# Research Papers — 2025-11 · bundle page 146 of 197

> Full-text markdown of papers #7251–7300 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/146
[← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/145.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-11/page/147.md)

### DETECT: Data-Driven Evaluation of Treatments Enabled by Classification Transformers

Authors: Yuanheng Mao, Lillian Yang, Stephen Yang, Ethan Shao, Zihan Li
Published: 2025-11-10
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.07213v3

Chronic pain is a global health challenge affecting millions of individuals, making it essential for physicians to have reliable and objective methods to measure the functional impact of clinical treatments. Traditionally used methods, like the numeric rating scale, while personalized and easy to use, are subjective due to their self-reported nature. Thus, this paper proposes DETECT (Data-Driven Evaluation of Treatments Enabled by Classification Transformers), a data-driven framework that assesses treatment success by comparing patient activities of daily life before and after treatment. We use DETECT on public benchmark datasets and simulated patient data from smartphone sensors. Our results demonstrate that DETECT is objective yet lightweight, making it a significant and novel contribution to clinical decision-making. By using DETECT, independently or together with other self-reported metrics, physicians can improve their understanding of their treatment impacts, ultimately leading to more personalized and responsive patient care.

---

### Breaking the Stealth-Potency Trade-off in Clean-Image Backdoors with Generative Trigger Optimization

Authors: Binyan Xu, Fan Yang, Di Tang, Xilin Dai, Kehuan Zhang
Published: 2025-11-10
Categories: cs.CV, cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2511.07210v3

Clean-image backdoor attacks, which use only label manipulation in training datasets to compromise deep neural networks, pose a significant threat to security-critical applications. A critical flaw in existing methods is that the poison rate required for a successful attack induces a proportional, and thus noticeable, drop in Clean Accuracy (CA), undermining their stealthiness. This paper presents a new paradigm for clean-image attacks that minimizes this accuracy degradation by optimizing the trigger itself. We introduce Generative Clean-Image Backdoors (GCB), a framework that uses a conditional InfoGAN to identify naturally occurring image features that can serve as potent and stealthy triggers. By ensuring these triggers are easily separable from benign task-related features, GCB enables a victim model to learn the backdoor from an extremely small set of poisoned examples, resulting in a CA drop of less than 1%. Our experiments demonstrate GCB's remarkable versatility, successfully adapting to six datasets, five architectures, and four tasks, including the first demonstration of clean-image backdoors in regression and segmentation. GCB also exhibits resilience against most of the existing backdoor defenses.

---

### SMiLE: Provably Enforcing Global Relational Properties in Neural Networks

Authors: Matteo Francobaldi, Michele Lombardi, Andrea Lodi
Published: 2025-11-10
Categories: cs.LG, cs.AI, math.OC
arXiv: https://arxiv.org/abs/2511.07208v1

Artificial Intelligence systems are increasingly deployed in settings where ensuring robustness, fairness, or domain-specific properties is essential for regulation compliance and alignment with human values. However, especially on Neural Networks, property enforcement is very challenging, and existing methods are limited to specific constraints or local properties (defined around datapoints), or fail to provide full guarantees. We tackle these limitations by extending SMiLE, a recently proposed enforcement framework for NNs, to support global relational properties (defined over the entire input space). The proposed approach scales well with model complexity, accommodates general properties and backbones, and provides full satisfaction guarantees. We evaluate SMiLE on monotonicity, global robustness, and individual fairness, on synthetic and real data, for regression and classification tasks. Our approach is competitive with property-specific baselines in terms of accuracy and runtime, and strictly superior in terms of generality and level of guarantees. Overall, our results emphasize the potential of the SMiLE framework as a platform for future research and applications.

---

### Geometric implicit neural representations for signed distance functions

Authors: Luiz Schirmer, Tiago Novello, Vinícius da Silva, Guilherme Schardong, Daniel Perazzo, Hélio Lopes, Nuno Gonçalves, Luiz Velho
Published: 2025-11-10
Categories: cs.CV, cs.CG, cs.GR
arXiv: https://arxiv.org/abs/2511.07206v1

\textit{Implicit neural representations} (INRs) have emerged as a promising framework for representing signals in low-dimensional spaces. This survey reviews the existing literature on the specialized INR problem of approximating \textit{signed distance functions} (SDFs) for surface scenes, using either oriented point clouds or a set of posed images. We refer to neural SDFs that incorporate differential geometry tools, such as normals and curvatures, in their loss functions as \textit{geometric} INRs. The key idea behind this 3D reconstruction approach is to include additional \textit{regularization} terms in the loss function, ensuring that the INR satisfies certain global properties that the function should hold -- such as having unit gradient in the case of SDFs. We explore key methodological components, including the definition of INR, the construction of geometric loss functions, and sampling schemes from a differential geometry perspective. Our review highlights the significant advancements enabled by geometric INRs in surface reconstruction from oriented point clouds and posed images.

---

### Twenty-Five Years of MIR Research: Achievements, Practices, Evaluations, and Future Challenges

Authors: Geoffroy Peeters, Zafar Rafii, Magdalena Fuentes, Zhiyao Duan, Emmanouil Benetos, Juhan Nam, Yuki Mitsufuji
Published: 2025-11-10
Categories: cs.SD, cs.AI
arXiv: https://arxiv.org/abs/2511.07205v1

In this paper, we trace the evolution of Music Information Retrieval (MIR) over the past 25 years. While MIR gathers all kinds of research related to music informatics, a large part of it focuses on signal processing techniques for music data, fostering a close relationship with the IEEE Audio and Acoustic Signal Processing Technical Commitee. In this paper, we reflect the main research achievements of MIR along the three EDICS related to music analysis, processing and generation. We then review a set of successful practices that fuel the rapid development of MIR research. One practice is the annual research benchmark, the Music Information Retrieval Evaluation eXchange, where participants compete on a set of research tasks. Another practice is the pursuit of reproducible and open research. The active engagement with industry research and products is another key factor for achieving large societal impacts and motivating younger generations of students to join the field. Last but not the least, the commitment to diversity, equity and inclusion ensures MIR to be a vibrant and open community where various ideas, methodologies, and career pathways collide. We finish by providing future challenges MIR will have to face.

---

### Evaluating Online Moderation Via LLM-Powered Counterfactual Simulations

Authors: Giacomo Fidone, Lucia Passaro, Riccardo Guidotti
Published: 2025-11-10
Categories: cs.AI, cs.CY, cs.MA
arXiv: https://arxiv.org/abs/2511.07204v1

Online Social Networks (OSNs) widely adopt content moderation to mitigate the spread of abusive and toxic discourse. Nonetheless, the real effectiveness of moderation interventions remains unclear due to the high cost of data collection and limited experimental control. The latest developments in Natural Language Processing pave the way for a new evaluation approach. Large Language Models (LLMs) can be successfully leveraged to enhance Agent-Based Modeling and simulate human-like social behavior with unprecedented degree of believability. Yet, existing tools do not support simulation-based evaluation of moderation strategies. We fill this gap by designing a LLM-powered simulator of OSN conversations enabling a parallel, counterfactual simulation where toxic behavior is influenced by moderation interventions, keeping all else equal. We conduct extensive experiments, unveiling the psychological realism of OSN agents, the emergence of social contagion phenomena and the superior effectiveness of personalized moderation strategies.

---

### Resilient by Design -- Active Inference for Distributed Continuum Intelligence

Authors: Praveen Kumar Donta, Alfreds Lapkovskis, Enzo Mingozzi, Schahram Dustdar
Published: 2025-11-10
Categories: cs.DC, cs.AI, cs.MA, cs.NI
arXiv: https://arxiv.org/abs/2511.07202v3

Failures are the norm in highly complex and heterogeneous devices spanning the distributed computing continuum (DCC), from resource-constrained IoT and edge nodes to high-performance computing systems. Ensuring reliability and global consistency across these layers remains a major challenge, especially for AI-driven workloads requiring real-time, adaptive coordination. This work-in-progress paper introduces a Probabilistic Active Inference Resilience Agent (PAIR-Agent) to achieve resilience in DCC systems. PAIR-Agent performs three core operations: (i) constructing a causal fault graph from device logs, (ii) identifying faults while managing certainties and uncertainties using Markov blankets and the free energy principle, and (iii) autonomously healing issues through active inference. Through continuous monitoring and adaptive reconfiguration, the agent maintains service continuity and stability under diverse failure conditions. Theoretical validations confirm the reliability and effectiveness of the proposed framework.

---

### Automated Estimation of Anatomical Risk Metrics for Endoscopic Sinus Surgery Using Deep Learning

Authors: Konrad Reuter, Lennart Thaysen, Bilkay Doruk, Sarah Latus, Brigitte Holst, Benjamin Becker, Dennis Eggert, Christian Betz, Anna-Sophie Hoffmann, Alexander Schlaefer
Published: 2025-11-10
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.07199v1

Endoscopic sinus surgery requires careful preoperative assessment of the skull base anatomy to minimize risks such as cerebrospinal fluid leakage. Anatomical risk scores like the Keros, Gera and Thailand-Malaysia-Singapore score offer a standardized approach but require time-consuming manual measurements on coronal CT or CBCT scans. We propose an automated deep learning pipeline that estimates these risk scores by localizing key anatomical landmarks via heatmap regression. We compare a direct approach to a specialized global-to-local learning strategy and find mean absolute errors on the relevant anatomical measurements of 0.506mm for the Keros, 4.516° for the Gera and 0.802mm / 0.777mm for the TMS classification.

---

### Synergy over Discrepancy: A Partition-Based Approach to Multi-Domain LLM Fine-Tuning

Authors: Hua Ye, Siyuan Chen, Haoliang Zhang, Weihao Luo, Yanbin Li, Xuan Zhang
Published: 2025-11-10
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.07198v3

Large language models (LLMs) demonstrate impressive generalization abilities, yet adapting them effectively across multiple heterogeneous domains remains challenging due to inter-domain interference. To overcome this challenge, we propose a partition-based multi-stage fine-tuning framework designed to exploit inter-domain synergies while minimizing negative transfer. Our approach strategically partitions domains into subsets (stages) by balancing domain discrepancy, synergy, and model capacity constraints. We theoretically analyze the proposed framework and derive novel generalization bounds that justify our partitioning strategy. Extensive empirical evaluations on various language understanding tasks show that our method consistently outperforms state-of-the-art baselines.

---

### Simulation-based Methods for Optimal Sampling Design in Systems Biology

Authors: Tuan Minh Ha, Binh Thanh Nguyen, Lam Si Tung Ho
Published: 2025-11-10
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2511.07197v1

In many areas of systems biology, including virology, pharmacokinetics, and population biology, dynamical systems are commonly used to describe biological processes. These systems can be characterized by estimating their parameters from sampled data. The key problem is how to optimally select sampling points to achieve accurate parameter estimation. Classical approaches often rely on Fisher information matrix-based criteria such as A-, D-, and E-optimality, which require an initial parameter estimate and may yield suboptimal results when the estimate is inaccurate. This study proposes two simulation-based methods for optimal sampling design that do not depend on initial parameter estimates. The first method, E-optimal-ranking (EOR), employs the E-optimal criterion, while the second utilizes a Long Short-Term Memory (LSTM) neural network. Simulation studies based on the Lotka-Volterra and three-compartment models demonstrate that the proposed methods outperform both random selection and classical E-optimal design.

---

### EMODIS: A Benchmark for Context-Dependent Emoji Disambiguation in Large Language Models

Authors: Jiacheng Huang, Ning Yu, Xiaoyin Yi
Published: 2025-11-10
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.07193v1

Large language models (LLMs) are increasingly deployed in real-world communication settings, yet their ability to resolve context-dependent ambiguity remains underexplored. In this work, we present EMODIS, a new benchmark for evaluating LLMs' capacity to interpret ambiguous emoji expressions under minimal but contrastive textual contexts. Each instance in EMODIS comprises an ambiguous sentence containing an emoji, two distinct disambiguating contexts that lead to divergent interpretations, and a specific question that requires contextual reasoning. We evaluate both open-source and API-based LLMs, and find that even the strongest models frequently fail to distinguish meanings when only subtle contextual cues are present. Further analysis reveals systematic biases toward dominant interpretations and limited sensitivity to pragmatic contrast. EMODIS provides a rigorous testbed for assessing contextual disambiguation, and highlights the gap in semantic reasoning between humans and LLMs.

---

### LiteUpdate: A Lightweight Framework for Updating AI-Generated Image Detectors

Authors: Jiajie Lu, Zhenkan Fu, Na Zhao, Long Xing, Kejiang Chen, Weiming Zhang, Nenghai Yu
Published: 2025-11-10
Categories: cs.CV, cs.CR
arXiv: https://arxiv.org/abs/2511.07192v1

The rapid progress of generative AI has led to the emergence of new generative models, while existing detection methods struggle to keep pace, resulting in significant degradation in the detection performance. This highlights the urgent need for continuously updating AI-generated image detectors to adapt to new generators. To overcome low efficiency and catastrophic forgetting in detector updates, we propose LiteUpdate, a lightweight framework for updating AI-generated image detectors. LiteUpdate employs a representative sample selection module that leverages image confidence and gradient-based discriminative features to precisely select boundary samples. This approach improves learning and detection accuracy on new distributions with limited generated images, significantly enhancing detector update efficiency. Additionally, LiteUpdate incorporates a model merging module that fuses weights from multiple fine-tuning trajectories, including pre-trained, representative, and random updates. This balances the adaptability to new generators and mitigates the catastrophic forgetting of prior knowledge. Experiments demonstrate that LiteUpdate substantially boosts detection performance in various detectors. Specifically, on AIDE, the average detection accuracy on Midjourney improved from 87.63% to 93.03%, a 6.16% relative increase.

---

### Graph Representation-based Model Poisoning on the Heterogeneous Internet of Agents

Authors: Hanlin Cai, Houtianfu Wang, Haofan Dong, Kai Li, Sai Zou, Ozgur B. Akan
Published: 2025-11-10
Categories: cs.NI, cs.CL
arXiv: https://arxiv.org/abs/2511.07176v3

Internet of Agents (IoA) envisions a unified, agent-centric paradigm where heterogeneous large language model (LLM) agents can interconnect and collaborate at scale. Within this paradigm, federated fine-tuning (FFT) serves as a key enabler that allows distributed LLM agents to co-train an intelligent global LLM without centralizing local datasets. However, the FFT-enabled IoA systems remain vulnerable to model poisoning attacks, where adversaries can upload malicious updates to the server to degrade the performance of the aggregated global LLM. This paper proposes a graph representation-based model poisoning (GRMP) attack, which exploits overheard benign updates to construct a feature correlation graph and employs a variational graph autoencoder to capture structural dependencies and generate malicious updates. A novel attack algorithm is developed based on augmented Lagrangian and subgradient descent methods to optimize malicious updates that preserve benign-like statistics while embedding adversarial objectives. Experimental results show that the proposed GRMP attack can substantially decrease accuracy across different LLM models while remaining statistically consistent with benign updates, thereby evading detection by existing defense mechanisms and underscoring a severe threat to the ambitious IoA paradigm.

---

### Federated Learning for Video Violence Detection: Complementary Roles of Lightweight CNNs and Vision-Language Models for Energy-Efficient Use

Authors: Sébastien Thuau, Siba Haidar, Rachid Chelouah
Published: 2025-11-10
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.07171v1

Deep learning-based video surveillance increasingly demands privacy-preserving architectures with low computational and environmental overhead. Federated learning preserves privacy but deploying large vision-language models (VLMs) introduces major energy and sustainability challenges. We compare three strategies for federated violence detection under realistic non-IID splits on the RWF-2000 and RLVS datasets: zero-shot inference with pretrained VLMs, LoRA-based fine-tuning of LLaVA-NeXT-Video-7B, and personalized federated learning of a 65.8M-parameter 3D CNN. All methods exceed 90% accuracy in binary violence detection. The 3D CNN achieves superior calibration (ROC AUC 92.59%) at roughly half the energy cost (240 Wh vs. 570 Wh) of federated LoRA, while VLMs provide richer multimodal reasoning. Hierarchical category grouping (based on semantic similarity and class exclusion) boosts VLM multiclass accuracy from 65.31% to 81% on the UCF-Crime dataset. To our knowledge, this is the first comparative simulation study of LoRA-tuned VLMs and personalized CNNs for federated violence detection, with explicit energy and CO2e quantification. Our results inform hybrid deployment strategies that default to efficient CNNs for routine inference and selectively engage VLMs for complex contextual reasoning.

---

### On Stealing Graph Neural Network Models

Authors: Marcin Podhajski, Jan Dubiński, Franziska Boenisch, Adam Dziedzic, Agnieszka Pręgowska, Tomasz P. Michalak
Published: 2025-11-10
Categories: cs.LG, cs.CR
arXiv: https://arxiv.org/abs/2511.07170v2

Current graph neural network (GNN) model-stealing methods rely heavily on queries to the victim model, assuming no hard query limits. However, in reality, the number of allowed queries can be severely limited. In this paper, we demonstrate how an adversary can extract a GNN with very limited interactions with the model. Our approach first enables the adversary to obtain the model backbone without making direct queries to the victim model and then to strategically utilize a fixed query limit to extract the most informative data. The experiments on eight real-world datasets demonstrate the effectiveness of the attack, even under a very restricted query limit and under defense against model extraction in place. Our findings underscore the need for robust defenses against GNN model extraction threats.

---

### AdaRec: Adaptive Recommendation with LLMs via Narrative Profiling and Dual-Channel Reasoning

Authors: Meiyun Wang, Charin Polpanumas
Published: 2025-11-10
Categories: cs.CL, cs.AI, cs.CE
arXiv: https://arxiv.org/abs/2511.07166v1

We propose AdaRec, a few-shot in-context learning framework that leverages large language models for an adaptive personalized recommendation. AdaRec introduces narrative profiling, transforming user-item interactions into natural language representations to enable unified task handling and enhance human readability. Centered on a bivariate reasoning paradigm, AdaRec employs a dual-channel architecture that integrates horizontal behavioral alignment, discovering peer-driven patterns, with vertical causal attribution, highlighting decisive factors behind user preferences. Unlike existing LLM-based approaches, AdaRec eliminates manual feature engineering through semantic representations and supports rapid cross-task adaptation with minimal supervision. Experiments on real ecommerce datasets demonstrate that AdaRec outperforms both machine learning models and LLM-based baselines by up to eight percent in few-shot settings. In zero-shot scenarios, it achieves up to a nineteen percent improvement over expert-crafted profiling, showing effectiveness for long-tail personalization with minimal interaction data. Furthermore, lightweight fine-tuning on synthetic data generated by AdaRec matches the performance of fully fine-tuned models, highlighting its efficiency and generalization across diverse tasks.

---

### Fuzzy Label: From Concept to Its Application in Label Learning

Authors: Chenxi Luoa, Zhuangzhuang Zhaoa, Zhaohong Denga, Te Zhangb
Published: 2025-11-10
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.07165v1

Label learning is a fundamental task in machine learning that aims to construct intelligent models using labeled data, encompassing traditional single-label and multi-label classification models. Traditional methods typically rely on logical labels, such as binary indicators (e.g., "yes/no") that specify whether an instance belongs to a given category. However, in practical applications, label annotations often involve significant uncertainty due to factors such as data noise, inherent ambiguity in the observed entities, and the subjectivity of human annotators. Therefore, representing labels using simplistic binary logic can obscure valuable information and limit the expressiveness of label learning models. To overcome this limitation, this paper introduces the concept of fuzzy labels, grounded in fuzzy set theory, to better capture and represent label uncertainty. We further propose an efficient fuzzy labeling method that mines and generates fuzzy labels from the original data, thereby enriching the label space with more informative and nuanced representations. Based on this foundation, we present fuzzy-label-enhanced algorithms for both single-label and multi-label learning, using the classical K-Nearest Neighbors (KNN) and multi-label KNN algorithms as illustrative examples. Experimental results indicate that fuzzy labels can more effectively characterize the real-world labeling information and significantly enhance the performance of label learning models.

---

### Combining digital data streams and epidemic networks for real time outbreak detection

Authors: Ruiqi Lyu, Alistair Turcan, Bryan Wilder
Published: 2025-11-10
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.07163v1

Responding to disease outbreaks requires close surveillance of their trajectories, but outbreak detection is hindered by the high noise in epidemic time series. Aggregating information across data sources has shown great denoising ability in other fields, but remains underexplored in epidemiology. Here, we present LRTrend, an interpretable machine learning framework to identify outbreaks in real time. LRTrend effectively aggregates diverse health and behavioral data streams within one region and learns disease-specific epidemic networks to aggregate information across regions. We reveal diverse epidemic clusters and connections across the United States that are not well explained by commonly used human mobility networks and may be informative for future public health coordination. We apply LRTrend to 2 years of COVID-19 data in 305 hospital referral regions and frequently detect regional Delta and Omicron waves within 2 weeks of the outbreak's start, when case counts are a small fraction of the wave's resulting peak.

---

### Categorical Emotions or Appraisals - Which Emotion Model Explains Argument Convincingness Better?

Authors: Lynn Greschner, Meike Bauer, Sabine Weber, Roman Klinger
Published: 2025-11-10
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.07162v4

The convincingness of an argument does not only depend on its structure (logos), the person who makes the argument (ethos), but also on the emotion that it causes in the recipient (pathos). While the overall intensity and categorical values of emotions in arguments have received considerable attention in the research community, we argue that the emotion an argument evokes in a recipient is subjective. It depends on the recipient's goals, standards, prior knowledge, and stance. Appraisal theories lend themselves as a link between the subjective cognitive assessment of events and emotions. They have been used in event-centric emotion analysis, but their suitability for assessing argument convincingness remains unexplored. In this paper, we evaluate whether appraisal theories are suitable for emotion analysis in arguments by considering subjective cognitive evaluations of the importance and impact of an argument on its receiver. Based on the annotations in the recently published ContArgA corpus, we perform zero-shot prompting experiments to evaluate the importance of gold-annotated and predicted emotions and appraisals for the assessment of the subjective convincingness labels. We find that, while categorical emotion information does improve convincingness prediction, the improvement is more pronounced with appraisals. This work presents the first systematic comparison between emotion models for convincingness prediction, demonstrating the advantage of appraisals, providing insights for theoretical and practical applications in computational argumentation.

---

### LLMscape

Authors: Gottfried Haider, Jie Zhang
Published: 2025-11-10
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.07161v3

LLMscape is an interactive installation that investigates how humans and AI construct meaning under shared conditions of uncertainty. Within a mutable, projection-mapped landscape, human participants reshape the world and engage with multiple AI agents, each developing incomplete and provisional accounts of their environment. Exhibited in Shanghai and continually evolving, the work positions AI not as deterministic tools but as embodied co-witnesses to an unstable world, examining the parallels between human and artificial meaning-making and inviting reflection on our shared epistemic limits.

---

### Guiding Generative Models to Uncover Diverse and Novel Crystals via Reinforcement Learning

Authors: Hyunsoo Park, Aron Walsh
Published: 2025-11-10
Categories: cs.LG, physics.comp-ph
arXiv: https://arxiv.org/abs/2511.07158v1

Discovering functional crystalline materials entails navigating an immense combinatorial design space. While recent advances in generative artificial intelligence have enabled the sampling of chemically plausible compositions and structures, a fundamental challenge remains: the objective misalignment between likelihood-based sampling in generative modelling and targeted focus on underexplored regions where novel compounds reside. Here, we introduce a reinforcement learning framework that guides latent denoising diffusion models toward diverse and novel, yet thermodynamically viable crystalline compounds. Our approach integrates group relative policy optimisation with verifiable, multi-objective rewards that jointly balance creativity, stability, and diversity. Beyond de novo generation, we demonstrate enhanced property-guided design that preserves chemical validity, while targeting desired functional properties. This approach establishes a modular foundation for controllable AI-driven inverse design that addresses the novelty-validity trade-off across scientific discovery applications of generative models.

---

### Conditional Diffusion as Latent Constraints for Controllable Symbolic Music Generation

Authors: Matteo Pettenó, Alessandro Ilic Mezza, Alberto Bernardini
Published: 2025-11-10
Categories: cs.LG, cs.AI, eess.AS
arXiv: https://arxiv.org/abs/2511.07156v1

Recent advances in latent diffusion models have demonstrated state-of-the-art performance in high-dimensional time-series data synthesis while providing flexible control through conditioning and guidance. However, existing methodologies primarily rely on musical context or natural language as the main modality of interacting with the generative process, which may not be ideal for expert users who seek precise fader-like control over specific musical attributes. In this work, we explore the application of denoising diffusion processes as plug-and-play latent constraints for unconditional symbolic music generation models. We focus on a framework that leverages a library of small conditional diffusion models operating as implicit probabilistic priors on the latents of a frozen unconditional backbone. While previous studies have explored domain-specific use cases, this work, to the best of our knowledge, is the first to demonstrate the versatility of such an approach across a diverse array of musical attributes, such as note density, pitch range, contour, and rhythm complexity. Our experiments show that diffusion-driven constraints outperform traditional attribute regularization and other latent constraints architectures, achieving significantly stronger correlations between target and generated attributes while maintaining high perceptual quality and diversity.

---

### Dynamics-Decoupled Trajectory Alignment for Sim-to-Real Transfer in Reinforcement Learning for Autonomous Driving

Authors: Thomas Steinecker, Alexander Bienemann, Denis Trescher, Thorsten Luettel, Mirko Maehlisch
Published: 2025-11-10
Categories: cs.RO, cs.LG
arXiv: https://arxiv.org/abs/2511.07155v1

Reinforcement learning (RL) has shown promise in robotics, but deploying RL on real vehicles remains challenging due to the complexity of vehicle dynamics and the mismatch between simulation and reality. Factors such as tire characteristics, road surface conditions, aerodynamic disturbances, and vehicle load make it infeasible to model real-world dynamics accurately, which hinders direct transfer of RL agents trained in simulation. In this paper, we present a framework that decouples motion planning from vehicle control through a spatial and temporal alignment strategy between a virtual vehicle and the real system. An RL agent is first trained in simulation using a kinematic bicycle model to output continuous control actions. Its behavior is then distilled into a trajectory-predicting agent that generates finite-horizon ego-vehicle trajectories, enabling synchronization between virtual and real vehicles. At deployment, a Stanley controller governs lateral dynamics, while longitudinal alignment is maintained through adaptive update mechanisms that compensate for deviations between virtual and real trajectories. We validate our approach on a real vehicle and demonstrate that the proposed alignment strategy enables robust zero-shot transfer of RL-based motion planning from simulation to reality, successfully decoupling high-level trajectory generation from low-level vehicle control.

---

### Improved Runtime Guarantees for the SPEA2 Multi-Objective Optimizer

Authors: Benjamin Doerr, Martin S. Krejca, Milan Stanković
Published: 2025-11-10
Categories: cs.NE
arXiv: https://arxiv.org/abs/2511.07150v2

Together with the NSGA-II, the SPEA2 is one of the most widely used domination-based multi-objective evolutionary algorithms. For both algorithms, the known runtime guarantees are linear in the population size; for the NSGA-II, matching lower bounds exist. With a careful study of the more complex selection mechanism of the SPEA2, we show that it has very different population dynamics. From these, we prove runtime guarantees for the OneMinMax, LeadingOnesTrailingZeros, and OneJumpZeroJump benchmarks that depend less on the population size. For example, we show that the SPEA2 with parent population size $μ\ge n - 2k + 3$ and offspring population size $λ$ computes the Pareto front of the OneJumpZeroJump benchmark with gap size $k$ in an expected number of $O( (λ+μ)n + n^{k+1})$ function evaluations. This shows that the best runtime guarantee of $O(n^{k+1})$ is not only achieved for $μ= Θ(n)$ and $λ= O(n)$ but for arbitrary $μ, λ= O(n^k)$. Thus, choosing suitable parameters -- a key challenge in using heuristic algorithms -- is much easier for the SPEA2 than the NSGA-II.

---

### TCM-Eval: An Expert-Level Dynamic and Extensible Benchmark for Traditional Chinese Medicine

Authors: Zihao Cheng, Yuheng Lu, Huaiqian Ye, Zeming Liu, Minqi Wang, Jingjing Liu, Zihan Li, Wei Fan, Yuanfang Guo, Ruiji Fu, Shifeng She, Gang Wang et al.
Published: 2025-11-10
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.07148v2

Large Language Models (LLMs) have demonstrated remarkable capabilities in modern medicine, yet their application in Traditional Chinese Medicine (TCM) remains severely limited by the absence of standardized benchmarks and the scarcity of high-quality training data. To address these challenges, we introduce TCM-Eval, the first dynamic and extensible benchmark for TCM, meticulously curated from national medical licensing examinations and validated by TCM experts. Furthermore, we construct a large-scale training corpus and propose Self-Iterative Chain-of-Thought Enhancement (SI-CoTE) to autonomously enrich question-answer pairs with validated reasoning chains through rejection sampling, establishing a virtuous cycle of data and model co-evolution. Using this enriched training data, we develop ZhiMingTang (ZMT), a state-of-the-art LLM specifically designed for TCM, which significantly exceeds the passing threshold for human practitioners. To encourage future research and development, we release a public leaderboard, fostering community engagement and continuous improvement.

---

### ProcGen3D: Learning Neural Procedural Graph Representations for Image-to-3D Reconstruction

Authors: Xinyi Zhang, Daoyi Gao, Naiqi Li, Angela Dai
Published: 2025-11-10
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.07142v1

We introduce ProcGen3D, a new approach for 3D content creation by generating procedural graph abstractions of 3D objects, which can then be decoded into rich, complex 3D assets. Inspired by the prevalent use of procedural generators in production 3D applications, we propose a sequentialized, graph-based procedural graph representation for 3D assets. We use this to learn to approximate the landscape of a procedural generator for image-based 3D reconstruction. We employ edge-based tokenization to encode the procedural graphs, and train a transformer prior to predict the next token conditioned on an input RGB image. Crucially, to enable better alignment of our generated outputs to an input image, we incorporate Monte Carlo Tree Search (MCTS) guided sampling into our generation process, steering output procedural graphs towards more image-faithful reconstructions. Our approach is applicable across a variety of objects that can be synthesized with procedural generators. Extensive experiments on cacti, trees, and bridges show that our neural procedural graph generation outperforms both state-of-the-art generative 3D methods and domain-specific modeling techniques. Furthermore, this enables improved generalization on real-world input images, despite training only on synthetic data.

---

### Trading Vector Data in Vector Databases

Authors: Jin Cheng, Xiangxiang Dai, Ningning Ding, John C. S. Lui, Jianwei Huang
Published: 2025-11-10
Categories: cs.DB, cs.LG
arXiv: https://arxiv.org/abs/2511.07139v1

Vector data trading is essential for cross-domain learning with vector databases, yet it remains largely unexplored. We study this problem under online learning, where sellers face uncertain retrieval costs and buyers provide stochastic feedback to posted prices. Three main challenges arise: (1) heterogeneous and partial feedback in configuration learning, (2) variable and complex feedback in pricing learning, and (3) inherent coupling between configuration and pricing decisions. We propose a hierarchical bandit framework that jointly optimizes retrieval configurations and pricing. Stage I employs contextual clustering with confidence-based exploration to learn effective configurations with logarithmic regret. Stage II adopts interval-based price selection with local Taylor approximation to estimate buyer responses and achieve sublinear regret. We establish theoretical guarantees with polynomial time complexity and validate the framework on four real-world datasets, demonstrating consistent improvements in cumulative reward and regret reduction compared with existing methods.

---

### MPJudge: Towards Perceptual Assessment of Music-Induced Paintings

Authors: Shiqi Jiang, Tianyi Liang, Huayuan Ye, Changbo Wang, Chenhui Li
Published: 2025-11-10
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.07137v2

Music induced painting is a unique artistic practice, where visual artworks are created under the influence of music. Evaluating whether a painting faithfully reflects the music that inspired it poses a challenging perceptual assessment task. Existing methods primarily rely on emotion recognition models to assess the similarity between music and painting, but such models introduce considerable noise and overlook broader perceptual cues beyond emotion. To address these limitations, we propose a novel framework for music induced painting assessment that directly models perceptual coherence between music and visual art. We introduce MPD, the first large scale dataset of music painting pairs annotated by domain experts based on perceptual coherence. To better handle ambiguous cases, we further collect pairwise preference annotations. Building on this dataset, we present MPJudge, a model that integrates music features into a visual encoder via a modulation based fusion mechanism. To effectively learn from ambiguous cases, we adopt Direct Preference Optimization for training. Extensive experiments demonstrate that our method outperforms existing approaches. Qualitative results further show that our model more accurately identifies music relevant regions in paintings.

---

### LoRA on the Go: Instance-level Dynamic LoRA Selection and Merging

Authors: Seungeon Lee, Soumi Das, Manish Gupta, Krishna P. Gummadi
Published: 2025-11-10
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.07129v3

Low-Rank Adaptation (LoRA) has emerged as a parameter-efficient approach for fine-tuning large language models. However, conventional LoRA adapters are typically trained for a single task, limiting their applicability in real-world settings where inputs may span diverse and unpredictable domains. At inference time, existing approaches combine multiple LoRAs for improving performance on diverse tasks, while usually requiring labeled data or additional task-specific training, which is expensive at scale. In this work, we introduce LoRA on the Go (LoGo), a training-free framework that dynamically selects and merges adapters at the instance level without any additional requirements. LoGo leverages signals extracted from a single forward pass through LoRA adapters, to identify the most relevant adapters and determine their contributions on-the-fly. Across 5 NLP benchmarks, 27 datasets, and 3 model families, LoGo outperforms training-based baselines on some tasks upto a margin of 3.6% while remaining competitive on other tasks and maintaining inference throughput, highlighting its effectiveness and practicality.

---

### REACT-LLM: A Benchmark for Evaluating LLM Integration with Causal Features in Clinical Prognostic Tasks

Authors: Linna Wang, Zhixuan You, Qihui Zhang, Jiunan Wen, Ji Shi, Yimin Chen, Yusen Wang, Fanqi Ding, Ziliang Feng, Li Lu
Published: 2025-11-10
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.07127v3

Large Language Models (LLMs) and causal learning each hold strong potential for clinical decision making (CDM). However, their synergy remains poorly understood, largely due to the lack of systematic benchmarks evaluating their integration in clinical risk prediction. In real-world healthcare, identifying features with causal influence on outcomes is crucial for actionable and trustworthy predictions. While recent work highlights LLMs' emerging causal reasoning abilities, there lacks comprehensive benchmarks to assess their causal learning and performance informed by causal features in clinical risk prediction. To address this, we introduce REACT-LLM, a benchmark designed to evaluate whether combining LLMs with causal features can enhance clinical prognostic performance and potentially outperform traditional machine learning (ML) methods. Unlike existing LLM-clinical benchmarks that often focus on a limited set of outcomes, REACT-LLM evaluates 7 clinical outcomes across 2 real-world datasets, comparing 15 prominent LLMs, 6 traditional ML models, and 3 causal discovery (CD) algorithms. Our findings indicate that while LLMs perform reasonably in clinical prognostics, they have not yet outperformed traditional ML models. Integrating causal features derived from CD algorithms into LLMs offers limited performance gains, primarily due to the strict assumptions of many CD methods, which are often violated in complex clinical data. While the direct integration yields limited improvement, our benchmark reveals a more promising synergy.

---

### Saliency Map-Guided Knowledge Discovery for Subclass Identification with LLM-Based Symbolic Approximations

Authors: Tim Bohne, Anne-Kathrin Patricia Windler, Martin Atzmueller
Published: 2025-11-10
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.07126v1

This paper proposes a novel neuro-symbolic approach for sensor signal-based knowledge discovery, focusing on identifying latent subclasses in time series classification tasks. The approach leverages gradient-based saliency maps derived from trained neural networks to guide the discovery process. Multiclass time series classification problems are transformed into binary classification problems through label subsumption, and classifiers are trained for each of these to yield saliency maps. The input signals, grouped by predicted class, are clustered under three distinct configurations. The centroids of the final set of clusters are provided as input to an LLM for symbolic approximation and fuzzy knowledge graph matching to discover the underlying subclasses of the original multiclass problem. Experimental results on well-established time series classification datasets demonstrate the effectiveness of our saliency map-driven method for knowledge discovery, outperforming signal-only baselines in both clustering and subclass identification.

---

### Towards a Rigorous Understanding of the Population Dynamics of the NSGA-III: Tight Runtime Bounds

Authors: Andre Opris
Published: 2025-11-10
Categories: cs.NE
arXiv: https://arxiv.org/abs/2511.07125v1

Evolutionary algorithms are widely used for solving multi-objective optimization problems. A prominent example is NSGA-III, which is particularly well suited for solving problems involving more than three objectives, distinguishing it from the classical NSGA-II. Despite its empirical success, the theoretical understanding of NSGA III remains very limited, especially with respect to runtime analysis. A central open problem concerns its population dynamics, which involve controlling the maximum number of individuals sharing the same fitness value during the exploration process. In this paper, we make a significant step towards such an understanding by proving tight runtime bounds for NSGA-III on the bi-objective OneMinMax ($2$-OMM) problem. Firstly, we prove that NSGA-III requires $Ω(n^2 \log(n) / μ)$ generations in expectation to optimize $2$-OMM assuming the population size $μ$ satisfies $n+1 \leq μ=O(\log(n)^c(n+1))$ where $n$ denotes the problem size and $c<1$ is a constant. Apart from~\cite{opris2025multimodal}, this is the first proven lower runtime bound for NSGA-III on a classical benchmark problem. Complementing this, we secondly improve the best known upper bound of NSGA-III on the $m$-objective OneMinMax problem ($m$-OMM) of $O(n \log(n))$ generations by a factor of $μ/(2n/m + 1)^{m/2}$ for a constant number $m$ of objectives and population size $(2n/m + 1)^{m/2} \leq μ\in O(\sqrt{\log(n)} (2n/m + 1)^{m/2})$. This yields tight runtime bounds in the case $m = 2$, and the surprising result that NSGA-III beats NSGA-II by a factor of $μ/n$ in the expected runtime.

---

### Think Consistently, Reason Efficiently: Energy-Based Calibration for Implicit Chain-of-Thought

Authors: Zhikang Chen, Sen Cui, Deheng Ye, Yu Zhang, Yatao Bian, Tingting Zhu
Published: 2025-11-10
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.07124v1

Large Language Models (LLMs) have demonstrated strong reasoning capabilities through \emph{Chain-of-Thought} (CoT) prompting, which enables step-by-step intermediate reasoning. However, explicit CoT methods rely on discrete token-level reasoning processes that are prone to error propagation and limited by vocabulary expressiveness, often resulting in rigid and inconsistent reasoning trajectories. Recent research has explored implicit or continuous reasoning in latent spaces, allowing models to perform internal reasoning before generating explicit output. Although such approaches alleviate some limitations of discrete CoT, they generally lack explicit mechanisms to enforce consistency among reasoning steps, leading to divergent reasoning paths and unstable outcomes. To address this issue, we propose EBM-CoT, an Energy-Based Chain-of-Thought Calibration framework that refines latent thought representations through an energy-based model (EBM). Our method dynamically adjusts latent reasoning trajectories toward lower-energy, high-consistency regions in the embedding space, improving both reasoning accuracy and consistency without modifying the base language model. Extensive experiments across mathematical, commonsense, and symbolic reasoning benchmarks demonstrate that the proposed framework significantly enhances the consistency and efficiency of multi-step reasoning in LLMs.

---

### Sparse4DGS: 4D Gaussian Splatting for Sparse-Frame Dynamic Scene Reconstruction

Authors: Changyue Shi, Chuxiao Yang, Xinyuan Hu, Minghao Chen, Wenwen Pan, Yan Yang, Jiajun Ding, Zhou Yu, Jun Yu
Published: 2025-11-10
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.07122v1

Dynamic Gaussian Splatting approaches have achieved remarkable performance for 4D scene reconstruction. However, these approaches rely on dense-frame video sequences for photorealistic reconstruction. In real-world scenarios, due to equipment constraints, sometimes only sparse frames are accessible. In this paper, we propose Sparse4DGS, the first method for sparse-frame dynamic scene reconstruction. We observe that dynamic reconstruction methods fail in both canonical and deformed spaces under sparse-frame settings, especially in areas with high texture richness. Sparse4DGS tackles this challenge by focusing on texture-rich areas. For the deformation network, we propose Texture-Aware Deformation Regularization, which introduces a texture-based depth alignment loss to regulate Gaussian deformation. For the canonical Gaussian field, we introduce Texture-Aware Canonical Optimization, which incorporates texture-based noise into the gradient descent process of canonical Gaussians. Extensive experiments show that when taking sparse frames as inputs, our method outperforms existing dynamic or few-shot techniques on NeRF-Synthetic, HyperNeRF, NeRF-DS, and our iPhone-4D datasets.

---

### On the Joint Minimization of Regularization Loss Functions in Deep Variational Bayesian Methods for Attribute-Controlled Symbolic Music Generation

Authors: Matteo Pettenó, Alessandro Ilic Mezza, Alberto Bernardini
Published: 2025-11-10
Categories: cs.LG, cs.AI, eess.AS
arXiv: https://arxiv.org/abs/2511.07118v1

Explicit latent variable models provide a flexible yet powerful framework for data synthesis, enabling controlled manipulation of generative factors. With latent variables drawn from a tractable probability density function that can be further constrained, these models enable continuous and semantically rich exploration of the output space by navigating their latent spaces. Structured latent representations are typically obtained through the joint minimization of regularization loss functions. In variational information bottleneck models, reconstruction loss and Kullback-Leibler Divergence (KLD) are often linearly combined with an auxiliary Attribute-Regularization (AR) loss. However, balancing KLD and AR turns out to be a very delicate matter. When KLD dominates over AR, generative models tend to lack controllability; when AR dominates over KLD, the stochastic encoder is encouraged to violate the standard normal prior. We explore this trade-off in the context of symbolic music generation with explicit control over continuous musical attributes. We show that existing approaches struggle to jointly minimize both regularization objectives, whereas suitable attribute transformations can help achieve both controllability and regularization of the target latent dimensions.

---

### More Agents Improve Math Problem Solving but Adversarial Robustness Gap Persists

Authors: Khashayar Alavi, Zhastay Yeltay, Lucie Flek, Akbar Karimi
Published: 2025-11-10
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.07112v2

When LLM agents work together, they seem to be more powerful than a single LLM in mathematical question answering. However, are they also more robust to adversarial inputs? We investigate this question using adversarially perturbed math questions. These perturbations include punctuation noise with three intensities (10%, 30%, 50%), plus real-world and human-like typos (WikiTypo, R2ATA). Using a unified sampling-and-voting framework (Agent Forest), we evaluate six open-source models (Qwen3-4B/14B, Llama3.1-8B, Mistral-7B, Gemma3-4B/12B) across four benchmarks (GSM8K, MATH, MMLU-Math, MultiArith), with various numbers of agents n = {1,2,5,10,15,20,25}. Our findings show that 1) Noise type matters: punctuation noise harm scales with its severity, and the human typos remain the dominant bottleneck, yielding the largest gaps to Clean accuracy and the highest attack success rate (ASR) even with a large number of agents; 2) Collaboration reliably improves accuracy as the number of agents, n, increases, with the largest gains from n=1 to n=5 and diminishing returns beyond n$\approx$10. However, the adversarial robustness gap persists regardless of the agent count.

---

### Two Heads are Better than One: Distilling Large Language Model Features Into Small Models with Feature Decomposition and Mixture

Authors: Tianhao Fu, Xinxin Xu, Weichen Xu, Jue Chen, Ruilong Ren, Bowen Deng, Xinyu Zhao, Jian Cao, Xixin Cao
Published: 2025-11-10
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.07110v3

Market making (MM) through Reinforcement Learning (RL) has attracted significant attention in financial trading. With the development of Large Language Models (LLMs), more and more attempts are being made to apply LLMs to financial areas. A simple, direct application of LLM as an agent shows significant performance. Such methods are hindered by their slow inference speed, while most of the current research has not studied LLM distillation for this specific task. To address this, we first propose the normalized fluorescent probe to study the mechanism of the LLM's feature. Based on the observation found by our investigation, we propose Cooperative Market Making (CMM), a novel framework that decouples LLM features across three orthogonal dimensions: layer, task, and data. Various student models collaboratively learn simple LLM features along with different dimensions, with each model responsible for a distinct feature to achieve knowledge distillation. Furthermore, CMM introduces an Hájek-MoE to integrate the output of the student models by investigating the contribution of different models in a kernel function-generated common feature space. Extensive experimental results on four real-world market datasets demonstrate the superiority of CMM over the current distillation method and RL-based market-making strategies.

---

### A Provably-Correct and Robust Convex Model for Smooth Separable NMF

Authors: Junjun Pan, Valentin Leplat, Michael Ng, Nicolas Gillis
Published: 2025-11-10
Categories: math.NA, cs.LG, eess.SP, math.OC, stat.ML
arXiv: https://arxiv.org/abs/2511.07109v2

Nonnegative matrix factorization (NMF) is a linear dimensionality reduction technique for nonnegative data, with applications such as hyperspectral unmixing and topic modeling. NMF is a difficult problem in general (NP-hard), and its solutions are typically not unique. To address these two issues, additional constraints or assumptions are often used. In particular, separability assumes that the basis vectors in the NMF are equal to some columns of the input matrix. In that case, the problem is referred to as separable NMF (SNMF) and can be solved in polynomial-time with robustness guarantees, while identifying a unique solution. However, in real-world scenarios, due to noise or variability, multiple data points may lie near the basis vectors, which SNMF does not leverage. In this work, we rely on the smooth separability assumption, which assumes that each basis vector is close to multiple data points. We explore the properties of the corresponding problem, referred to as smooth SNMF (SSNMF), and examine how it relates to SNMF and orthogonal NMF. We then propose a convex model for SSNMF and show that it provably recovers the sought-after factors, even in the presence of noise. We finally adapt an existing fast gradient method to solve this convex model for SSNMF, and show that it compares favorably with state-of-the-art methods on both synthetic and hyperspectral datasets.

---

### MENTOR: A Metacognition-Driven Self-Evolution Framework for Uncovering and Mitigating Implicit Domain Risks in LLMs

Authors: Liang Shan, Kaicheng Shen, Wen Wu, Zhenyu Ying, Chaochao Lu, Yan Teng, Jingqi Huang, Qingshan Liu, Guangze Ye, Guoqing Wang, Jie Zhou, Liang He
Published: 2025-11-10
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2511.07107v4

Ensuring the safety of Large Language Models (LLMs) is critical for real-world deployment. However, current safety measures often fail to address implicit, domain-specific risks. To investigate this gap, we introduce a dataset of 3,000 annotated queries spanning education, finance, and management. Evaluations across 14 leading LLMs reveal a concerning vulnerability: an average jailbreak success rate of 57.8\%. In response, we propose MENTOR, a metacognition-driven self-evolution framework. MENTOR performs metacognitive self-assessment, using strategies such as perspective-taking and consequential reasoning to uncover latent model misalignments. MENTOR couples single-pass rule-guided inference for routine requests with a selectively invoked metacognitive evolution cycle that revises residual unsafe responses, distills successful corrections into a dynamic rule graph, and compiles validated rules into activation-level steering signals for future inference. Experiments demonstrate that MENTOR substantially reduces attack success rates across all tested domains and outperforms existing safety alignment methods. The code and dataset for MENTOR are available at: https://anonymous.4open.science/r/MENTOR-Evo.

---

### HENet++: Hybrid Encoding and Multi-task Learning for 3D Perception and End-to-end Autonomous Driving

Authors: Zhongyu Xia, Zhiwei Lin, Yongtao Wang, Ming-Hsuan Yang
Published: 2025-11-10
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.07106v2

Three-dimensional feature extraction and multi-task perception are fundamental components of modern autonomous driving systems. Although large image encoders, high-resolution inputs, and long temporal contexts can substantially improve representation quality and overall performance, jointly leveraging these strategies remains challenging due to prohibitive computational costs during both training and inference. Furthermore, different perception tasks often require distinct feature representations, making it difficult for a unified architecture to achieve end-to-end multi-task performance comparable to specialized single-task systems. To address these challenges, we propose HENet++, a unified framework for multi-task 3D perception and end-to-end autonomous driving that employs a hybrid image encoding strategy, using a large encoder for short-term frames and a lightweight encoder for long-term temporal context to strike a favorable balance between accuracy and efficiency. The framework jointly extracts dense background features and sparse foreground features, enabling task-specific representations that reduce cumulative errors and provide richer information for downstream prediction and planning modules. HENet++ is compatible with diverse 3D feature extraction pipelines and supports multi-modal inputs, including camera and radar data. Extensive experiments demonstrate state-of-the-art performance on the nuScenes multi-task 3D perception benchmark, achieving the lowest collision rate on the nuScenes planning benchmark and higher PDMS on the NAVSIM benchmark.

---

### A Theoretical Analysis of Detecting Large Model-Generated Time Series

Authors: Junji Hou, Junzhou Zhao, Shuo Zhang, Pinghui Wang
Published: 2025-11-10
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.07104v3

Motivated by the increasing risks of data misuse and fabrication, we investigate the problem of identifying synthetic time series generated by Time-Series Large Models (TSLMs) in this work. While there are extensive researches on detecting model generated text, we find that these existing methods are not applicable to time series data due to the fundamental modality difference, as time series usually have lower information density and smoother probability distributions than text data, which limit the discriminative power of token-based detectors. To address this issue, we examine the subtle distributional differences between real and model-generated time series and propose the contraction hypothesis, which states that model-generated time series, unlike real ones, exhibit progressively decreasing uncertainty under recursive forecasting. We formally prove this hypothesis under theoretical assumptions on model behavior and time series structure. Model-generated time series exhibit progressively concentrated distributions under recursive forecasting, leading to uncertainty contraction. We provide empirical validation of the hypothesis across diverse datasets. Building on this insight, we introduce the Uncertainty Contraction Estimator (UCE), a white-box detector that aggregates uncertainty metrics over successive prefixes to identify TSLM-generated time series. Extensive experiments on 32 datasets show that UCE consistently outperforms state-of-the-art baselines, offering a reliable and generalizable solution for detecting model-generated time series.

---

### GEWDiff: Geometric Enhanced Wavelet-based Diffusion Model for Hyperspectral Image Super-resolution

Authors: Sirui Wang, Jiang He, Natàlia Blasco Andreo, Xiao Xiang Zhu
Published: 2025-11-10
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.07103v1

Improving the quality of hyperspectral images (HSIs), such as through super-resolution, is a crucial research area. However, generative modeling for HSIs presents several challenges. Due to their high spectral dimensionality, HSIs are too memory-intensive for direct input into conventional diffusion models. Furthermore, general generative models lack an understanding of the topological and geometric structures of ground objects in remote sensing imagery. In addition, most diffusion models optimize loss functions at the noise level, leading to a non-intuitive convergence behavior and suboptimal generation quality for complex data. To address these challenges, we propose a Geometric Enhanced Wavelet-based Diffusion Model (GEWDiff), a novel framework for reconstructing hyperspectral images at 4-times super-resolution. A wavelet-based encoder-decoder is introduced that efficiently compresses HSIs into a latent space while preserving spectral-spatial information. To avoid distortion during generation, we incorporate a geometry-enhanced diffusion process that preserves the geometric features. Furthermore, a multi-level loss function was designed to guide the diffusion process, promoting stable convergence and improved reconstruction fidelity. Our model demonstrated state-of-the-art results across multiple dimensions, including fidelity, spectral accuracy, visual realism, and clarity.

---

### E2E-VGuard: Adversarial Prevention for Production LLM-based End-To-End Speech Synthesis

Authors: Zhisheng Zhang, Derui Wang, Yifan Mi, Zhiyong Wu, Jie Gao, Yuxin Cao, Kai Ye, Minhui Xue, Jie Hao
Published: 2025-11-10
Categories: cs.SD, cs.AI, cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2511.07099v1

Recent advancements in speech synthesis technology have enriched our daily lives, with high-quality and human-like audio widely adopted across real-world applications. However, malicious exploitation like voice-cloning fraud poses severe security risks. Existing defense techniques struggle to address the production large language model (LLM)-based speech synthesis. While previous studies have considered the protection for fine-tuning synthesizers, they assume manually annotated transcripts. Given the labor intensity of manual annotation, end-to-end (E2E) systems leveraging automatic speech recognition (ASR) to generate transcripts are becoming increasingly prevalent, e.g., voice cloning via commercial APIs. Therefore, this E2E speech synthesis also requires new security mechanisms. To tackle these challenges, we propose E2E-VGuard, a proactive defense framework for two emerging threats: (1) production LLM-based speech synthesis, and (2) the novel attack arising from ASR-driven E2E scenarios. Specifically, we employ the encoder ensemble with a feature extractor to protect timbre, while ASR-targeted adversarial examples disrupt pronunciation. Moreover, we incorporate the psychoacoustic model to ensure perturbative imperceptibility. For a comprehensive evaluation, we test 16 open-source synthesizers and 3 commercial APIs across Chinese and English datasets, confirming E2E-VGuard's effectiveness in timbre and pronunciation protection. Real-world deployment validation is also conducted. Our code and demo page are available at https://wxzyd123.github.io/e2e-vguard/.

---

### Boosting Fine-Grained Urban Flow Inference via Lightweight Architecture and Focalized Optimization

Authors: Yuanshao Zhu, Xiangyu Zhao, Zijian Zhang, Xuetao Wei, James Jianqiao Yu
Published: 2025-11-10
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.07098v1

Fine-grained urban flow inference is crucial for urban planning and intelligent transportation systems, enabling precise traffic management and resource allocation. However, the practical deployment of existing methods is hindered by two key challenges: the prohibitive computational cost of over-parameterized models and the suboptimal performance of conventional loss functions on the highly skewed distribution of urban flows. To address these challenges, we propose a unified solution that synergizes architectural efficiency with adaptive optimization. Specifically, we first introduce PLGF, a lightweight yet powerful architecture that employs a Progressive Local-Global Fusion strategy to effectively capture both fine-grained details and global contextual dependencies. Second, we propose DualFocal Loss, a novel function that integrates dual-space supervision with a difficulty-aware focusing mechanism, enabling the model to adaptively concentrate on hard-to-predict regions. Extensive experiments on 4 real-world scenarios validate the effectiveness and scalability of our method. Notably, while achieving state-of-the-art performance, PLGF reduces the model size by up to 97% compared to current high-performing methods. Furthermore, under comparable parameter budgets, our model yields an accuracy improvement of over 10% against strong baselines. The implementation is included in the https://github.com/Yasoz/PLGF.

---

### Agentic AI Sustainability Assessment for Supply Chain Document Insights

Authors: Diego Gosmar, Anna Chiara Pallotta, Giovanni Zenezini
Published: 2025-11-10
Categories: cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2511.07097v1

This paper presents a comprehensive sustainability assessment framework for document intelligence within supply chain operations, centered on agentic artificial intelligence (AI). We address the dual objective of improving automation efficiency while providing measurable environmental performance in document-intensive workflows. The research compares three scenarios: fully manual (human-only), AI-assisted (human-in-the-loop, HITL), and an advanced multi-agent agentic AI workflow leveraging parsers and verifiers. Empirical results show that AI-assisted HITL and agentic AI scenarios achieve reductions of up to 70-90% in energy consumption, 90-97% in carbon dioxide emissions, and 89-98% in water usage compared to manual processes. Notably, full agentic configurations, combining advanced reasoning (thinking mode) and multi-agent validation, achieve substantial sustainability gains over human-only approaches, even when resource usage increases slightly versus simpler AI-assisted solutions. The framework integrates performance, energy, and emission indicators into a unified ESG-oriented methodology for assessing and governing AI-enabled supply chain solutions. The paper includes a complete replicability use case demonstrating the methodology's application to real-world document extraction tasks.

---

### Data Complexity of Querying Description Logic Knowledge Bases under Cost-Based Semantics

Authors: Meghyn Bienvenu, Quentin Manière
Published: 2025-11-10
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.07095v2

In this paper, we study the data complexity of querying inconsistent weighted description logic (DL) knowledge bases under recently-introduced cost-based semantics. In a nutshell, the idea is to assign each interpretation a cost based upon the weights of the violated axioms and assertions, and certain and possible query answers are determined by considering all (resp. some) interpretations having optimal or bounded cost. Whereas the initial study of cost-based semantics focused on DLs between $\mathcal{EL}_\bot$ and $\mathcal{ALCO}$, we consider DLs that may contain inverse roles and role inclusions, thus covering prominent DL-Lite dialects. Our data complexity analysis goes significantly beyond existing results by sharpening several lower bounds and pinpointing the precise complexity of optimal-cost certain answer semantics (no non-trivial upper bound was known). Moreover, while all existing results show the intractability of cost-based semantics, our most challenging and surprising result establishes that if we consider $\text{DL-Lite}^\mathcal{H}_\mathsf{bool}$ ontologies and a fixed cost bound, certain answers for instance queries and possible answers for conjunctive queries can be computed using first-order rewriting and thus enjoy the lowest possible data complexity ($\mathsf{TC}_0$).

---

### Task-Adaptive Low-Dose CT Reconstruction

Authors: Necati Sefercioglu, Mehmet Ozan Unal, Metin Ertas, Isa Yildirim
Published: 2025-11-10
Categories: eess.IV, cs.CV
arXiv: https://arxiv.org/abs/2511.07094v1

Deep learning-based low-dose computed tomography reconstruction methods already achieve high performance on standard image quality metrics like peak signal-to-noise ratio and structural similarity index measure. Yet, they frequently fail to preserve the critical anatomical details needed for diagnostic tasks. This fundamental limitation hinders their clinical applicability despite their high metric scores. We propose a novel task-adaptive reconstruction framework that addresses this gap by incorporating a frozen pre-trained task network as a regularization term in the reconstruction loss function. Unlike existing joint-training approaches that simultaneously optimize both reconstruction and task networks, and risk diverging from satisfactory reconstructions, our method leverages a pre-trained task model to guide reconstruction training while still maintaining diagnostic quality. We validate our framework on a liver and liver tumor segmentation task. Our task-adaptive models achieve Dice scores up to 0.707, approaching the performance of full-dose scans (0.874), and substantially outperforming joint-training approaches (0.331) and traditional reconstruction methods (0.626). Critically, our framework can be integrated into any existing deep learning-based reconstruction model through simple loss function modification, enabling widespread adoption for task-adaptive optimization in clinical practice. Our codes are available at: https://github.com/itu-biai/task_adaptive_ct

---

### Sample-efficient quantum error mitigation via classical learning surrogates

Authors: Wei-You Liao, Ge Yan, Yujin Song, Tian-Ci Tian, Wei-Ming Zhu, De-Tao Jiang, Yuxuan Du, He-Liang Huang
Published: 2025-11-10
Categories: quant-ph, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.07092v1

The pursuit of practical quantum utility on near-term quantum processors is critically challenged by their inherent noise. Quantum error mitigation (QEM) techniques are leading solutions to improve computation fidelity with relatively low qubit-overhead, while full-scale quantum error correction remains a distant goal. However, QEM techniques incur substantial measurement overheads, especially when applied to families of quantum circuits parameterized by classical inputs. Focusing on zero-noise extrapolation (ZNE), a widely adopted QEM technique, here we devise the surrogate-enabled ZNE (S-ZNE), which leverages classical learning surrogates to perform ZNE entirely on the classical side. Unlike conventional ZNE, whose measurement cost scales linearly with the number of circuits, S-ZNE requires only constant measurement overhead for an entire family of quantum circuits, offering superior scalability. Theoretical analysis indicates that S-ZNE achieves accuracy comparable to conventional ZNE in many practical scenarios, and numerical experiments on up to 100-qubit ground-state energy and quantum metrology tasks confirm its effectiveness. Our approach provides a template that can be effectively extended to other quantum error mitigation protocols, opening a promising path toward scalable error mitigation.

---

### How Bias Binds: Measuring Hidden Associations for Bias Control in Text-to-Image Compositions

Authors: Jeng-Lin Li, Ming-Ching Chang, Wei-Chao Chen
Published: 2025-11-10
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.07091v1

Text-to-image generative models often exhibit bias related to sensitive attributes. However, current research tends to focus narrowly on single-object prompts with limited contextual diversity. In reality, each object or attribute within a prompt can contribute to bias. For example, the prompt "an assistant wearing a pink hat" may reflect female-inclined biases associated with a pink hat. The neglected joint effects of the semantic binding in the prompts cause significant failures in current debiasing approaches. This work initiates a preliminary investigation on how bias manifests under semantic binding, where contextual associations between objects and attributes influence generative outcomes. We demonstrate that the underlying bias distribution can be amplified based on these associations. Therefore, we introduce a bias adherence score that quantifies how specific object-attribute bindings activate bias. To delve deeper, we develop a training-free context-bias control framework to explore how token decoupling can facilitate the debiasing of semantic bindings. This framework achieves over 10% debiasing improvement in compositional generation tasks. Our analysis of bias scores across various attribute-object bindings and token decorrelation highlights a fundamental challenge: reducing bias without disrupting essential semantic relationships. These findings expose critical limitations in current debiasing approaches when applied to semantically bound contexts, underscoring the need to reassess prevailing bias mitigation strategies.

---

### Green AI: A systematic review and meta-analysis of its definitions, lifecycle models, hardware and measurement attempts

Authors: Marcel Rojahn, Marcus Grum
Published: 2025-11-10
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.07090v4

Across the Artificial Intelligence (AI) lifecycle - from hardware to development, deployment, and reuse - burdens span energy, carbon, water, and embodied impacts. Cloud provider tools improve transparency but remain heterogeneous and often omit water and value chain effects, limiting comparability and reproducibility. Addressing these multi dimensional burdens requires a lifecycle approach linking phase explicit mapping with system levers (hardware, placement, energy mix, cooling, scheduling) and calibrated measurement across facility, system, device, and workload levels. This article (i) establishes a unified, operational definition of Green AI distinct from Sustainable AI; (ii) formalizes a five phase lifecycle mapped to Life Cycle Assessment (LCA) stages, making energy, carbon, water, and embodied impacts first class; (iii) specifies governance via Plan Do Check Act (PDCA) cycles with decision gateways; (iv) systematizes hardware and system level strategies across the edge cloud continuum to reduce embodied burdens; and (v) defines a calibrated measurement framework combining estimator models with direct metering to enable reproducible, provider agnostic comparisons. Combining definition, lifecycle processes, hardware strategies, and calibrated measurement, this article offers actionable, evidence based guidance for researchers, practitioners, and policymakers.

---