# Research Papers — 2025-11 · bundle page 126 of 197 > Full-text markdown of papers #6251–6300 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/126 [← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/125.md) [Next bundle →](https://aipod.dev/papers/archive/2025-11/page/127.md) ### Do AI Voices Learn Social Nuances? A Case of Politeness and Speech Rate Authors: Eyal Rabin, Zohar Elyoseph, Rotem Israel-Fishelson, Adi Dali, Ravit Nussinson Published: 2025-11-12 Categories: cs.CL, cs.AI, cs.HC, cs.SD arXiv: https://arxiv.org/abs/2511.10693v1 Voice-based artificial intelligence is increasingly expected to adhere to human social conventions, but can it learn implicit cues that are not explicitly programmed? This study investigates whether state-of-the-art text-to-speech systems have internalized the human tendency to reduce speech rate to convey politeness - a non-obvious prosodic marker. We prompted 22 synthetic voices from two leading AI platforms (AI Studio and OpenAI) to read a fixed script under both "polite and formal" and "casual and informal" conditions and measured the resulting speech duration. Across both AI platforms, the polite prompt produced slower speech than the casual prompt with very large effect sizes, an effect that was statistically significant for all of AI Studio's voices and for a large majority of OpenAI's voices. These results demonstrate that AI can implicitly learn and replicate psychological nuances of human communication, highlighting its emerging role as a social actor capable of reinforcing human social norms. --- ### Evaluating from Benign to Dynamic Adversarial: A Squid Game for Large Language Models Authors: Zijian Chen, Wenjun Zhang, Guangtao Zhai Published: 2025-11-12 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.10691v2 The potential data contamination issue in contemporary large language models (LLMs) benchmarks presents a fundamental challenge to establishing trustworthy evaluation frameworks. Meanwhile, they predominantly assume benign, resource-rich settings, leaving the behavior of LLMs under pressure unexplored. In this paper, we introduce \textsc{Squid Game}, a dynamic and adversarial evaluation environment with resource-constrained and asymmetric information settings elaborated to evaluate LLMs through interactive gameplay against other LLM opponents. Squid Game consists of six elimination-style levels, focusing on multi-faceted abilities, including instruction-following, code, reasoning, planning, and safety alignment. We evaluate over 50 LLMs on Squid Game, presenting the largest behavioral evaluation study of general LLMs on dynamic adversarial scenarios. We observe a clear generational phase transition in performance in the same model lineage and find evidence that some models resort to speculative shortcuts to win the game, indicating the possibility of higher-level evaluation paradigm contamination in static benchmarks. We also compare prominent LLM benchmarks and \textsc{Squid Game}, highlighting that dynamic evaluation can serve as a complementary part for static evaluations. Project page: https://github.com/zijianchen98/LLM_Squid_Game. --- ### Saying the Unsaid: Revealing the Hidden Language of Multimodal Systems Through Telephone Games Authors: Juntu Zhao, Jialing Zhang, Chongxuan Li, Dequan Wang Published: 2025-11-12 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.10690v1 Recent closed-source multimodal systems have made great advances, but their hidden language for understanding the world remains opaque because of their black-box architectures. In this paper, we use the systems' preference bias to study their hidden language: During the process of compressing the input images (typically containing multiple concepts) into texts and then reconstructing them into images, the systems' inherent preference bias introduces specific shifts in the outputs, disrupting the original input concept co-occurrence. We employ the multi-round "telephone game" to strategically leverage this bias. By observing the co-occurrence frequencies of concepts in telephone games, we quantitatively investigate the concept connection strength in the understanding of multimodal systems, i.e., "hidden language." We also contribute Telescope, a dataset of 10,000+ concept pairs, as the database of our telephone game framework. Our telephone game is test-time scalable: By iteratively running telephone games, we can construct a global map of concept connections in multimodal systems' understanding. Here we can identify preference bias inherited from training, assess generalization capability advancement, and discover more stable pathways for fragile concept connections. Furthermore, we use Reasoning-LLMs to uncover unexpected concept relationships that transcend textual and visual similarities, inferring how multimodal systems understand and simulate the world. This study offers a new perspective on the hidden language of multimodal systems and lays the foundation for future research on the interpretability and controllability of multimodal systems. --- ### Equilibrium Dynamics and Mitigation of Gender Bias in Synthetically Generated Data Authors: Ashish Kattamuri, Arpita Vats, Harshwardhan Fartale, Rahul Raja, Akshata Kishore Moharir, Ishita Prasad Published: 2025-11-12 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.10689v1 Recursive prompting with large language models enables scalable synthetic dataset generation but introduces the risk of bias amplification. We investigate gender bias dynamics across three generations of recursive text generation using three complementary evaluation frameworks: rule-based pattern matching, embedding-based semantic similarity, and downstream task performance. Experiments with three initial bias levels (0.1, 0.3, 0.6) and four mitigation strategies reveal equilibrium dynamics rather than monotonic amplification. The low initial bias amplifies toward the model's inherent bias level (+36%), whereas the high initial bias decays toward it (-26%). Among mitigation methods, contrastive augmentation, which introduces gender-swapped variants, achieves significant downstream bias reduction (98.8% for low initial bias and 91% on average) despite producing higher embedding-based bias scores. This paradox demonstrates that semantic similarity metrics may diverge from behavioral fairness outcomes, highlighting the need for multidimensional evaluation in responsible synthetic data generation. --- ### Modeling and Predicting Multi-Turn Answer Instability in Large Language Models Authors: Jiahang He, Rishi Ramachandran, Neel Ramachandran, Aryan Katakam, Kevin Zhu, Sunishchal Dev, Ashwinee Panda, Aryan Shrivastava Published: 2025-11-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.10688v1 As large language models (LLMs) are adopted in an increasingly wide range of applications, user-model interactions have grown in both frequency and scale. Consequently, research has focused on evaluating the robustness of LLMs, an essential quality for real-world tasks. In this paper, we employ simple multi-turn follow-up prompts to evaluate models' answer changes, model accuracy dynamics across turns with Markov chains, and examine whether linear probes can predict these changes. Our results show significant vulnerabilities in LLM robustness: a simple "Think again" prompt led to an approximate 10% accuracy drop for Gemini 1.5 Flash over nine turns, while combining this prompt with a semantically equivalent reworded question caused a 7.5% drop for Claude 3.5 Haiku. Additionally, we find that model accuracy across turns can be effectively modeled using Markov chains, enabling the prediction of accuracy probabilities over time. This allows for estimation of the model's stationary (long-run) accuracy, which we find to be on average approximately 8% lower than its first-turn accuracy for Gemini 1.5 Flash. Our results from a model's hidden states also reveal evidence that linear probes can help predict future answer changes. Together, these results establish stationary accuracy as a principled robustness metric for interactive settings and expose the fragility of models under repeated questioning. Addressing this instability will be essential for deploying LLMs in high-stakes and interactive settings where consistent reasoning is as important as initial accuracy. --- ### Robust Watermarking on Gradient Boosting Decision Trees Authors: Jun Woo Chung, Yingjie Lao, Weijie Zhao Published: 2025-11-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.09822v1 Gradient Boosting Decision Trees (GBDTs) are widely used in industry and academia for their high accuracy and efficiency, particularly on structured data. However, watermarking GBDT models remains underexplored compared to neural networks. In this work, we present the first robust watermarking framework tailored to GBDT models, utilizing in-place fine-tuning to embed imperceptible and resilient watermarks. We propose four embedding strategies, each designed to minimize impact on model accuracy while ensuring watermark robustness. Through experiments across diverse datasets, we demonstrate that our methods achieve high watermark embedding rates, low accuracy degradation, and strong resistance to post-deployment fine-tuning. --- ### From Street to Orbit: Training-Free Cross-View Retrieval via Location Semantics and LLM Guidance Authors: Jeongho Min, Dongyoung Kim, Jaehyup Lee Published: 2025-11-12 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.09820v1 Cross-view image retrieval, particularly street-to-satellite matching, is a critical task for applications such as autonomous navigation, urban planning, and localization in GPS-denied environments. However, existing approaches often require supervised training on curated datasets and rely on panoramic or UAV-based images, which limits real-world deployment. In this paper, we present a simple yet effective cross-view image retrieval framework that leverages a pretrained vision encoder and a large language model (LLM), requiring no additional training. Given a monocular street-view image, our method extracts geographic cues through web-based image search and LLM-based location inference, generates a satellite query via geocoding API, and retrieves matching tiles using a pretrained vision encoder (e.g., DINOv2) with PCA-based whitening feature refinement. Despite using no ground-truth supervision or finetuning, our proposed method outperforms prior learning-based approaches on the benchmark dataset under zero-shot settings. Moreover, our pipeline enables automatic construction of semantically aligned street-to-satellite datasets, which is offering a scalable and cost-efficient alternative to manual annotation. All source codes will be made publicly available at https://jeonghomin.github.io/street2orbit.github.io/. --- ### Improving Graduate Outcomes by Identifying Skills Gaps and Recommending Courses Based on Career Interests Authors: Rahul Soni, Basem Suleiman, Sonit Singh Published: 2025-11-12 Categories: cs.CL, cs.CY arXiv: https://arxiv.org/abs/2511.09819v1 This paper aims to address the challenge of selecting relevant courses for students by proposing the design and development of a course recommendation system. The course recommendation system utilises a combination of data analytics techniques and machine learning algorithms to recommend courses that align with current industry trends and requirements. In order to provide customised suggestions, the study entails the design and implementation of an extensive algorithmic framework that combines machine learning methods, user preferences, and academic criteria. The system employs data mining and collaborative filtering techniques to examine past courses and individual career goals in order to provide course recommendations. Moreover, to improve the accessibility and usefulness of the recommendation system, special attention is given to the development of an easy-to-use front-end interface. The front-end design prioritises visual clarity, interaction, and simplicity through iterative prototyping and user input revisions, guaranteeing a smooth and captivating user experience. We refined and optimised the proposed system by incorporating user feedback, ensuring that it effectively meets the needs and preferences of its target users. The proposed course recommendation system could be a useful tool for students, instructors, and career advisers to use in promoting lifelong learning and professional progression as it fills the gap between university learning and industry expectations. We hope that the proposed course recommendation system will help university students in making data-drive and industry-informed course decisions, in turn, improving graduate outcomes for the university sector. --- ### Lumos3D: A Single-Forward Framework for Low-Light 3D Scene Restoration Authors: Hanzhou Liu, Peng Jiang, Jia Huang, Mi Lu Published: 2025-11-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.09818v3 Restoring 3D scenes with low-light conditions is challenging, and most existing methods depend on precomputed camera poses and scene-specific optimization, which greatly restricts their application to real-world scenarios. To overcome these limitations, we propose Lumos3D, a pose-free single-forward framework for 3D low-light scene restoration. First, we develop a cross-illumination distillation scheme, where a frozen teacher network takes normal-light ground truth images as input to distill accurate geometric information to the student model. Second, we define a Lumos loss to improve the restoration quality of the reconstructed 3D Gaussian space. Trained on a single dataset, Lumos3D performs inference in a purely feed-forward manner, directly restoring illumination and structure from unposed, low-light multi-view images without any per-scene training or optimization. Experiments on real-world datasets demonstrate that Lumos3D achieves competitive restoration results compared to scene-specific methods. Our codes are available at https://github.com/HanzhouLiu/Lumos3D. --- ### Multiple Treatments Causal Effects Estimation with Task Embeddings and Balanced Representation Learning Authors: Yuki Murakami, Takumi Hattori, Kohsuke Kubota Published: 2025-11-12 Categories: stat.ME, cs.AI arXiv: https://arxiv.org/abs/2511.09814v1 The simultaneous application of multiple treatments is increasingly common in many fields, such as healthcare and marketing. In such scenarios, it is important to estimate the single treatment effects and the interaction treatment effects that arise from treatment combinations. Previous studies have proposed using independent outcome networks with subnetworks for interactions, or combining task embedding networks that capture treatment similarity with variational autoencoders. However, these methods suffer from the lack of parameter sharing among related treatments, or the estimation of unnecessary latent variables reduces the accuracy of causal effect estimation. To address these issues, we propose a novel deep learning framework that incorporates a task embedding network and a representation learning network with the balancing penalty. The task embedding network enables parameter sharing across related treatment patterns because it encodes elements common to single effects and contributions specific to interaction effects. The representation learning network with the balancing penalty learns representations nonparametrically from observed covariates while reducing distances in representation distributions across different treatment patterns. This process mitigates selection bias and avoids model misspecification. Simulation studies demonstrate that the proposed method outperforms existing baselines, and application to real-world marketing datasets confirms the practical implications and utility of our framework. --- ### Khmer Spellchecking: A Holistic Approach Authors: Marry Kong, Rina Buoy, Sovisal Chenda, Nguonly Taing Published: 2025-11-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.09812v1 Compared to English and other high-resource languages, spellchecking for Khmer remains an unresolved problem due to several challenges. First, there are misalignments between words in the lexicon and the word segmentation model. Second, a Khmer word can be written in different forms. Third, Khmer compound words are often loosely and easily formed, and these compound words are not always found in the lexicon. Fourth, some proper nouns may be flagged as misspellings due to the absence of a Khmer named-entity recognition (NER) model. Unfortunately, existing solutions do not adequately address these challenges. This paper proposes a holistic approach to the Khmer spellchecking problem by integrating Khmer subword segmentation, Khmer NER, Khmer grapheme-to-phoneme (G2P) conversion, and a Khmer language model to tackle these challenges, identify potential correction candidates, and rank the most suitable candidate. Experimental results show that the proposed approach achieves a state-of-the-art Khmer spellchecking accuracy of up to 94.4%, compared to existing solutions. The benchmark datasets for Khmer spellchecking and NER tasks in this study will be made publicly available. --- ### On the Convergence of Overparameterized Problems: Inherent Properties of the Compositional Structure of Neural Networks Authors: Arthur Castello Branco de Oliveira, Dhruv Jatkar, Eduardo Sontag Published: 2025-11-12 Categories: cs.LG, cs.AI, eess.SY, math.OC arXiv: https://arxiv.org/abs/2511.09810v1 This paper investigates how the compositional structure of neural networks shapes their optimization landscape and training dynamics. We analyze the gradient flow associated with overparameterized optimization problems, which can be interpreted as training a neural network with linear activations. Remarkably, we show that the global convergence properties can be derived for any cost function that is proper and real analytic. We then specialize the analysis to scalar-valued cost functions, where the geometry of the landscape can be fully characterized. In this setting, we demonstrate that key structural features -- such as the location and stability of saddle points -- are universal across all admissible costs, depending solely on the overparameterized representation rather than on problem-specific details. Moreover, we show that convergence can be arbitrarily accelerated depending on the initialization, as measured by an imbalance metric introduced in this work. Finally, we discuss how these insights may generalize to neural networks with sigmoidal activations, showing through a simple example which geometric and dynamical properties persist beyond the linear case. --- ### Test-Time Spectrum-Aware Latent Steering for Zero-Shot Generalization in Vision-Language Models Authors: Konstantinos M. Dafnis, Dimitris N. Metaxas Published: 2025-11-12 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.09809v2 Vision-Language Models (VLMs) excel at zero-shot inference but often degrade under test-time domain shifts. For this reason, episodic test-time adaptation strategies have recently emerged as powerful techniques for adapting VLMs to a single unlabeled image. However, existing adaptation strategies, such as test-time prompt tuning, typically require backpropagating through large encoder weights or altering core model components. In this work, we introduce Spectrum-Aware Test-Time Steering (STS), a lightweight adaptation framework that extracts a spectral subspace from the textual embeddings to define principal semantic directions and learns to steer latent representations in a spectrum-aware manner by adapting a small number of per-sample shift parameters to minimize entropy across augmented views. STS operates entirely at inference in the latent space, without backpropagation through or modification of the frozen encoders. Building on standard evaluation protocols, our comprehensive experiments demonstrate that STS largely surpasses or compares favorably against state-of-the-art test-time adaptation methods, while introducing only a handful of additional parameters and achieving inference speeds up to 8x faster with a 12x smaller memory footprint than conventional test-time prompt tuning. The code is available at https://github.com/kdafnis/STS. --- ### Constrained Best Arm Identification with Tests for Feasibility Authors: Ting Cai, Kirthevasan Kandasamy Published: 2025-11-12 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.09808v2 Best arm identification (BAI) aims to identify the highest-performance arm among a set of $K$ arms by collecting stochastic samples from each arm. In real-world problems, the best arm needs to satisfy additional feasibility constraints. While there is limited prior work on BAI with feasibility constraints, they typically assume the performance and constraints are observed simultaneously on each pull of an arm. However, this assumption does not reflect most practical use cases, e.g., in drug discovery, we wish to find the most potent drug whose toxicity and solubility are below certain safety thresholds. These safety experiments can be conducted separately from the potency measurement. Thus, this requires designing BAI algorithms that not only decide which arm to pull but also decide whether to test for the arm's performance or feasibility. In this work, we study feasible BAI which allows a decision-maker to choose a tuple $(i,\ell)$, where $i\in (K)$ denotes an arm and $\ell$ denotes whether she wishes to test for its performance ($\ell=0$) or any of its $N$ feasibility constraints ($\ell\in(N)$). We focus on the fixed confidence setting, which is to identify the feasible arm with the highest performance, with a probability of at least $1-δ$. We propose an efficient algorithm and upper-bound its sample complexity, showing our algorithm can naturally adapt to the problem's difficulty and eliminate arms by worse performance or infeasibility, whichever is easier. We complement this upper bound with a lower bound showing that our algorithm is \textit{asymptotically ($δ\rightarrow 0$) optimal}. Finally, we empirically show that our algorithm outperforms other state-of-the-art BAI algorithms in both synthetic and real-world datasets. --- ### SlideBot: A Multi-Agent Framework for Generating Informative, Reliable, Multi-Modal Presentations Authors: Eric Xie, Danielle Waterfield, Michael Kennedy, Aidong Zhang Published: 2025-11-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.09804v1 Large Language Models (LLMs) have shown immense potential in education, automating tasks like quiz generation and content summarization. However, generating effective presentation slides introduces unique challenges due to the complexity of multimodal content creation and the need for precise, domain-specific information. Existing LLM-based solutions often fail to produce reliable and informative outputs, limiting their educational value. To address these limitations, we introduce SlideBot - a modular, multi-agent slide generation framework that integrates LLMs with retrieval, structured planning, and code generation. SlideBot is organized around three pillars: informativeness, ensuring deep and contextually grounded content; reliability, achieved by incorporating external sources through retrieval; and practicality, which enables customization and iterative feedback through instructor collaboration. It incorporates evidence-based instructional design principles from Cognitive Load Theory (CLT) and the Cognitive Theory of Multimedia Learning (CTML), using structured planning to manage intrinsic load and consistent visual macros to reduce extraneous load and enhance dual-channel learning. Within the system, specialized agents collaboratively retrieve information, summarize content, generate figures, and format slides using LaTeX, aligning outputs with instructor preferences through interactive refinement. Evaluations from domain experts and students in AI and biomedical education show that SlideBot consistently enhances conceptual accuracy, clarity, and instructional value. These findings demonstrate SlideBot's potential to streamline slide preparation while ensuring accuracy, relevance, and adaptability in higher education. --- ### Retrieval as a Decision: Training-Free Adaptive Gating for Efficient RAG Authors: Yufeng Wang, Lu wei, Haibin Ling Published: 2025-11-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.09803v2 Retrieval-Augmented Generation (RAG) improves factuality but retrieving for every query often hurts quality while inflating tokens and latency. We propose Training-free Adaptive Retrieval Gating (TARG), a single-shot policy that decides when to retrieve using only a short, no-context draft from the base model. From the draft's prefix logits, TARG computes lightweight uncertainty scores-mean token entropy, a margin signal derived from the top-1/top-2 logit gap via a monotone link, or small-N variance across a handful of stochastic prefixes-and triggers retrieval only when the score exceeds a threshold. The gate is model-agnostic, adds only tens to hundreds of draft tokens, and requires no additional training or auxiliary heads. On five QA benchmarks spanning short-answer (NQ-Open, TriviaQA, PopQA), multi-hop (MuSiQue), and long-form (ASQA) tasks, TARG consistently pushes the accuracy-efficiency frontier: compared with Alway-RAG, TARG matches or improves EM/F1 while reducing retrieval by 70-90% and cutting end-to-end latency, and it remains close to Never-RAG in overhead. A central empirical finding is that under modern instruction-tuned LLMs the margin signal is a robust default (entropy compresses as backbones sharpen), with small-N variance offering a conservative, budget-first alternative. We provide ablations over gate type and prefix length and use a $Δ$-latency view to make budget trade-offs explicit. --- ### Generalized infinite dimensional Alpha-Procrustes based geometries Authors: Salvish Goomanee, Andi Han, Pratik Jawanpuria, Bamdev Mishra Published: 2025-11-12 Categories: stat.ML, cs.LG, math.FA, math.OC arXiv: https://arxiv.org/abs/2511.09801v3 This work extends the recently introduced Alpha-Procrustes family of Riemannian metrics for symmetric positive definite (SPD) matrices by incorporating generalized versions of the Bures-Wasserstein (GBW), Log-Euclidean, and Wasserstein distances. While the Alpha-Procrustes framework has unified many classical metrics in both finite- and infinite- dimensional settings, it previously lacked the structural components necessary to realize these generalized forms. We introduce a formalism based on unitized Hilbert-Schmidt operators and an extended Mahalanobis norm that allows the construction of robust, infinite-dimensional generalizations of GBW and Log-Hilbert-Schmidt distances. Our approach also incorporates a learnable regularization parameter that enhances geometric stability in high-dimensional comparisons. Preliminary experiments reproducing benchmarks from the literature demonstrate the improved performance of our generalized metrics, particularly in scenarios involving comparisons between datasets of varying dimension and scale. This work lays a theoretical and computational foundation for advancing robust geometric methods in machine learning, statistical inference, and functional data analysis. --- ### Predicate-Argument Structure Divergences in Chinese and English Parallel Sentences and their Impact on Language Transfer Authors: Rocco Tripodi, Xiaoyu Liu Published: 2025-11-12 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.09796v1 Cross-lingual Natural Language Processing (NLP) has gained significant traction in recent years, offering practical solutions in low-resource settings by transferring linguistic knowledge from resource-rich to low-resource languages. This field leverages techniques like annotation projection and model transfer for language adaptation, supported by multilingual pre-trained language models. However, linguistic divergences hinder language transfer, especially among typologically distant languages. In this paper, we present an analysis of predicate-argument structures in parallel Chinese and English sentences. We explore the alignment and misalignment of predicate annotations, inspecting similarities and differences and proposing a categorization of structural divergences. The analysis and the categorization are supported by a qualitative and quantitative analysis of the results of an annotation projection experiment, in which, in turn, one of the two languages has been used as source language to project annotations into the corresponding parallel sentences. The results of this analysis show clearly that language transfer is asymmetric. An aspect that requires attention when it comes to selecting the source language in transfer learning applications and that needs to be investigated before any scientific claim about cross-lingual NLP is proposed. --- ### Beyond Monotonicity: Revisiting Factorization Principles in Multi-Agent Q-Learning Authors: Tianmeng Hu, Yongzheng Cui, Rui Tang, Biao Luo, Ke Li Published: 2025-11-12 Categories: cs.LG, cs.MA arXiv: https://arxiv.org/abs/2511.09792v1 Value decomposition is a central approach in multi-agent reinforcement learning (MARL), enabling centralized training with decentralized execution by factorizing the global value function into local values. To ensure individual-global-max (IGM) consistency, existing methods either enforce monotonicity constraints, which limit expressive power, or adopt softer surrogates at the cost of algorithmic complexity. In this work, we present a dynamical systems analysis of non-monotonic value decomposition, modeling learning dynamics as continuous-time gradient flow. We prove that, under approximately greedy exploration, all zero-loss equilibria violating IGM consistency are unstable saddle points, while only IGM-consistent solutions are stable attractors of the learning dynamics. Extensive experiments on both synthetic matrix games and challenging MARL benchmarks demonstrate that unconstrained, non-monotonic factorization reliably recovers IGM-optimal solutions and consistently outperforms monotonic baselines. Additionally, we investigate the influence of temporal-difference targets and exploration strategies, providing actionable insights for the design of future value-based MARL algorithms. --- ### PANDA -- Patch And Distribution-Aware Augmentation for Long-Tailed Exemplar-Free Continual Learning Authors: Siddeshwar Raghavan, Jiangpeng He, Fengqing Zhu Published: 2025-11-12 Categories: cs.CV, eess.IV arXiv: https://arxiv.org/abs/2511.09791v3 Exemplar-Free Continual Learning (EFCL) restricts the storage of previous task data and is highly susceptible to catastrophic forgetting. While pre-trained models (PTMs) are increasingly leveraged for EFCL, existing methods often overlook the inherent imbalance of real-world data distributions. We discovered that real-world data streams commonly exhibit dual-level imbalances, dataset-level distributions combined with extreme or reversed skews within individual tasks, creating both intra-task and inter-task disparities that hinder effective learning and generalization. To address these challenges, we propose PANDA, a Patch-and-Distribution-Aware Augmentation framework that integrates seamlessly with existing PTM-based EFCL methods. PANDA amplifies low-frequency classes by using a CLIP encoder to identify representative regions and transplanting those into frequent-class samples within each task. Furthermore, PANDA incorporates an adaptive balancing strategy that leverages prior task distributions to smooth inter-task imbalances, reducing the overall gap between average samples across tasks and enabling fairer learning with frozen PTMs. Extensive experiments and ablation studies demonstrate PANDA's capability to work with existing PTM-based CL methods, improving accuracy and reducing catastrophic forgetting. --- ### A Robust Task-Level Control Architecture for Learned Dynamical Systems Authors: Eshika Pathak, Ahmed Aboudonia, Sandeep Banik, Naira Hovakimyan Published: 2025-11-12 Categories: cs.RO, cs.LG, eess.SY arXiv: https://arxiv.org/abs/2511.09790v2 Dynamical system (DS)-based learning from demonstration (LfD) is a powerful tool for generating motion plans in the operation ('task') space of robotic systems. However, realizing generated motion plans is often compromised by a "task-execution mismatch", where unmodeled dynamics, persistent disturbances, and system latency cause the robot's task-space state to diverge from the desired state. We propose a novel task-level robust control architecture, L1-augmented Dynamical Systems (L1-DS), that explicitly handles the task-execution mismatch in tracking a nominal motion plan generated by any DS-based LfD scheme. Our framework augments any DS-based LfD model with a nominal stabilizing controller and an L1 adaptive controller. Furthermore, we introduce a windowed Dynamic Time Warping (DTW)-based target selector, which enables the nominal stabilizing controller to handle temporal misalignment for improved phase-consistent tracking. We demonstrate the efficacy of our architecture on the LASA and IROS handwriting datasets. --- ### Trend-Aware Multi-Task Learning for Short-Term Energy Forecasting Authors: Fulong Yao, Wanqing Zhao, Chao Zheng, Xiaofei Han Published: 2025-11-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.09789v3 Short-term energy forecasting plays an important role in real-time operational decision-making, such as electricity market bidding and power system dispatch, where both numerical accuracy and correct directional signals are essential. However, most existing forecasting approaches formulate the problem purely as a regression task, limiting their ability to explicitly capture stepwise directional movements and trend consistency required for operational decisions. To address this limitation, this paper proposes a trend-aware multi-task forecasting framework that decomposes forecasting outputs into directional movements and deviation magnitudes relative to the latest observation, enabling both accurate numerical prediction and interpretable trend-aware outputs. The framework adopts a task-specific dual-stream architecture and explores key design choices for integrating trend and deviation information, including hard versus probabilistic trend representations, symmetric versus asymmetric deviation modelling, and parallel versus sequential conditioning strategies. To stabilize multi-task learning and reduce manual tuning, an uncertainty-aware task weighting scheme is incorporated to automatically balance directional classification, deviation regression, and final output prediction during training. Experimental results on real-world energy datasets demonstrate that the proposed framework achieves competitive numerical accuracy compared with state-of-the-art algorithms, while consistently improving trend prediction performance with moderate computational cost. This capability is particularly beneficial in short-term energy system management, where consistent directional forecasting can provide more reliable decision support for practical operational scenarios such as market bidding, resource scheduling, and risk-aware energy management. --- ### Why Open Small AI Models Matter for Interactive Art Authors: Mar Canet Sola, Varvara Guljajeva Published: 2025-11-12 Categories: cs.AI, cs.HC arXiv: https://arxiv.org/abs/2511.09788v1 This position paper argues for the importance of open small AI models in creative independence for interactive art practices. Deployable locally, these models offer artists vital control over infrastructure and code, unlike dominant large, closed-source corporate systems. Such centralized platforms function as opaque black boxes, imposing severe limitations on interactive artworks, including restrictive content filters, preservation issues, and technical challenges such as increased latency and limited interfaces. In contrast, small AI models empower creators with more autonomy, control, and sustainability for these artistic processes. They enable the ability to use a model as long as they want, create their own custom model, either by making code changes to integrate new interfaces, or via new datasets by re-training or fine-tuning the model. This fosters technological self-determination, offering greater ownership and reducing reliance on corporate AI ill-suited for interactive art's demands. Critically, this approach empowers the artist and supports long-term preservation and exhibition of artworks with AI components. This paper explores the practical applications and implications of using open small AI models in interactive art, contrasting them with closed-source alternatives. --- ### AI Annotation Orchestration: Evaluating LLM verifiers to Improve the Quality of LLM Annotations in Learning Analytics Authors: Bakhtawar Ahtisham, Kirk Vanacore, Jinsook Lee, Zhuqian Zhou, Doug Pietrzak, Rene F. Kizilcec Published: 2025-11-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.09785v2 Large Language Models (LLMs) are increasingly used to annotate learning interactions, yet concerns about reliability limit their utility. We test whether verification-oriented orchestration-prompting models to check their own labels (self-verification) or audit one another (cross-verification)-improves qualitative coding of tutoring discourse. Using transcripts from 30 one-to-one math sessions, we compare three production LLMs (GPT, Claude, Gemini) under three conditions: unverified annotation, self-verification, and cross-verification across all orchestration configurations. Outputs are benchmarked against a blinded, disagreement-focused human adjudication using Cohen's kappa. Overall, orchestration yields a 58 percent improvement in kappa. Self-verification nearly doubles agreement relative to unverified baselines, with the largest gains for challenging tutor moves. Cross-verification achieves a 37 percent improvement on average, with pair- and construct-dependent effects: some verifier-annotator pairs exceed self-verification, while others reduce alignment, reflecting differences in verifier strictness. We contribute: (1) a flexible orchestration framework instantiating control, self-, and cross-verification; (2) an empirical comparison across frontier LLMs on authentic tutoring data with blinded human "gold" labels; and (3) a concise notation, verifier(annotator) (e.g., Gemini(GPT) or Claude(Claude)), to standardize reporting and make directional effects explicit for replication. Results position verification as a principled design lever for reliable, scalable LLM-assisted annotation in Learning Analytics. --- ### Koopman Invariants as Drivers of Emergent Time-Series Clustering in Joint-Embedding Predictive Architectures Authors: Pablo Ruiz-Morales, Dries Vanoost, Davy Pissoort, Mathias Verbeke Published: 2025-11-12 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.09783v2 Joint-Embedding Predictive Architectures (JEPAs), a powerful class of self-supervised models, exhibit an unexplained ability to cluster time-series data by their underlying dynamical regimes. We propose a novel theoretical explanation for this phenomenon, hypothesizing that JEPA's predictive objective implicitly drives it to learn the invariant subspace of the system's Koopman operator. We prove that an idealized JEPA loss is minimized when the encoder represents the system's regime indicator functions, which are Koopman eigenfunctions. This theory was validated on synthetic data with known dynamics, demonstrating that constraining the JEPA's linear predictor to be a near-identity operator is the key inductive bias that forces the encoder to learn these invariants. We further discuss that this constraint is critical for selecting this interpretable solution from a class of mathematically equivalent but entangled optima, revealing the predictor's role in representation disentanglement. This work demystifies a key behavior of JEPAs, provides a principled connection between modern self-supervised learning and dynamical systems theory, and informs the design of more robust and interpretable time-series models. --- ### Hail to the Thief: Exploring Attacks and Defenses in Decentralised GRPO Authors: Nikolay Blagoev, Oğuzhan Ersoy, Lydia Yiyu Chen Published: 2025-11-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.09780v2 Group Relative Policy Optimization (GRPO) has demonstrated wide adoption in the post-training of Large Language Models (LLMs). In GRPO, prompts are answered by the model and preferred behaviour is learnt via reinforcement learning. Owing to the small communication volume, GRPO is inherently suitable for decentralised training as the prompts can be concurrently answered by multiple nodes and these completions are exchanged in the form of strings. In this work, we explore the robustness of decentralised GRPO by presenting the first adversarial attacks and countermeasures. We present a diverse set of attacks where malicious nodes poison benign models by sharing their poisoned completions. We demonstrate these attacks on math and coding tasks and show that an adversary can achieve attack success rates of up to 100% in as few as 50 iterations. Moreover, to mitigate the attacks, we propose two defense mechanisms that check logit probabilities of completions or utilize an LLM judge to filter completions. The defenses prevent all but the DoS attack that causes unnecessarily lengthy but conceptually correct completions. The code of both attacks and defenses can be found at: https://github.com/gensyn-ai/HTTT. --- ### Privacy-Preserving Explainable AIoT Application via SHAP Entropy Regularization Authors: Dilli Prasad Sharma, Xiaowei Sun, Liang Xue, Xiaodong Lin, Pulei Xiong Published: 2025-11-12 Categories: cs.CR, cs.AI, cs.IT, cs.LG, cs.NI arXiv: https://arxiv.org/abs/2511.09775v2 The widespread integration of Artificial Intelligence of Things (AIoT) in smart home environments has amplified the demand for transparent and interpretable machine learning models. To foster user trust and comply with emerging regulatory frameworks, the Explainable AI (XAI) methods, particularly post-hoc techniques such as SHapley Additive exPlanations (SHAP), and Local Interpretable Model-Agnostic Explanations (LIME), are widely employed to elucidate model behavior. However, recent studies have shown that these explanation methods can inadvertently expose sensitive user attributes and behavioral patterns, thereby introducing new privacy risks. To address these concerns, we propose a novel privacy-preserving approach based on SHAP entropy regularization to mitigate privacy leakage in explainable AIoT applications. Our method incorporates an entropy-based regularization objective that penalizes low-entropy SHAP attribution distributions during training, promoting a more uniform spread of feature contributions. To evaluate the effectiveness of our approach, we developed a suite of SHAP-based privacy attacks that strategically leverage model explanation outputs to infer sensitive information. We validate our method through comparative evaluations using these attacks alongside utility metrics on benchmark smart home energy consumption datasets. Experimental results demonstrate that SHAP entropy regularization substantially reduces privacy leakage compared to baseline models, while maintaining high predictive accuracy and faithful explanation fidelity. This work contributes to the development of privacy-preserving explainable AI techniques for secure and trustworthy AIoT applications. --- ### Solvaformer: an SE(3)-equivariant graph transformer for small molecule solubility prediction Authors: Jonathan Broadbent, Michael Bailey, Mingxuan Li, Abhishek Paul, Louis De Lescure, Paul Chauvin, Lorenzo Kogler-Anele, Yasser Jangjou, Sven Jager Published: 2025-11-12 Categories: physics.chem-ph, cs.AI arXiv: https://arxiv.org/abs/2511.09774v1 Accurate prediction of small molecule solubility using material-sparing approaches is critical for accelerating synthesis and process optimization, yet experimental measurement is costly and many learning approaches either depend on quantumderived descriptors or offer limited interpretability. We introduce Solvaformer, a geometry-aware graph transformer that models solutions as multiple molecules with independent SE(3) symmetries. The architecture combines intramolecular SE(3)-equivariant attention with intermolecular scalar attention, enabling cross-molecular communication without imposing spurious relative geometry. We train Solvaformer in a multi-task setting to predict both solubility (log S) and solvation free energy, using an alternating-batch regimen that trains on quantum-mechanical data (CombiSolv-QM) and on experimental measurements (BigSolDB 2.0). Solvaformer attains the strongest overall performance among the learned models and approaches a DFT-assisted gradient-boosting baseline, while outperforming an EquiformerV2 ablation and sequence-based alternatives. In addition, token-level attention produces chemically coherent attributions: case studies recover known intra- vs. inter-molecular hydrogen-bonding patterns that govern solubility differences in positional isomers. Taken together, Solvaformer provides an accurate, scalable, and interpretable approach to solution-phase property prediction by uniting geometric inductive bias with a mixed dataset training strategy on complementary computational and experimental data. --- ### NeuroLingua: A Language-Inspired Hierarchical Framework for Multimodal Sleep Stage Classification Using EEG and EOG Authors: Mahdi Samaee, Mehran Yazdi, Daniel Massicotte Published: 2025-11-12 Categories: cs.LG, eess.SP arXiv: https://arxiv.org/abs/2511.09773v1 Automated sleep stage classification from polysomnography remains limited by the lack of expressive temporal hierarchies, challenges in multimodal EEG and EOG fusion, and the limited interpretability of deep learning models. We propose NeuroLingua, a language-inspired framework that conceptualizes sleep as a structured physiological language. Each 30-second epoch is decomposed into overlapping 3-second subwindows ("tokens") using a CNN-based tokenizer, enabling hierarchical temporal modeling through dual-level Transformers: intra-segment encoding of local dependencies and inter-segment integration across seven consecutive epochs (3.5 minutes) for extended context. Modality-specific embeddings from EEG and EOG channels are fused via a Graph Convolutional Network, facilitating robust multimodal integration. NeuroLingua is evaluated on the Sleep-EDF Expanded and ISRUC-Sleep datasets, achieving state-of-the-art results on Sleep-EDF (85.3% accuracy, 0.800 macro F1, and 0.796 Cohen's kappa) and competitive performance on ISRUC (81.9% accuracy, 0.802 macro F1, and 0.755 kappa), matching or exceeding published baselines in overall and per-class metrics. The architecture's attention mechanisms enhance the detection of clinically relevant sleep microevents, providing a principled foundation for future interpretability, explainability, and causal inference in sleep research. By framing sleep as a compositional language, NeuroLingua unifies hierarchical sequence modeling and multimodal fusion, advancing automated sleep staging toward more transparent and clinically meaningful applications. --- ### STORM: Segment, Track, and Object Re-Localization from a Single Image Authors: Yu Deng, Teng Cao, Hikaru Shindo, Quentin Delfosse, Jiahong Xue, Kristian Kersting Published: 2025-11-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.09771v3 Accurate 6D pose estimation and tracking are core capabilities for physical AI systems, yet real-world deployment remains brittle and labor-intensive. Many pipelines rely on CAD models, manual masking, or per-object adaptation, and still fail under occlusion or fast motion without a principled way to recognize failure. We propose STORM, a unified framework for reference-conditioned 6D tracking that can operate from a single reference image, with minimal manual input and improved robustness. STORM combines: (i) Hierarchical Spatial Fusion Attention (HSFA), a task-driven reference-query fusion architecture that supports both single-reference and multi-reference conditioning and can optionally use vision-language semantic conditioning to resolve instance ambiguities; and (ii) a BCE-trained tracking verifier whose continuous compatibility logit is used as an energy-like score to detect drift and trigger automatic re-initialization. Experiments on LM-O and YCB-Video show that STORM improves annotation-free pose tracking accuracy over strong baselines and recovers reliably from severe occlusions and rapid viewpoint changes with minimal overhead. --- ### Structure tensor Reynolds-averaged Navier-Stokes turbulence models with equivariant neural networks Authors: Aaron Miller, Sahil Kommalapati, Robert Moser, Petros Koumoutsakos Published: 2025-11-12 Categories: physics.flu-dyn, cs.LG arXiv: https://arxiv.org/abs/2511.09769v2 Accurate and generalizable Reynolds-averaged Navier-Stokes (RANS) models for turbulent flows rely on effective closures, but currently available closures are notoriously unreliable. Kassinos et al. (J. Fluid Mechanics, 428, pp. 213-248, 2001) hypothesized that this unreliability of RANS models was due to an insufficient description of the statistical state of the turbulence and proposed a set of structure tensors as a candidate for a sufficiently rich description. To test this hypothesis for the rapid pressure-strain term, we introduce tensor-based, symmetry aware closures in terms of the structure tensors using equivariant neural networks (ENNs), and present an algorithm for enforcing algebraic contraction relations among tensor components. Using data from rapid distortion theory, experiments show that such ENNs can effectively learn relationships involving high-order tensors. The resulting ENN structure tensor models are orders of magnitude more accurate than existing models for the rapid pressure-strain correlation, effectively validating the Kassinos et al. hypothesis for this term. Results show that ENNs provide a physically consistent alternative to classical tensor basis models, enabling end-to-end learning of unclosed terms in RANS and other tensor modeling domains, and rapid exploration of model dependencies. --- ### ProbLog4Fairness: A Neurosymbolic Approach to Modeling and Mitigating Bias Authors: Rik Adriaensen, Lucas Van Praet, Jessa Bekker, Robin Manhaeve, Pieter Delobelle, Maarten Buyl Published: 2025-11-12 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.09768v1 Operationalizing definitions of fairness is difficult in practice, as multiple definitions can be incompatible while each being arguably desirable. Instead, it may be easier to directly describe algorithmic bias through ad-hoc assumptions specific to a particular real-world task, e.g., based on background information on systemic biases in its context. Such assumptions can, in turn, be used to mitigate this bias during training. Yet, a framework for incorporating such assumptions that is simultaneously principled, flexible, and interpretable is currently lacking. Our approach is to formalize bias assumptions as programs in ProbLog, a probabilistic logic programming language that allows for the description of probabilistic causal relationships through logic. Neurosymbolic extensions of ProbLog then allow for easy integration of these assumptions in a neural network's training process. We propose a set of templates to express different types of bias and show the versatility of our approach on synthetic tabular datasets with known biases. Using estimates of the bias distortions present, we also succeed in mitigating algorithmic bias in real-world tabular and image data. We conclude that ProbLog4Fairness outperforms baselines due to its ability to flexibly model the relevant bias assumptions, where other methods typically uphold a fixed bias type or notion of fairness. --- ### Modelos Empiricos de Pos-Dupla Selecao por LASSO: Discussoes para Estudos do Transporte Aereo Authors: Alessandro V. M. Oliveira Published: 2025-11-12 Categories: stat.ME, cs.LG, econ.GN, eess.SY, stat.AP arXiv: https://arxiv.org/abs/2511.09767v1 This paper presents and discusses forms of estimation by regularized regression and model selection using the LASSO method - Least Absolute Shrinkage and Selection Operator. LASSO is recognized as one of the main supervised learning methods applied to high-dimensional econometrics, allowing work with large volumes of data and multiple correlated controls. Conceptual issues related to the consequences of high dimensionality in modern econometrics and the principle of sparsity, which underpins regularization procedures, are addressed. The study examines the main post-double selection and post-regularization models, including variations applied to instrumental variable models. A brief description of the lassopack routine package, its syntaxes, and examples of HD, HDS (High-Dimension Sparse), and IV-HDS models, with combinations involving fixed effects estimators, is also presented. Finally, the potential application of the approach in research focused on air transport is discussed, with emphasis on an empirical study on the operational efficiency of airlines and aircraft fuel consumption. --- ### Ksurf-Drone: Attention Kalman Filter for Contextual Bandit Optimization in Cloud Resource Allocation Authors: Michael Dang'ana, Yuqiu Zhang, Hans-Arno Jacobsen Published: 2025-11-12 Categories: cs.DC, cs.AI arXiv: https://arxiv.org/abs/2511.09766v1 Resource orchestration and configuration parameter search are key concerns for container-based infrastructure in cloud data centers. Large configuration search space and cloud uncertainties are often mitigated using contextual bandit techniques for resource orchestration including the state-of-the-art Drone orchestrator. Complexity in the cloud provider environment due to varying numbers of virtual machines introduces variability in workloads and resource metrics, making orchestration decisions less accurate due to increased nonlinearity and noise. Ksurf, a state-of-the-art variance-minimizing estimator method ideal for highly variable cloud data, enables optimal resource estimation under conditions of high cloud variability. This work evaluates the performance of Ksurf on estimation-based resource orchestration tasks involving highly variable workloads when employed as a contextual multi-armed bandit objective function model for cloud scenarios using Drone. Ksurf enables significantly lower latency variance of $41\%$ at p95 and $47\%$ at p99, demonstrates a $4\%$ reduction in CPU usage and 7 MB reduction in master node memory usage on Kubernetes, resulting in a $7\%$ cost savings in average worker pod count on VarBench Kubernetes benchmark. --- ### Brian Intensify: An Adaptive Machine Learning Framework for Auditory EEG Stimulation and Cognitive Enhancement in FXS Authors: Zag ElSayed, Grace Westerkamp, Jack Yanchen Liu, Ernest Pedapati Published: 2025-11-12 Categories: q-bio.NC, cs.AI, cs.LG, eess.SP arXiv: https://arxiv.org/abs/2511.09765v1 Neurodevelopmental disorders such as Fragile X Syndrome (FXS) and Autism Spectrum Disorder (ASD) are characterized by disrupted cortical oscillatory activity, particularly in the alpha and gamma frequency bands. These abnormalities are linked to deficits in attention, sensory processing, and cognitive function. In this work, we present an adaptive machine learning-based brain-computer interface (BCI) system designed to modulate neural oscillations through frequency-specific auditory stimulation to enhance cognitive readiness in individuals with FXS. EEG data were recorded from 38 participants using a 128-channel system under a stimulation paradigm consisting of a 30-second baseline (no stimulus) followed by 60-second auditory entrainment episodes at 7Hz, 9Hz, 11Hz, and 13Hz. A comprehensive analysis of power spectral features (Alpha, Gamma, Delta, Theta, Beta) and cross-frequency coupling metrics (Alpha-Gamma, Alpha-Beta, etc.) was conducted. The results identified Peak Alpha Power, Peak Gamma Power, and Alpha Power per second per channel as the most discriminative biomarkers. The 13Hz stimulation condition consistently elicited a significant increase in Alpha activity and suppression of Gamma activity, aligning with our optimization objective. A supervised machine learning framework was developed to predict EEG responses and dynamically adjust stimulation parameters, enabling real-time, subject-specific adaptation. This work establishes a novel EEG-driven optimization framework for cognitive neuromodulation, providing a foundational model for next-generation AI-integrated BCI systems aimed at personalized neurorehabilitation in FXS and related disorders. --- ### Is nasty noise actually harder than malicious noise? Authors: Guy Blanc, Yizhi Huang, Tal Malkin, Rocco A. Servedio Published: 2025-11-12 Categories: cs.LG, cs.CC, cs.DS arXiv: https://arxiv.org/abs/2511.09763v2 We consider the relative abilities and limitations of computationally efficient algorithms for learning in the presence of noise, under two well-studied and challenging adversarial noise models for learning Boolean functions: malicious noise, in which an adversary can arbitrarily corrupt a random subset of examples given to the learner; and nasty noise, in which an adversary can arbitrarily corrupt an adversarially chosen subset of examples given to the learner. We consider both the distribution-independent and fixed-distribution settings. Our main results highlight a dramatic difference between these two settings: For distribution-independent learning, we prove a strong equivalence between the two noise models: If a class ${\cal C}$ of functions is efficiently learnable in the presence of $η$-rate malicious noise, then it is also efficiently learnable in the presence of $η$-rate nasty noise. In sharp contrast, for the fixed-distribution setting we show an arbitrarily large separation: Under a standard cryptographic assumption, for any arbitrarily large value $r$ there exists a concept class for which there is a ratio of $r$ between the rate $η_{malicious}$ of malicious noise that polynomial-time learning algorithms can tolerate, versus the rate $η_{nasty}$ of nasty noise that such learning algorithms can tolerate. To offset the negative result for the fixed-distribution setting, we define a broad and natural class of algorithms, namely those that ignore contradictory examples (ICE). We show that for these algorithms, malicious noise and nasty noise are equivalent up to a factor of two in the noise rate: Any efficient ICE learner that succeeds with $η$-rate malicious noise can be converted to an efficient learner that succeeds with $η/2$-rate nasty noise. We further show that the above factor of two is necessary, again under a standard cryptographic assumption. --- ### Distributional Treatment Effect Transportability across Heterogeneous Sites Authors: Borna Bateni, Yubai Yuan, Qi Xu, Annie Qu Published: 2025-11-12 Categories: stat.ME, math.ST, stat.ML arXiv: https://arxiv.org/abs/2511.09759v2 We study distributional transportability of treatment effects in a ``cross-site, one-armed target" design, where both treated and control units are observed in a source site, but only control units are observed in a target site. Our object of interest is not estimating the average treatment effect, but recovering the full treated distribution in the target site using transfer knowledge from the source site, while allowing cross-site heterogeneity in measurement systems, observed features, outcome reporting, population composition, and latent contextual factors. We model cross-site heterogeneity through a transformation between the sites that transports the joint feature--outcome distributions. This transformation is learned from comparing the observed control samples in the source and target sites, using an optimal transport criterion. The learned transformation is then applied to the source treated sample to construct a synthetic sample from the target treated distribution. We establish convergence of the resulting synthetic empirical distribution to the target treated distribution. Simulation studies across multiple data-generating scenarios and a real-world application to patient-derived xenograft (PDX) data demonstrate that our framework recovers the full distributional properties of the target treated population. --- ### History Rhymes: Macro-Contextual Retrieval for Robust Financial Forecasting Authors: Sarthak Khanna, Armin Berger, Muskaan Chopra, David Berghaus, Rafet Sifa Published: 2025-11-12 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.09754v2 Financial markets are inherently non-stationary: structural breaks and macroeconomic regime shifts often cause forecasting models to fail when deployed out of distribution (OOD). Conventional multimodal approaches that simply fuse numerical indicators and textual sentiment rarely adapt to such shifts. We introduce macro-contextual retrieval, a retrieval-augmented forecasting framework that grounds each prediction in historically analogous macroeconomic regimes. The method jointly embeds macro indicators (e.g., CPI, unemployment, yield spread, GDP growth) and financial news sentiment in a shared similarity space, enabling causal retrieval of precedent periods during inference without retraining. Trained on seventeen years of S&P 500 data (2007-2023) and evaluated OOD on AAPL (2024) and XOM (2024), the framework consistently narrows the CV to OOD performance gap. Macro-conditioned retrieval achieves the only positive out-of-sample trading outcomes (AAPL: PF=1.18, Sharpe=0.95; XOM: PF=1.16, Sharpe=0.61), while static numeric, text-only, and naive multimodal baselines collapse under regime shifts. Beyond metric gains, retrieved neighbors form interpretable evidence chains that correspond to recognizable macro contexts, such as inflationary or yield-curve inversion phases, supporting causal interpretability and transparency. By operationalizing the principle that "financial history may not repeat, but it often rhymes," this work demonstrates that macro-aware retrieval yields robust, explainable forecasts under distributional change. All datasets, models, and source code are publicly available. --- ### Gradient-Guided Exploration of Generative Model's Latent Space for Controlled Iris Image Augmentations Authors: Mahsa Mitcheff, Siamul Karim Khan, Adam Czajka Published: 2025-11-12 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2511.09749v2 Developing reliable iris recognition and presentation attack detection methods requires diverse datasets that capture realistic variations in iris features and a wide spectrum of anomalies. Because of the rich texture of iris images, which spans a wide range of spatial frequencies, synthesizing same-identity iris images while controlling specific attributes remains challenging. In this work, we introduce a new iris image augmentation strategy by traversing a generative model's latent space toward latent codes that represent same-identity samples but with some desired iris image properties manipulated. The latent space traversal is guided by a gradient of specific geometrical, textural, or quality-related iris image features (e.g., sharpness, pupil size, iris size, or pupil-to-iris ratio) and preserves the identity represented by the image being manipulated. The proposed approach can be easily extended to manipulate any attribute for which a differentiable loss term can be formulated. Additionally, our approach can use either randomly generated images using either a pre-train GAN model or real-world iris images. We can utilize GAN inversion to project any given iris image into the latent space and obtain its corresponding latent code. --- ### How Small Can You Go? Compact Language Models for On-Device Critical Error Detection in Machine Translation Authors: Muskaan Chopra, Lorenz Sparrenberg, Sarthak Khanna, Rafet Sifa Published: 2025-11-12 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.09748v1 Large Language Models (LLMs) excel at evaluating machine translation (MT), but their scale and cost hinder deployment on edge devices and in privacy-sensitive workflows. We ask: how small can you get while still detecting meaning-altering translation errors? Focusing on English->German Critical Error Detection (CED), we benchmark sub-2B models (LFM2-350M, Qwen-3-0.6B/1.7B, Llama-3.2-1B-Instruct, Gemma-3-1B) across WMT21, WMT22, and SynCED-EnDe-2025. Our framework standardizes prompts, applies lightweight logit-bias calibration and majority voting, and reports both semantic quality (MCC, F1-ERR/F1-NOT) and compute metrics (VRAM, latency, throughput). Results reveal a clear sweet spot around one billion parameters: Gemma-3-1B provides the best quality-efficiency trade-off, reaching MCC=0.77 with F1-ERR=0.98 on SynCED-EnDe-2025 after merged-weights fine-tuning, while maintaining 400 ms single-sample latency on a MacBook Pro M4 Pro (24 GB). At larger scale, Qwen-3-1.7B attains the highest absolute MCC (+0.11 over Gemma) but with higher compute cost. In contrast, ultra-small models (0.6B) remain usable with few-shot calibration yet under-detect entity and number errors. Overall, compact, instruction-tuned LLMs augmented with lightweight calibration and small-sample supervision can deliver trustworthy, on-device CED for MT, enabling private, low-cost error screening in real-world translation pipelines. All datasets, prompts, and scripts are publicly available at our GitHub repository. --- ### Feature Quality and Adaptability of Medical Foundation Models: A Comparative Evaluation for Radiographic Classification and Segmentation Authors: Frank Li, Theo Dapamede, Mohammadreza Chavoshi, Young Seok Jeon, Bardia Khosravi, Abdulhameed Dere, Beatrice Brown-Mulry, Rohan Satya Isaac, Aawez Mansuri, Chiratidzo Sanyika, Janice Newsome, Saptarshi Purkayastha et al. Published: 2025-11-12 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.09742v1 Foundation models (FMs) promise to generalize medical imaging, but their effectiveness varies. It remains unclear how pre-training domain (medical vs. general), paradigm (e.g., text-guided), and architecture influence embedding quality, hindering the selection of optimal encoders for specific radiology tasks. To address this, we evaluate vision encoders from eight medical and general-domain FMs for chest X-ray analysis. We benchmark classification (pneumothorax, cardiomegaly) and segmentation (pneumothorax, cardiac boundary) using linear probing and fine-tuning. Our results show that domain-specific pre-training provides a significant advantage; medical FMs consistently outperformed general-domain models in linear probing, establishing superior initial feature quality. However, feature utility is highly task-dependent. Pre-trained embeddings were strong for global classification and segmenting salient anatomy (e.g., heart). In contrast, for segmenting complex, subtle pathologies (e.g., pneumothorax), all FMs performed poorly without significant fine-tuning, revealing a critical gap in localizing subtle disease. Subgroup analysis showed FMs use confounding shortcuts (e.g., chest tubes for pneumothorax) for classification, a strategy that fails for precise segmentation. We also found that expensive text-image alignment is not a prerequisite; image-only (RAD-DINO) and label-supervised (Ark+) FMs were among top performers. Notably, a supervised, end-to-end baseline remained highly competitive, matching or exceeding the best FMs on segmentation tasks. These findings show that while medical pre-training is beneficial, architectural choices (e.g., multi-scale) are critical, and pre-trained features are not universally effective, especially for complex localization tasks where supervised models remain a strong alternative. --- ### TawPipe: Topology-Aware Weight Pipeline Parallelism for Accelerating Long-Context Large Models Training Authors: Houming Wu, Ling Chen Published: 2025-11-12 Categories: cs.LG, cs.AI, cs.DC arXiv: https://arxiv.org/abs/2511.09741v1 Training large language models (LLMs) is fundamentally constrained by limited device memory and costly inter-device communication. Although pipeline parallelism alleviates memory pressure by partitioning models across devices, it incurs activation communication overhead that scales linearly with sequence length, limiting efficiency in long-context training. Recent weight-passing approaches (e.g., WeiPipe) mitigate this by transmitting model weights instead of activations, but suffer from redundant peer-to-peer (P2P) transfers and underutilized intra-node bandwidth. We propose TawPipe--topology-aware weight pipeline parallelism, which exploits hierarchical bandwidth in distributed clusters for improved communication efficiency. TawPipe: (i) groups devices based on topology to optimize intra-node collective and inter-node P2P communication; (ii) assigns each device a fixed shard of model weights and gradients, avoiding redundant transfers; and (iii) overlaps communication with computation to hide latency. Unlike global collective operations used in fully sharded data parallelism (FSDP), TawPipe confines most communication within node boundaries, significantly reducing cross-node traffic. Extensive experiments on up to 24 GPUs with LLaMA-style models show that TawPipe achieves superior throughput and scalability compared to state-of-the-art baselines. --- ### Soiling detection for Advanced Driver Assistance Systems Authors: Filip Beránek, Václav Diviš, Ivan Gruber Published: 2025-11-12 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.09740v1 Soiling detection for automotive cameras is a crucial part of advanced driver assistance systems to make them more robust to external conditions like weather, dust, etc. In this paper, we regard the soiling detection as a semantic segmentation problem. We provide a comprehensive comparison of popular segmentation methods and show their superiority in performance while comparing them to tile-level classification approaches. Moreover, we present an extensive analysis of the Woodscape dataset showing that the original dataset contains a data-leakage and imprecise annotations. To address these problems, we create a new data subset, which, despite being much smaller, provides enough information for the segmentation method to reach comparable results in a much shorter time. All our codes and dataset splits are available at https://github.com/filipberanek/woodscape_revision. --- ### Assessing the Applicability of Natural Language Processing to Traditional Social Science Methodology: A Case Study in Identifying Strategic Signaling Patterns in Presidential Directives Authors: C. LeMay, A. Lane, J. Seales, M. Winstead, S. Baty Published: 2025-11-12 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2511.09738v1 Our research investigates how Natural Language Processing (NLP) can be used to extract main topics from a larger corpus of written data, as applied to the case of identifying signaling themes in Presidential Directives (PDs) from the Reagan through Clinton administrations. Analysts and NLP both identified relevant documents, demonstrating the potential utility of NLPs in research involving large written corpuses. However, we also identified discrepancies between NLP and human-labeled results that indicate a need for more research to assess the validity of NLP in this use case. The research was conducted in 2023, and the rapidly evolving landscape of AIML means existing tools have improved and new tools have been developed; this research displays the inherent capabilities of a potentially dated AI tool in emerging social science applications. --- ### Out-of-Distribution Generalization with a SPARC: Racing 100 Unseen Vehicles with a Single Policy Authors: Bram Grooten, Patrick MacAlpine, Kaushik Subramanian, Peter Stone, Peter R. Wurman Published: 2025-11-12 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.09737v1 Generalization to unseen environments is a significant challenge in the field of robotics and control. In this work, we focus on contextual reinforcement learning, where agents act within environments with varying contexts, such as self-driving cars or quadrupedal robots that need to operate in different terrains or weather conditions than they were trained for. We tackle the critical task of generalizing to out-of-distribution (OOD) settings, without access to explicit context information at test time. Recent work has addressed this problem by training a context encoder and a history adaptation module in separate stages. While promising, this two-phase approach is cumbersome to implement and train. We simplify the methodology and introduce SPARC: single-phase adaptation for robust control. We test SPARC on varying contexts within the high-fidelity racing simulator Gran Turismo 7 and wind-perturbed MuJoCo environments, and find that it achieves reliable and robust OOD generalization. --- ### Data Heterogeneity and Forgotten Labels in Split Federated Learning Authors: Joana Tirana, Dimitra Tsigkari, David Solans Noguero, Nicolas Kourtellis Published: 2025-11-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.09736v2 In Split Federated Learning (SFL), the clients collaboratively train a model with the help of a server by splitting the model into two parts. Part-1 is trained locally at each client and aggregated by the aggregator at the end of each round. Part-2 is trained at a server that sequentially processes the intermediate activations received from each client. We study the phenomenon of catastrophic forgetting (CF) in SFL in the presence of data heterogeneity. In detail, due to the nature of SFL, local updates of part-1 may drift away from global optima, while part-2 is sensitive to the processing sequence, similar to forgetting in continual learning (CL). Specifically, we observe that the trained model performs better in classes (labels) seen at the end of the sequence. We investigate this phenomenon with emphasis on key aspects of SFL, such as the processing order at the server and the cut layer. Based on our findings, we propose Hydra, a novel mitigation method inspired by multi-head neural networks and adapted for the SFL setting. Extensive numerical evaluations show that Hydra outperforms baselines and methods from the literature. --- ### Social LSTM with Dynamic Occupancy Modeling for Realistic Pedestrian Trajectory Prediction Authors: Ahmed Alia, Mohcine Chraibi, Armin Seyfried Published: 2025-11-12 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.09735v1 In dynamic and crowded environments, realistic pedestrian trajectory prediction remains a challenging task due to the complex nature of human motion and the mutual influences among individuals. Deep learning models have recently achieved promising results by implicitly learning such patterns from 2D trajectory data. However, most approaches treat pedestrians as point entities, ignoring the physical space that each person occupies. To address these limitations, this paper proposes a novel deep learning model that enhances the Social LSTM with a new Dynamic Occupied Space loss function. This loss function guides Social LSTM in learning to avoid realistic collisions without increasing displacement error across different crowd densities, ranging from low to high, in both homogeneous and heterogeneous density settings. Such a function achieves this by combining the average displacement error with a new collision penalty that is sensitive to scene density and individual spatial occupancy. For efficient training and evaluation, five datasets were generated from real pedestrian trajectories recorded during the Festival of Lights in Lyon 2022. Four datasets represent homogeneous crowd conditions -- low, medium, high, and very high density -- while the fifth corresponds to a heterogeneous density distribution. The experimental findings indicate that the proposed model not only lowers collision rates but also enhances displacement prediction accuracy in each dataset. Specifically, the model achieves up to a 31% reduction in the collision rate and reduces the average displacement error and the final displacement error by 5% and 6%, respectively, on average across all datasets compared to the baseline. Moreover, the proposed model consistently outperforms several state-of-the-art deep learning models across most test sets. --- ### A Fourier-Based Global Denoising Model for Smart Artifacts Removing of Microscopy Images Authors: Huanhuan Zhao, Connor Vernachio, Laxmi Bhurtel, Wooin Yang, Ruben Millan-Solsona, Spenser R. Brown, Marti Checa, Komal Sharma Agrawal, Adam M. Guss, Liam Collins, Wonhee Ko, Arpan Biswas Published: 2025-11-12 Categories: eess.IV, cs.LG arXiv: https://arxiv.org/abs/2511.09734v1 Microscopy such as Scanning Tunneling Microscopy (STM), Atomic Force Microscopy (AFM) and Scanning Electron Microscopy (SEM) are essential tools in material imaging at micro- and nanoscale resolutions to extract physical knowledge and materials structure-property relationships. However, tuning microscopy controls (e.g. scanning speed, current setpoint, tip bias etc.) to obtain a high-quality of images is a non-trivial and time-consuming effort. On the other hand, with sub-standard images, the key features are not accurately discovered due to noise and artifacts, leading to erroneous analysis. Existing denoising models mostly build on generalizing the weak signals as noises while the strong signals are enhanced as key features, which is not always the case in microscopy images, thus can completely erase a significant amount of hidden physical information. To address these limitations, we propose a global denoising model (GDM) to smartly remove artifacts of microscopy images while preserving weaker but physically important features. The proposed model is developed based on 1) first designing a two-imaging input channel of non-pair and goal specific pre-processed images with user-defined trade-off information between two channels and 2) then integrating a loss function of pixel- and fast Fourier-transformed (FFT) based on training the U-net model. We compared the proposed GDM with the non-FFT denoising model over STM-generated images of Copper(Cu) and Silicon(Si) materials, AFM-generated Pantoea sp.YR343 bio-film images and SEM-generated plastic degradation images. We believe this proposed workflow can be extended to improve other microscopy image quality and will benefit the experimentalists with the proposed design flexibility to smartly tune via domain-experts preferences. --- ### FlowCast: Advancing Precipitation Nowcasting with Conditional Flow Matching Authors: Bernardo Perrone Ribeiro, Jana Faganeli Pucer Published: 2025-11-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.09731v4 Radar-based precipitation nowcasting, the task of forecasting short-term precipitation fields from previous radar images, is a critical problem for flood risk management and decision-making. While deep learning has substantially advanced this field, two challenges remain fundamental: the uncertainty of atmospheric dynamics and the efficient modeling of high-dimensional data. Diffusion models have shown strong promise by producing sharp, reliable forecasts, but their iterative sampling process is computationally prohibitive for time-critical applications. We introduce FlowCast, the first end-to-end probabilistic model leveraging Conditional Flow Matching (CFM) as a direct noise-to-data generative framework for precipitation nowcasting. Unlike hybrid approaches, FlowCast learns a direct noise-to-data mapping in a compressed latent space, enabling rapid, high-fidelity sample generation. Our experiments demonstrate that FlowCast establishes a new state-of-the-art in probabilistic performance while also exceeding deterministic baselines in predictive accuracy. A direct comparison further reveals the CFM objective is both more accurate and significantly more efficient than a diffusion objective on the same architecture, maintaining high performance with significantly fewer sampling steps. This work positions CFM as a powerful and practical alternative for high-dimensional spatiotemporal forecasting. --- ### Generalizing PDE Emulation with Equation-Aware Neural Operators Authors: Qian-Ze Zhu, Paul Raccuglia, Michael P. Brenner Published: 2025-11-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.09729v1 Solving partial differential equations (PDEs) can be prohibitively expensive using traditional numerical methods. Deep learning-based surrogate models typically specialize in a single PDE with fixed parameters. We present a framework for equation-aware emulation that generalizes to unseen PDEs, conditioning a neural model on a vector encoding representing the terms in a PDE and their coefficients. We present a baseline of four distinct modeling technqiues, trained on a family of 1D PDEs from the APEBench suite. Our approach achieves strong performance on parameter sets held out from the training distribution, with strong stability for rollout beyond the training window, and generalization to an entirely unseen PDE. This work was developed as part of a broader effort exploring AI systems that automate the creation of expert-level empirical software for scorable scientific tasks. The data and codebase are available at https://github.com/google-research/generalized-pde-emulator. ---