# Research Papers — 2025-11 · bundle page 24 of 197

> Full-text markdown of papers #1151–1200 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/24
[← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/23.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-11/page/25.md)

### The Risk-Adjusted Intelligence Dividend: A Quantitative Framework for Measuring AI Return on Investment Integrating ISO 42001 and Regulatory Exposure

Authors: Hernan Huwyler
Published: 2025-11-26
Categories: cs.CY, cs.AI, cs.CE, q-fin.RM
arXiv: https://arxiv.org/abs/2511.21975v1

Organizations investing in artificial intelligence face a fundamental challenge: traditional return on investment calculations fail to capture the dual nature of AI implementations, which simultaneously reduce certain operational risks while introducing novel exposures related to algorithmic malfunction, adversarial attacks, and regulatory liability. This research presents a comprehensive financial framework for quantifying AI project returns that explicitly integrates changes in organizational risk profiles. The methodology addresses a critical gap in current practice where investment decisions rely on optimistic benefit projections without accounting for the probabilistic costs of AI-specific threats including model drift, bias-related litigation, and compliance failures under emerging regulations such as the European Union Artificial Intelligence Act and ISO/IEC 42001. Drawing on established risk quantification methods, including annual loss expectancy calculations and Monte Carlo simulation techniques, this framework enables practitioners to compute net benefits that incorporate both productivity gains and the delta between pre-implementation and post-implementation risk exposures. The analysis demonstrates that accurate AI investment evaluation requires explicit modeling of control effectiveness, reserve requirements for algorithmic failures, and the ongoing operational costs of maintaining model performance. Practical implications include specific guidance for establishing governance structures, conducting phased validations, and integrating risk-adjusted metrics into capital allocation decisions, ultimately enabling evidence-based AI portfolio management that satisfies both fiduciary responsibilities and regulatory mandates.

---

### Start Making Sense(s): A Developmental Probe of Attention Specialization Using Lexical Ambiguity

Authors: Pamela D. Rivière, Sean Trott
Published: 2025-11-26
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.21974v1

Despite an in-principle understanding of self-attention matrix operations in Transformer language models (LMs), it remains unclear precisely how these operations map onto interpretable computations or functions--and how or when individual attention heads develop specialized attention patterns. Here, we present a pipeline to systematically probe attention mechanisms, and we illustrate its value by leveraging lexical ambiguity--where a single word has multiple meanings--to isolate attention mechanisms that contribute to word sense disambiguation. We take a "developmental" approach: first, using publicly available Pythia LM checkpoints, we identify inflection points in disambiguation performance for each LM in the suite; in 14M and 410M, we identify heads whose attention to disambiguating words covaries with overall disambiguation performance across development. We then stress-test the robustness of these heads to stimulus perturbations: in 14M, we find limited robustness, but in 410M, we identify multiple heads with surprisingly generalizable behavior. Then, in a causal analysis, we find that ablating the target heads demonstrably impairs disambiguation performance, particularly in 14M. We additionally reproduce developmental analyses of 14M across all of its random seeds. Together, these results suggest: that disambiguation benefits from a constellation of mechanisms, some of which (especially in 14M) are highly sensitive to the position and part-of-speech of the disambiguating cue; and that larger models (410M) may contain heads with more robust disambiguation behavior. They also join a growing body of work that highlights the value of adopting a developmental perspective when probing LM mechanisms.

---

### MOTIF-RF: Multi-template On-chip Transformer Synthesis Incorporating Frequency-domain Self-transfer Learning for RFIC Design Automation

Authors: Houbo He, Yizhou Xu, Lei Xia, Yaolong Hu, Fan Cai, Taiyun Chi
Published: 2025-11-26
Categories: cs.LG, eess.SP
arXiv: https://arxiv.org/abs/2511.21970v1

This paper presents a systematic study on developing multi-template machine learning (ML) surrogate models and applying them to the inverse design of transformers (XFMRs) in radio-frequency integrated circuits (RFICs). Our study starts with benchmarking four widely used ML architectures, including MLP-, CNN-, UNet-, and GT-based models, using the same datasets across different XFMR topologies. To improve modeling accuracy beyond these baselines, we then propose a new frequency-domain self-transfer learning technique that exploits correlations between adjacent frequency bands, leading to around 30%-50% accuracy improvement in the S-parameters prediction. Building on these models, we further develop an inverse design framework based on the covariance matrix adaptation evolutionary strategy (CMA-ES) algorithm. This framework is validated using multiple impedance-matching tasks, all demonstrating fast convergence and trustworthy performance. These results advance the goal of AI-assisted specs-to-GDS automation for RFICs and provide RFIC designers with actionable tools for integrating AI into their workflows.

---

### CTR Prediction on Alibaba's Taobao Advertising Dataset Using Traditional and Deep Learning Models

Authors: Hongyu Yang, Chunxi Wen, Jiyin Zhang, Nanfei Shen, Shijiao Zhang, Xiyan Han
Published: 2025-11-26
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.21963v1

Click-through rates prediction is critical in modern advertising systems, where ranking relevance and user engagement directly impact platform efficiency and business value. In this project, we explore how to model CTR more effectively using a large-scale Taobao dataset released by Alibaba. We start with supervised learning models, including logistic regression and Light-GBM, that are trained on static features such as user demographics, ad attributes, and contextual metadata. These models provide fast, interpretable benchmarks, but have limited capabilities to capture patterns of behavior that drive clicks. To better model user intent, we combined behavioral data from hundreds of millions of interactions over a 22-day period. By extracting and encoding user action sequences, we construct representations of user interests over time. We use deep learning models to fuse behavioral embeddings with static features. Among them, multilayer perceptrons (MLPs) have achieved significant performance improvements. To capture temporal dynamics, we designed a Transformer-based architecture that uses a self-attention mechanism to learn contextual dependencies across behavioral sequences, modeling not only what the user interacts with, but also the timing and frequency of interactions. Transformer improves AUC by 2.81 % over the baseline (LR model), with the largest gains observed for users whose interests are diverse or change over time. In addition to modeling, we propose an A/B testing strategy for real-world evaluation. We also think about the broader implications: personalized ad targeting technology can be applied to public health scenarios to achieve precise delivery of health information or behavior guidance. Our research provides a roadmap for advancing click-through rate predictions and extending their value beyond e-commerce.

---

### DeepGI: Explainable Deep Learning for Gastrointestinal Image Classification

Authors: Walid Houmaidi, Mohamed Hadadi, Youssef Sabiri, Yousra Chtouki
Published: 2025-11-26
Categories: cs.CV, cs.AI, cs.CY, cs.LG
arXiv: https://arxiv.org/abs/2511.21959v1

This paper presents a comprehensive comparative model analysis on a novel gastrointestinal medical imaging dataset, comprised of 4,000 endoscopic images spanning four critical disease classes: Diverticulosis, Neoplasm, Peritonitis, and Ureters. Leveraging state-of-the-art deep learning techniques, the study confronts common endoscopic challenges such as variable lighting, fluctuating camera angles, and frequent imaging artifacts. The best performing models, VGG16 and MobileNetV2, each achieved a test accuracy of 96.5%, while Xception reached 94.24%, establishing robust benchmarks and baselines for automated disease classification. In addition to strong classification performance, the approach includes explainable AI via Grad-CAM visualization, enabling identification of image regions most influential to model predictions and enhancing clinical interpretability. Experimental results demonstrate the potential for robust, accurate, and interpretable medical image analysis even in complex real-world conditions. This work contributes original benchmarks, comparative insights, and visual explanations, advancing the landscape of gastrointestinal computer-aided diagnosis and underscoring the importance of diverse, clinically relevant datasets and model explainability in medical AI research.

---

### ABLE: Using Adversarial Pairs to Construct Local Models for Explaining Model Predictions

Authors: Krishna Khadka, Sunny Shree, Pujan Budhathoki, Yu Lei, Raghu Kacker, D. Richard Kuhn
Published: 2025-11-26
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.21952v1

Machine learning models are increasingly used in critical applications but are mostly "black boxes" due to their lack of transparency. Local explanation approaches, such as LIME, address this issue by approximating the behavior of complex models near a test instance using simple, interpretable models. However, these approaches often suffer from instability and poor local fidelity. In this paper, we propose a novel approach called Adversarially Bracketed Local Explanation (ABLE) to address these limitations. Our approach first generates a set of neighborhood points near the test instance, x_test, by adding bounded Gaussian noise. For each neighborhood point D, we apply an adversarial attack to generate an adversarial point A with minimal perturbation that results in a different label than D. A second adversarial attack is then performed on A to generate a point A' that has the same label as D (and thus different than A). The points A and A' form an adversarial pair that brackets the local decision boundary for x_test. We then train a linear model on these adversarial pairs to approximate the local decision boundary. Experimental results on six UCI benchmark datasets across three deep neural network architectures demonstrate that our approach achieves higher stability and fidelity than the state-of-the-art.

---

### WalkCLIP: Multimodal Learning for Urban Walkability Prediction

Authors: Shilong Xiang, JangHyeon Lee, Min Namgung, Yao-Yi Chiang
Published: 2025-11-26
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.21947v1

Urban walkability is a cornerstone of public health, sustainability, and quality of life. Traditional walkability assessments rely on surveys and field audits, which are costly and difficult to scale. Recent studies have used satellite imagery, street view imagery, or population indicators to estimate walkability, but these single-source approaches capture only one dimension of the walking environment. Satellite data describe the built environment from above, but overlook the pedestrian perspective. Street view imagery captures conditions at the ground level, but lacks broader spatial context. Population dynamics reveal patterns of human activity but not the visual form of the environment. We introduce WalkCLIP, a multimodal framework that integrates these complementary viewpoints to predict urban walkability. WalkCLIP learns walkability-aware vision-language representations from GPT-4o generated image captions, refines these representations with a spatial aggregation module that incorporates neighborhood context, and fuses the resulting features with representations from a population dynamics foundation model. Evaluated at 4,660 locations throughout Minneapolis-Saint Paul, WalkCLIP outperforms unimodal and multimodal baselines in both predictive accuracy and spatial alignment. These results show that the integration of visual and behavioral signals yields reliable predictions of the walking environment.

---

### TAPVid-360: Tracking Any Point in 360 from Narrow Field of View Video

Authors: Finlay G. C. Hudson, James A. D. Gardner, William A. P. Smith
Published: 2025-11-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.21946v2

Humans excel at constructing panoramic mental models of their surroundings, maintaining object permanence and inferring scene structure beyond visible regions. In contrast, current artificial vision systems struggle with persistent, panoramic understanding, often processing scenes egocentrically on a frame-by-frame basis. This limitation is pronounced in the Track Any Point (TAP) task, where existing methods fail to track 2D points outside the field of view. To address this, we introduce TAPVid-360, a novel task that requires predicting the 3D direction to queried scene points across a video sequence, even when far outside the narrow field of view of the observed video. This task fosters learning allocentric scene representations without needing dynamic 4D ground truth scene models for training. Instead, we exploit 360 videos as a source of supervision, resampling them into narrow field-of-view perspectives while computing ground truth directions by tracking points across the full panorama using a 2D pipeline. We introduce a new dataset and benchmark, TAPVid360-10k comprising 10k perspective videos with ground truth directional point tracking. Our baseline adapts CoTracker v3 to predict per-point rotations for direction updates, outperforming existing TAP and TAPVid 3D methods. Project page: https://finlay-hudson.github.io/tapvid360

---

### GENA3D: Generative Amodal 3D Modeling by Bridging 2D Priors and 3D Coherence

Authors: Junwei Zhou, Yu-Wing Tai
Published: 2025-11-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.21945v3

Generating complete 3D objects under partial occlusions (i.e., amodal scenarios) is a practically important yet challenging problem, as large portions of object geometry are unobserved in real-world scenarios. Existing approaches either operate directly in 3D, which ensures geometric consistency but often lacks generative expressiveness, or rely on 2D amodal completion, which provides strong appearance priors but does not guarantee reliable 3D structure. This raises a key question: how can we achieve both generative plausibility and geometric coherence in amodal 3D modeling? To answer this question, we introduce GENA3D (GENarative Amodal 3D), a framework that integrates learned 2D generative priors with explicit 3D geometric reasoning within a conditional 3D generation paradigm. The 2D priors enable the model to plausibly infer diverse occluded content, while the 3D representation enforces multi-view consistency and spatial validity. Our design incorporates a novel View-Wise Cross-Attention for multi-view alignment and a Stereo-Conditioned Cross-Attention to anchor generative predictions in 3D relationships. By combining generative imagination with structural constraints, GENA3D generates complete and coherent 3D objects from limited observations without sacrificing geometric fidelity. Experiments demonstrate that our method outperforms existing approaches in both synthetic and real-world amodal scenarios, highlighting the effectiveness of bridging 2D priors and 3D coherence in generating plausible and geometrically consistent 3D structures in complex environments.

---

### Deep Learning Architectures for Code-Modulated Visual Evoked Potentials Detection

Authors: Kiran Nair, Hubert Cecotti
Published: 2025-11-26
Categories: cs.LG, eess.SP, q-bio.NC
arXiv: https://arxiv.org/abs/2511.21940v1

Non-invasive Brain-Computer Interfaces (BCIs) based on Code-Modulated Visual Evoked Potentials (C-VEPs) require highly robust decoding methods to address temporal variability and session-dependent noise in EEG signals. This study proposes and evaluates several deep learning architectures, including convolutional neural networks (CNNs) for 63-bit m-sequence reconstruction and classification, and Siamese networks for similarity-based decoding, alongside canonical correlation analysis (CCA) baselines. EEG data were recorded from 13 healthy adults under single-target flicker stimulation. The proposed deep models significantly outperformed traditional approaches, with distance-based decoding using Earth Mover's Distance (EMD) and constrained EMD showing greater robustness to latency variations than Euclidean and Mahalanobis metrics. Temporal data augmentation with small shifts further improved generalization across sessions. Among all models, the multi-class Siamese network achieved the best overall performance with an average accuracy of 96.89%, demonstrating the potential of data-driven deep architectures for reliable, single-trial C-VEP decoding in adaptive non-invasive BCI systems.

---

### Interpretable Multimodal Cancer Prototyping with Whole Slide Images and Incompletely Paired Genomics

Authors: Yupei Zhang, Yating Huang, Wanming Hu, Lequan Yu, Hujun Yin, Chao Li
Published: 2025-11-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.21937v1

Multimodal approaches that integrate histology and genomics hold strong potential for precision oncology. However, phenotypic and genotypic heterogeneity limits the quality of intra-modal representations and hinders effective inter-modal integration. Furthermore, most existing methods overlook real-world clinical scenarios where genomics may be partially missing or entirely unavailable. We propose a flexible multimodal prototyping framework to integrate whole slide images and incomplete genomics for precision oncology. Our approach has four key components: 1) Biological Prototyping using text prompting and prototype-wise weighting; 2) Multiview Alignment through sample- and distribution-wise alignments; 3) Bipartite Fusion to capture both shared and modality-specific information for multimodal fusion; and 4) Semantic Genomics Imputation to handle missing data. Extensive experiments demonstrate the consistent superiority of the proposed method compared to other state-of-the-art approaches on multiple downstream tasks. The code is available at https://github.com/helenypzhang/Interpretable-Multimodal-Prototyping.

---

### Breaking Algorithmic Collusion in Human-AI Ecosystems

Authors: Natalie Collina, Eshwar Ram Arunachaleswaran, Meena Jagadeesan
Published: 2025-11-26
Categories: cs.LG, cs.GT
arXiv: https://arxiv.org/abs/2511.21935v1

AI agents are increasingly deployed in ecosystems where they repeatedly interact not only with each other but also with humans. In this work, we study these human-AI ecosystems from a theoretical perspective, focusing on the classical framework of repeated pricing games. In our stylized model, the AI agents play equilibrium strategies, and one or more humans manually perform the pricing task instead of adopting an AI agent, thereby defecting to a no-regret strategy. Motivated by how populations of AI agents can sustain supracompetitive prices, we investigate whether high prices persist under such defections. Our main finding is that even a single human defection can destabilize collusion and drive down prices, and multiple defections push prices even closer to competitive levels. We further show how the nature of collusion changes under defection-aware AI agents. Taken together, our results characterize when algorithmic collusion is fragile--and when it persists--in mixed ecosystems of AI agents and humans.

---

### Heterogeneous Multi-Agent Reinforcement Learning with Attention for Cooperative and Scalable Feature Transformation

Authors: Tao Zhe, Huazhen Fang, Kunpeng Liu, Qian Lou, Tamzidul Hoque, Dongjie Wang
Published: 2025-11-26
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.21934v2

Feature transformation enhances downstream task performance by generating informative features through mathematical feature crossing. Despite the advancements in deep learning, feature transformation remains essential for structured data, where deep models often struggle to capture complex feature interactions. Prior literature on automated feature transformation has achieved success but often relies on heuristics or exhaustive searches, leading to inefficient and time-consuming processes. Recent works employ reinforcement learning (RL) to enhance traditional approaches through a more effective trial-and-error way. However, two limitations remain: 1) Dynamic feature expansion during the transformation process, which causes instability and increases the learning complexity for RL agents; 2) Insufficient cooperation and communication between agents, which results in suboptimal feature crossing operations and degraded model performance. To address them, we propose a novel heterogeneous multi-agent RL framework to enable cooperative and scalable feature transformation. The framework comprises three heterogeneous agents, grouped into two types, each designed to select essential features and operations for feature crossing. To enhance communication among these agents, we implement a shared critic mechanism that facilitates information exchange during feature transformation. To handle the dynamically expanding feature space, we tailor multi-head attention-based feature agents to select suitable features for feature crossing. Additionally, we introduce a state encoding technique during the optimization process to stabilize and enhance the learning dynamics of the RL agents, resulting in more robust and reliable transformation policies. Finally, we conduct extensive experiments to validate the effectiveness, efficiency, robustness, and interpretability of our model.

---

### Modeling Quantum Autoencoder Trainable Kernel for IoT Anomaly Detection

Authors: Swathi Chandrasekhar, Shiva Raj Pokhrel, Swati Kumari, Navneet Singh
Published: 2025-11-26
Categories: cs.LG, quant-ph
arXiv: https://arxiv.org/abs/2511.21932v1

Escalating cyber threats and the high-dimensional complexity of IoT traffic have outpaced classical anomaly detection methods. While deep learning offers improvements, computational bottlenecks limit real-time deployment at scale. We present a quantum autoencoder (QAE) framework that compresses network traffic into discriminative latent representations and employs quantum support vector classification (QSVC) for intrusion detection. Evaluated on three datasets, our approach achieves improved accuracy on ideal simulators and on the IBM Quantum hardware demonstrating practical quantum advantage on current NISQ devices. Crucially, moderate depolarizing noise acts as implicit regularization, stabilizing training and enhancing generalization. This work establishes quantum machine learning as a viable, hardware-ready solution for real-world cybersecurity challenges.

---

### Does the Model Say What the Data Says? A Simple Heuristic for Model Data Alignment

Authors: Henry Salgado, Meagan R. Kendall, Martine Ceberio
Published: 2025-11-26
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.21931v2

In this work, we propose a simple and computationally efficient framework for evaluating whether machine learning models align with the structure of the data they learn from; that is, whether the model says what the data says. Unlike existing interpretability methods that focus exclusively on explaining model behavior, our approach establishes a baseline derived directly from the data itself. Drawing inspiration from Rubin's Potential Outcomes Framework, we quantify how strongly each feature separates the two outcome groups in a binary classification task, moving beyond traditional descriptive statistics to estimate each feature's effect on the outcome. By comparing these data-derived feature rankings with model-based explanations, we provide practitioners with an interpretable and model-agnostic method for assessing model-data alignment.

---

### A Comparative Study of LLM Prompting and Fine-Tuning for Cross-genre Authorship Attribution on Chinese Lyrics

Authors: Yuxin Li, Lorraine Xu, Meng Fan Wang
Published: 2025-11-26
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.21930v1

We propose a novel study on authorship attribution for Chinese lyrics, a domain where clean, public datasets are sorely lacking. Our contributions are twofold: (1) we create a new, balanced dataset of Chinese lyrics spanning multiple genres, and (2) we develop and fine-tune a domain-specific model, comparing its performance against zero-shot inference using the DeepSeek LLM. We test two central hypotheses. First, we hypothesize that a fine-tuned model will outperform a zero-shot LLM baseline. Second, we hypothesize that performance is genre-dependent. Our experiments strongly confirm Hypothesis 2: structured genres (e.g. Folklore & Tradition) yield significantly higher attribution accuracy than more abstract genres (e.g. Love & Romance). Hypothesis 1 receives only partial support: fine-tuning improves robustness and generalization in Test1 (real-world data and difficult genres), but offers limited or ambiguous gains in Test2, a smaller, synthetically-augmented set. We show that the design limitations of Test2 (e.g., label imbalance, shallow lexical differences, and narrow genre sampling) can obscure the true effectiveness of fine-tuning. Our work establishes the first benchmark for cross-genre Chinese lyric attribution, highlights the importance of genre-sensitive evaluation, and provides a public dataset and analytical framework for future research. We conclude with recommendations: enlarge and diversify test sets, reduce reliance on token-level data augmentation, balance author representation across genres, and investigate domain-adaptive pretraining as a pathway for improved attribution performance.

---

### Prompted Policy Search: Reinforcement Learning through Linguistic and Numerical Reasoning in LLMs

Authors: Yifan Zhou, Sachin Grover, Mohamed El Mistiri, Kamalesh Kalirathnam, Pratyush Kerhalkar, Swaroop Mishra, Neelesh Kumar, Sanket Gaurav, Oya Aran, Heni Ben Amor
Published: 2025-11-26
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.21928v1

Reinforcement Learning (RL) traditionally relies on scalar reward signals, limiting its ability to leverage the rich semantic knowledge often available in real-world tasks. In contrast, humans learn efficiently by combining numerical feedback with language, prior knowledge, and common sense. We introduce Prompted Policy Search (ProPS), a novel RL method that unifies numerical and linguistic reasoning within a single framework. Unlike prior work that augment existing RL components with language, ProPS places a large language model (LLM) at the center of the policy optimization loop-directly proposing policy updates based on both reward feedback and natural language input. We show that LLMs can perform numerical optimization in-context, and that incorporating semantic signals, such as goals, domain knowledge, and strategy hints can lead to more informed exploration and sample-efficient learning. ProPS is evaluated across fifteen Gymnasium tasks, spanning classic control, Atari games, and MuJoCo environments, and compared to seven widely-adopted RL algorithms (e.g., PPO, SAC, TRPO). It outperforms all baselines on eight out of fifteen tasks and demonstrates substantial gains when provided with domain knowledge. These results highlight the potential of unifying semantics and numerics for transparent, generalizable, and human-aligned RL.

---

### Comparing SAM 2 and SAM 3 for Zero-Shot Segmentation of 3D Medical Data

Authors: Satrajit Chakrabarty, Ravi Soni
Published: 2025-11-26
Categories: eess.IV, cs.CV
arXiv: https://arxiv.org/abs/2511.21926v2

Foundation models, such as the Segment Anything Model (SAM), have heightened interest in promptable zero-shot segmentation. Although these models perform strongly on natural images, their behavior on medical data remains insufficiently characterized. While SAM 2 has been widely adopted for annotation in 3D medical workflows, the recently released SAM 3 introduces a new architecture that may change how visual prompts are interpreted and propagated. Therefore, to assess whether SAM 3 can serve as an out-of-the-box replacement for SAM 2 for zero-shot segmentation of 3D medical data, we present the first controlled comparison of both models by evaluating SAM 3 in its Promptable Visual Segmentation (PVS) mode using a variety of prompting strategies. We benchmark on 16 public datasets (CT, MRI, Ultrasound, endoscopy) covering 54 anatomical structures, pathologies, and surgical instruments. We further quantify three failure modes: prompt-frame over-segmentation, over-propagation after object disappearance, and temporal retention of well-initialized predictions. Our results show that SAM 3 is consistently stronger under click prompting across modalities, with fewer prompt-frame over-segmentation failures and slower prediction retention decay compared to SAM 2. Under bounding-box and mask prompts, performance gaps narrow in few structures of CT/MR and the models trade off termination behavior, while SAM 3 remains stronger on ultrasound and endoscopy sequences. The overall results position SAM 3 as the superior default choice for most medical segmentation tasks, while clarifying when SAM 2 remains a preferable propagator.

---

### Exploring Dynamic Properties of Backdoor Training Through Information Bottleneck

Authors: Xinyu Liu, Xu Zhang, Can Chen, Ren Wang
Published: 2025-11-26
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.21923v1

Understanding how backdoor data influences neural network training dynamics remains a complex and underexplored challenge. In this paper, we present a rigorous analysis of the impact of backdoor data on the learning process, with a particular focus on the distinct behaviors between the target class and other clean classes. Leveraging the Information Bottleneck (IB) principle connected with clustering of internal representation, We find that backdoor attacks create unique mutual information (MI) signatures, which evolve across training phases and differ based on the attack mechanism. Our analysis uncovers a surprising trade-off: visually conspicuous attacks like BadNets can achieve high stealthiness from an information-theoretic perspective, integrating more seamlessly into the model than many visually imperceptible attacks. Building on these insights, we propose a novel, dynamics-based stealthiness metric that quantifies an attack's integration at the model level. We validate our findings and the proposed metric across multiple datasets and diverse attack types, offering a new dimension for understanding and evaluating backdoor threats. Our code is available in: https://github.com/XinyuLiu71/Information_Bottleneck_Backdoor.git.

---

### Toward Automated and Trustworthy Scientific Analysis and Visualization with LLM-Generated Code

Authors: Apu Kumar Chakroborti, Yi Ding, Lipeng Wan
Published: 2025-11-26
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2511.21920v1

As modern science becomes increasingly data-intensive, the ability to analyze and visualize large-scale, complex datasets is critical to accelerating discovery. However, many domain scientists lack the programming expertise required to develop custom data analysis workflows, creating barriers to timely and effective insight. Large language models (LLMs) offer a promising solution by generating executable code from natural language descriptions. In this paper, we investigate the trustworthiness of open-source LLMs in autonomously producing Python scripts for scientific data analysis and visualization. We construct a benchmark suite of domain-inspired prompts that reflect real-world research tasks and systematically evaluate the executability and correctness of the generated code. Our findings show that, without human intervention, the reliability of LLM-generated code is limited, with frequent failures caused by ambiguous prompts and the models' insufficient understanding of domain-specific contexts. To address these challenges, we design and assess three complementary strategies: data-aware prompt disambiguation, retrieval-augmented prompt enhancement, and iterative error repair. While these methods significantly improve execution success rates and output quality, further refinement is needed. This work highlights both the promise and current limitations of LLM-driven automation in scientific workflows and introduces actionable techniques and a reusable benchmark for building more inclusive, accessible, and trustworthy AI-assisted research tools.

---

### Algorithms and Scientific Software for Quasi-Monte Carlo, Fast Gaussian Process Regression, and Scientific Machine Learning

Authors: Aleksei G. Sorokin
Published: 2025-11-26
Categories: stat.ML, cs.LG, math.PR
arXiv: https://arxiv.org/abs/2511.21915v1

Most scientific domains elicit the development of efficient algorithms and accessible scientific software. This thesis unifies our developments in three broad domains: Quasi-Monte Carlo (QMC) methods for efficient high-dimensional integration, Gaussian process (GP) regression for high-dimensional interpolation with built-in uncertainty quantification, and scientific machine learning (sciML) for modeling partial differential equations (PDEs) with mesh-free solvers. For QMC, we built new algorithms for vectorized error estimation and developed QMCPy (https://qmcsoftware.github.io/QMCSoftware/): an open-source Python interface to randomized low-discrepancy sequence generators, automatic variable transforms, adaptive error estimation procedures, and diverse use cases. For GPs, we derived new digitally-shift-invariant kernels of higher-order smoothness, developed novel fast multitask GP algorithms, and produced the scalable Python software FastGPs (https://alegresor.github.io/fastgps/). For sciML, we developed a new algorithm capable of machine precision recovery of PDEs with random coefficients. We have also studied a number of applications including GPs for probability of failure estimation, multilevel GPs for the Darcy flow equation, neural surrogates for modeling radiative transfer, and fast GPs for Bayesian multilevel QMC.

---

### Tracing How Annotators Think: Augmenting Preference Judgments with Reading Processes

Authors: Karin de Langis, William Walker, Khanh Chi Le, Dongyeop Kang
Published: 2025-11-26
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.21912v1

We propose an annotation approach that captures not only labels but also the reading process underlying annotators' decisions, e.g., what parts of the text they focus on, re-read or skim. Using this framework, we conduct a case study on the preference annotation task, creating a dataset PreferRead that contains fine-grained annotator reading behaviors obtained from mouse tracking. PreferRead enables detailed analysis of how annotators navigate between a prompt and two candidate responses before selecting their preference. We find that annotators re-read a response in roughly half of all trials, most often revisiting the option they ultimately choose, and rarely revisit the prompt. Reading behaviors are also significantly related to annotation outcomes: re-reading is associated with higher inter-annotator agreement, whereas long reading paths and times are associated with lower agreement. These results demonstrate that reading processes provide a complementary cognitive dimension for understanding annotator reliability, decision-making and disagreement in complex, subjective NLP tasks. Our code and data are publicly available.

---

### A Customer Journey in the Land of Oz: Leveraging the Wizard of Oz Technique to Model Emotions in Customer Service Interactions

Authors: Sofie Labat, Thomas Demeester, Véronique Hoste
Published: 2025-11-26
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.21909v1

Emotion-aware customer service needs in-domain conversational data, rich annotations, and predictive capabilities, but existing resources for emotion recognition are often out-of-domain, narrowly labeled, and focused on post-hoc detection. To address this, we conducted a controlled Wizard of Oz (WOZ) experiment to elicit interactions with targeted affective trajectories. The resulting corpus, EmoWOZ-CS, contains 2,148 bilingual (Dutch-English) written dialogues from 179 participants across commercial aviation, e-commerce, online travel agencies, and telecommunication scenarios. Our contributions are threefold: (1) Evaluate WOZ-based operator-steered valence trajectories as a design for emotion research; (2) Quantify human annotation performance and variation, including divergences between self-reports and third-party judgments; (3) Benchmark detection and forward-looking emotion inference in real-time support. Findings show neutral dominates participant messages; desire and gratitude are the most frequent non-neutral emotions. Agreement is moderate for multilabel emotions and valence, lower for arousal and dominance; self-reports diverge notably from third-party labels, aligning most for neutral, gratitude, and anger. Objective strategies often elicit neutrality or gratitude, while suboptimal strategies increase anger, annoyance, disappointment, desire, and confusion. Some affective strategies (cheerfulness, gratitude) foster positive reciprocity, whereas others (apology, empathy) can also leave desire, anger, or annoyance. Temporal analysis confirms successful conversation-level steering toward prescribed trajectories, most distinctly for negative targets; positive and neutral targets yield similar final valence distributions. Benchmarks highlight the difficulty of forward-looking emotion inference from prior turns, underscoring the complexity of proactive emotion-aware support.

---

### Multi-Modal Machine Learning for Early Trust Prediction in Human-AI Interaction Using Face Image and GSR Bio Signals

Authors: Hamid Shamszare, Avishek Choudhury
Published: 2025-11-26
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.21908v2

Predicting human trust in AI systems is crucial for safe integration of AI-based decision support tools, especially in healthcare. This study proposes a multi-modal machine learning framework that combines image and galvanic skin response (GSR) data to predict early user trust in AI- or human-generated recommendations in a simulated ADHD mHealth context. Facial video data were processed using OpenCV for frame extraction and transferred learning with a pre-trained transformer model to derive emotional features. Concurrently, GSR signals were decomposed into tonic and phasic components to capture physiological arousal patterns. Two temporal windows were defined for trust prediction: the Early Detection Window (6 to 3 seconds before decision-making) and the Proximal Detection Window (3 to 0 seconds before decision-making). For each window, trust prediction was conducted separately using image-based, GSR-based, and multimodal (image + GSR) features. Each modality was analyzed using machine learning algorithms, and the top-performing unimodal models were integrated through a multimodal stacking ensemble for final prediction. Experimental results showed that combining facial and physiological cues significantly improved prediction performance. The multimodal stacking framework achieved an accuracy of 0.83, F1-score of 0.88, and ROC-AUC of 0.87 in the Early Detection Window, and an accuracy of 0.75, F1-score of 0.82, and ROC-AUC of 0.66 in the Proximal Detection Window. These results demonstrate the potential of bio signals as real-time, objective markers of user trust, enabling adaptive AI systems that dynamically adjust their responses to maintain calibrated trust which is a critical capability in mental health applications where mis-calibrated trust can affect diagnostic and treatment outcomes.

---

### Adaptive Parameter Optimization for Robust Remote Photoplethysmography

Authors: Cecilia G. Morales, Fanurs Chi En Teh, Kai Li, Pushpak Agrawal, Artur Dubrawski
Published: 2025-11-26
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.21903v1

Remote photoplethysmography (rPPG) enables contactless vital sign monitoring using standard RGB cameras. However, existing methods rely on fixed parameters optimized for particular lighting conditions and camera setups, limiting adaptability to diverse deployment environments. This paper introduces the Projection-based Robust Signal Mixing (PRISM) algorithm, a training-free method that jointly optimizes photometric detrending and color mixing through online parameter adaptation based on signal quality assessment. PRISM achieves state-of-the-art performance among unsupervised methods, with MAE of 0.77 bpm on PURE and 0.66 bpm on UBFC-rPPG, and accuracy of 97.3\% and 97.5\% respectively at a 5 bpm threshold. Statistical analysis confirms PRISM performs equivalently to leading supervised methods ($p > 0.2$), while maintaining real-time CPU performance without training. This validates that adaptive time series optimization significantly improves rPPG across diverse conditions.

---

### PathReasoning: A multimodal reasoning agent for query-based ROI navigation on whole-slide images

Authors: Kunpeng Zhang, Hanwen Xu, Sheng Wang
Published: 2025-11-26
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.21902v1

Deciphering tumor microenvironment from Whole Slide Images (WSIs) is intriguing as it is key to cancer diagnosis, prognosis and treatment response. While these gigapixel images on one hand offer a comprehensive portrait of cancer, on the other hand, the extremely large size, as much as more than 10 billion pixels, make it challenging and time-consuming to navigate to corresponding regions to support diverse clinical inspection. Inspired by pathologists who conducted navigation on WSIs with a combination of sampling, reasoning and self-reflection, we proposed "PathReasoning", a multi-modal reasoning agent that iteratively navigates across WSIs through multiple rounds of reasoning and refinements. Specifically, starting with randomly sampled candidate regions, PathReasoning reviews current selections with self-reflection, reasoning over the correspondence between visual observations and clinical questions, and concludes by proposing new regions to explore. Across rounds, PathReasoning builds a reasoning chain that gradually directs attention to diagnostically relevant areas. PathReasoning turns each whole slide into a sequence of question-guided views, allowing the model to efficiently find informative ROIs within a fixed number of steps, without the need for dense pixel-level annotations. PathReasoning can substantially outperform strong ROI-selection approaches by 6.7% and 3.1% of AUROC on subtyping and longitudinal analysis tasks. The high-quality ROIs further support accurate report generation on breast cancer, significantly outperforming the standard GPT-4o by 10% in accuracy. PathReasoning prioritizes question-specific regions and constructs interpretable reasoning chains, supporting efficient slide review, consistent diagnostic interpretations, comprehensive reporting, and evidence traceability in digital pathology.

---

### Standardized Threat Taxonomy for AI Security, Governance, and Regulatory Compliance

Authors: Hernan Huwyler
Published: 2025-11-26
Categories: cs.CR, cs.AI, q-fin.RM
arXiv: https://arxiv.org/abs/2511.21901v1

The accelerating deployment of artificial intelligence systems across regulated sectors has exposed critical fragmentation in risk assessment methodologies. A significant "language barrier" currently separates technical security teams, who focus on algorithmic vulnerabilities (e.g., MITRE ATLAS), from legal and compliance professionals, who address regulatory mandates (e.g., EU AI Act, NIST AI RMF). This disciplinary disconnect prevents the accurate translation of technical vulnerabilities into financial liability, leaving practitioners unable to answer fundamental economic questions regarding contingency reserves, control return-on-investment, and insurance exposure. To bridge this gap, this research presents the AI System Threat Vector Taxonomy, a structured ontology designed explicitly for Quantitative Risk Assessment (QRA). The framework categorizes AI-specific risks into nine critical domains: Misuse, Poisoning, Privacy, Adversarial, Biases, Unreliable Outputs, Drift, Supply Chain, and IP Threat, integrating 53 operationally defined sub-threats. Uniquely, each domain maps technical vectors directly to business loss categories (Confidentiality, Integrity, Availability, Legal, Reputation), enabling the translation of abstract threats into measurable financial impact. The taxonomy is empirically validated through an analysis of 133 documented AI incidents from 2025 (achieving 100% classification coverage) and reconciled against the main AI risk frameworks. Furthermore, it is explicitly aligned with ISO/IEC 42001 controls and NIST AI RMF functions to facilitate auditability.

---

### Beyond Atoms: Evaluating Electron Density Representation for 3D Molecular Learning

Authors: Patricia Suriana, Joshua A. Rackers, Ewa M. Nowara, Pedro O. Pinheiro, John M. Nicoloudis, Vishnu Sresht
Published: 2025-11-26
Categories: cs.LG, q-bio.BM
arXiv: https://arxiv.org/abs/2511.21900v1

Machine learning models for 3D molecular property prediction typically rely on atom-based representations, which may overlook subtle physical information. Electron density maps -- the direct output of X-ray crystallography and cryo-electron microscopy -- offer a continuous, physically grounded alternative. We compare three voxel-based input types for 3D convolutional neural networks (CNNs): atom types, raw electron density, and density gradient magnitude, across two molecular tasks -- protein-ligand binding affinity prediction (PDBbind) and quantum property prediction (QM9). We focus on voxel-based CNNs because electron density is inherently volumetric, and voxel grids provide the most natural representation for both experimental and computed densities. On PDBbind, all representations perform similarly with full data, but in low-data regimes, density-based inputs outperform atom types, while a shape-based baseline performs comparably -- suggesting that spatial occupancy dominates this task. On QM9, where labels are derived from Density Functional Theory (DFT) but input densities from a lower-level method (XTB), density-based inputs still outperform atom-based ones at scale, reflecting the rich structural and electronic information encoded in density. Overall, these results highlight the task- and regime-dependent strengths of density-derived inputs, improving data efficiency in affinity prediction and accuracy in quantum property modeling.

---

### Breaking the Illusion: Consensus-Based Generative Mitigation of Adversarial Illusions in Multi-Modal Embeddings

Authors: Fatemeh Akbarian, Anahita Baninajjar, Yingyi Zhang, Ananth Balashankar, Amir Aminifar
Published: 2025-11-26
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.21893v2

Multi-modal foundation models align images, text, and other modalities in a shared embedding space but remain vulnerable to adversarial illusions (35), where imperceptible perturbations disrupt cross-modal alignment and mislead downstream tasks. To counteract the effects of adversarial illusions, we propose a task-agnostic mitigation mechanism that purifies the attacker's perturbed input using generative models, e.g., Variational Autoencoders (VAEs), to restore natural alignment. To further enhance the defense mechanism, we adopt a generative sampling strategy combined with a consensus-based aggregation scheme over the outcomes of the generated samples. Our experiments on ImageBind, a state-of-the-art multi-modal encoder, show that our approach substantially reduces the illusion attack success rates to near-zero and improves cross-modal alignment in unperturbed and perturbed input settings, providing an effective and task-agnostic defense against adversarial illusions. The code is available at https://github.com/fatemehakb/adversarial-illusions-mitigation.

---

### Sparse Multiple Kernel Learning: Alternating Best Response and Semidefinite Relaxations

Authors: Dimitris Bertsimas, Caio de Prospero Iglesias, Nicholas A. G. Johnson
Published: 2025-11-26
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2511.21890v2

We study Sparse Multiple Kernel Learning (SMKL), which is the problem of selecting a sparse convex combination of prespecified kernels for support vector binary classification. Unlike prevailing l1 regularized approaches that approximate a sparsifying penalty, we formulate the problem by imposing an explicit cardinality constraint on the kernel weights and add an l2 penalty for robustness. We solve the resulting non-convex minimax problem via an alternating best response algorithm with two subproblems: the alpha subproblem is a standard kernel SVM dual solved via LIBSVM, while the beta subproblem admits an efficient solution via the Greedy Selector and Simplex Projector algorithm. We reformulate SMKL as a mixed integer semidefinite optimization problem and derive a hierarchy of semidefinite convex relaxations which can be used to certify near-optimality of the solutions returned by our best response algorithm and also to warm start it. On ten UCI benchmarks, our method with random initialization outperforms state-of-the-art MKL approaches in out-of-sample prediction accuracy on average by 3.34 percentage points (relative to the best performing benchmark) while selecting a small number of candidate kernels in comparable runtime. With warm starting, our method outperforms the best performing benchmark's out-of-sample prediction accuracy on average by 4.05 percentage points. Our convex relaxations provide a certificate that in several cases, the solution returned by our best response algorithm is the globally optimal solution.

---

### Exploring Fusion Strategies for Multimodal Vision-Language Systems

Authors: Regan Willis, Jason Bakos
Published: 2025-11-26
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.21889v1

Modern machine learning models often combine multiple input streams of data to more accurately capture the information that informs their decisions. In multimodal machine learning, choosing the strategy for fusing data together requires careful consideration of the application's accuracy and latency requirements, as fusing the data at earlier or later stages in the model architecture can lead to performance changes in accuracy and latency. To demonstrate this tradeoff, we investigate different fusion strategies using a hybrid BERT and vision network framework that integrates image and text data. We explore two different vision networks: MobileNetV2 and ViT. We propose three models for each vision network, which fuse data at late, intermediate, and early stages in the architecture. We evaluate the proposed models on the CMU MOSI dataset and benchmark their latency on an NVIDIA Jetson Orin AGX. Our experimental results demonstrate that while late fusion yields the highest accuracy, early fusion offers the lowest inference latency. We describe the three proposed model architectures and discuss the accuracy and latency tradeoffs, concluding that data fusion earlier in the model architecture results in faster inference times at the cost of accuracy.

---

### UniArt: Unified 3D Representation for Generating 3D Articulated Objects with Open-Set Articulation

Authors: Bu Jin, Weize Li, Songen Gu, Yupeng Zheng, Yuhang Zheng, Zhengyi Zhou, Yao Yao
Published: 2025-11-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.21887v1

Articulated 3D objects play a vital role in realistic simulation and embodied robotics, yet manually constructing such assets remains costly and difficult to scale. In this paper, we present UniArt, a diffusion-based framework that directly synthesizes fully articulated 3D objects from a single image in an end-to-end manner. Unlike prior multi-stage techniques, UniArt establishes a unified latent representation that jointly encodes geometry, texture, part segmentation, and kinematic parameters. We introduce a reversible joint-to-voxel embedding, which spatially aligns articulation features with volumetric geometry, enabling the model to learn coherent motion behaviors alongside structural formation. Furthermore, we formulate articulation type prediction as an open-set problem, removing the need for fixed joint semantics and allowing generalization to novel joint categories and unseen object types. Experiments on the PartNet-Mobility benchmark demonstrate that UniArt achieves state-of-the-art mesh quality and articulation accuracy.

---

### From Discrete Plans to Real-World Execution: A World-Model-Driven Framework for Execution-Aware Multi-Agent Path Finding

Authors: Jingtian Yan, Shuai Zhou, He Jiang, Stephen F. Smith, Jiaoyang Li
Published: 2025-11-26
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2511.21886v2

Multi-Agent Path Finding (MAPF) studies how to coordinate multiple agents to reach their goals without collisions and underpins a range of large-scale robotic systems, including automated warehousing and manufacturing. Recent advances enable MAPF solvers to compute high-quality plans for hundreds of agents. However, these plans are generated using simplified robot models with discretized time and action spaces. When they are deployed in physical systems, heterogeneous robot dynamics, asynchronous interactions, communication delays, and other real-world factors can lead to substantial deviations from planned performance. We bridge the gap between discrete planning and real-world execution through ExecTimeNet, a learned world model of MAPF execution that predicts how a discrete MAPF solution will unfold on physical robots, mapping each discrete action to its realized execution state, including its wall-clock completion time and the kinodynamic state in which it ends. Building on this capability, we first propose REMAP, an execution-aware MAPF framework that integrates execution-time estimation into planning, guiding the search toward MAPF solutions with improved execution performance. We also introduce ESADG, a post-planning optimization procedure that optimizes the execution schedule of a given MAPF solution while preserving path feasibility. We evaluate proposed frameworks in high-fidelity simulation with up to 300 agents and on physical robots. In simulation, ExecTimeNet predicts the execution state accurately and transfers to unseen maps and agent counts. Across simulation benchmarks spanning diverse map topologies, REMAP reduces delays by up to 21% over baselines, while ESADG achieves up to 40% normalized improvement. On physical hardware, the full pipeline reduces total execution time by up to 15.3%, demonstrating effective transfer from simulation to real-world deployment.

---

### Physically Interpretable Representation Learning with Gaussian Mixture Variational AutoEncoder (GM-VAE)

Authors: Tiffany Fan, Murray Cutforth, Marta D'Elia, Alexandre Cortiella, Alireza Doostan, Eric Darve
Published: 2025-11-26
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.21883v1

Extracting compact, physically interpretable representations from high-dimensional scientific data is a persistent challenge due to the complex, nonlinear structures inherent in physical systems. We propose a Gaussian Mixture Variational Autoencoder (GM-VAE) framework designed to address this by integrating an Expectation-Maximization (EM)-inspired training scheme with a novel spectral interpretability metric. Unlike conventional VAEs that jointly optimize reconstruction and clustering (often leading to training instability), our method utilizes a block-coordinate descent strategy, alternating between expectation and maximization steps. This approach stabilizes training and naturally aligns latent clusters with distinct physical regimes. To objectively evaluate the learned representations, we introduce a quantitative metric based on graph-Laplacian smoothness, which measures the coherence of physical quantities across the latent manifold. We demonstrate the efficacy of this framework on datasets of increasing complexity: surface reaction ODEs, Navier-Stokes wake flows, and experimental laser-induced combustion Schlieren images. The results show that our GM-VAE yields smooth, physically consistent manifolds and accurate regime clustering, offering a robust data-driven tool for interpreting turbulent and reactive flow systems.

---

### Closed-Loop Transformers: Autoregressive Modeling as Iterative Latent Equilibrium

Authors: Akbar Anbar Jafari, Gholamreza Anbarjafari
Published: 2025-11-26
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2511.21882v1

Contemporary autoregressive transformers operate in open loop: each hidden state is computed in a single forward pass and never revised, causing errors to propagate uncorrected through the sequence. We identify this open-loop bottleneck as a fundamental architectural limitation underlying well-documented failures in long-range reasoning, factual consistency, and multi-step planning. To address this limitation, we introduce the closed-loop prediction principle, which requires that models iteratively refine latent representations until reaching a self-consistent equilibrium before committing to each token. We instantiate this principle as Equilibrium Transformers (EqT), which augment standard transformer layers with an Equilibrium Refinement Module that minimizes a learned energy function via gradient descent in latent space. The energy function enforces bidirectional prediction consistency, episodic memory coherence, and output confidence, all computed without external supervision. Theoretically, we prove that EqT performs approximate MAP inference in a latent energy-based model, establish linear convergence guarantees, and show that refinement improves predictions precisely on hard instances where one-shot inference is suboptimal. The framework unifies deep equilibrium models, diffusion language models, and test-time training as special cases. Preliminary experiments on the binary parity task demonstrate +3.28% average improvement on challenging sequences, with gains reaching +8.07% where standard transformers approach random performance, validating that the benefit of deliberation scales with task difficulty. Just as attention mechanisms resolved the sequential bottleneck of recurrent networks, we propose that closed-loop equilibrium may resolve the commitment bottleneck of open-loop autoregression, representing a foundational step toward language models.

---

### LLM-Empowered Event-Chain Driven Code Generation for ADAS in SDV systems

Authors: Nenad Petrovic, Norbert Kroth, Axel Torschmied, Yinglei Song, Fengjunjie Pan, Vahid Zolfaghari, Nils Purschke, Sven Kirchner, Chengdong Wu, Andre Schamschurko, Yi Zhang, Alois Knoll
Published: 2025-11-26
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2511.21877v1

This paper presents an event-chain-driven, LLM-empowered workflow for generating validated, automotive code from natural-language requirements. A Retrieval-Augmented Generation (RAG) layer retrieves relevant signals from large and evolving Vehicle Signal Specification (VSS) catalogs as code generation prompt context, reducing hallucinations and ensuring architectural correctness. Retrieved signals are mapped and validated before being transformed into event chains that encode causal and timing constraints. These event chains guide and constrain LLM-based code synthesis, ensuring behavioral consistency and real-time feasibility. Based on our initial findings from the emergency braking case study, with the proposed approach, we managed to achieve valid signal usage and consistent code generation without LLM retraining.

---

### Differential privacy from axioms

Authors: Guy Blanc, William Pires, Toniann Pitassi
Published: 2025-11-26
Categories: cs.DS, cs.LG
arXiv: https://arxiv.org/abs/2511.21876v1

Differential privacy (DP) is the de facto notion of privacy both in theory and in practice. However, despite its popularity, DP imposes strict requirements which guard against strong worst-case scenarios. For example, it guards against seemingly unrealistic scenarios where an attacker has full information about all but one point in the data set, and still nothing can be learned about the remaining point. While preventing such a strong attack is desirable, many works have explored whether average-case relaxations of DP are easier to satisfy (HWR13,WLF16,BF16,LWX23). In this work, we are motivated by the question of whether alternate, weaker notions of privacy are possible: can a weakened privacy notion still guarantee some basic level of privacy, and on the other hand, achieve privacy more efficiently and/or for a substantially broader set of tasks? Our main result shows the answer is no: even in the statistical setting, any reasonable measure of privacy satisfying nontrivial composition is equivalent to DP. To prove this, we identify a core set of four axioms or desiderata: pre-processing invariance, prohibition of blatant non-privacy, strong composition, and linear scalability. Our main theorem shows that any privacy measure satisfying our axioms is equivalent to DP, up to polynomial factors in sample complexity. We complement this result by showing our axioms are minimal: removing any one of our axioms enables ill-behaved measures of privacy.

---

### Advancing Marine Bioacoustics with Deep Generative Models: A Hybrid Augmentation Strategy for Southern Resident Killer Whale Detection

Authors: Bruno Padovese, Fabio Frazao, Michael Dowd, Ruth Joy
Published: 2025-11-26
Categories: cs.SD, cs.AI, cs.LG, eess.AS
arXiv: https://arxiv.org/abs/2511.21872v1

Automated detection and classification of marine mammals vocalizations is critical for conservation and management efforts but is hindered by limited annotated datasets and the acoustic complexity of real-world marine environments. Data augmentation has proven to be an effective strategy to address this limitation by increasing dataset diversity and improving model generalization without requiring additional field data. However, most augmentation techniques used to date rely on effective but relatively simple transformations, leaving open the question of whether deep generative models can provide additional benefits. In this study, we evaluate the potential of deep generative for data augmentation in marine mammal call detection including: Variational Autoencoders, Generative Adversarial Networks, and Denoising Diffusion Probabilistic Models. Using Southern Resident Killer Whale (Orcinus orca) vocalizations from two long-term hydrophone deployments in the Salish Sea, we compare these approaches against traditional augmentation methods such as time-shifting and vocalization masking. While all generative approaches improved classification performance relative to the baseline, diffusion-based augmentation yielded the highest recall (0.87) and overall F1-score (0.75). A hybrid strategy combining generative-based synthesis with traditional methods achieved the best overall performance with an F1-score of 0.81. We hope this study encourages further exploration of deep generative models as complementary augmentation strategies to advance acoustic monitoring of threatened marine mammal populations.

---

### Invited to Develop: Institutional Belonging and the Counterfactual Architecture of Development

Authors: Diego Vallarino
Published: 2025-11-26
Categories: econ.GN, cs.LG
arXiv: https://arxiv.org/abs/2511.21865v1

This paper examines how institutional belonging shapes long-term development by comparing Spain and Uruguay, two small democracies with similar historical endowments whose trajectories diverged sharply after the 1960s. While Spain integrated into dense European institutional architectures, Uruguay remained embedded within the Latin American governance regime, characterized by weaker coordination and lower institutional coherence. To assess how alternative institutional embeddings could have altered these paths, the study develops a generative counterfactual framework grounded in economic complexity, institutional path dependence, and a Wasserstein GAN trained on data from 1960-2020. The resulting Expected Developmental Shift (EDS) quantifies structural gains or losses from hypothetical re-embedding in different institutional ecosystems. Counterfactual simulations indicate that Spain would have experienced significant developmental decline under a Latin American configuration, while Uruguay would have achieved higher complexity and resilience within a European regime. These findings suggest that development is not solely determined by domestic reforms but emerges from a country's structural position within transnational institutional networks.

---

### Saddle-Free Guidance: Improved On-Manifold Sampling without Labels or Additional Training

Authors: Eric Yeats, Darryl Hannan, Wilson Fearn, Timothy Doster, Henry Kvinge, Scott Mahan
Published: 2025-11-26
Categories: cs.CV, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2511.21863v1

Score-based generative models require guidance in order to generate plausible, on-manifold samples. The most popular guidance method, Classifier-Free Guidance (CFG), is only applicable in settings with labeled data and requires training an additional unconditional score-based model. More recently, Auto-Guidance adopts a smaller, less capable version of the original model to guide generation. While each method effectively promotes the fidelity of generated data, each requires labeled data or the training of additional models, making it challenging to guide score-based models when (labeled) training data are not available or training new models is not feasible. We make the surprising discovery that the positive curvature of log density estimates in saddle regions provides strong guidance for score-based models. Motivated by this, we develop saddle-free guidance (SFG) which maintains estimates of maximal positive curvature of the log density to guide individual score-based models. SFG has the same computational cost of classifier-free guidance, does not require additional training, and works with off-the-shelf diffusion and flow matching models. Our experiments indicate that SFG achieves state-of-the-art FID and FD-DINOv2 metrics in single-model unconditional ImageNet-512 generation. When SFG is combined with Auto-Guidance, its unconditional samples achieve general state-of-the-art in FD-DINOv2 score. Our experiments with FLUX.1-dev and Stable Diffusion v3.5 indicate that SFG boosts the diversity of output images compared to CFG while maintaining excellent prompt adherence and image fidelity.

---

### Towards a Foundation Model for Partial Differential Equations Across Physics Domains

Authors: Eduardo Soares, Emilio Vital Brazil, Victor Shirasuna, Breno W. S. R. de Carvalho, Cristiano Malossi
Published: 2025-11-26
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.21861v1

We present PDE-FM, a modular foundation model for physics-informed machine learning that unifies spatial, spectral, and temporal reasoning across heterogeneous partial differential equation (PDE) systems. PDE-FM combines spatial-spectral tokenization, physics-aware conditioning, and a Mamba-based state-space backbone with an operator-theoretic decoder, enabling scalable and data-efficient modeling of complex physical dynamics. In contrast to task-specific neural operators, PDE-FM is pretrained once on diverse PDE datasets and can be transferred to new physical regimes without architectural or data-specific modifications. Evaluated on twelve 2D and 3D datasets from The Well benchmark - spanning hydrodynamic, radiative, elastic, and astrophysical phenomena - PDE-FM achieves state-of-the-art accuracy in six domains, reducing mean VRMSE by 46% relative to prior operator-learning baselines. The model demonstrates robust cross-physics generalization, excelling in turbulent and radiative systems while maintaining strong performance in linear and steady-state regimes. These results suggest that large-scale pretraining across diverse physical processes can yield transferable representations of dynamics, marking a step toward unified, foundation-level surrogates for multi-physics simulation and scientific discovery.

---

### Improving Score Reliability of Multiple Choice Benchmarks with Consistency Evaluation and Altered Answer Choices

Authors: Paulo Cavalin, Cassia Sanctos, Marcelo Grave, Claudio Pinhanez, Yago Primerano
Published: 2025-11-26
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.21860v1

In this work we present the Consistency-Rebalanced Accuracy (CoRA) metric, improving the reliability of Large Language Model (LLM) scores computed on multiple choice (MC) benchmarks. Our metric explores the response consistency of the LLMs, taking advantage of synthetically-generated questions with altered answer choices. With two intermediate scores, i.e. Bare-Minimum-Consistency Accuracy (BMCA) and Consistency Index (CI), CoRA is computed by adjusting the multiple-choice question answering (MCQA) scores to better reflect the level of consistency of the LLM. We present evaluations in different benchmarks using diverse LLMs, and not only demonstrate that LLMs can present low response consistency even when they present high MCQA scores, but also that CoRA can successfully scale down the scores of inconsistent models.

---

### Lightweight ML-Based Air Quality Prediction for IoT and Embedded Applications

Authors: Md. Sad Abdullah Sami, Mushfiquzzaman Abid
Published: 2025-11-26
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.21857v1

This study investigates the effectiveness and efficiency of two variants of the XGBoost regression model, the full-capacity and lightweight (tiny) versions, for predicting the concentrations of carbon monoxide (CO) and nitrogen dioxide (NO2). Using the AirQualityUCI dataset collected over one year in an urban environment, we conducted a comprehensive evaluation based on widely accepted metrics, including Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Mean Bias Error (MBE), and the coefficient of determination (R2). In addition, we assessed resource-oriented metrics such as inference time, model size, and peak RAM usage. The full XGBoost model achieved superior predictive accuracy for both pollutants, while the tiny model, though slightly less precise, offered substantial computational benefits with significantly reduced inference time and model storage requirements. These results demonstrate the feasibility of deploying simplified models in resource-constrained environments without compromising predictive quality. This makes the tiny XGBoost model suitable for real-time air-quality monitoring in IoT and embedded applications.

---

### Massively Parallel Imitation Learning of Mouse Forelimb Musculoskeletal Reaching Dynamics

Authors: Eric Leonardis, Akira Nagamori, Ayesha Thanawalla, Yuanjia Yang, Joshua Park, Hutton Saunders, Eiman Azim, Talmo Pereira
Published: 2025-11-26
Categories: cs.LG, cs.RO, q-bio.NC, q-bio.QM
arXiv: https://arxiv.org/abs/2511.21848v1

The brain has evolved to effectively control the body, and in order to understand the relationship we need to model the sensorimotor transformations underlying embodied control. As part of a coordinated effort, we are developing a general-purpose platform for behavior-driven simulation modeling high fidelity behavioral dynamics, biomechanics, and neural circuit architectures underlying embodied control. We present a pipeline for taking kinematics data from the neuroscience lab and creating a pipeline for recapitulating those natural movements in a biomechanical model. We implement a imitation learning framework to perform a dexterous forelimb reaching task with a musculoskeletal model in a simulated physics environment. The mouse arm model is currently training at faster than 1 million training steps per second due to GPU acceleration with JAX and Mujoco-MJX. We present results that indicate that adding naturalistic constraints on energy and velocity lead to simulated musculoskeletal activity that better predict real EMG signals. This work provides evidence to suggest that energy and control constraints are critical to modeling musculoskeletal motor control.

---

### LILAD: Learning In-context Lyapunov-stable Adaptive Dynamics Models

Authors: Amit Jena, Na Li, Le Xie
Published: 2025-11-26
Categories: eess.SY, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.21846v1

System identification in control theory aims to approximate dynamical systems from trajectory data. While neural networks have demonstrated strong predictive accuracy, they often fail to preserve critical physical properties such as stability and typically assume stationary dynamics, limiting their applicability under distribution shifts. Existing approaches generally address either stability or adaptability in isolation, lacking a unified framework that ensures both. We propose LILAD (Learning In-Context Lyapunov-stable Adaptive Dynamics), a novel framework for system identification that jointly guarantees adaptability and stability. LILAD simultaneously learns a dynamics model and a Lyapunov function through in-context learning (ICL), explicitly accounting for parametric uncertainty. Trained across a diverse set of tasks, LILAD produces a stability-aware, adaptive dynamics model alongside an adaptive Lyapunov certificate. At test time, both components adapt to a new system instance using a short trajectory prompt, which enables fast generalization. To rigorously ensure stability, LILAD also computes a state-dependent attenuator that enforces a sufficient decrease condition on the Lyapunov function for any state in the new system instance. This mechanism extends stability guarantees even under out-of-distribution and out-of-task scenarios. We evaluate LILAD on benchmark autonomous systems and demonstrate that it outperforms adaptive, robust, and non-adaptive baselines in predictive accuracy.

---

### FLAWS: A Benchmark for Error Identification and Localization in Scientific Papers

Authors: Sarina Xi, Vishisht Rao, Justin Payan, Nihar B. Shah
Published: 2025-11-26
Categories: cs.CL, cs.AI, cs.DL, cs.LG
arXiv: https://arxiv.org/abs/2511.21843v1

The identification and localization of errors is a core task in peer review, yet the exponential growth of scientific output has made it increasingly difficult for human reviewers to reliably detect errors given the limited pool of experts. Recent advances in Large Language Models (LLMs) have sparked interest in their potential to support such evaluation tasks, from academic peer review to automated scientific assessment. However, despite the growing use of LLMs in review systems, their capabilities to pinpoint errors remain underexplored. In this work, we introduce Fault Localization Across Writing in Science (FLAWS), an automated benchmark consisting of 713 paper-error pairs designed to evaluate how effectively LLMs detect errors that undermine key claims in research papers. We construct the benchmark by systematically inserting claim-invalidating errors into peer-reviewed papers using LLMs, paired with an automated evaluation metric that measures whether models can identify and localize these errors. Developing such a benchmark presents unique challenges that we overcome: ensuring that the inserted errors are well-defined, challenging, and relevant to the content of the paper, avoiding artifacts that would make identification trivial, and designing a scalable, automated evaluation metric. On the resulting benchmark, we evaluate five frontier LLMs: Claude Sonnet 4.5, DeepSeek Reasoner v3.1, Gemini 2.5 Pro, GPT 5, and Grok 4. Among these, GPT 5 is the top-performing model, achieving 39.1% identification accuracy when k=10, where k is the number of top-ranked error text candidates generated by the LLM.

---

### Unsupervised Anomaly Detection for Smart IoT Devices: Performance and Resource Comparison

Authors: Md. Sad Abdullah Sami, Mushfiquzzaman Abid
Published: 2025-11-26
Categories: cs.LG, cs.CR
arXiv: https://arxiv.org/abs/2511.21842v1

The rapid expansion of Internet of Things (IoT) deployments across diverse sectors has significantly enhanced operational efficiency, yet concurrently elevated cybersecurity vulnerabilities due to increased exposure to cyber threats. Given the limitations of traditional signature-based Anomaly Detection Systems (ADS) in identifying emerging and zero-day threats, this study investigates the effectiveness of two unsupervised anomaly detection techniques, Isolation Forest (IF) and One-Class Support Vector Machine (OC-SVM), using the TON_IoT thermostat dataset. A comprehensive evaluation was performed based on standard metrics (accuracy, precision, recall, and F1-score) alongside critical resource utilization metrics such as inference time, model size, and peak RAM usage. Experimental results revealed that IF consistently outperformed OC-SVM, achieving higher detection accuracy, superior precision, and recall, along with a significantly better F1-score. Furthermore, Isolation Forest demonstrated a markedly superior computational footprint, making it more suitable for deployment on resource-constrained IoT edge devices. These findings underscore Isolation Forest's robustness in high-dimensional and imbalanced IoT environments and highlight its practical viability for real-time anomaly detection.

---

### Dark Speculation: Combining Qualitative and Quantitative Understanding in Frontier AI Risk Analysis

Authors: Daniel Carpenter, Carson Ezell, Pratyush Mallick, Alexandria Westray
Published: 2025-11-26
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2511.21838v2

Estimating catastrophic harms from frontier AI is hindered by deep ambiguity: many of its risks are not only unobserved but unanticipated by analysts. The central limitation of current risk analysis is the inability to populate the $\textit{catastrophic event space}$, or the set of potential large-scale harms to which probabilities might be assigned. This intractability is worsened by the $\textit{Lucretius problem}$, or the tendency to infer future risks only from past experience. We propose a process of $\textit{dark speculation}$, in which systematically generating and refining catastrophic scenarios ("qualitative" work) is coupled with estimating their likelihoods and associated damages (quantitative underwriting analysis). The idea is neither to predict the future nor to enable insurance for its own sake, but to use narrative and underwriting tools together to generate probability distributions over outcomes. We formalize this process using a simplified catastrophic Lévy stochastic framework and propose an iterative institutional design in which (1) speculation (including scenario planning) generates detailed catastrophic event narratives, (2) insurance underwriters assign probabilistic and financial parameters to these narratives, and (3) decision-makers synthesize the results into summary statistics to inform judgment. Analysis of the model reveals the value of (a) maintaining independence between speculation and underwriting, (b) analyzing multiple risk categories in parallel, and (c) generating "thick" catastrophic narrative rich in causal (counterfactual) and mitigative detail. While the approach cannot eliminate deep ambiguity, it offers a systematic approach to reason about extreme, low-probability events in frontier AI, tempering complacency and overreaction. The framework is adaptable for iterative use and can be further augmented with AI systems.

---

### Evaluating Strategies for Synthesizing Clinical Notes for Medical Multimodal AI

Authors: Niccolo Marini, Zhaohui Liang, Sivaramakrishnan Rajaraman, Zhiyun Xue, Sameer Antani
Published: 2025-11-26
Categories: cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2511.21827v1

Multimodal (MM) learning is emerging as a promising paradigm in biomedical artificial intelligence (AI) applications, integrating complementary modality, which highlight different aspects of patient health. The scarcity of large heterogeneous biomedical MM data has restrained the development of robust models for medical AI applications. In the dermatology domain, for instance, skin lesion datasets typically include only images linked to minimal metadata describing the condition, thereby limiting the benefits of MM data integration for reliable and generalizable predictions. Recent advances in Large Language Models (LLMs) enable the synthesis of textual description of image findings, potentially allowing the combination of image and text representations. However, LLMs are not specifically trained for use in the medical domain, and their naive inclusion has raised concerns about the risk of hallucinations in clinically relevant contexts. This work investigates strategies for generating synthetic textual clinical notes, in terms of prompt design and medical metadata inclusion, and evaluates their impact on MM architectures toward enhancing performance in classification and cross-modal retrieval tasks. Experiments across several heterogeneous dermatology datasets demonstrate that synthetic clinical notes not only enhance classification performance, particularly under domain shift, but also unlock cross-modal retrieval capabilities, a downstream task that is not explicitly optimized during training.

---

### Beyond Membership: Limitations of Add/Remove Adjacency in Differential Privacy

Authors: Gauri Pradhan, Joonas Jälkö, Santiago Zanella-Béguelin, Antti Honkela
Published: 2025-11-26
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2511.21804v2

Training machine learning models with differential privacy (DP) limits an adversary's ability to infer sensitive information about the training data. It can be interpreted as a bound on adversary's capability to distinguish two adjacent datasets according to chosen adjacency relation. In practice, most DP implementations use the add/remove adjacency relation, where two datasets are adjacent if one can be obtained from the other by adding or removing a single record, thereby protecting membership. In many ML applications, however, the goal is to protect attributes of individual records (e.g., labels used in supervised fine-tuning). We show that privacy accounting under add/remove overstates attribute privacy compared to accounting under the substitute adjacency relation, which permits substituting one record. To demonstrate this gap, we develop novel attacks to audit DP under substitute adjacency, and show empirically that audit results are inconsistent with DP guarantees reported under add/remove, yet remain consistent with the budget accounted under the substitute adjacency relation. Our results highlight that the choice of adjacency when reporting DP guarantees is critical when the protection target is per-record attributes rather than membership.

---