlphaFold3 and related models. CODE strongly correlates with protein folding rates driven by topological frustration, achieving a correlation of 0.82 compared to pLDDT's 0.33 (a relative improvement of 148\%). CONFIDE significantly enhances the reliability of quality evaluation in molecular glue structure prediction benchmarks, achieving a Spearman correlation of 0.73 with RMSD, compared to pLDDT's correlation of 0.42, a relative improvement of 73.8\%. Beyond quality assessment, our approach applies to diverse drug design tasks, including all-atom binder design, enzymatic active site mapping, mutation induced binding affinity prediction, nucleic acid aptamer screening, and flexible protein modeling. By combining data driven embeddings with theoretical insight, CODE and CONFIDE outperform existing metrics across a wide range of biomolecular systems, offering robust and versatile tools to refine structure predictions, advance structural biology, and accelerate drug discovery. --- ### Characterizing Continuous and Discrete Hybrid Latent Spaces for Structural Connectomes Authors: Gaurav Rudravaram, Lianrui Zuo, Adam M. Saunders, Michael E. Kim, Praitayini Kanakaraj, Nancy R. Newlin, Aravind R. Krishnan, Elyssa M. McMaster, Chloe Cho, Susan M. Resnick, Lori L. Beason Held, Derek Archer et al. Published: 2025-11-20 Categories: q-bio.NC, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.02032v1 Structural connectomes are detailed graphs that map how different brain regions are physically connected, offering critical insight into aging, cognition, and neurodegenerative diseases. However, these connectomes are high-dimensional and densely interconnected, which makes them difficult to interpret and analyze at scale. While low-dimensional spaces like PCA and autoencoders are often used to capture major sources of variation, their latent spaces are generally continuous and cannot fully reflect the mixed nature of variability in connectomes, which include both continuous (e.g., connectivity strength) and discrete factors (e.g., imaging site). Motivated by this, we propose a variational autoencoder (VAE) with a hybrid latent space that jointly models the discrete and continuous components. We analyze a large dataset of 5,761 connectomes from six Alzheimer's disease studies with ten acquisition protocols. Each connectome represents a single scan from a unique subject (3579 females, 2182 males), aged 22 to 102, with 4338 cognitively normal, 809 with mild cognitive impairment (MCI), and 614 with Alzheimer's disease (AD). Each connectome contains 121 brain regions defined by the BrainCOLOR atlas. We train our hybrid VAE in an unsupervised way and characterize what each latent component captures. We find that the discrete space is particularly effective at capturing subtle site-related differences, achieving an Adjusted Rand Index (ARI) of 0.65 with site labels, significantly outperforming PCA and a standard VAE followed by clustering (p < 0.05). These results demonstrate that the hybrid latent space can disentangle distinct sources of variability in connectomes in an unsupervised manner, offering potential for large-scale connectome analysis. --- ### KAN-SAs: Efficient Acceleration of Kolmogorov-Arnold Networks on Systolic Arrays Authors: Sohaib Errabii, Olivier Sentieys, Marcello Traiola Published: 2025-11-20 Categories: cs.AR, cs.AI arXiv: https://arxiv.org/abs/2512.00055v1 Kolmogorov-Arnold Networks (KANs) have garnered significant attention for their promise of improved parameter efficiency and explainability compared to traditional Deep Neural Networks (DNNs). KANs' key innovation lies in the use of learnable non-linear activation functions, which are parametrized as splines. Splines are expressed as a linear combination of basis functions (B-splines). B-splines prove particularly challenging to accelerate due to their recursive definition. Systolic Array (SA)based architectures have shown great promise as DNN accelerators thanks to their energy efficiency and low latency. However, their suitability and efficiency in accelerating KANs have never been assessed. Thus, in this work, we explore the use of SA architecture to accelerate the KAN inference. We show that, while SAs can be used to accelerate part of the KAN inference, their utilization can be reduced to 30%. Hence, we propose KAN-SAs, a novel SA-based accelerator that leverages intrinsic properties of B-splines to enable efficient KAN inference. By including a nonrecursive B-spline implementation and leveraging the intrinsic KAN sparsity, KAN-SAs enhances conventional SAs, enabling efficient KAN inference, in addition to conventional DNNs. KAN-SAs achieves up to 100% SA utilization and up to 50% clock cycles reduction compared to conventional SAs of equivalent area, as shown by hardware synthesis results on a 28nm FD-SOI technology. We also evaluate different configurations of the accelerator on various KAN applications, confirming the improved efficiency of KAN inference provided by KAN-SAs. --- ### Goal-Directed Search Outperforms Goal-Agnostic Memory Compression in Long-Context Memory Tasks Authors: Yicong Zheng, Kevin L. McKee, Thomas Miconi, Zacharie Bugaud, Mick van Gelderen, Jed McCaleb Published: 2025-11-20 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.21726v1 How to enable human-like long-term memory in large language models (LLMs) has been a central question for unlocking more general capabilities such as few-shot generalization. Existing memory frameworks and benchmarks focus on finding the optimal memory compression algorithm for higher performance in tasks that require recollection and sometimes further reasoning. However, such efforts have ended up building more human bias into the compression algorithm, through the search for the best prompts and memory architectures that suit specific benchmarks, rather than finding a general solution that would work on other data distributions. On the other hand, goal-directed search on uncompressed information could potentially exhibit superior performance because compression is lossy, and a predefined compression algorithm will not fit all raw data distributions. Here we present SUMER (Search in Uncompressed Memory via Experience Replay), an end-to-end reinforcement learning agent with verifiable reward (RLVR) that learns to use search tools to gather information and answer a target question. On the LoCoMo dataset for long-context conversation understanding, SUMER with Qwen2.5-7B-Instruct learned to use search tools and outperformed all other biased memory compression approaches and also the full-context baseline, reaching SOTA performance (43% gain over the prior best). We demonstrate that a simple search method applied to raw data outperforms goal-agnostic and biased compression algorithms in current long-context memory tasks, arguing for new paradigms and benchmarks that are more dynamic and autonomously scalable. Code for SUMER and all implemented baselines is publicly available at https://github.com/zycyc/SUMER. --- ### PromptTailor: Multi-turn Intent-Aligned Prompt Synthesis for Lightweight LLMs Authors: Yizhou Xu, Janet Davis Published: 2025-11-20 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.21725v1 Lightweight language models remain attractive for on-device and privacy-sensitive applications, but their responses are highly sensitive to prompt quality. For open-ended generation, non-expert users often lack the knowledge or time to consistently craft high-quality prompts, leading them to rely on prompt optimization tools. However, a key challenge is ensuring the optimized prompts genuinely align with users' original intents and preferences. We introduce PromptTailor, a system for controllable prompt generation for open-ended text that improves model output quality by intent-aligned prompt synthesis. PromptTailor expands minimal user instructions into rich, domain-aware prompts while preserving the user's stated preferences. The system is a quantized Llama3-8B model fine-tuned with a lightweight LoRA adapter on 12,300 prompt-refinement dialogues spanning 41 everyday domains, distilled from three stronger LLMs. The adapter attaches to any Llama3-8B base, enabling edge deployment. In human and LLM-judge evaluations across multiple target models and optimization baselines, PromptTailor yields higher preference rates than chain-of-thought prompting and matches or surpasses state-of-the-art prompt optimization methods while requiring fewer model calls (e.g., 3 vs. 9). These results show that a compact student, guided by powerful teachers, can learn effective prompt-generation strategies that enhance response quality while maintaining alignment with user intent. --- ### AD-CDO: A Lightweight Ontology for Representing Eligibility Criteria in Alzheimer's Disease Clinical Trials Authors: Zenan Sun, Rashmie Abeysinghe, Xiaojin Li, Xinyue Hu, Licong Cui, Guo-Qiang Zhang, Jiang Bian, Cui Tao Published: 2025-11-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.21724v1 Objective This study introduces the Alzheimer's Disease Common Data Element Ontology for Clinical Trials (AD-CDO), a lightweight, semantically enriched ontology designed to represent and standardize key eligibility criteria concepts in Alzheimer's disease (AD) clinical trials. Materials and Methods We extracted high-frequency concepts from more than 1,500 AD clinical trials on ClinicalTrials.gov and organized them into seven semantic categories: Disease, Medication, Diagnostic Test, Procedure, Social Determinants of Health, Rating Criteria, and Fertility. Each concept was annotated with standard biomedical vocabularies, including the UMLS, OMOP Standardized Vocabularies, DrugBank, NDC, and NLM VSAC value sets. To balance coverage and manageability, we applied the Jenks Natural Breaks method to identify an optimal set of representative concepts. Results The optimized AD-CDO achieved over 63% coverage of extracted trial concepts while maintaining interpretability and compactness. The ontology effectively captured the most frequent and clinically meaningful entities used in AD eligibility criteria. We demonstrated AD-CDO's practical utility through two use cases: (a) an ontology-driven trial simulation system for formal modeling and virtual execution of clinical trials, and (b) an entity normalization task mapping raw clinical text to ontology-aligned terms, enabling consistency and integration with EHR data. Discussion AD-CDO bridges the gap between broad biomedical ontologies and task-specific trial modeling needs. It supports multiple downstream applications, including phenotyping algorithm development, cohort identification, and structured data integration. Conclusion By harmonizing essential eligibility entities and aligning them with standardized vocabularies, AD-CDO provides a versatile foundation for ontology-driven AD clinical trial research. --- ### Hybrid coupling with operator inference and the overlapping Schwarz alternating method Authors: Irina Tezaur, Eric Parish, Anthony Gruber, Ian Moore, Christopher Wentland, Alejandro Mota Published: 2025-11-20 Categories: math.NA, cs.AI, math-ph arXiv: https://arxiv.org/abs/2511.20687v4 This paper presents a novel hybrid approach for coupling subdomain-local non-intrusive Operator Inference (OpInf) reduced order models (ROMs) with each other and with subdomain-local high-fidelity full order models (FOMs) with using the overlapping Schwarz alternating method (O-SAM). The proposed methodology addresses significant challenges in multiscale modeling and simulation, particularly the long runtime and complex mesh generation requirements associated with traditional high-fidelity simulations. By leveraging the flexibility of O-SAM, we enable the seamless integration of disparate models, meshes, and time integration schemes, enhancing computational efficiency while maintaining high accuracy. Our approach is demonstrated through a series of numerical experiments on complex three-dimensional (3D) solid dynamics problems, showcasing speedups of up to 106x compared to conventional FOM-FOM couplings. This work paves the way for more efficient simulation workflows in engineering applications, with potential extensions to a wide range of partial differential equations. --- ### AssurAI: Experience with Constructing Korean Socio-cultural Datasets to Discover Potential Risks of Generative AI Authors: Chae-Gyun Lim, Seung-Ho Han, EunYoung Byun, Jeongyun Han, Soohyun Cho, Eojin Joo, Heehyeon Kim, Sieun Kim, Juhoon Lee, Hyunsoo Lee, Dongkun Lee, Jonghwan Hyeon et al. Published: 2025-11-20 Categories: cs.AI, cs.CY, cs.LG arXiv: https://arxiv.org/abs/2511.20686v1 The rapid evolution of generative AI necessitates robust safety evaluations. However, current safety datasets are predominantly English-centric, failing to capture specific risks in non-English, socio-cultural contexts such as Korean, and are often limited to the text modality. To address this gap, we introduce AssurAI, a new quality-controlled Korean multimodal dataset for evaluating the safety of generative AI. First, we define a taxonomy of 35 distinct AI risk factors, adapted from established frameworks by a multidisciplinary expert group to cover both universal harms and relevance to the Korean socio-cultural context. Second, leveraging this taxonomy, we construct and release AssurAI, a large-scale Korean multimodal dataset comprising 11,480 instances across text, image, video, and audio. Third, we apply the rigorous quality control process used to ensure data integrity, featuring a two-phase construction (i.e., expert-led seeding and crowdsourced scaling), triple independent annotation, and an iterative expert red-teaming loop. Our pilot study validates AssurAI's effectiveness in assessing the safety of recent LLMs. We release AssurAI to the public to facilitate the development of safer and more reliable generative AI systems for the Korean community. --- ### AI-based framework to predict animal and pen feed intake in feedlot beef cattle Authors: Alex S. C. Maia, John B. Hall, Hugo F. M. Milan, Izabelle A. M. A. Teixeira Published: 2025-11-20 Categories: cs.LG, cs.AI, eess.SY arXiv: https://arxiv.org/abs/2511.17663v1 Advances in technology are transforming sustainable cattle farming practices, with electronic feeding systems generating big longitudinal datasets on individual animal feed intake, offering the possibility for autonomous precision livestock systems. However, the literature still lacks a methodology that fully leverages these longitudinal big data to accurately predict feed intake accounting for environmental conditions. To fill this gap, we developed an AI-based framework to accurately predict feed intake of individual animals and pen-level aggregation. Data from 19 experiments (>16.5M samples; 2013-2024) conducted at Nancy M. Cummings Research Extension & Education Center (Carmen, ID) feedlot facility and environmental data from AgriMet Network weather stations were used to develop two novel environmental indices: InComfort-Index, based solely on meteorological variables, showed good predictive capability for thermal comfort but had limited ability to predict feed intake; EASI-Index, a hybrid index integrating environmental variables with feed intake behavior, performed well in predicting feed intake but was less effective for thermal comfort. Together with the environmental indices, machine learning models were trained and the best-performing machine learning model (XGBoost) accuracy was RMSE of 1.38 kg/day for animal-level and only 0.14 kg/(day-animal) at pen-level. This approach provides a robust AI-based framework for predicting feed intake in individual animals and pens, with potential applications in precision management of feedlot cattle, through feed waste reduction, resource optimization, and climate-adaptive livestock management. --- ### Enhancing Breast Cancer Prediction with LLM-Inferred Confounders Authors: Debmita Roy Published: 2025-11-20 Categories: cs.LG, q-bio.QM arXiv: https://arxiv.org/abs/2511.17662v1 This study enhances breast cancer prediction by using large language models to infer the likelihood of confounding diseases, namely diabetes, obesity, and cardiovascular disease, from routine clinical data. These AI-generated features improved Random Forest model performance, particularly for LLMs like Gemma (3.9%) and Llama (6.4%). The approach shows promise for noninvasive prescreening and clinical integration, supporting improved early detection and shared decision-making in breast cancer diagnosis. --- ### Frugality in second-order optimization: floating-point approximations for Newton's method Authors: Giuseppe Carrino, Elena Loli Piccolomini, Elisa Riccietti, Theo Mary Published: 2025-11-20 Categories: cs.LG, cs.AI, math.OC arXiv: https://arxiv.org/abs/2511.17660v1 Minimizing loss functions is central to machine-learning training. Although first-order methods dominate practical applications, higher-order techniques such as Newton's method can deliver greater accuracy and faster convergence, yet are often avoided due to their computational cost. This work analyzes the impact of finite-precision arithmetic on Newton steps and establishes a convergence theorem for mixed-precision Newton optimizers, including "quasi" and "inexact" variants. The theorem provides not only convergence guarantees but also a priori estimates of the achievable solution accuracy. Empirical evaluations on standard regression benchmarks demonstrate that the proposed methods outperform Adam on the Australian and MUSH datasets. The second part of the manuscript introduces GN_k, a generalized Gauss-Newton method that enables partial computation of second-order derivatives. GN_k attains performance comparable to full Newton's method on regression tasks while requiring significantly fewer derivative evaluations. --- ### Predicting Healthcare Provider Engagement in SMS Campaigns Authors: Daanish Aleem Qureshi, Rafay Chaudhary, Kok Seng Tan, Or Maoz, Scott Burian, Michael Gelber, Phillip Hoon Kang, Alan George Labouseur Published: 2025-11-20 Categories: physics.soc-ph, cs.AI, cs.CY, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2511.17658v1 As digital communication grows in importance when connecting with healthcare providers, traditional behavioral and content message features are imbued with renewed significance. If one is to meaningfully connect with them, it is crucial to understand what drives them to engage and respond. In this study, the authors analyzed several million text messages sent through the Impiricus platform to learn which factors influenced whether or not a doctor clicked on a link in a message. Several key insights came to light through the use of logistic regression, random forest, and neural network models, the details of which the authors discuss in this paper. --- ### Multi-Agent Coordination in Autonomous Vehicle Routing: A Simulation-Based Study of Communication, Memory, and Routing Loops Authors: KM Khalid Saifullah, Daniel Palmer Published: 2025-11-20 Categories: cs.MA, cs.LG, cs.RO arXiv: https://arxiv.org/abs/2511.17656v1 Multi-agent coordination is critical for next-generation autonomous vehicle (AV) systems, yet naive implementations of communication-based rerouting can lead to catastrophic performance degradation. This study investigates a fundamental problem in decentralized multi-agent navigation: routing loops, where vehicles without persistent obstacle memory become trapped in cycles of inefficient path recalculation. Through systematic simulation experiments involving 72 unique configurations across varying vehicle densities (15, 35, 55 vehicles) and obstacle frequencies (6, 20 obstacles), we demonstrate that memory-less reactive rerouting increases average travel time by up to 682% compared to baseline conditions. To address this, we introduce Object Memory Management (OMM), a lightweight mechanism enabling agents to retain and share knowledge of previously encountered obstacles. OMM operates by maintaining a distributed blacklist of blocked nodes, which each agent consults during Dijkstra-based path recalculation, effectively preventing redundant routing attempts. Our results show that OMM-enabled coordination reduces average travel time by 75.7% and wait time by 88% compared to memory-less systems, while requiring only 1.67 route recalculations per vehicle versus 9.83 in memory-less scenarios. This work provides empirical evidence that persistent, shared memory is not merely beneficial but essential for robust multi-agent coordination in dynamic environments. The findings have implications beyond autonomous vehicles, informing the design of decentralized systems in robotics, network routing, and distributed AI. We provide a comprehensive experimental analysis, including detailed scenario breakdowns, scalability assessments, and visual documentation of the routing loop phenomenon, demonstrating OMM's critical role in preventing detrimental feedback cycles in cooperative multi-agent systems. --- ### Intelligent Systems in Neuroimaging: Pioneering AI Techniques for Brain Tumor Detection Authors: Md. Mohaiminul Islam, Md. Mofazzal Hossen, Maher Ali Rusho, Nahiyan Nazah Ridita, Zarin Tasnia Shanta, Md. Simanto Haider, Ahmed Faizul Haque Dhrubo, Md. Khurshid Jahan, Mohammad Abdul Qayum Published: 2025-11-20 Categories: cs.CV, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2511.17655v2 This study deliberates on the application of advanced AI techniques for brain tumor classification through MRI, wherein the training includes the present best deep learning models to enhance diagnosis accuracy and the potential of usability in clinical practice. By combining custom convolutional models with pre-trained neural network architectures, our approach exposes the utmost performance in the classification of four classes: glioma, meningioma, pituitary tumors, and no-tumor cases. Assessing the models on a large dataset of over 7,000 MRI images focused on detection accuracy, computational efficiency, and generalization to unseen data. The results indicate that the Xception architecture surpasses all other were tested, obtaining a testing accuracy of 98.71% with the least validation loss. While presenting this case with findings that demonstrate AI as a probable scorer in brain tumor diagnosis, we demonstrate further motivation by reducing computational complexity toward real-world clinical deployment. These aspirations offer an abundant future for progress in automated neuroimaging diagnostics. --- ### Dialogue Diplomats: An End-to-End Multi-Agent Reinforcement Learning System for Automated Conflict Resolution and Consensus Building Authors: Deepak Bolleddu Published: 2025-11-20 Categories: cs.MA, cs.AI arXiv: https://arxiv.org/abs/2511.17654v1 Conflict resolution and consensus building represent critical challenges in multi-agent systems, negotiations, and collaborative decision-making processes. This paper introduces Dialogue Diplomats, a novel end-to-end multi-agent reinforcement learning (MARL) framework designed for automated conflict resolution and consensus building in complex, dynamic environments. The proposed system integrates advanced deep reinforcement learning architectures with dialogue-based negotiation protocols, enabling autonomous agents to engage in sophisticated conflict resolution through iterative communication and strategic adaptation. We present three primary contributions: first, a novel Hierarchical Consensus Network (HCN) architecture that combines attention mechanisms with graph neural networks to model inter-agent dependencies and conflict dynamics. second, a Progressive Negotiation Protocol (PNP) that structures multi-round dialogue interactions with adaptive concession strategies; and third, a Context-Aware Reward Shaping mechanism that balances individual agent objectives with collective consensus goals. --- ### TeamPath: Building MultiModal Pathology Experts with Reasoning AI Copilots Authors: Tianyu Liu, Weihao Xuan, Hao Wu, Peter Humphrey, Marcello DiStasio, Mohamed Kahila, Alfonso Garcia Tan, Heli Qi, Rui Yang, Simeng Han, Tinglin Huang, Fang Wu et al. Published: 2025-11-20 Categories: q-bio.QM, cs.CV arXiv: https://arxiv.org/abs/2511.17652v2 Advances in AI have introduced several strong models in computational pathology to usher it into the era of multi-modal diagnosis, analysis, and interpretation. However, the current pathology-specific visual language models still lack capacities in making the diagnosis with rigorous reasoning paths as well as handling divergent tasks, and thus, challenges of building AI Copilots for real scenarios still exist. Here we introduce TeamPath, an AI system powered by reinforcement learning and router-enhanced solutions based on large-scale histopathology multimodal datasets, to work as a virtual assistant for expert-level disease diagnosis, patch-level information summarization, and cross-modality generation to integrate transcriptomic information for clinical usage. We also collaborate with pathologists from Yale School of Medicine to demonstrate that TeamPath can assist them in working more efficiently by identifying and correcting expert conclusions and reasoning paths. We also discuss the human evaluation results to support the reasoning quality from TeamPath. Overall, TeamPath can flexibly choose the best settings according to the needs, and serve as an innovative and reliable system for information communication across different modalities and experts. --- ### SWITCH: Benchmarking Modeling and Handling of Tangible Interfaces in Long-horizon Embodied Scenarios Authors: Juntao Cheng, Wanyue Zhang, Zhiwei Yu, Shuo Ren, Zheqi He, Shaoxuan Xie, Guocai Yao, Jieru Lin, Börje F. Karlsson, Jiajun Zhang Published: 2025-11-20 Categories: cs.CV, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2511.17649v5 Tangible control interfaces (TCIs), such as appliance panels, remotes, elevators, and embedded GUIs, are a fundamental component of everyday human-built environments. Interacting with these interfaces requires agents not only to ground language in visual observations,but also to execute actions, track temporally evolving state changes, and verify whether intended outcomes have been achieved. However, existing benchmarks predominantly evaluate open-loop perception or single-step action execution, failing to capture this continuous cycle of interaction, feedback, and correction. We introduce SWITCH, a benchmark for closed-loop interactive reasoning with TCIs in realistic egocentric environments1. SWITCH comprises 1,170 temporally interactive videos across diverse functional categories, providing structured annotations of instructions, actions, state transitions, outcomes, and recovery behaviors over time. To probe generative world modeling, SWITCH also evaluates video generation models on interaction-centered tasks using both LLM-as-judge and human evaluation2.Experiments with frontier proprietary and opensource multimodal models reveal persistent weaknesses in fine-grained visual-temporal perception, outcome verification, and error recovery, highlighting SWITCH as a testbed for closed-loop embodied intelligence. --- ### MamTiff-CAD: Multi-Scale Latent Diffusion with Mamba+ for Complex Parametric Sequence Authors: Liyuan Deng, Yunpeng Bai, Yongkang Dai, Xiaoshui Huang, Hongping Gan, Dongshuo Huang, Hao jiacheng, Yilei Shi Published: 2025-11-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.17647v1 Parametric Computer-Aided Design (CAD) is crucial in industrial applications, yet existing approaches often struggle to generate long sequence parametric commands due to complex CAD models' geometric and topological constraints. To address this challenge, we propose MamTiff-CAD, a novel CAD parametric command sequences generation framework that leverages a Transformer-based diffusion model for multi-scale latent representations. Specifically, we design a novel autoencoder that integrates Mamba+ and Transformer, to transfer parameterized CAD sequences into latent representations. The Mamba+ block incorporates a forget gate mechanism to effectively capture long-range dependencies. The non-autoregressive Transformer decoder reconstructs the latent representations. A diffusion model based on multi-scale Transformer is then trained on these latent embeddings to learn the distribution of long sequence commands. In addition, we also construct a dataset that consists of long parametric sequences, which is up to 256 commands for a single CAD model. Experiments demonstrate that MamTiff-CAD achieves state-of-the-art performance on both reconstruction and generation tasks, confirming its effectiveness for long sequence (60-256) CAD model generation. --- ### BlockCert: Certified Blockwise Extraction of Transformer Mechanisms Authors: Sandro Andric Published: 2025-11-20 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2511.17645v1 Mechanistic interpretability aspires to reverse-engineer neural networks into explicit algorithms, while model editing seeks to modify specific behaviours without retraining. Both areas are typically evaluated with informal evidence and ad-hoc experiments, with few explicit guarantees about how far an extracted or edited model can drift from the original on relevant inputs. We introduce BlockCert, a framework for certified blockwise extraction of transformer mechanisms, and outline how a lightweight extension can support certified local edits. Given a pre-trained transformer and a prompt distribution, BlockCert extracts structured surrogate implementations for residual blocks together with machine-checkable certificates that bound approximation error, record coverage metrics, and hash the underlying artifacts. We formalize a simple Lipschitz-based composition theorem in Lean 4 that lifts these local guarantees to a global deviation bound. Empirically, we apply the framework to GPT-2 small, TinyLlama-1.1B-Chat, and Llama-3.2-3B. Across these models we obtain high per-block coverage and small residual errors on the evaluated prompts, and in the TinyLlama setting we show that a fully stitched model matches the baseline perplexity within approximately 6e-5 on stress prompts. Our results suggest that blockwise extraction with explicit certificates is feasible for real transformer language models and offers a practical bridge between mechanistic interpretability and formal reasoning about model behaviour. --- ### Hybrid Neuro-Symbolic Models for Ethical AI in Risk-Sensitive Domains Authors: Chaitanya Kumar Kolli Published: 2025-11-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.17644v1 Artificial intelligence deployed in risk-sensitive domains such as healthcare, finance, and security must not only achieve predictive accuracy but also ensure transparency, ethical alignment, and compliance with regulatory expectations. Hybrid neuro symbolic models combine the pattern-recognition strengths of neural networks with the interpretability and logical rigor of symbolic reasoning, making them well-suited for these contexts. This paper surveys hybrid architectures, ethical design considerations, and deployment patterns that balance accuracy with accountability. We highlight techniques for integrating knowledge graphs with deep inference, embedding fairness-aware rules, and generating human-readable explanations. Through case studies in healthcare decision support, financial risk management, and autonomous infrastructure, we show how hybrid systems can deliver reliable and auditable AI. Finally, we outline evaluation protocols and future directions for scaling neuro symbolic frameworks in complex, high stakes environments. --- ### Fluid Grey 2: How Well Does Generative Adversarial Network Learn Deeper Topology Structure in Architecture That Matches Images? Authors: Yayan Qiu, Sean Hanna Published: 2025-11-20 Categories: cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2511.17643v1 Taking into account the regional characteristics of intrinsic and extrinsic properties of space is an essential issue in architectural design and urban renewal, which is often achieved step by step using image and graph-based GANs. However, each model nesting and data conversion may cause information loss, and it is necessary to streamline the tools to facilitate architects and users to participate in the design. Therefore, this study hopes to prove that I2I GAN also has the potential to recognize topological relationships autonomously. Therefore, this research proposes a method for quickly detecting the ability of pix2pix to learn topological relationships, which is achieved by adding two Grasshopper-based detection modules before and after GAN. At the same time, quantitative data is provided and its learning process is visualized, and changes in different input modes such as greyscale and RGB affect its learning efficiency. There are two innovations in this paper: 1) It proves that pix2pix can automatically learn spatial topological relationships and apply them to architectural design. 2) It fills the gap in detecting the performance of Image-based Generation GAN from a topological perspective. Moreover, the detection method proposed in this study takes a short time and is simple to operate. The two detection modules can be widely used for customizing image datasets with the same topological structure and for batch detection of topological relationships of images. In the future, this paper may provide a theoretical foundation and data support for the application of architectural design and urban renewal that use GAN to preserve spatial topological characteristics. --- ### Is Phase Really Needed for Weakly-Supervised Dereverberation ? Authors: Marius Rodrigues, Louis Bahrman, Roland Badeau, Gaël Richard Published: 2025-11-20 Categories: cs.SD, cs.AI, eess.SP, physics.class-ph, stat.ML arXiv: https://arxiv.org/abs/2511.17346v1 In unsupervised or weakly-supervised approaches for speech dereverberation, the target clean (dry) signals are considered to be unknown during training. In that context, evaluating to what extent information can be retrieved from the sole knowledge of reverberant (wet) speech becomes critical. This work investigates the role of the reverberant (wet) phase in the time-frequency domain. Based on Statistical Wave Field Theory, we show that late reverberation perturbs phase components with white, uniformly distributed noise, except at low frequencies. Consequently, the wet phase carries limited useful information and is not essential for weakly supervised dereverberation. To validate this finding, we train dereverberation models under a recent weak supervision framework and demonstrate that performance can be significantly improved by excluding the reverberant phase from the loss function. --- ### Investigating Test Overfitting on SWE-bench Authors: Toufique Ahmed, Jatin Ganhotra, Avraham Shinnar, Martin Hirzel Published: 2025-11-20 Categories: cs.SE, cs.LG arXiv: https://arxiv.org/abs/2511.16858v3 Tests can be useful towards resolving issues on code repositories. However, relying too much on tests for issue resolution can lead to code that technically passes observed tests but actually misses important cases or even breaks functionality. This problem, called test overfitting, is exacerbated by the fact that issues usually lack readily executable tests. Instead, several issue resolution systems use tests auto-generated from issues, which may be imperfect. Some systems even iteratively refine code and tests jointly. This paper presents the first empirical study of test overfitting in this setting. --- ### BOP-ASK: Object-Interaction Reasoning for Vision-Language Models Authors: Vineet Bhat, Sungsu Kim, Valts Blukis, Greg Heinrich, Prashanth Krishnamurthy, Ramesh Karri, Stan Birchfield, Farshad Khorrami, Jonathan Tremblay Published: 2025-11-20 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2511.16857v3 Vision Language Models (VLMs) have achieved impressive performance on spatial reasoning benchmarks, yet these evaluations mask critical weaknesses in understanding object interactions. Current benchmarks test high level relationships ('left of,' 'behind', etc.) but ignore fine-grained spatial understanding needed for real world applications: precise 3D localization, physical compatibility between objects, object affordances and multi step spatial planning. In this work, we present BOP-ASK, a novel large scale dataset for object interaction reasoning for both training and benchmarking. Our data generation pipeline leverages 6D object poses from the Benchmark for Object Pose Estimation (BOP) datasets from which we derive fine grained annotations such as grasp poses, referred object poses, path planning trajectories, relative spatial and depth relationships, and object-to-object relationships. BOP-ASK comprises over 150k images and 33M question answer pairs spanning six tasks (four novel), providing a rich resource for training and evaluating VLMs. We evaluate proprietary and open sourced VLMs, and conduct human evaluations on BOP-ASK-core, a contributed test benchmark. We also release BOP-ASK-lab, an out-of-distribution benchmark with images not sourced from BOP, enabling testing of generalization. Our experiments demonstrate that models trained on BOP-ASK outperform baselines and exhibit emergent capabilities such as precise object and grasp pose estimation, trajectory planning, and fine-grained object-centric spatial reasoning in cluttered environments. --- ### The use of vocal biomarkers in the detection of Parkinson's disease: a robust statistical performance comparison of classic machine learning models Authors: Katia Pires Nascimento do Sacramento, Elliot Q. C. Garcia, Nicéias Silva Vilela, Vinicius P. Sacramento, Tiago A. E. Ferreira Published: 2025-11-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.16856v1 Parkinson's disease (PD) is a progressive neurodegenerative disorder that, in addition to directly impairing functional mobility, is frequently associated with vocal impairments such as hypophonia and dysarthria, which typically manifest in the early stages. The use of vocal biomarkers to support the early diagnosis of PD presents a non-invasive, low-cost, and accessible alternative in clinical settings. Thus, the objective of this cross-sectional study was to consistently evaluate the effectiveness of a Deep Neural Network (DNN) in distinguishing individuals with Parkinson's disease from healthy controls, in comparison with traditional Machine Learning (ML) methods, using vocal biomarkers. Two publicly available voice datasets were used. Mel-frequency cepstral coefficients (MFCCs) were extracted from the samples, and model robustness was assessed using a validation strategy with 1000 independent random executions. Performance was evaluated using classification statistics. Since normality assumptions were not satisfied, non-parametric tests (Kruskal-Wallis and Bonferroni post-hoc tests) were applied to verify whether the tested classification models were similar or different in the classification of PD. With an average accuracy of $98.65\%$ and $92.11\%$ on the Italian Voice dataset and Parkinson's Telemonitoring dataset, respectively, the DNN demonstrated superior performance and efficiency compared to traditional ML models, while also achieving competitive results when benchmarked against relevant studies. Overall, this study confirms the efficiency of DNNs and emphasizes their potential to provide greater accuracy and reliability for the early detection of neurodegenerative diseases using voice-based biomarkers. --- ### MRI Super-Resolution with Deep Learning: A Comprehensive Survey Authors: Mohammad Khateri, Serge Vasylechko, Morteza Ghahremani, Liam Timms, Deniz Kocanaogullari, Simon K. Warfield, Camilo Jaimes, Davood Karimi, Alejandra Sierra, Jussi Tohka, Sila Kurugol, Onur Afacan Published: 2025-11-20 Categories: eess.IV, cs.AI, cs.CV, eess.SP arXiv: https://arxiv.org/abs/2511.16854v3 High-resolution (HR) magnetic resonance imaging (MRI) is crucial for many clinical and research applications. However, achieving it remains costly and constrained by technical trade-offs and experimental limitations. Super-resolution (SR) presents a promising computational approach to overcome these challenges by generating HR images from more affordable low-resolution (LR) scans, potentially improving diagnostic accuracy and efficiency without requiring additional hardware. This survey reviews recent advances in MRI SR techniques, with a focus on deep learning (DL) approaches. It examines DL-based MRI SR methods from the perspectives of computer vision, computational imaging, inverse problems, and MR physics, covering theoretical foundations, architectural designs, learning strategies, benchmark datasets, and performance metrics. We propose a systematic taxonomy to categorize these methods and present an in-depth study of both established and emerging SR techniques applicable to MRI, considering unique challenges in clinical and research contexts. We also highlight open challenges and directions that the community needs to address. Additionally, we provide a collection of essential open-access resources, tools, and tutorials, available on our GitHub: https://github.com/mkhateri/Awesome-MRI-Super-Resolution. IEEE keywords: MRI, Super-Resolution, Deep Learning, Computational Imaging, Inverse Problem, Survey. --- ### Towards Unified Vision Language Models for Forest Ecological Analysis in Earth Observation Authors: Xizhe Xue, Xiao Xiang Zhu Published: 2025-11-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.16853v1 Recent progress in vision language models (VLMs) has enabled remarkable perception and reasoning capabilities, yet their potential for scientific regression in Earth Observation (EO) remains largely unexplored. Existing EO datasets mainly emphasize semantic understanding tasks such as captioning or classification, lacking benchmarks that align multimodal perception with measurable biophysical variables. To fill this gap, we present REO-Instruct, the first unified benchmark designed for both descriptive and regression tasks in EO. REO-Instruct establishes a cognitively interpretable logic chain in forest ecological scenario (human activity,land-cover classification, ecological patch counting, above-ground biomass (AGB) regression), bridging qualitative understanding and quantitative prediction. The dataset integrates co-registered Sentinel-2 and ALOS-2 imagery with structured textual annotations generated and validated through a hybrid human AI pipeline. Comprehensive evaluation protocols and baseline results across generic VLMs reveal that current models struggle with numeric reasoning, highlighting an essential challenge for scientific VLMs. REO-Instruct offers a standardized foundation for developing and assessing next-generation geospatial models capable of both description and scientific inference. The project page are publicly available at \href{https://github.com/zhu-xlab/REO-Instruct}{REO-Instruct}. --- ### Better audio representations are more brain-like: linking model-brain alignment with performance in downstream auditory tasks Authors: Leonardo Pepino, Pablo Riera, Juan Kamienkowski, Luciana Ferrer Published: 2025-11-20 Categories: cs.LG, cs.SD arXiv: https://arxiv.org/abs/2511.16849v2 Artificial neural networks are increasingly powerful models of brain computation, yet it remains unclear whether improving their performance in downstream tasks also makes their internal representations more similar to brain signals. To address this question in the auditory domain, we quantified the alignment between the internal representations of 36 different audio models and brain activity from two independent fMRI datasets. Using voxel-wise and component-wise regression, and representation similarity analysis, we found that recent self-supervised audio models with strong performance in diverse downstream tasks are better predictors of auditory cortex activity than previously studied models. To assess the quality of the audio representations, we evaluated these models in 6 auditory tasks from the HEAREval benchmark, spanning music, speech, and environmental sounds. This revealed strong positive Pearson correlations (r > 0.8) between a model's overall task performance and its alignment with brain representations. Finally, we analyzed the evolution of the similarity between audio and brain representations during the pretraining of EnCodecMAE, a recent audio representation model. We discovered that brain similarity increases progressively and emerges early during pretraining, despite the model not being explicitly optimized for this objective. This suggests that brain-like representations can be an emergent byproduct of learning to reconstruct missing information from naturalistic audio data. --- ### Sex and age determination in European lobsters using AI-Enhanced bioacoustics Authors: Feliciano Pedro Francisco Domingos, Isibor Kennedy Ihianle, Omprakash Kaiwartya, Ahmad Lotfi, Nicola Khan, Nicholas Beaudreau, Amaya Albalat, Pedro Machado Published: 2025-11-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.16848v1 Monitoring aquatic species, especially elusive ones like lobsters, presents challenges. This study focuses on Homarus gammarus (European lobster), a key species for fisheries and aquaculture, and leverages non-invasive Passive Acoustic Monitoring (PAM). Understanding lobster habitats, welfare, reproduction, sex, and age is crucial for management and conservation. While bioacoustic emissions have classified various aquatic species using Artificial Intelligence (AI) models, this research specifically uses H. gammarus bioacoustics (buzzing/carapace vibrations) to classify lobsters by age (juvenile/adult) and sex (male/female). The dataset was collected at Johnshaven, Scotland, using hydrophones in concrete tanks. We explored the efficacy of Deep Learning (DL) models (1D-CNN, 1D-DCNN) and six Machine Learning (ML) models (SVM, k-NN, Naive Bayes, Random Forest, XGBoost, MLP). Mel-frequency cepstral coefficients (MFCCs) were used as features. For age classification (adult vs. juvenile), most models achieved over 97% accuracy (Naive Bayes: 91.31%). For sex classification, all models except Naive Bayes surpassed 93.23%. These strong results demonstrate the potential of supervised ML and DL to extract age- and sex-related features from lobster sounds. This research offers a promising non-invasive PAM approach for lobster conservation, detection, and management in aquaculture and fisheries, enabling real-world edge computing applications for underwater species. --- ### ConCISE: A Reference-Free Conciseness Evaluation Metric for LLM-Generated Answers Authors: Seyed Mohssen Ghafari, Ronny Kol, Juan C. Quiroz, Nella Luan, Monika Patial, Chanaka Rupasinghe, Herman Wandabwa, Luiz Pizzato Published: 2025-11-20 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.16846v2 Large language models (LLMs) frequently generate responses that are lengthy and verbose, filled with redundant or unnecessary details. This diminishes clarity and user satisfaction, and it increases costs for model developers, especially with well-known proprietary models that charge based on the number of output tokens. In this paper, we introduce a novel reference-free metric for evaluating the conciseness of responses generated by LLMs. Our method quantifies non-essential content without relying on gold standard references and calculates the average of three calculations: i) a compression ratio between the original response and an LLM abstractive summary; ii) a compression ratio between the original response and an LLM extractive summary; and iii) wordremoval compression, where an LLM removes as many non-essential words as possible from the response while preserving its meaning, with the number of tokens removed indicating the conciseness score. Experimental results demonstrate that our proposed metric identifies redundancy in LLM outputs, offering a practical tool for automated evaluation of response brevity in conversational AI systems without the need for ground truth human annotations. --- ### Provably Minimum-Length Conformal Prediction Sets for Ordinal Classification Authors: Zijian Zhang, Xinyu Chen, Yuanjie Shi, Liyuan Lillian Ma, Zifan Xu, Yan Yan Published: 2025-11-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.16845v1 Ordinal classification has been widely applied in many high-stakes applications, e.g., medical imaging and diagnosis, where reliable uncertainty quantification (UQ) is essential for decision making. Conformal prediction (CP) is a general UQ framework that provides statistically valid guarantees, which is especially useful in practice. However, prior ordinal CP methods mainly focus on heuristic algorithms or restrictively require the underlying model to predict a unimodal distribution over ordinal labels. Consequently, they provide limited insight into coverage-efficiency trade-offs, or a model-agnostic and distribution-free nature favored by CP methods. To this end, we fill this gap by propose an ordinal-CP method that is model-agnostic and provides instance-level optimal prediction intervals. Specifically, we formulate conformal ordinal classification as a minimum-length covering problem at the instance level. To solve this problem, we develop a sliding-window algorithm that is optimal on each calibration data, with only a linear time complexity in K, the number of label candidates. The local optimality per instance further also improves predictive efficiency in expectation. Moreover, we propose a length-regularized variant that shrinks prediction set size while preserving coverage. Experiments on four benchmark datasets from diverse domains are conducted to demonstrate the significantly improved predictive efficiency of the proposed methods over baselines (by 15% decrease on average over four datasets). --- ### Fantastic Bugs and Where to Find Them in AI Benchmarks Authors: Sang Truong, Yuheng Tu, Michael Hardy, Anka Reuel, Zeyu Tang, Jirayu Burapacheep, Jonathan Perera, Chibuike Uwakwe, Ben Domingue, Nick Haber, Sanmi Koyejo Published: 2025-11-20 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2511.16842v1 Benchmarks are pivotal in driving AI progress, and invalid benchmark questions frequently undermine their reliability. Manually identifying and correcting errors among thousands of benchmark questions is not only infeasible but also a critical bottleneck for reliable evaluation. In this work, we introduce a framework for systematic benchmark revision that leverages statistical analysis of response patterns to flag potentially invalid questions for further expert review. Our approach builds on a core assumption commonly used in AI evaluations that the mean score sufficiently summarizes model performance. This implies a unidimensional latent construct underlying the measurement experiment, yielding expected ranges for various statistics for each item. When empirically estimated values for these statistics fall outside the expected range for an item, the item is more likely to be problematic. Across nine widely used benchmarks, our method guides expert review to identify problematic questions with up to 84\% precision. In addition, we introduce an LLM-judge first pass to review questions, further reducing human effort. Together, these components provide an efficient and scalable framework for systematic benchmark revision. --- ### Trajectory-guided discharge stratification for heart failure using short-context electronic health record sequence modeling Authors: Falk Dippel, Yinan Yu, Annika Rosengren, Martin Lindgren, Christina E. Lundberg, Erik Aerts, Martin Adiels, Helen Sjöland Published: 2025-11-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.16839v4 Purpose: Heart failure (HF) discharge planning depends on identifying patients at risk of deterioration or death, yet accurate prediction from routinely collected electronic health records (EHRs) remains challenging. Methods: We develop trajectory-guided discharge stratification for heart failure (TGDS-HF), a methodology that reads the patient in-hospital trajectory of diagnoses, vital signs, laboratories, medications, and procedures end-to-end with a compact short-context autoregressive Transformer, and uses it to stratify one-year risks of clinical instability (a rehospitalization phenotype) or mortality for discharge care. We instantiate TGDS-HF on a Swedish HF cohort (N = 42,820) to predict one-year clinical instability or mortality at the initial HF diagnosis in-hospital. TGDS-HF has three components: category-level tokenization, recency-weighted temporal representation, and sequence model configuration. We run ablations on these components to show the effectiveness of TGDS-HF. Results: Against traditional eXtreme gradient boosting machine (XGBoost) and bidirectional encoder representations from Transformers (BERT)-based EHR sequence-modeling baselines, TGDS-HF (Llama backbone) achieved area under the precision-recall curves (AUPRCs) with 95% confidence intervals of 0.555 (0.535-0.575) and 0.574 (0.550-0.599) across the two tasks at the method default, with robust calibration. A task-specific refinement using daily aggregation of repeated continuous events improves the mortality task to 0.582 (0.558-0.608). Further, TGDS-HF maintains strong performance under reduced clinical concept availability and limited training data. Conclusion: Combined predictions of instability and mortality from TGDS-HF may support personalized discharge planning, ranging from follow-up in primary care to specialist-led management and, when appropriate, palliative care. ---