# Research Papers — 2025-11 · bundle page 158 of 197

> Full-text markdown of papers #7851–7900 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/158
[← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/157.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-11/page/159.md)

### DiagnoLLM: A Hybrid Bayesian Neural Language Framework for Interpretable Disease Diagnosis

Authors: Bowen Xu, Xinyue Zeng, Jiazhen Hu, Tuo Wang, Adithya Kulkarni
Published: 2025-11-08
Categories: cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2511.05810v2

Building trustworthy clinical AI systems requires not only accurate predictions but also transparent, biologically grounded explanations. We present \texttt{DiagnoLLM}, a hybrid framework that integrates Bayesian deconvolution, eQTL-guided deep learning, and LLM-based narrative generation for interpretable disease diagnosis. DiagnoLLM begins with GP-unmix, a Gaussian Process-based hierarchical model that infers cell-type-specific gene expression profiles from bulk and single-cell RNA-seq data while modeling biological uncertainty. These features, combined with regulatory priors from eQTL analysis, power a neural classifier that achieves high predictive performance in Alzheimer's Disease (AD) detection (88.0\% accuracy). To support human understanding and trust, we introduce an LLM-based reasoning module that translates model outputs into audience-specific diagnostic reports, grounded in clinical features, attribution signals, and domain knowledge. Human evaluations confirm that these reports are accurate, actionable, and appropriately tailored for both physicians and patients. Our findings show that LLMs, when deployed as post-hoc reasoners rather than end-to-end predictors, can serve as effective communicators within hybrid diagnostic pipelines.

---

### Measuring Model Performance in the Presence of an Intervention

Authors: Winston Chen, Michael W. Sjoding, Jenna Wiens
Published: 2025-11-08
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.05805v2

AI models are often evaluated based on their ability to predict the outcome of interest. However, in many AI for social impact applications, the presence of an intervention that affects the outcome can bias the evaluation. Randomized controlled trials (RCTs) randomly assign interventions, allowing data from the control group to be used for unbiased model evaluation. However, this approach is inefficient because it ignores data from the treatment group. Given the complexity and cost often associated with RCTs, making the most use of the data is essential. Thus, we investigate model evaluation strategies that leverage all data from an RCT. First, we theoretically quantify the estimation bias that arises from naïvely aggregating performance estimates from treatment and control groups and derive the condition under which this bias leads to incorrect model selection. Leveraging these theoretical insights, we propose nuisance parameter weighting (NPW), an unbiased model evaluation approach that reweights data from the treatment group to mimic the distributions of samples that would or would not experience the outcome under no intervention. Using synthetic and real-world datasets, we demonstrate that our proposed evaluation approach consistently yields better model selection than the standard approach, which ignores data from the treatment group, across various intervention effect and sample size settings. Our contribution represents a meaningful step towards more efficient model evaluation in real-world contexts.

---

### Catching Contamination Before Generation: Spectral Kill Switches for Agents

Authors: Valentin Noël
Published: 2025-11-08
Categories: cs.LG, eess.SP, eess.SY, stat.ML
arXiv: https://arxiv.org/abs/2511.05804v1

Agentic language models compose multi step reasoning chains, yet intermediate steps can be corrupted by inconsistent context, retrieval errors, or adversarial inputs, which makes post hoc evaluation too late because errors propagate before detection. We introduce a diagnostic that requires no additional training and uses only the forward pass to emit a binary accept or reject signal during agent execution. The method analyzes token graphs induced by attention and computes two spectral statistics in early layers, namely the high frequency energy ratio and spectral entropy. We formalize these signals, establish invariances, and provide finite sample estimators with uncertainty quantification. Under a two regime mixture assumption with a monotone likelihood ratio property, we show that a single threshold on the high frequency energy ratio is optimal in the Bayes sense for detecting context inconsistency. Empirically, the high frequency energy ratio exhibits robust bimodality during context verification across multiple model families, which enables gating decisions with overhead below one millisecond on our hardware and configurations. We demonstrate integration into retrieval augmented agent pipelines and discuss deployment as an inline safety monitor. The approach detects contamination while the model is still processing the text, before errors commit to the reasoning chain.

---

### MACMD: Multi-dilated Contextual Attention and Channel Mixer Decoding for Medical Image Segmentation

Authors: Lalit Maurya, Honghai Liu, Reyer Zwiggelaar
Published: 2025-11-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.05803v1

Medical image segmentation faces challenges due to variations in anatomical structures. While convolutional neural networks (CNNs) effectively capture local features, they struggle with modeling long-range dependencies. Transformers mitigate this issue with self-attention mechanisms but lack the ability to preserve local contextual information. State-of-the-art models primarily follow an encoder-decoder architecture, achieving notable success. However, two key limitations remain: (1) Shallow layers, which are closer to the input, capture fine-grained details but suffer from information loss as data propagates through deeper layers. (2) Inefficient integration of local details and global context between the encoder and decoder stages. To address these challenges, we propose the MACMD-based decoder, which enhances attention mechanisms and facilitates channel mixing between encoder and decoder stages via skip connections. This design leverages hierarchical dilated convolutions, attention-driven modulation, and a cross channel-mixing module to capture long-range dependencies while preserving local contextual details, essential for precise medical image segmentation. We evaluated our approach using multiple transformer encoders on both binary and multi-organ segmentation tasks. The results demonstrate that our method outperforms state-of-the-art approaches in terms of Dice score and computational efficiency, highlighting its effectiveness in achieving accurate and robust segmentation performance. The code available at https://github.com/lalitmaurya47/MACMD

---

### Beyond the Lower Bound: Bridging Regret Minimization and Best Arm Identification in Lexicographic Bandits

Authors: Bo Xue, Yuanyu Wan, Zhichao Lu, Qingfu Zhang
Published: 2025-11-08
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.05802v1

In multi-objective decision-making with hierarchical preferences, lexicographic bandits provide a natural framework for optimizing multiple objectives in a prioritized order. In this setting, a learner repeatedly selects arms and observes reward vectors, aiming to maximize the reward for the highest-priority objective, then the next, and so on. While previous studies have primarily focused on regret minimization, this work bridges the gap between \textit{regret minimization} and \textit{best arm identification} under lexicographic preferences. We propose two elimination-based algorithms to address this joint objective. The first algorithm eliminates suboptimal arms sequentially, layer by layer, in accordance with the objective priorities, and achieves sample complexity and regret bounds comparable to those of the best single-objective algorithms. The second algorithm simultaneously leverages reward information from all objectives in each round, effectively exploiting cross-objective dependencies. Remarkably, it outperforms the known lower bound for the single-objective bandit problem, highlighting the benefit of cross-objective information sharing in the multi-objective setting. Empirical results further validate their superior performance over baselines.

---

### When AI Meets the Web: Prompt Injection Risks in Third-Party AI Chatbot Plugins

Authors: Yigitcan Kaya, Anton Landerer, Stijn Pletinckx, Michelle Zimmermann, Christopher Kruegel, Giovanni Vigna
Published: 2025-11-08
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2511.05797v1

Prompt injection attacks pose a critical threat to large language models (LLMs), with prior work focusing on cutting-edge LLM applications like personal copilots. In contrast, simpler LLM applications, such as customer service chatbots, are widespread on the web, yet their security posture and exposure to such attacks remain poorly understood. These applications often rely on third-party chatbot plugins that act as intermediaries to commercial LLM APIs, offering non-expert website builders intuitive ways to customize chatbot behaviors. To bridge this gap, we present the first large-scale study of 17 third-party chatbot plugins used by over 10,000 public websites, uncovering previously unknown prompt injection risks in practice. First, 8 of these plugins (used by 8,000 websites) fail to enforce the integrity of the conversation history transmitted in network requests between the website visitor and the chatbot. This oversight amplifies the impact of direct prompt injection attacks by allowing adversaries to forge conversation histories (including fake system messages), boosting their ability to elicit unintended behavior (e.g., code generation) by 3 to 8x. Second, 15 plugins offer tools, such as web-scraping, to enrich the chatbot's context with website-specific content. However, these tools do not distinguish the website's trusted content (e.g., product descriptions) from untrusted, third-party content (e.g., customer reviews), introducing a risk of indirect prompt injection. Notably, we found that ~13% of e-commerce websites have already exposed their chatbots to third-party content. We systematically evaluate both vulnerabilities through controlled experiments grounded in real-world observations, focusing on factors such as system prompt design and the underlying LLM. Our findings show that many plugins adopt insecure practices that undermine the built-in LLM safeguards.

---

### Position-Prior-Guided Network for System Matrix Super-Resolution in Magnetic Particle Imaging

Authors: Xuqing Geng, Lei Su, Zhongwei Bian, Zewen Sun, Jiaxuan Wen, Jie Tian, Yang Du
Published: 2025-11-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.05795v1

Magnetic Particle Imaging (MPI) is a novel medical imaging modality. One of the established methods for MPI reconstruction is based on the System Matrix (SM). However, the calibration of the SM is often time-consuming and requires repeated measurements whenever the system parameters change. Current methodologies utilize deep learning-based super-resolution (SR) techniques to expedite SM calibration; nevertheless, these strategies do not fully exploit physical prior knowledge associated with the SM, such as symmetric positional priors. Consequently, we integrated positional priors into existing frameworks for SM calibration. Underpinned by theoretical justification, we empirically validated the efficacy of incorporating positional priors through experiments involving both 2D and 3D SM SR methods.

---

### VLAD-Grasp: Zero-shot Grasp Detection via Vision-Language Models

Authors: Manav Kulshrestha, S. Talha Bukhari, Damon Conover, Aniket Bera
Published: 2025-11-08
Categories: cs.RO, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.05791v2

Robotic grasping is a fundamental capability for enabling autonomous manipulation, with usually infinite solutions. State-of-the-art approaches for grasping rely on learning from large-scale datasets comprising expert annotations of feasible grasps. Curating such datasets is challenging, and hence, learning-based methods are limited by the solution coverage of the dataset, and require retraining to handle novel objects. Towards this, we present VLAD-Grasp, a Vision-Language model Assisted zero-shot approach for Detecting Grasps. Our method (1) prompts a large vision-language model to generate a goal image where a virtual cylindrical proxy intersects the object's geometry, explicitly encoding an antipodal grasp axis in image space, then (2) predicts depth and segmentation to lift this generated image into 3D, and (3) aligns generated and observed object point clouds via principal components and correspondence-free optimization to recover an executable grasp pose. Unlike prior work, our approach is training-free and does not require curated grasp datasets, while achieving performance competitive with the state-of-the-art methods on the Cornell and Jacquard datasets. Furthermore, we demonstrate zero-shot generalization to real-world objects on a Franka Research 3 robot, highlighting vision-language models as powerful priors for robotic manipulation.

---

### SymLight: Exploring Interpretable and Deployable Symbolic Policies for Traffic Signal Control

Authors: Xiao-Cheng Liao, Yi Mei, Mengjie Zhang
Published: 2025-11-08
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.05790v1

Deep Reinforcement Learning have achieved significant success in automatically devising effective traffic signal control (TSC) policies. Neural policies, however, tend to be over-parameterized and non-transparent, hindering their interpretability and deployability on resource-limited edge devices. This work presents SymLight, a priority function search framework based on Monte Carlo Tree Search (MCTS) for discovering inherently interpretable and deployable symbolic priority functions to serve as the TSC policies. The priority function, in particular, accepts traffic features as input and then outputs a priority for each traffic signal phase, which subsequently directs the phase transition. For effective search, we propose a concise yet expressive priority function representation. This helps mitigate the combinatorial explosion of the action space in MCTS. Additionally, a probabilistic structural rollout strategy is introduced to leverage structural patterns from previously discovered high-quality priority functions, guiding the rollout process. Our experiments on real-world datasets demonstrate SymLight's superior performance across a range of baselines. A key advantage is SymLight's ability to produce interpretable and deployable TSC policies while maintaining excellent performance.

---

### DRAGON: Guard LLM Unlearning in Context via Negative Detection and Reasoning

Authors: Yaxuan Wang, Chris Yuhao Liu, Quan Liu, Jinglong Pang, Wei Wei, Yujia Bao, Yang Liu
Published: 2025-11-08
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.05784v2

Unlearning in Large Language Models (LLMs) is crucial for protecting private data and removing harmful knowledge. Most existing approaches rely on fine-tuning to balance unlearning efficiency with general language capabilities. However, these methods typically require training or access to retain data, which is often unavailable in real world scenarios. Although these methods can perform well when both forget and retain data are available, few works have demonstrated equivalent capability in more practical, data-limited scenarios. To overcome these limitations, we propose Detect-Reasoning Augmented GeneratiON (DRAGON), a systematic, reasoning-based framework that utilizes in-context chain-of-thought (CoT) instructions to guard deployed LLMs before inference. Instead of modifying the base model, DRAGON leverages the inherent instruction-following ability of LLMs and introduces a lightweight detection module to identify forget-worthy prompts without any retain data. These are then routed through a dedicated CoT guard model to enforce safe and accurate in-context intervention. To robustly evaluate unlearning performance, we introduce novel metrics for unlearning performance and the continual unlearning setting. Extensive experiments across three representative unlearning tasks validate the effectiveness of DRAGON, demonstrating its strong unlearning capability, scalability, and applicability in practical scenarios.

---

### TCSA-UDA: Text-Driven Cross-Semantic Alignment for Unsupervised Domain Adaptation in Medical Image Segmentation

Authors: Lalit Maurya, Honghai Liu, Reyer Zwiggelaar
Published: 2025-11-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.05782v3

Unsupervised domain adaptation (UDA) for medical image segmentation remains challenging due to substantial domain shifts across imaging modalities, such as CT and MRI. Although recent vision-language representation learning methods have shown promise in medical image analysis, their role in cross-modality UDA segmentation remains underexplored. To address this problem, we propose TCSA-UDA, a Text-driven Cross-Semantic Alignment framework that uses modality-aware textual prompting to guide domain-invariant visual representation learning. Specifically, we introduce a vision-language covariance cosine loss (VLCoL) that aligns inter-class visual feature relationships with text-derived semantic relationships, encouraging the image encoder to learn semantically structured and modality-robust representations. In addition, we incorporate a prototype alignment module to reduce residual class-level discrepancies between source and target domains by aligning high-level class prototypes. Extensive experiments on cross-modality cardiac, abdominal, and brain tumor segmentation benchmarks demonstrate that TCSA-UDA consistently improves adaptation performance and outperforms state-of-the-art UDA methods. These results highlight the potential of language-driven semantic guidance for domain-adaptive medical image segmentation. The code is available at https://github.com/lalitmaurya47/TCSA_UDA

---

### TOPSIS-like metaheuristic for LABS problem

Authors: Aleksandra Urbańczyk, Bogumiła Papiernik, Piotr Magiera, Piotr Urbańczyk, Aleksander Byrski
Published: 2025-11-08
Categories: cs.NE, math.OC
arXiv: https://arxiv.org/abs/2511.05778v1

This paper presents the application of socio-cognitive mutation operators inspired by the TOPSIS method to the Low Autocorrelation Binary Sequence (LABS) problem. Traditional evolutionary algorithms, while effective, often suffer from premature convergence and poor exploration-exploitation balance. To address these challenges, we introduce socio-cognitive mutation mechanisms that integrate strategies of following the best solutions and avoiding the worst. By guiding search agents to imitate high-performing solutions and avoid poor ones, these operators enhance both solution diversity and convergence efficiency. Experimental results demonstrate that TOPSIS-inspired mutation outperforms the base algorithm in optimizing LABS sequences. The study highlights the potential of socio-cognitive learning principles in evolutionary computation and suggests directions for further refinement.

---

### MARAuder's Map: Motion-Aware Real-time Activity Recognition with Layout-Based Trajectories

Authors: Zishuai Liu, Weihang You, Jin Lu, Fei Dou
Published: 2025-11-08
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2511.05773v1

Ambient sensor-based human activity recognition (HAR) in smart homes remains challenging due to the need for real-time inference, spatially grounded reasoning, and context-aware temporal modeling. Existing approaches often rely on pre-segmented, within-activity data and overlook the physical layout of the environment, limiting their robustness in continuous, real-world deployments. In this paper, we propose MARAuder's Map, a novel framework for real-time activity recognition from raw, unsegmented sensor streams. Our method projects sensor activations onto the physical floorplan to generate trajectory-aware, image-like sequences that capture the spatial flow of human movement. These representations are processed by a hybrid deep learning model that jointly captures spatial structure and temporal dependencies. To enhance temporal awareness, we introduce a learnable time embedding module that encodes contextual cues such as hour-of-day and day-of-week. Additionally, an attention-based encoder selectively focuses on informative segments within each observation window, enabling accurate recognition even under cross-activity transitions and temporal ambiguity. Extensive experiments on multiple real-world smart home datasets demonstrate that our method outperforms strong baselines, offering a practical solution for real-time HAR in ambient sensor environments.

---

### Sign language recognition from skeletal data using graph and recurrent neural networks

Authors: B. Mederos, J. Mejía, A. Medina-Reyes, Y. Espinosa-Almeyda, J. D. Díaz-Roman, I. Rodríguez-Mederos, M. Mejía-Carreon, F. Gonzalez-Lopez
Published: 2025-11-08
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.05772v1

This work presents an approach for recognizing isolated sign language gestures using skeleton-based pose data extracted from video sequences. A Graph-GRU temporal network is proposed to model both spatial and temporal dependencies between frames, enabling accurate classification. The model is trained and evaluated on the AUTSL (Ankara university Turkish sign language) dataset, achieving high accuracy. Experimental results demonstrate the effectiveness of integrating graph-based spatial representations with temporal modeling, providing a scalable framework for sign language recognition. The results of this approach highlight the potential of pose-driven methods for sign language understanding.

---

### Beyond Clicking:A Step Towards Generalist GUI Grounding via Text Dragging

Authors: Zeyi Liao, Yadong Lu, Boyu Gou, Huan Sun, Ahmed Awadallah
Published: 2025-11-07
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2601.06031v1

Graphical user interface (GUI) grounding, the process of mapping human instructions to GUI actions, serves as a fundamental basis to autonomous GUI agents. While existing grounding models achieve promising performance to simulate the mouse click action on various click-based benchmarks, another essential mode of mouse interaction, namely dragging, remains largely underexplored. Yet, dragging the mouse to select and manipulate textual content represents a prevalent and important usage in practical GUI scenarios. To narrow this gap, we first introduce GUI-Drag, a diverse dataset of 161K text dragging examples synthesized through a scalable pipeline. To support systematic and robust evaluation, we further construct ScreenDrag, a benchmark with 5,333 examples spanning three levels of interface context, together with three dedicated metrics designed for assessing text dragging capability. Models trained on GUI-Drag with an efficient continual training strategy achieve substantial improvements on ScreenDrag, while preserving the original click-based performance on ScreenSpot, ScreenSpot-v2, and OSWorld-G. Our work encourages further research on broader GUI grounding beyond just clicking and paves way toward a truly generalist GUI grounding model. All benchmark, data, checkpoints, and code are open-sourced and available at https://osu-nlp-group.github.io/GUI-Drag.

---

### From Augmentation to Symbiosis: A Review of Human-AI Collaboration Frameworks, Performance, and Perils

Authors: Richard Jiarui Tong
Published: 2025-11-07
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2601.06030v1

This paper offers a concise, 60-year synthesis of human-AI collaboration, from Licklider's ``man-computer symbiosis" (AI as colleague) and Engelbart's ``augmenting human intellect" (AI as tool) to contemporary poles: Human-Centered AI's ``supertool" and Symbiotic Intelligence's mutual-adaptation model. We formalize the mechanism for effective teaming as a causal chain: Explainable AI (XAI) -> co-adaptation -> shared mental models (SMMs). A meta-analytic ``performance paradox" is then examined: human-AI teams tend to show negative synergy in judgment/decision tasks (underperforming AI alone) but positive synergy in content creation and problem formulation. We trace failures to the algorithm-in-the-loop dynamic, aversion/bias asymmetries, and cumulative cognitive deskilling. We conclude with a unifying framework--combining extended-self and dual-process theories--arguing that durable gains arise when AI functions as an internalized cognitive component, yielding a unitary human-XAI symbiotic agency. This resolves the paradox and delineates a forward agenda for research and practice.

---

### Engineering the RAG Stack: A Comprehensive Review of the Architecture and Trust Frameworks for Retrieval-Augmented Generation Systems

Authors: Dean Wampler, Dave Nielson, Alireza Seddighi
Published: 2025-11-07
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2601.05264v1

This article provides a comprehensive systematic literature review of academic studies, industrial applications, and real-world deployments from 2018 to 2025, providing a practical guide and detailed overview of modern Retrieval-Augmented Generation (RAG) architectures. RAG offers a modular approach for integrating external knowledge without increasing the capacity of the model as LLM systems expand. Research and engineering practices have been fragmented as a result of the increasing diversity of RAG methodologies, which encompasses a variety of fusion mechanisms, retrieval strategies, and orchestration approaches. We provide quantitative assessment frameworks, analyze the implications for trust and alignment, and systematically consolidate existing RAG techniques into a unified taxonomy. This document is a practical framework for the deployment of resilient, secure, and domain-adaptable RAG systems, synthesizing insights from academic literature, industry reports, and technical implementation guides. It also functions as a technical reference.

---

### Towards Trustworthy LLM-Based Recommendation via Rationale Integration

Authors: Chung Park, Taesan Kim, Hyeongjun Yun, Dongjoon Hong, Junui Hong, Kijung Park, MinCheol Cho, Mira Myong, Jihoon Oh, Min sung Choi
Published: 2025-11-07
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2601.02364v1

Traditional recommender systems (RS) have been primarily optimized for accuracy and short-term engagement, often overlooking transparency and trustworthiness. Recently, platforms such as Amazon and Instagram have begun providing recommendation rationales to users, acknowledging their critical role in fostering trust and enhancing engagement; however, most existing systems still treat them as post-hoc artifacts. We propose an LLM-based recommender (LLM-Rec) that not only predicts items but also generates logically grounded rationales. Our approach leverages a self-annotated rationale dataset and instruction tuning in a rationale-first format, where the model generates an explanation before outputting the recommended item. By adopting this strategy and representing rationales in a chain-of-thought (CoT) style, LLM-Rec strengthens both interpretability and recommendation performance. Experiments on the Fashion and Scientific domains of the Amazon Review dataset demonstrate significant improvements over well-established baselines. To encourage reproducibility and future research, we publicly release a rationale-augmented recommendation dataset containing user histories, rationales, and recommended items.

---

### Cooperation Through Indirect Reciprocity in Child-Robot Interactions

Authors: Isabel Neto, Alexandre S. Pires, Filipa Correia, Fernando P. Santos
Published: 2025-11-07
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2512.20621v1

Social interactions increasingly involve artificial agents, such as conversational or collaborative bots. Understanding trust and prosociality in these settings is fundamental to improve human-AI teamwork. Research in biology and social sciences has identified mechanisms to sustain cooperation among humans. Indirect reciprocity (IR) is one of them. With IR, helping someone can enhance an individual's reputation, nudging others to reciprocate in the future. Transposing IR to human-AI interactions is however challenging, as differences in human demographics, moral judgements, and agents' learning dynamics can affect how interactions are assessed. To study IR in human-AI groups, we combine laboratory experiments and theoretical modelling. We investigate whether 1) indirect reciprocity can be transposed to children-robot interactions; 2) artificial agents can learn to cooperate given children's strategies; and 3) how differences in learning algorithms impact human-AI cooperation. We find that IR extends to children and robots solving coordination dilemmas. Furthermore, we observe that the strategies revealed by children provide a sufficient signal for multi-armed bandit algorithms to learn cooperative actions. Beyond the experimental scenarios, we observe that cooperating through multi-armed bandit algorithms is highly dependent on the strategies revealed by humans.

---

### Toward Better Generalization in Few-Shot Learning through the Meta-Component Combination

Authors: Qiuhao Zeng
Published: 2025-11-07
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.11632v1

In few-shot learning, classifiers are expected to generalize to unseen classes given only a small number of instances of each new class. One of the popular solutions to few-shot learning is metric-based meta-learning. However, it highly depends on the deep metric learned on seen classes, which may overfit to seen classes and fail to generalize well on unseen classes. To improve the generalization, we explore the substructures of classifiers and propose a novel meta-learning algorithm to learn each classifier as a combination of meta-components. Meta-components are learned across meta-learning episodes on seen classes and disentangled by imposing an orthogonal regularizer to promote its diversity and capture various shared substructures among different classifiers. Extensive experiments on few-shot benchmark tasks show superior performances of the proposed method.

---

### Predicting Grain Growth in Polycrystalline Materials Using Deep Learning Time Series Models

Authors: Eliane Younes, Elie Hachem, Marc Bernacki
Published: 2025-11-07
Categories: cs.LG, cond-mat.mtrl-sci, cs.AI, cs.CE
arXiv: https://arxiv.org/abs/2511.11630v1

Grain Growth strongly influences the mechanical behavior of materials, making its prediction a key objective in microstructural engineering. In this study, several deep learning approaches were evaluated, including recurrent neural networks (RNN), long short-term memory (LSTM), temporal convolutional networks (TCN), and transformers, to forecast grain size distributions during grain growth. Unlike full-field simulations, which are computationally demanding, the present work relies on mean-field statistical descriptors extracted from high-fidelity simulations. A dataset of 120 grain growth sequences was processed into normalized grain size distributions as a function of time. The models were trained to predict future distributions from a short temporal history using a recursive forecasting strategy. Among the tested models, the LSTM network achieved the highest accuracy (above 90\%) and the most stable performance, maintaining physically consistent predictions over extended horizons while reducing computation time from about 20 minutes per sequence to only a few seconds, whereas the other architectures tended to diverge when forecasting further in time. These results highlight the potential of low-dimensional descriptors and LSTM-based forecasting for efficient and accurate microstructure prediction, with direct implications for digital twin development and process optimization.

---

### Global Feature Enhancing and Fusion Framework for Strain Gauge Time Series Classification

Authors: Xu Zhang, Peng Wang, Chen Wang, Zhe Xu, Xiaohua Nie, Wei Wang
Published: 2025-11-07
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.11629v2

Strain Gauge Status (SGS) time series recognition is crucial in the field of intelligent manufacturing based on the Internet of Things, as accurate identification helps timely detection of failed mechanical components, avoiding accidents. The loading and unloading sequences generated by strain gauges can be identified through time series classification (TSC) algorithms. Recently, deep learning models, e.g., convolutional neural networks (CNNs) have shown remarkable success in the TSC task, as they can extract discriminative local features from the subsequences to identify the time series. However, we observe that only the local features may not be sufficient for expressing the time series, especially when the local sub-sequences between different time series are very similar, e.g., SGS data of aircraft wings in static strength experiments. Nevertheless, CNNs suffer from the limitation in extracting global features due to the nature of convolution operations. For extracting global features to more comprehensively represent the SGS time series, we propose two insights: (i) Constructing global features through feature engineering. (ii) Learning high-order relationships between local features to capture global features. To realize and utilize them, we propose a hypergraph-based global feature learning and fusion framework, which learns and fuses global features for semantic consistency to enhance the representation of SGS time series, thereby improving recognition accuracy. Our method designs are validated on industrial SGS and public UCR datasets, showing better generalization for unseen data in SGS recognition. The code is available at the link https://github.com/Meteor-Stars/GFEF.

---

### Mixture-of-Schedulers: An Adaptive Scheduling Agent as a Learned Router for Expert Policies

Authors: Xinbo Wang, Shian Jia, Ziyang Huang, Jing Cao, Mingli Song
Published: 2025-11-07
Categories: cs.DC, cs.AI
arXiv: https://arxiv.org/abs/2511.11628v1

Modern operating system schedulers employ a single, static policy, which struggles to deliver optimal performance across the diverse and dynamic workloads of contemporary systems. This "one-policy-fits-all" approach leads to significant compromises in fairness, throughput, and latency, particularly with the rise of heterogeneous hardware and varied application architectures. This paper proposes a new paradigm: dynamically selecting the optimal policy from a portfolio of specialized schedulers rather than designing a single, monolithic one. We present the Adaptive Scheduling Agent (ASA), a lightweight framework that intelligently matches workloads to the most suitable "expert" scheduling policy at runtime. ASA's core is a novel, low-overhead offline/online approach. First, an offline process trains a universal, hardware-agnostic machine learning model to recognize abstract workload patterns from system behaviors. Second, at runtime, ASA continually processes the model's predictions using a time-weighted probability voting algorithm to identify the workload, then makes a scheduling decision by consulting a pre-configured, machine-specific mapping table to switch to the optimal scheduler via Linux's sched_ext framework. This decoupled architecture allows ASA to adapt to new hardware platforms rapidly without expensive retraining of the core recognition model. Our evaluation, based on a novel benchmark focused on user-experience metrics, demonstrates that ASA consistently outperforms the default Linux scheduler (EEVDF), achieving superior results in 86.4% of test scenarios. Furthermore, ASA's selections are near-optimal, ranking among the top three schedulers in 78.6% of all scenarios. This validates our approach as a practical path toward more intelligent, adaptive, and responsive operating system schedulers.

---

### SA-EMO: Structure-Aligned Encoder Mixture of Operators for Generalizable Full-waveform Inversion

Authors: Wang Zhenyu, Li Peiyuan, Shi Yongxiang, Wu Ruoyu, Zhang Lei
Published: 2025-11-07
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.11627v1

Full-waveform inversion (FWI) can produce high-resolution subsurface models, yet it remains inherently ill-posed, highly nonlinear, and computationally intensive. Although recent deep learning and numerical acceleration methods have improved speed and scalability, they often rely on single CNN architectures or single neural operators, which struggle to generalize in unknown or complex geological settings and are ineffective at distinguishing diverse geological types. To address these issues, we propose a Structure-Aligned Encoder-Mixture-of-Operators (SA-EMO) architecture for velocity-field inversion under unknown subsurface structures. First, a structure-aligned encoder maps high-dimensional seismic wavefields into a physically consistent latent space, thereby eliminating spatio-temporal mismatch between the waveform and velocity domains, recovering high-frequency components, and enhancing feature generalization. Then, an adaptive routing mechanism selects and fuses multiple neural-operator experts, including spectral, wavelet, multiscale, and local operators, to predict the velocity model. We systematically evaluate our approach on the OpenFWI benchmark and the Marmousi2 dataset. Results show that SA-EMO significantly outperforms traditional CNN or single-operator methods, achieving an average MAE reduction of approximately 58.443% and an improvement in boundary resolution of about 10.308%. Ablation studies further reveal that the structure-aligned encoder, the expert-fusion mechanism, and the routing module each contribute markedly to the performance gains. This work introduces a new paradigm for efficient, scalable, and physically interpretable full-waveform inversion.

---

### Omics-scale polymer computational database transferable to real-world artificial intelligence applications

Authors: Ryo Yoshida, Yoshihiro Hayashi, Hidemine Furuya, Ryohei Hosoya, Kazuyoshi Kaneko, Hiroki Sugisawa, Yu Kaneko, Aiko Takahashi, Yoh Noguchi, Shun Nanjo, Keiko Shinoda, Tomu Hamakawa et al.
Published: 2025-11-07
Categories: physics.chem-ph, cond-mat.mtrl-sci, cond-mat.soft, cs.LG
arXiv: https://arxiv.org/abs/2511.11626v1

Developing large-scale foundational datasets is a critical milestone in advancing artificial intelligence (AI)-driven scientific innovation. However, unlike AI-mature fields such as natural language processing, materials science, particularly polymer research, has significantly lagged in developing extensive open datasets. This lag is primarily due to the high costs of polymer synthesis and property measurements, along with the vastness and complexity of the chemical space. This study presents PolyOmics, an omics-scale computational database generated through fully automated molecular dynamics simulation pipelines that provide diverse physical properties for over $10^5$ polymeric materials. The PolyOmics database is collaboratively developed by approximately 260 researchers from 48 institutions to bridge the gap between academia and industry. Machine learning models pretrained on PolyOmics can be efficiently fine-tuned for a wide range of real-world downstream tasks, even when only limited experimental data are available. Notably, the generalisation capability of these simulation-to-real transfer models improve significantly as the size of the PolyOmics database increases, exhibiting power-law scaling. The emergence of scaling laws supports the "more is better" principle, highlighting the significance of ultralarge-scale computational materials data for improving real-world prediction performance. This unprecedented omics-scale database reveals vast unexplored regions of polymer materials, providing a foundation for AI-driven polymer science.

---

### MedFedPure: A Medical Federated Framework with MAE-based Detection and Diffusion Purification for Inference-Time Attacks

Authors: Mohammad Karami, Mohammad Reza Nemati, Aidin Kazemi, Ali Mikaeili Barzili, Hamid Azadegan, Behzad Moshiri
Published: 2025-11-07
Categories: cs.LG, cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2511.11625v2

Artificial intelligence (AI) has shown great potential in medical imaging, particularly for brain tumor detection using Magnetic Resonance Imaging (MRI). However, the models remain vulnerable at inference time when they are trained collaboratively through Federated Learning (FL), an approach adopted to protect patient privacy. Adversarial attacks can subtly alter medical scans in ways invisible to the human eye yet powerful enough to mislead AI models, potentially causing serious misdiagnoses. Existing defenses often assume centralized data and struggle to cope with the decentralized and diverse nature of federated medical settings. In this work, we present MedFedPure, a personalized federated learning defense framework designed to protect diagnostic AI models at inference time without compromising privacy or accuracy. MedFedPure combines three key elements: (1) a personalized FL model that adapts to the unique data distribution of each institution; (2) a Masked Autoencoder (MAE) that detects suspicious inputs by exposing hidden perturbations; and (3) an adaptive diffusion-based purification module that selectively cleans only the flagged scans before classification. Together, these steps offer robust protection while preserving the integrity of normal, benign images. We evaluated MedFedPure on the Br35H brain MRI dataset. The results show a significant gain in adversarial robustness, improving performance from 49.50% to 87.33% under strong attacks, while maintaining a high clean accuracy of 97.67%. By operating locally and in real time during diagnosis, our framework provides a practical path to deploying secure, trustworthy, and privacy-preserving AI tools in clinical workflows. Index Terms: cancer, tumor detection, federated learning, masked autoencoder, diffusion, privacy

---

### Characterizing and Understanding Energy Footprint and Efficiency of Small Language Model on Edges

Authors: Md Romyull Islam, Bobin Deng, Nobel Dhar, Tu N. Nguyen, Selena He, Yong Shi, Kun Suo
Published: 2025-11-07
Categories: cs.DC, cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2511.11624v1

Cloud-based large language models (LLMs) and their variants have significantly influenced real-world applications. Deploying smaller models (i.e., small language models (SLMs)) on edge devices offers additional advantages, such as reduced latency and independence from network connectivity. However, edge devices' limited computing resources and constrained energy budgets challenge efficient deployment. This study evaluates the power efficiency of five representative SLMs - Llama 3.2, Phi-3 Mini, TinyLlama, and Gemma 2 on Raspberry Pi 5, Jetson Nano, and Jetson Orin Nano (CPU and GPU configurations). Results show that Jetson Orin Nano with GPU acceleration achieves the highest energy-to-performance ratio, significantly outperforming CPU-based setups. Llama 3.2 provides the best balance of accuracy and power efficiency, while TinyLlama is well-suited for low-power environments at the cost of reduced accuracy. In contrast, Phi-3 Mini consumes the most energy despite its high accuracy. In addition, GPU acceleration, memory bandwidth, and model architecture are key in optimizing inference energy efficiency. Our empirical analysis offers practical insights for AI, smart systems, and mobile ad-hoc platforms to leverage tradeoffs from accuracy, inference latency, and power efficiency in energy-constrained environments.

---

### Evaluating LLM Understanding via Structured Tabular Decision Simulations

Authors: Sichao Li, Xinyue Xu, Xiaomeng Li
Published: 2025-11-07
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.10667v1

Large language models (LLMs) often achieve impressive predictive accuracy, yet correctness alone does not imply genuine understanding. True LLM understanding, analogous to human expertise, requires making consistent, well-founded decisions across multiple instances and diverse domains, relying on relevant and domain-grounded decision factors. We introduce Structured Tabular Decision Simulations (STaDS), a suite of expert-like decision settings that evaluate LLMs as if they were professionals undertaking structured decision ``exams''. In this context, understanding is defined as the ability to identify and rely on the correct decision factors, features that determine outcomes within a domain. STaDS jointly assesses understanding through: (i) question and instruction comprehension, (ii) knowledge-based prediction, and (iii) reliance on relevant decision factors. By analyzing 9 frontier LLMs across 15 diverse decision settings, we find that (a) most models struggle to achieve consistently strong accuracy across diverse domains; (b) models can be accurate yet globally unfaithful, and there are frequent mismatches between stated rationales and factors driving predictions. Our findings highlight the need for global-level understanding evaluation protocols and advocate for novel frameworks that go beyond accuracy to enhance LLMs' understanding ability.

---

### An Efficient and Almost Optimal Solver for the Joint Routing-Assignment Problem via Partial JRA and Large-α Optimization

Authors: Qilong Yuan
Published: 2025-11-07
Categories: cs.AI, math.CO
arXiv: https://arxiv.org/abs/2511.09563v1

The Joint Routing-Assignment (JRA) optimization problem simultaneously determines the assignment of items to placeholders and a Hamiltonian cycle that visits each node pair exactly once, with the objective of minimizing total travel cost. Previous studies introduced an exact mixed-integer programming (MIP) solver, along with datasets and a Gurobi implementation, showing that while the exact approach guarantees optimality, it becomes computationally inefficient for large-scale instances. To overcome this limitation, heuristic methods based on merging algorithms and shaking procedures were proposed, achieving solutions within approximately 1% deviation from the optimum. This work presents a novel and more efficient approach that attains high-accuracy, near-optimal solutions for large-scale JRA problems. The proposed method introduces a Partial Path Reconstructon (PPR) solver that first identifies key item-placeholder pairs to form a reduced subproblem, which is solved efficiently to refine the global solution. Using this PJAR framework, the initial heuristic merging solutions can be further improved, reducing the deviation by half. Moreover, the solution can be iteratively polished with PPR based solver along the optimization path to yield highly accurate tours. Additionally, a global Large-α constraint is incorporated into the JRA model to further enhance solution optimality. Experimental evaluations on benchmark datasets with n = 300, 500, and 1000 demonstrate that the proposed method consistently delivers almost optimal solutions, achieving an average deviation of 0.00% from the ground truth while maintaining high computational efficiency. Beyond the JRA problem, the proposed framework and methodologies exhibit strong potential for broader applications. The Framework can be applied to TSP and related optimization problems.

---

### Multi-period Learning for Financial Time Series Forecasting

Authors: Xu Zhang, Zhengang Huang, Yunzhi Wu, Xun Lu, Erpeng Qi, Yunkai Chen, Zhongya Xue, Qitong Wang, Peng Wang, Wei Wang
Published: 2025-11-07
Categories: q-fin.ST, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.08622v2

Time series forecasting is important in finance domain. Financial time series (TS) patterns are influenced by both short-term public opinions and medium-/long-term policy and market trends. Hence, processing multi-period inputs becomes crucial for accurate financial time series forecasting (TSF). However, current TSF models either use only single-period input, or lack customized designs for addressing multi-period characteristics. In this paper, we propose a Multi-period Learning Framework (MLF) to enhance financial TSF performance. MLF considers both TSF's accuracy and efficiency requirements. Specifically, we design three new modules to better integrate the multi-period inputs for improving accuracy: (i) Inter-period Redundancy Filtering (IRF), that removes the information redundancy between periods for accurate self-attention modeling, (ii) Learnable Weighted-average Integration (LWI), that effectively integrates multi-period forecasts, (iii) Multi-period self-Adaptive Patching (MAP), that mitigates the bias towards certain periods by setting the same number of patches across all periods. Furthermore, we propose a Patch Squeeze module to reduce the number of patches in self-attention modeling for maximized efficiency. MLF incorporates multiple inputs with varying lengths (periods) to achieve better accuracy and reduces the costs of selecting input lengths during training. The codes and datasets are available at https://github.com/Meteor-Stars/MLF.

---

### The LLM Pro Finance Suite: Multilingual Large Language Models for Financial Applications

Authors: Gaëtan Caillaut, Raheel Qader, Jingshu Liu, Mariam Nakhlé, Arezki Sadoune, Massinissa Ahmim, Jean-Gabriel Barthelemy
Published: 2025-11-07
Categories: q-fin.ST, cs.AI, q-fin.CP
arXiv: https://arxiv.org/abs/2511.08621v1

The financial industry's growing demand for advanced natural language processing (NLP) capabilities has highlighted the limitations of generalist large language models (LLMs) in handling domain-specific financial tasks. To address this gap, we introduce the LLM Pro Finance Suite, a collection of five instruction-tuned LLMs (ranging from 8B to 70B parameters) specifically designed for financial applications. Our approach focuses on enhancing generalist instruction-tuned models, leveraging their existing strengths in instruction following, reasoning, and toxicity control, while fine-tuning them on a curated, high-quality financial corpus comprising over 50% finance-related data in English, French, and German. We evaluate the LLM Pro Finance Suite on a comprehensive financial benchmark suite, demonstrating consistent improvement over state-of-the-art baselines in finance-oriented tasks and financial translation. Notably, our models maintain the strong general-domain capabilities of their base models, ensuring reliable performance across non-specialized tasks. This dual proficiency, enhanced financial expertise without compromise on general abilities, makes the LLM Pro Finance Suite an ideal drop-in replacement for existing LLMs in financial workflows, offering improved domain-specific performance while preserving overall versatility. We publicly release two 8B-parameters models to foster future research and development in financial NLP applications: https://huggingface.co/collections/DragonLLM/llm-open-finance.

---

### Learn More, Forget Less: A Gradient-Aware Data Selection Approach for LLM

Authors: Yibai Liu, Shihang Wang, Zeming Liu, Zheming Song, Junzhe Wang, Jingjing Liu, Qingjie Liu, Yunhong Wang
Published: 2025-11-07
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.08620v1

Despite large language models (LLMs) have achieved impressive achievements across numerous tasks, supervised fine-tuning (SFT) remains essential for adapting these models to specialized domains. However, SFT for domain specialization can be resource-intensive and sometimes leads to a deterioration in performance over general capabilities due to catastrophic forgetting (CF). To address these issues, we propose a self-adaptive gradient-aware data selection approach (GrADS) for supervised fine-tuning of LLMs, which identifies effective subsets of training data by analyzing gradients obtained from a preliminary training phase. Specifically, we design self-guided criteria that leverage the magnitude and statistical distribution of gradients to prioritize examples that contribute the most to the model's learning process. This approach enables the acquisition of representative samples that enhance LLMs understanding of domain-specific tasks. Through extensive experimentation with various LLMs across diverse domains such as medicine, law, and finance, GrADS has demonstrated significant efficiency and cost-effectiveness. Remarkably, utilizing merely 5% of the selected GrADS data, LLMs already surpass the performance of those fine-tuned on the entire dataset, and increasing to 50% of the data results in significant improvements! With catastrophic forgetting substantially mitigated simultaneously. We will release our code for GrADS later.

---

### Motif 2 12.7B technical report

Authors: Junghwan Lim, Sungmin Lee, Dongseok Kim, Taehyun Kim, Eunhwan Park, Jeesoo Lee, Jeongdoo Lee, Junhyeok Lee, Wai Ting Cheung, Dahye Choi, Jaeheui Her, Jaeyeon Huh et al.
Published: 2025-11-07
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.07464v1

We introduce Motif-2-12.7B, a new open-weight foundation model that pushes the efficiency frontier of large language models by combining architectural innovation with system-level optimization. Designed for scalable language understanding and robust instruction generalization under constrained compute budgets, Motif-2-12.7B builds upon Motif-2.6B with the integration of Grouped Differential Attention (GDA), which improves representational efficiency by disentangling signal and noise-control attention pathways. The model is pre-trained on 5.5 trillion tokens spanning diverse linguistic, mathematical, scientific, and programming domains using a curriculum-driven data scheduler that gradually changes the data composition ratio. The training system leverages the MuonClip optimizer alongside custom high-performance kernels, including fused PolyNorm activations and the Parallel Muon algorithm, yielding significant throughput and memory efficiency gains in large-scale distributed environments. Post-training employs a three-stage supervised fine-tuning pipeline that successively enhances general instruction adherence, compositional understanding, and linguistic precision. Motif-2-12.7B demonstrates competitive performance across diverse benchmarks, showing that thoughtful architectural scaling and optimized training design can rival the capabilities of much larger models.

---

### Dynamic Stability of LLM-Generated Code

Authors: Prateek Rajput, Abdoul Aziz Bonkoungou, Yewei Song, Abdoul Kader Kabore, Iyiola E. Olatunji, Jacques Klein, Tegewende Bissyande
Published: 2025-11-07
Categories: cs.PL, cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2511.07463v1

Current evaluations of LLMs for code generation emphasize functional correctness, overlooking the fact that functionally correct solutions can differ significantly in algorithmic complexity. For instance, an $(O(n^2))$ versus $(O(n \log n))$ sorting algorithm may yield similar output but incur vastly different performance costs in production. This discrepancy reveals a critical limitation in current evaluation methods: they fail to capture the behavioral and performance diversity among correct solutions. To address this, we introduce a principled framework for evaluating the dynamic stability of generated code. We propose two metrics derived from opcode distributions: Static Canonical Trace Divergence (SCTD), which captures algorithmic structure diversity across generated solutions, and Dynamic Canonical Trace Divergence (DCTD), which quantifies runtime behavioral variance. Their ratio, the Behavioral Expression Factor (BEF), serves as a diagnostic signal: it indicates critical runtime instability when BEF $\ll$ 1 and functional redundancy when BEF $\gg$ 1. Empirical results on BigOBench and CodeContests show that state-of-the-art LLMs exhibit significant algorithmic variance even among functionally correct outputs. Notably, increasing sampling temperature improves pass@1 rates but degrades stability, revealing an unrecognized trade-off: searching for correct solutions in diverse output spaces introduces a "penalty of instability" between correctness and behavioral consistency. Our findings call for stability-aware objectives in code generation and new benchmarks with asymptotic test cases for robust, real-world LLM evaluation.

---

### It Takes Two: A Dual Stage Approach for Terminology-Aware Translation

Authors: Akshat Singh Jaswal
Published: 2025-11-07
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.07461v1

This paper introduces DuTerm, a novel two-stage architecture for terminology-constrained machine translation. Our system combines a terminology-aware NMT model, adapted via fine-tuning on large-scale synthetic data, with a prompt-based LLM for post-editing. The LLM stage refines NMT output and enforces terminology adherence. We evaluate DuTerm on English-to German, English-to-Spanish, and English-to-Russian with the WMT 2025 Terminology Shared Task corpus. We demonstrate that flexible, context-driven terminology handling by the LLM consistently yields higher quality translations than strict constraint enforcement. Our results highlight a critical trade-off, revealing that an LLM's work best for high-quality translation as context-driven mutators rather than generators.

---

### Optimizing Classification of Infrequent Labels by Reducing Variability in Label Distribution

Authors: Ashutosh Agarwal
Published: 2025-11-07
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.07459v1

This paper presents a novel solution, LEVER, designed to address the challenges posed by underperforming infrequent categories in Extreme Classification (XC) tasks. Infrequent categories, often characterized by sparse samples, suffer from high label inconsistency, which undermines classification performance. LEVER mitigates this problem by adopting a robust Siamese-style architecture, leveraging knowledge transfer to reduce label inconsistency and enhance the performance of One-vs-All classifiers. Comprehensive testing across multiple XC datasets reveals substantial improvements in the handling of infrequent categories, setting a new benchmark for the field. Additionally, the paper introduces two newly created multi-intent datasets, offering essential resources for future XC research.

---

### Lived Experience in Dialogue: Co-designing Personalization in Large Language Models to Support Youth Mental Well-being

Authors: Kathleen W. Guan, Sarthak Giri, Mohammed Amara, Bernard J. Jansen, Enrico Liscio, Milena Esherick, Mohammed Al Owayyed, Ausrine Ratkute, Gayane Sedrakyan, Mark de Reuver, Joao Fernando Ferreira Goncalves, Caroline A. Figueroa
Published: 2025-11-07
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2511.05769v1

Youth increasingly turn to large language models (LLMs) for mental well-being support, yet current personalization in LLMs can overlook the heterogeneous lived experiences shaping their needs. We conducted a participatory study with youth, parents, and youth care workers (N=38), using co-created youth personas as scaffolds, to elicit community perspectives on how LLMs can facilitate more meaningful personalization to support youth mental well-being. Analysis identified three themes: person-centered contextualization responsive to momentary needs, explicit boundaries around scope and offline referral, and dialogic scaffolding for reflection and autonomy. We mapped these themes to persuasive design features for task suggestions, social facilitation, and system trustworthiness, and created corresponding dialogue extracts to guide LLM fine-tuning. Our findings demonstrate how lived experience can be operationalized to inform design features in LLMs, which can enhance the alignment of LLM-based interventions with the realities of youth and their communities, contributing to more effectively personalized digital well-being tools.

---

### Anchors in the Machine: Behavioral and Attributional Evidence of Anchoring Bias in LLMs

Authors: Felipe Valencia-Clavijo
Published: 2025-11-07
Categories: cs.AI, cs.CL, econ.GN
arXiv: https://arxiv.org/abs/2511.05766v1

Large language models (LLMs) are increasingly examined as both behavioral subjects and decision systems, yet it remains unclear whether observed cognitive biases reflect surface imitation or deeper probability shifts. Anchoring bias, a classic human judgment bias, offers a critical test case. While prior work shows LLMs exhibit anchoring, most evidence relies on surface-level outputs, leaving internal mechanisms and attributional contributions unexplored. This paper advances the study of anchoring in LLMs through three contributions: (1) a log-probability-based behavioral analysis showing that anchors shift entire output distributions, with controls for training-data contamination; (2) exact Shapley-value attribution over structured prompt fields to quantify anchor influence on model log-probabilities; and (3) a unified Anchoring Bias Sensitivity Score integrating behavioral and attributional evidence across six open-source models. Results reveal robust anchoring effects in Gemma-2B, Phi-2, and Llama-2-7B, with attribution signaling that the anchors influence reweighting. Smaller models such as GPT-2, Falcon-RW-1B, and GPT-Neo-125M show variability, suggesting scale may modulate sensitivity. Attributional effects, however, vary across prompt designs, underscoring fragility in treating LLMs as human substitutes. The findings demonstrate that anchoring bias in LLMs is robust, measurable, and interpretable, while highlighting risks in applied domains. More broadly, the framework bridges behavioral science, LLM safety, and interpretability, offering a reproducible path for evaluating other cognitive biases in LLMs.

---

### A Second-Order Attention Mechanism For Prostate Cancer Segmentation and Detection in Bi-Parametric MRI

Authors: Mateo Ortiz, Juan Olmos, Fabio Martínez
Published: 2025-11-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.05760v1

The detection of clinically significant prostate cancer lesions (csPCa) from biparametric magnetic resonance imaging (bp-MRI) has emerged as a noninvasive imaging technique for improving accurate diagnosis. Nevertheless, the analysis of such images remains highly dependent on the subjective expert interpretation. Deep learning approaches have been proposed for csPCa lesions detection and segmentation, but they remain limited due to their reliance on extensively annotated datasets. Moreover, the high lesion variability across prostate zones poses additional challenges, even for expert radiologists. This work introduces a second-order geometric attention (SOGA) mechanism that guides a dedicated segmentation network, through skip connections, to detect csPCa lesions. The proposed attention is modeled on the Riemannian manifold, learning from symmetric positive definitive (SPD) representations. The proposed mechanism was integrated into standard U-Net and nnU-Net backbones, and was validated on the publicly available PI-CAI dataset, achieving an Average Precision (AP) of 0.37 and an Area Under the ROC Curve (AUC-ROC) of 0.83, outperforming baseline networks and attention-based methods. Furthermore, the approach was evaluated on the Prostate158 dataset as an independent test cohort, achieving an AP of 0.37 and an AUC-ROC of 0.75, confirming robust generalization and suggesting discriminative learned representations.

---

### Language Generation: Complexity Barriers and Implications for Learning

Authors: Marcelo Arenas, Pablo Barceló, Luis Cofré, Alexander Kozachinskiy
Published: 2025-11-07
Categories: cs.CL, cs.AI, cs.FL, cs.LG
arXiv: https://arxiv.org/abs/2511.05759v2

Kleinberg and Mullainathan showed that language generation in the limit is always possible at the level of computability: given enough positive examples, a learner can eventually generate data indistinguishable from a target language. However, such existence results do not address feasibility. We study the sample complexity of language generation in the limit for several canonical classes of formal languages. Our results show that infeasibility already appears for context-free and regular languages, and persists even for strict subclasses such as locally threshold testable languages, as well as for incomparable classes such as non-erasing pattern languages, a well-studied class in the theory of language identification. Overall, our results establish a clear gap between the theoretical possibility of language generation in the limit and its computational feasibility.

---

### Primal-Only Actor Critic Algorithm for Robust Constrained Average Cost MDPs

Authors: Anirudh Satheesh, Sooraj Sathish, Swetha Ganesh, Keenan Powell, Vaneet Aggarwal
Published: 2025-11-07
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.05758v1

In this work, we study the problem of finding robust and safe policies in Robust Constrained Average-Cost Markov Decision Processes (RCMDPs). A key challenge in this setting is the lack of strong duality, which prevents the direct use of standard primal-dual methods for constrained RL. Additional difficulties arise from the average-cost setting, where the Robust Bellman operator is not a contraction under any norm. To address these challenges, we propose an actor-critic algorithm for Average-Cost RCMDPs. We show that our method achieves both \(ε\)-feasibility and \(ε\)-optimality, and we establish a sample complexities of \(\tilde{O}\left(ε^{-4}\right)\) and \(\tilde{O}\left(ε^{-6}\right)\) with and without slackness assumption, which is comparable to the discounted setting.

---

### Zero-Shot Function Encoder-Based Differentiable Predictive Control

Authors: Hassan Iqbal, Xingjian Li, Tyler Ingebrand, Adam Thorpe, Krishna Kumar, Ufuk Topcu, Ján Drgoňa
Published: 2025-11-07
Categories: eess.SY, cs.LG
arXiv: https://arxiv.org/abs/2511.05757v3

We introduce a differentiable framework for zero-shot adaptive control over parametric families of nonlinear dynamical systems. Our approach integrates a function encoder-based neural ODE (FE-NODE) for modeling system dynamics with a differentiable predictive control (DPC) for offline self-supervised learning of explicit control policies. The FE-NODE captures nonlinear behaviors in state transitions and enables zero-shot adaptation to new systems without retraining, while the DPC efficiently learns control policies across system parameterizations, thus eliminating costly online optimization common in classical model predictive control. We demonstrate the efficiency, accuracy, and online adaptability of the proposed method across a range of nonlinear systems with varying parametric scenarios, highlighting its potential as a general-purpose tool for fast zero-shot adaptive control.

---

### Multi-Scale Feature Fusion and Graph Neural Network Integration for Text Classification with Large Language Models

Authors: Xiangchen Song, Yulin Huang, Jinxu Guo, Yuchen Liu, Yaxuan Luan
Published: 2025-11-07
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.05752v1

This study investigates a hybrid method for text classification that integrates deep feature extraction from large language models, multi-scale fusion through feature pyramids, and structured modeling with graph neural networks to enhance performance in complex semantic contexts. First, the large language model captures contextual dependencies and deep semantic representations of the input text, providing a rich feature foundation for subsequent modeling. Then, based on multi-level feature representations, the feature pyramid mechanism effectively integrates semantic features of different scales, balancing global information and local details to construct hierarchical semantic expressions. Furthermore, the fused features are transformed into graph representations, and graph neural networks are employed to capture latent semantic relations and logical dependencies in the text, enabling comprehensive modeling of complex interactions among semantic units. On this basis, the readout and classification modules generate the final category predictions. The proposed method demonstrates significant advantages in robustness alignment experiments, outperforming existing models on ACC, F1-Score, AUC, and Precision, which verifies the effectiveness and stability of the framework. This study not only constructs an integrated framework that balances global and local information as well as semantics and structure, but also provides a new perspective for multi-scale feature fusion and structured semantic modeling in text classification tasks.

---

### CoT-X: An Adaptive Framework for Cross-Model Chain-of-Thought Transfer and Optimization

Authors: Ziqian Bi, Yinzhi Wang, Tianyang Wang, Junfeng Hao, Benji Peng, Wenqian Weng, Jiayi Gu, Jacqueline Pang, Xinyuan Song
Published: 2025-11-07
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.05747v4

Long Chain-of-Thought (CoT) traces can improve reasoning accuracy, but repeatedly generating them is costly for smaller or latency-constrained language models. This paper studies a practical alternative: produce a rich rationale once with a capable \emph{thinking} model, compress it, and reuse the compressed trace as context for a cheaper \emph{answering} model. We introduce CoT-X, an adaptive framework for cross-model CoT transfer. CoT-X segments reasoning traces into semantic units, scores their diagnostic and logical importance, selects budget-feasible evidence paths, and reconstructs a coherent compressed rationale for the answering model. On $7,501$ Japanese medical licensing questions spanning $10$ specialties, CoT-X improves accuracy over direct truncation by up to $40.5\%$ under the same token budget, with the largest gains at $64$--$256$ tokens. Across $64$ thinking--answering pairs from eight DeepSeek-R1 and Qwen3 models (1.5B--32B parameters), reasoning transfer is most reliable within a model family, yet remains effective across families once compression normalizes the trace. A Gaussian Process Bayesian optimization layer finds near-optimal model--budget configurations with $15$ evaluations rather than an exhaustive search over all $64$ pairs, reducing evaluation cost by $84\%$. These results show that reasoning quality, token budget, and model compatibility can be optimized jointly, making CoT-style reasoning more practical under realistic deployment constraints.

---

### Beyond Redundancy: Diverse and Specialized Multi-Expert Sparse Autoencoder

Authors: Zhen Xu, Zhen Tan, Song Wang, Kaidi Xu, Tianlong Chen
Published: 2025-11-07
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.05745v1

Sparse autoencoders (SAEs) have emerged as a powerful tool for interpreting large language models (LLMs) by decomposing token activations into combinations of human-understandable features. While SAEs provide crucial insights into LLM explanations, their practical adoption faces a fundamental challenge: better interpretability demands that SAEs' hidden layers have high dimensionality to satisfy sparsity constraints, resulting in prohibitive training and inference costs. Recent Mixture of Experts (MoE) approaches attempt to address this by partitioning SAEs into narrower expert networks with gated activation, thereby reducing computation. In a well-designed MoE, each expert should focus on learning a distinct set of features. However, we identify a \textit{critical limitation} in MoE-SAE: Experts often fail to specialize, which means they frequently learn overlapping or identical features. To deal with it, we propose two key innovations: (1) Multiple Expert Activation that simultaneously engages semantically weighted expert subsets to encourage specialization, and (2) Feature Scaling that enhances diversity through adaptive high-frequency scaling. Experiments demonstrate a 24\% lower reconstruction error and a 99\% reduction in feature redundancy compared to existing MoE-SAE methods. This work bridges the interpretability-efficiency gap in LLM analysis, allowing transparent model inspection without compromising computational feasibility.

---

### In-Context Learning Without Copying

Authors: Kerem Sahin, Sheridan Feucht, Adam Belfki, Jannik Brinkmann, Aaron Mueller, David Bau, Chris Wendler
Published: 2025-11-07
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.05743v2

Induction heads are attention heads that perform inductive copying by matching patterns from earlier context and copying their continuations verbatim. As models develop induction heads, they experience a sharp drop in training loss, a phenomenon cited as evidence that induction heads may underlie a wide range of in-context learning (ICL) capabilities. In this work, we investigate whether induction heads are a necessary building block for learning abstractive ICL capabilities (i.e., tasks where the answer is not contained in the input context), or whether such capabilities can emerge independently. We propose Hapax, a training regime that omits the loss contribution of tokens predictable by induction heads. Despite a significant reduction in inductive copying, abstractive ICL capabilities are preserved, with the model achieving higher accuracy than the vanilla model on 13 out of 21 tasks, even though 31.7% of tokens are omitted from the loss. Furthermore, our model achieves lower loss values on token positions that induction heads cannot predict. Mechanistic analysis shows that models trained with Hapax develop fewer and weaker induction heads despite preserving abstractive ICL capabilities. Our findings suggest that the developmental link between induction heads and abstractive ICL capabilities is weaker than previously hypothesized.

---

### Near-Exponential Savings for Mean Estimation with Active Learning

Authors: Julian M. Morimoto, Jacob Goldin, Daniel E. Ho
Published: 2025-11-07
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.05736v1

We study the problem of efficiently estimating the mean of a $k$-class random variable, $Y$, using a limited number of labels, $N$, in settings where the analyst has access to auxiliary information (i.e.: covariates) $X$ that may be informative about $Y$. We propose an active learning algorithm ("PartiBandits") to estimate $\mathbb{E}(Y)$. The algorithm yields an estimate, $\widehatμ_{\text{PB}}$, such that $\left( \widehatμ_{\text{PB}} - \mathbb{E}(Y)\right)^2$ is $\tilde{\mathcal{O}}\left( \frac{ν+ \exp(c \cdot (-N/\log(N))) }{N} \right)$, where $c > 0$ is a constant and $ν$ is the risk of the Bayes-optimal classifier. PartiBandits is essentially a two-stage algorithm. In the first stage, it learns a partition of the unlabeled data that shrinks the average conditional variance of $Y$. In the second stage it uses a UCB-style subroutine ("WarmStart-UCB") to request labels from each stratum round-by-round. Both the main algorithm's and the subroutine's convergence rates are minimax optimal in classical settings. PartiBandits bridges the UCB and disagreement-based approaches to active learning despite these two approaches being designed to tackle very different tasks. We illustrate our methods through simulation using nationwide electronic health records. Our methods can be implemented using the PartiBandits package in R.

---

### Towards Better Ultrasound Video Segmentation Foundation Model: An Empirical study on SAM2 Finetuning from Data Perspective

Authors: Xing Yao, Ahana Gangopadhyay, Hsi-Ming Chang, Ravi Soni
Published: 2025-11-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.05731v1

Ultrasound (US) video segmentation remains a challenging problem due to strong inter- and intra-dataset variability, motion artifacts, and limited annotated data. Although foundation models such as Segment Anything Model 2 (SAM2) demonstrate strong zero-shot and prompt-guided segmentation capabilities, their performance deteriorates substantially when transferred to medical imaging domains. Current adaptation studies mainly emphasize architectural modifications, while the influence of data characteristics and training regimes has not been systematically examined. In this study, we present a comprehensive, data-centric investigation of SAM2 adaptation for ultrasound video segmentation. We analyze how training-set size, video duration, and augmentation schemes affect adaptation performance under three paradigms: task-specific fine-tuning, intermediate adaptation, and multi-task joint training, across five SAM2 variants and multiple prompting modes. We further design six ultrasound-specific augmentations, assessing their effect relative to generic strategies. Experiments on three representative ultrasound datasets reveal that data scale and temporal context play a more decisive role than model architecture or initialization. Moreover, joint training offers an efficient compromise between modality alignment and task specialization. This work aims to provide empirical insights for developing efficient, data-aware adaptation pipelines for SAM2 in ultrasound video analysis.

---

### QiVC-Net: Quantum-Inspired Variational Convolutional Network, with Application to Biosignal Classification

Authors: Amin Golnari, Jamileh Yousefi, Reza Moheimani, Saeid Sanei
Published: 2025-11-07
Categories: cs.LG, eess.SP
arXiv: https://arxiv.org/abs/2511.05730v2

In this paper, a learning framework is introduced which incorporates principles of probabilistic inference, variational optimization, and geometry-preserving operations inspired by quantum transformations. The central innovation of this quantum-inspired variational convolution (QiVC) lies in its quantum-inspired rotated ensemble (QiRE) mechanism. QiRE performs differentiable low-dimensional subspace rotations of convolutional weights. By drawing a mathematical analogy from unitary evolution, this approach enables structured uncertainty modeling that respects the intrinsic geometry of the parameter space. To demonstrate its practical potential, the concept is instantiated in a QiVC-based convolutional network (QiVC-Net) and evaluated in the context of biosignal classification, focusing on phonocardiogram (PCG) recordings. The proposed QiVC-Net integrates an architecture in which the QiVC layer does not introduce additional parameters, instead performing an ensemble rotation of the convolutional weights through a structured mechanism ensuring robustness without added highly computational burden. Experiments on two benchmark datasets, PhysioNet CinC 2016 and PhysioNet CirCor DigiScope 2022, show that QiVC-Net achieves state-of-the-art performance, reaching accuracies of 97.84% and 97.89%, respectively. These findings highlight the versatility of the QiVC framework and its promise for advancing uncertainty-aware modeling in real-world biomedical signal analysis. The implementation of the QiVConv layer is available in GitHub for public use.

---

### Compressing Chemistry Reveals Functional Groups

Authors: Ruben Sharma, Ross D. King
Published: 2025-11-07
Categories: cs.LG, cs.AI, cs.IT
arXiv: https://arxiv.org/abs/2511.05728v1

We introduce the first formal large-scale assessment of the utility of traditional chemical functional groups as used in chemical explanations. Our assessment employs a fundamental principle from computational learning theory: a good explanation of data should also compress the data. We introduce an unsupervised learning algorithm based on the Minimum Message Length (MML) principle that searches for substructures that compress around three million biologically relevant molecules. We demonstrate that the discovered substructures contain most human-curated functional groups as well as novel larger patterns with more specific functions. We also run our algorithm on 24 specific bioactivity prediction datasets to discover dataset-specific functional groups. Fingerprints constructed from dataset-specific functional groups are shown to significantly outperform other fingerprint representations, including the MACCS and Morgan fingerprint, when training ridge regression models on bioactivity regression tasks.

---