# Research Papers — 2025-11 · bundle page 138 of 197

> Full-text markdown of papers #6851–6900 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/138
[← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/137.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-11/page/139.md)

### VocalBench-zh: Decomposing and Benchmarking the Speech Conversational Abilities in Mandarin Context

Authors: Heyang Liu, Ziyang Cheng, Yuhao Wang, Hongcheng Liu, Yiqi Li, Ronghua Wu, Qunshan Gu, Yanfeng Wang, Yu Wang
Published: 2025-11-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.08230v2

The development of multi-modal large language models (LLMs) leads to intelligent approaches capable of speech interactions. As one of the most widely spoken languages globally, Mandarin is supported by most models to enhance their applicability and reach. However, the scarcity of comprehensive speech-to-speech (S2S) benchmarks in Mandarin contexts impedes systematic evaluation for developers and hinders fair model comparison for users. In this work, we propose VocalBench-zh, an ability-level divided evaluation suite adapted to Mandarin context consisting of 10 well-crafted subsets and over 10K high-quality instances, covering 12 user-oriented characters. The evaluation experiment on 14 mainstream models reveals the common challenges for current routes, and highlights the need for new insights into next-generation speech interactive systems. The evaluation codes and datasets will be available at https://github.com/SJTU-OmniAgent/VocalBench-zh.

---

### Towards Non-Stationary Time Series Forecasting with Temporal Stabilization and Frequency Differencing

Authors: Junkai Lu, Peng Chen, Chenjuan Guo, Yang Shu, Meng Wang, Bin Yang
Published: 2025-11-11
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.08229v6

Time series forecasting is critical for decision-making across dynamic domains such as energy, finance, transportation, and cloud computing. However, real-world time series often exhibit non-stationarity, including temporal distribution shifts and spectral variability, which pose significant challenges for long-term time series forecasting. In this paper, we propose DTAF, a dual-branch framework that addresses non-stationarity in both the temporal and frequency domains. For the temporal domain, the Temporal Stabilizing Fusion (TFS) module employs a non-stationary mix of experts (MOE) filter to disentangle and suppress temporal non-stationary patterns while preserving long-term dependencies. For the frequency domain, the Frequency Wave Modeling (FWM) module applies frequency differencing to dynamically highlight components with significant spectral shifts. By fusing the complementary outputs of TFS and FWM, DTAF generates robust forecasts that adapt to both temporal and frequency domain non-stationarity. Extensive experiments on real-world benchmarks demonstrate that DTAF outperforms state-of-the-art baselines, yielding significant improvements in forecasting accuracy under non-stationary conditions. All codes are available at https://github.com/decisionintelligence/DTAF.

---

### Are Current Continual Learning Methods Truly Agnostic? Introducing OPRE, a Step Toward Agnostic Continual Learning

Authors: Raphaël Bayle, Martial Mermillod, Robert M. French
Published: 2025-11-11
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2511.08226v2

In order to achieve Continual Learning (CL), the problem of catastrophic forgetting, one that has plagued neural networks since their inception, must be overcome. The evaluation of continual learning methods relies on splitting a known homogeneous dataset and learning the associated tasks one after the other. We argue that most CL methods introduce a priori information about the data to come and cannot be considered agnostic. We exemplify this point with the case of methods relying on pretrained feature extractors, which are still used in CL. After showing that pretrained feature extractors imply a loss of generality with respect to the data that can be learned by the model, we then discuss other kinds of a priori information introduced in other CL methods. We then present the Online Patch Redundancy Eliminator (OPRE), an online dataset-compression algorithm that discards information through two explicit, input-space criteria. With a classifier that was randomly initialized at test time, OPRE's performance matches reported state-of-the-art online continual-learning methods on CIFAR 10 and CIFAR-100 without any pretrained feature extractor, and outperforms GDumb at an identical memory budget-while making only minimal and interpretable assumptions about the data to come. We frame these results as an empirical, information-theoretic perspective on continual learning.

---

### Benchmarking Educational LLMs with Analytics: A Case Study on Gender Bias in Feedback

Authors: Yishan Du, Conrad Borchers, Mutlu Cukurova
Published: 2025-11-11
Categories: cs.CL, cs.AI, cs.CY, cs.HC
arXiv: https://arxiv.org/abs/2511.08225v2

As teachers increasingly turn to GenAI in their educational practice, we need robust methods to benchmark large language models (LLMs) for pedagogical purposes. This article presents an embedding-based benchmarking framework to detect bias in LLMs in the context of formative feedback. Using 600 authentic student essays from the AES 2.0 corpus, we constructed controlled counterfactuals along two dimensions: (i) implicit cues via lexicon-based swaps of gendered terms within essays, and (ii) explicit cues via gendered author background in the prompt. We investigated six representative LLMs (i.e. GPT-5 mini, GPT-4o mini, DeepSeek-R1, DeepSeek-R1-Qwen, Gemini 2.5 Pro, Llama-3-8B). We first quantified the response divergence with cosine and Euclidean distances over sentence embeddings, then assessed significance via permutation tests, and finally, visualised structure using dimensionality reduction. In all models, implicit manipulations reliably induced larger semantic shifts for male-female counterfactuals than for female-male. Only the GPT and Llama models showed sensitivity to explicit gender cues. These findings show that even state-of-the-art LLMs exhibit asymmetric semantic responses to gender substitutions, suggesting persistent gender biases in feedback they provide learners. Qualitative analyses further revealed consistent linguistic differences (e.g., more autonomy-supportive feedback under male cues vs. more controlling feedback under female cues). We discuss implications for fairness auditing of pedagogical GenAI, propose reporting standards for counterfactual evaluation in learning analytics, and outline practical guidance for prompt design and deployment to safeguard equitable feedback.

---

### 2D Representation for Unguided Single-View 3D Super-Resolution in Real-Time

Authors: Ignasi Mas, Ivan Huerta, Ramon Morros, Javier Ruiz-Hidalgo
Published: 2025-11-11
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.08224v1

We introduce 2Dto3D-SR, a versatile framework for real-time single-view 3D super-resolution that eliminates the need for high-resolution RGB guidance. Our framework encodes 3D data from a single viewpoint into a structured 2D representation, enabling the direct application of existing 2D image super-resolution architectures. We utilize the Projected Normalized Coordinate Code (PNCC) to represent 3D geometry from a visible surface as a regular image, thereby circumventing the complexities of 3D point-based or RGB-guided methods. This design supports lightweight and fast models adaptable to various deployment environments. We evaluate 2Dto3D-SR with two implementations: one using Swin Transformers for high accuracy, and another using Vision Mamba for high efficiency. Experiments show the Swin Transformer model achieves state-of-the-art accuracy on standard benchmarks, while the Vision Mamba model delivers competitive results at real-time speeds. This establishes our geometry-guided pipeline as a surprisingly simple yet viable and practical solution for real-world scenarios, especially where high-resolution RGB data is inaccessible.

---

### High-Performance Variance-Covariance Matrix Construction Using an Uncentered Gram Formulation

Authors: Felix Reichel
Published: 2025-11-11
Categories: stat.CO, cs.LG, math.NA
arXiv: https://arxiv.org/abs/2511.08223v2

Reichel (2025) defined the bariance as a pairwise-difference measure that can be rewritten in linear time using only scalar sums. We extend this idea to the covariance matrix by showing that the standard matrix expression involving the uncentered Gram matrix and a correction term is algebraically identical to the pairwise-difference definition while avoiding explicit centering. The computation then reduces to one outer product of dimension p-by-p and a single subtraction. Benchmarks in Python show clear runtime gains, especially when BLAS optimizations are absent. Optionally faster Gram-matrix routines such as RXTX (Rybin et al., 2025) further reduce overall cost.

---

### Emulating Radiative Transfer in Astrophysical Environments

Authors: Rune Rost, Lorenzo Branca, Tobias Buck
Published: 2025-11-11
Categories: astro-ph.IM, astro-ph.GA, cs.LG
arXiv: https://arxiv.org/abs/2511.08219v1

Radiative transfer is a fundamental process in astrophysics, essential for both interpreting observations and modeling thermal and dynamical feedback in simulations via ionizing radiation and photon pressure. However, numerically solving the underlying radiative transfer equation is computationally intensive due to the complex interaction of light with matter and the disparity between the speed of light and the typical gas velocities in astrophysical environments, making it particularly expensive to include the effects of on-the-fly radiation in hydrodynamic simulations. This motivates the development of surrogate models that can significantly accelerate radiative transfer calculations while preserving high accuracy. We present a surrogate model based on a Fourier Neural Operator architecture combined with U-Nets. Our model approximates three-dimensional, monochromatic radiative transfer in time-dependent regimes, in absorption-emission approximation, achieving speedups of more than 2 orders of magnitude while maintaining an average relative error below 3%, demonstrating our approach's potential to be integrated into state-of-the-art hydrodynamic simulations.

---

### MADD: Multi-Agent Drug Discovery Orchestra

Authors: Gleb V. Solovev, Alina B. Zhidkovskaya, Anastasia Orlova, Nina Gubina, Anastasia Vepreva, Rodion Golovinskii, Ilya Tonkii, Ivan Dubrovsky, Ivan Gurev, Dmitry Gilemkhanov, Denis Chistiakov, Timur A. Aliev et al.
Published: 2025-11-11
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.08217v1

Hit identification is a central challenge in early drug discovery, traditionally requiring substantial experimental resources. Recent advances in artificial intelligence, particularly large language models (LLMs), have enabled virtual screening methods that reduce costs and improve efficiency. However, the growing complexity of these tools has limited their accessibility to wet-lab researchers. Multi-agent systems offer a promising solution by combining the interpretability of LLMs with the precision of specialized models and tools. In this work, we present MADD, a multi-agent system that builds and executes customized hit identification pipelines from natural language queries. MADD employs four coordinated agents to handle key subtasks in de novo compound generation and screening. We evaluate MADD across seven drug discovery cases and demonstrate its superior performance compared to existing LLM-based solutions. Using MADD, we pioneer the application of AI-first drug design to five biological targets and release the identified hit molecules. Finally, we introduce a new benchmark of query-molecule pairs and docking scores for over three million compounds to contribute to the agentic future of drug design.

---

### Evaluating Gemini LLM in Food Image-Based Recipe and Nutrition Description with EfficientNet-B4 Visual Backbone

Authors: Rizal Khoirul Anam
Published: 2025-11-11
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2511.08215v1

The proliferation of digital food applications necessitates robust methods for automated nutritional analysis and culinary guidance. This paper presents a comprehensive comparative evaluation of a decoupled, multimodal pipeline for food recognition. We evaluate a system integrating a specialized visual backbone (EfficientNet-B4) with a powerful generative large language model (Google's Gemini LLM). The core objective is to evaluate the trade-offs between visual classification accuracy, model efficiency, and the quality of generative output (nutritional data and recipes). We benchmark this pipeline against alternative vision backbones (VGG-16, ResNet-50, YOLOv8) and a lightweight LLM (Gemma). We introduce a formalization for "Semantic Error Propagation" (SEP) to analyze how classification inaccuracies from the visual module cascade into the generative output. Our analysis is grounded in a new Custom Chinese Food Dataset (CCFD) developed to address cultural bias in public datasets. Experimental results demonstrate that while EfficientNet-B4 (89.0\% Top-1 Acc.) provides the best balance of accuracy and efficiency, and Gemini (9.2/10 Factual Accuracy) provides superior generative quality, the system's overall utility is fundamentally bottlenecked by the visual front-end's perceptive accuracy. We conduct a detailed per-class analysis, identifying high semantic similarity as the most critical failure mode.

---

### FedPoP: Federated Learning Meets Proof of Participation

Authors: Devriş İşler, Elina van Kempen, Seoyeon Hwang, Nikolaos Laoutaris
Published: 2025-11-11
Categories: cs.CR, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.08207v1

Federated learning (FL) offers privacy preserving, distributed machine learning, allowing clients to contribute to a global model without revealing their local data. As models increasingly serve as monetizable digital assets, the ability to prove participation in their training becomes essential for establishing ownership. In this paper, we address this emerging need by introducing FedPoP, a novel FL framework that allows nonlinkable proof of participation while preserving client anonymity and privacy without requiring either extensive computations or a public ledger. FedPoP is designed to seamlessly integrate with existing secure aggregation protocols to ensure compatibility with real-world FL deployments. We provide a proof of concept implementation and an empirical evaluation under realistic client dropouts. In our prototype, FedPoP introduces 0.97 seconds of per-round overhead atop securely aggregated FL and enables a client to prove its participation/contribution to a model held by a third party in 0.0612 seconds. These results indicate FedPoP is practical for real-world deployments that require auditable participation without sacrificing privacy.

---

### EHRStruct: A Comprehensive Benchmark Framework for Evaluating Large Language Models on Structured Electronic Health Record Tasks

Authors: Xiao Yang, Xuejiao Zhao, Zhiqi Shen
Published: 2025-11-11
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.08206v4

Structured Electronic Health Record (EHR) data stores patient information in relational tables and plays a central role in clinical decision-making. Recent advances have explored the use of large language models (LLMs) to process such data, showing promise across various clinical tasks. However, the absence of standardized evaluation frameworks and clearly defined tasks makes it difficult to systematically assess and compare LLM performance on structured EHR data. To address these evaluation challenges, we introduce EHRStruct, a benchmark specifically designed to evaluate LLMs on structured EHR tasks. EHRStruct defines 11 representative tasks spanning diverse clinical needs and includes 2,200 task-specific evaluation samples derived from two widely used EHR datasets. We use EHRStruct to evaluate 20 advanced and representative LLMs, covering both general and medical models. We further analyze key factors influencing model performance, including input formats, few-shot generalisation, and finetuning strategies, and compare results with 11 state-of-the-art LLM-based enhancement methods for structured data reasoning. Our results indicate that many structured EHR tasks place high demands on the understanding and reasoning capabilities of LLMs. In response, we propose EHRMaster, a code-augmented method that achieves state-of-the-art performance and offers practical insights to guide future research.

---

### From Classical to Hybrid: A Practical Framework for Quantum-Enhanced Learning

Authors: Silvie Illésová, Tomáš Bezděk, Vojtěch Novák, Ivan Zelinka, Stefano Cacciatore, Martin Beseda
Published: 2025-11-11
Categories: quant-ph, cs.LG
arXiv: https://arxiv.org/abs/2511.08205v1

This work addresses the challenge of enabling practitioners without quantum expertise to transition from classical to hybrid quantum-classical machine learning workflows. We propose a three-stage framework: starting with a classical self-training model, then introducing a minimal hybrid quantum variant, and finally applying diagnostic feedback via QMetric to refine the hybrid architecture. In experiments on the Iris dataset, the refined hybrid model improved accuracy from 0.31 in the classical approach to 0.87 in the quantum approach. These results suggest that even modest quantum components, when guided by proper diagnostics, can enhance class separation and representation capacity in hybrid learning, offering a practical pathway for classical machine learning practitioners to leverage quantum-enhanced methods.

---

### Encoder Fine-tuning with Stochastic Sampling Outperforms Open-weight GPT in Astronomy Knowledge Extraction

Authors: Shivam Rawat, Lucie Flek, Akbar Karimi
Published: 2025-11-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.08204v1

Scientific literature in astronomy is rapidly expanding, making it increasingly important to automate the extraction of key entities and contextual information from research papers. In this paper, we present an encoder-based system for extracting knowledge from astronomy articles. Our objective is to develop models capable of classifying telescope references, detecting auxiliary semantic attributes, and recognizing instrument mentions from textual content. To this end, we implement a multi-task transformer-based system built upon the SciBERT model and fine-tuned for astronomy corpora classification. To carry out the fine-tuning, we stochastically sample segments from the training data and use majority voting over the test segments at inference time. Our system, despite its simplicity and low-cost implementation, significantly outperforms the open-weight GPT baseline.

---

### Twist and Compute: The Cost of Pose in 3D Generative Diffusion

Authors: Kyle Fogarty, Jack Foster, Boqiao Zhang, Jing Yang, Cengiz Öztireli
Published: 2025-11-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.08203v1

Despite their impressive results, large-scale image-to-3D generative models remain opaque in their inductive biases. We identify a significant limitation in image-conditioned 3D generative models: a strong canonical view bias. Through controlled experiments using simple 2D rotations, we show that the state-of-the-art Hunyuan3D 2.0 model can struggle to generalize across viewpoints, with performance degrading under rotated inputs. We show that this failure can be mitigated by a lightweight CNN that detects and corrects input orientation, restoring model performance without modifying the generative backbone. Our findings raise an important open question: Is scale enough, or should we pursue modular, symmetry-aware designs?

---

### Do Syntactic Categories Help in Developmentally Motivated Curriculum Learning for Language Models?

Authors: Arzu Burcu Güven, Anna Rogers, Rob van der Goot
Published: 2025-11-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.08199v1

We examine the syntactic properties of BabyLM corpus, and age-groups within CHILDES. While we find that CHILDES does not exhibit strong syntactic differentiation by age, we show that the syntactic knowledge about the training data can be helpful in interpreting model performance on linguistic tasks. For curriculum learning, we explore developmental and several alternative cognitively inspired curriculum approaches. We find that some curricula help with reading tasks, but the main performance improvement come from using the subset of syntactically categorizable data, rather than the full noisy corpus.

---

### Proof Minimization in Neural Network Verification

Authors: Omri Isac, Idan Refaeli, Haoze Wu, Clark Barrett, Guy Katz
Published: 2025-11-11
Categories: cs.LO, cs.LG
arXiv: https://arxiv.org/abs/2511.08198v1

The widespread adoption of deep neural networks (DNNs) requires efficient techniques for verifying their safety. DNN verifiers are complex tools, which might contain bugs that could compromise their soundness and undermine the reliability of the verification process. This concern can be mitigated using proofs: artifacts that are checkable by an external and reliable proof checker, and which attest to the correctness of the verification process. However, such proofs tend to be extremely large, limiting their use in many scenarios. In this work, we address this problem by minimizing proofs of unsatisfiability produced by DNN verifiers. We present algorithms that remove facts which were learned during the verification process, but which are unnecessary for the proof itself. Conceptually, our method analyzes the dependencies among facts used to deduce UNSAT, and removes facts that did not contribute. We then further minimize the proof by eliminating remaining unnecessary dependencies, using two alternative procedures. We implemented our algorithms on top of a proof producing DNN verifier, and evaluated them across several benchmarks. Our results show that our best-performing algorithm reduces proof size by 37%-82% and proof checking time by 30%-88%, while introducing a runtime overhead of 7%-20% to the verification process itself.

---

### UCDSC: Open Set UnCertainty aware Deep Simplex Classifier for Medical Image Datasets

Authors: Arnav Aditya, Nitin Kumar, Saurabh Shigwan
Published: 2025-11-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.08196v1

Driven by advancements in deep learning, computer-aided diagnoses have made remarkable progress. However, outside controlled laboratory settings, algorithms may encounter several challenges. In the medical domain, these difficulties often stem from limited data availability due to ethical and legal restrictions, as well as the high cost and time required for expert annotations-especially in the face of emerging or rare diseases. In this context, open-set recognition plays a vital role by identifying whether a sample belongs to one of the known classes seen during training or should be rejected as an unknown. Recent studies have shown that features learned in the later stages of deep neural networks are observed to cluster around their class means, which themselves are arranged as individual vertices of a regular simplex (32). The proposed method introduces a loss function designed to reject samples of unknown classes effectively by penalizing open space regions using auxiliary datasets. This approach achieves significant performance gain across four MedMNIST datasets-BloodMNIST, OCTMNIST, DermaMNIST, TissueMNIST and a publicly available skin dataset (29) outperforming state-of-the-art techniques.

---

### UI2Code^N: UI-to-Code Generation as Interactive Visual Optimization

Authors: Zhen Yang, Wenyi Hong, Mingde Xu, Xinyue Fan, Weihan Wang, Jiale Cheng, Xiaotao Gu, Jie Tang
Published: 2025-11-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.08195v4

UI-to-code aims to translate UI screenshots into executable front-end code. Despite progress with vision-language models (VLMs), most existing methods formulate UI-to-code as a single-pass generation, which mismatches real-world UI development that is inherently iterative and feedback-driven. We reformulate UI-to-code as an interactive visual optimization problem, where code generation is embedded in a closed-loop process of execution, visual inspection, and iterative refinement driven by rendered visual feedback. To address the non-differentiability of visual objectives and the noise of absolute visual evaluators, we propose Relative Visual Policy Optimization (RVPO), a preference-based reinforcement learning method that optimizes relative visual rankings among rendered candidates under execution feedback. We instantiate this paradigm in UI2Code^N, an open-source 9B model trained via continual pre-training, supervised fine-tuning, and reinforcement learning. Experiments demonstrate state-of-the-art performance on UI drafting, UI polishing, and UI editing benchmarks, even outperforming larger models, with performance consistently improving through iterative visual optimization. Our code and models are available at https://github.com/zai-org/UI2Code_N.

---

### Towards Provably Unlearnable Examples via Bayes Error Optimisation

Authors: Ruihan Zhang, Jun Sun, Ee-Peng Lim, Peixin Zhang
Published: 2025-11-11
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.08191v1

The recent success of machine learning models, especially large-scale classifiers and language models, relies heavily on training with massive data. These data are often collected from online sources. This raises serious concerns about the protection of user data, as individuals may not have given consent for their data to be used in training. To address this concern, recent studies introduce the concept of unlearnable examples, i.e., data instances that appear natural but are intentionally altered to prevent models from effectively learning from them. While existing methods demonstrate empirical effectiveness, they typically rely on heuristic trials and lack formal guarantees. Besides, when unlearnable examples are mixed with clean data, as is often the case in practice, their unlearnability disappears. In this work, we propose a novel approach to constructing unlearnable examples by systematically maximising the Bayes error, a measurement of irreducible classification error. We develop an optimisation-based approach and provide an efficient solution using projected gradient ascent. Our method provably increases the Bayes error and remains effective when the unlearning examples are mixed with clean samples. Experimental results across multiple datasets and model architectures are consistent with our theoretical analysis and show that our approach can restrict data learnability, effectively in practice.

---

### Pixel-level Quality Assessment for Oriented Object Detection

Authors: Yunhui Zhu, Buliao Huang
Published: 2025-11-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.08186v1

Modern oriented object detectors typically predict a set of bounding boxes and select the top-ranked ones based on estimated localization quality. Achieving high detection performance requires that the estimated quality closely aligns with the actual localization accuracy. To this end, existing approaches predict the Intersection over Union (IoU) between the predicted and ground-truth (GT) boxes as a proxy for localization quality. However, box-level IoU prediction suffers from a structural coupling issue: since the predicted box is derived from the detector's internal estimation of the GT box, the predicted IoU--based on their similarity--can be overestimated for poorly localized boxes. To overcome this limitation, we propose a novel Pixel-level Quality Assessment (PQA) framework, which replaces box-level IoU prediction with the integration of pixel-level spatial consistency. PQA measures the alignment between each pixel's relative position to the predicted box and its corresponding position to the GT box. By operating at the pixel level, PQA avoids directly comparing the predicted box with the estimated GT box, thereby eliminating the inherent similarity bias in box-level IoU prediction. Furthermore, we introduce a new integration metric that aggregates pixel-level spatial consistency into a unified quality score, yielding a more accurate approximation of the actual localization quality. Extensive experiments on HRSC2016 and DOTA demonstrate that PQA can be seamlessly integrated into various oriented object detectors, consistently improving performance (e.g., +5.96% AP$_{50:95}$ on Rotated RetinaNet and +2.32% on STD).

---

### Improving Long-Range Interactions in Graph Neural Simulators via Hamiltonian Dynamics

Authors: Tai Hoang, Alessandro Trenta, Alessio Gravina, Niklas Freymuth, Philipp Becker, Davide Bacciu, Gerhard Neumann
Published: 2025-11-11
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.08185v2

Learning to simulate complex physical systems from data has emerged as a promising way to overcome the limitations of traditional numerical solvers, which often require prohibitive computational costs for high-fidelity solutions. Recent Graph Neural Simulators (GNSs) accelerate simulations by learning dynamics on graph-structured data, yet often struggle to capture long-range interactions and suffer from error accumulation under autoregressive rollouts. To address these challenges, we propose Information-preserving Graph Neural Simulators (IGNS), a graph-based neural simulator built on the principles of Hamiltonian dynamics. This structure guarantees preservation of information across the graph, while extending to port-Hamiltonian systems allows the model to capture a broader class of dynamics, including non-conservative effects. IGNS further incorporates a warmup phase to initialize global context, geometric encoding to handle irregular meshes, and a multi-step training objective that facilitates PDE matching, where the trajectory produced by integrating the port-Hamiltonian core aligns with the ground-truth trajectory, thereby reducing rollout error. To evaluate these properties systematically, we introduce new benchmarks that target long-range dependencies and challenging external forcing scenarios. Across all tasks, IGNS consistently outperforms state-of-the-art GNSs, achieving higher accuracy and stability under challenging and complex dynamical systems. Our project page: https://thobotics.github.io/neural_pde_matching.

---

### MARC: Multimodal and Multi-Task Agentic Retrieval-Augmented Generation for Cold-Start Recommender System

Authors: Seung Hwan Cho, Yujin Yang, Danik Baeck, Minjoo Kim, Young-Min Kim, Heejung Lee, Sangjin Park
Published: 2025-11-11
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2511.08181v2

Recommender systems (RS) are currently being studied to mitigate limitations during cold-start conditions by leveraging modality information or introducing Agent concepts based on the exceptional reasoning capabilities of Large Language Models (LLMs). Meanwhile, food and beverage recommender systems have traditionally used knowledge graph and ontology concepts due to the domain's unique data attributes and relationship characteristics. On this background, we propose MARC, a multimodal and multi-task cocktail recommender system based on Agentic Retrieval-Augmented Generation (RAG) utilizing graph database under cold-start conditions. The proposed system generates high-quality, contextually appropriate answers through two core processes: a task recognition router and a reflection process. The graph database was constructed by processing cocktail data from Kaggle, and its effectiveness was evaluated using 200 manually crafted questions. The evaluation used both LLM-as-a-judge and human evaluation to demonstrate that answers generated via the graph database outperformed those from a simple vector database in terms of quality. The code is available at https://github.com/diddbwls/cocktail_rec_agentrag

---

### Simulation-Based Fitting of Intractable Models via Sequential Sampling and Local Smoothing

Authors: Guido Masarotto
Published: 2025-11-11
Categories: stat.ME, stat.CO, stat.ML
arXiv: https://arxiv.org/abs/2511.08180v1

This paper presents a comprehensive algorithm for fitting generative models whose likelihood, moments, and other quantities typically used for inference are not analytically or numerically tractable. The proposed method aims to provide a general solution that requires only limited prior information on the model parameters. The algorithm combines a global search phase, aimed at identifying the region of the solution, with a local search phase that mimics a trust region version of the Fisher scoring algorithm for computing a quasi-likelihood estimator. Comparisons with alternative methods demonstrate the strong performance of the proposed approach. An R package implementing the algorithm is available on CRAN.

---

### WarpGAN: Warping-Guided 3D GAN Inversion with Style-Based Novel View Inpainting

Authors: Kaitao Huang, Yan Yan, Jing-Hao Xue, Hanzi Wang
Published: 2025-11-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.08178v1

3D GAN inversion projects a single image into the latent space of a pre-trained 3D GAN to achieve single-shot novel view synthesis, which requires visible regions with high fidelity and occluded regions with realism and multi-view consistency. However, existing methods focus on the reconstruction of visible regions, while the generation of occluded regions relies only on the generative prior of 3D GAN. As a result, the generated occluded regions often exhibit poor quality due to the information loss caused by the low bit-rate latent code. To address this, we introduce the warping-and-inpainting strategy to incorporate image inpainting into 3D GAN inversion and propose a novel 3D GAN inversion method, WarpGAN. Specifically, we first employ a 3D GAN inversion encoder to project the single-view image into a latent code that serves as the input to 3D GAN. Then, we perform warping to a novel view using the depth map generated by 3D GAN. Finally, we develop a novel SVINet, which leverages the symmetry prior and multi-view image correspondence w.r.t. the same latent code to perform inpainting of occluded regions in the warped image. Quantitative and qualitative experiments demonstrate that our method consistently outperforms several state-of-the-art methods.

---

### Deep (Predictive) Discounted Counterfactual Regret Minimization

Authors: Hang Xu, Kai Li, Haobo Fu, Qiang Fu, Junliang Xing, Jian Cheng
Published: 2025-11-11
Categories: cs.LG, cs.AI, cs.GT
arXiv: https://arxiv.org/abs/2511.08174v1

Counterfactual regret minimization (CFR) is a family of algorithms for effectively solving imperfect-information games. To enhance CFR's applicability in large games, researchers use neural networks to approximate its behavior. However, existing methods are mainly based on vanilla CFR and struggle to effectively integrate more advanced CFR variants. In this work, we propose an efficient model-free neural CFR algorithm, overcoming the limitations of existing methods in approximating advanced CFR variants. At each iteration, it collects variance-reduced sampled advantages based on a value network, fits cumulative advantages by bootstrapping, and applies discounting and clipping operations to simulate the update mechanisms of advanced CFR variants. Experimental results show that, compared with model-free neural algorithms, it exhibits faster convergence in typical imperfect-information games and demonstrates stronger adversarial performance in a large poker game.

---

### VLMDiff: Leveraging Vision-Language Models for Multi-Class Anomaly Detection with Diffusion

Authors: Samet Hicsonmez, Abd El Rahman Shabayek, Djamila Aouada
Published: 2025-11-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.08173v1

Detecting visual anomalies in diverse, multi-class real-world images is a significant challenge. We introduce \ours, a novel unsupervised multi-class visual anomaly detection framework. It integrates a Latent Diffusion Model (LDM) with a Vision-Language Model (VLM) for enhanced anomaly localization and detection. Specifically, a pre-trained VLM with a simple prompt extracts detailed image descriptions, serving as additional conditioning for LDM training. Current diffusion-based methods rely on synthetic noise generation, limiting their generalization and requiring per-class model training, which hinders scalability. \ours, however, leverages VLMs to obtain normal captions without manual annotations or additional training. These descriptions condition the diffusion model, learning a robust normal image feature representation for multi-class anomaly detection. Our method achieves competitive performance, improving the pixel-level Per-Region-Overlap (PRO) metric by up to 25 points on the Real-IAD dataset and 8 points on the COCO-AD dataset, outperforming state-of-the-art diffusion-based approaches. Code is available at https://github.com/giddyyupp/VLMDiff.

---

### An Efficient Training Pipeline for Reasoning Graphical User Interface Agents

Authors: Georgios Pantazopoulos, Eda B. Özyiğit
Published: 2025-11-11
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.08172v3

Visual grounding is the task of localising image regions from natural language queries and is critical for reasoning capable Graphical User Interface agents. Many existing methods rely on massive, noisy synthetic datasets. This work introduces an efficient training pipeline that combines model-based data filtering with parameter-efficient fine-tuning. From 4.8M synthetic examples, 12K clean and diverse instances are curated by first identifying challenging cases, removing misaligned and then selecting a diverse set of multimodal instances. On this data, a 3B-parameter Vision-Language Model is trained under three regimes: supervised fine-tuning, chain-of-thought-augmented fine-tuning, and reinforcement learning via Group Relative Policy Optimization. Models trained with the filtered data and lightweight training strategies match or surpass larger baselines on benchmarks such as ScreenSpot, Multimodal-Mind2Web, and AndroidControl. These results demonstrate that principled data curation and robust adaptation can rival large-scale training, enabling compact yet capable multimodal reasoning agents.

---

### Distributed Zero-Shot Learning for Visual Recognition

Authors: Zhi Chen, Yadan Luo, Zi Huang, Jingjing Li, Sen Wang, Xin Yu
Published: 2025-11-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.08170v1

In this paper, we propose a Distributed Zero-Shot Learning (DistZSL) framework that can fully exploit decentralized data to learn an effective model for unseen classes. Considering the data heterogeneity issues across distributed nodes, we introduce two key components to ensure the effective learning of DistZSL: a cross-node attribute regularizer and a global attribute-to-visual consensus. Our proposed cross-node attribute regularizer enforces the distances between attribute features to be similar across different nodes. In this manner, the overall attribute feature space would be stable during learning, and thus facilitate the establishment of visual-to-attribute(V2A) relationships. Then, we introduce the global attribute-tovisual consensus to mitigate biased V2A mappings learned from individual nodes. Specifically, we enforce the bilateral mapping between the attribute and visual feature distributions to be consistent across different nodes. Thus, the learned consistent V2A mapping can significantly enhance zero-shot learning across different nodes. Extensive experiments demonstrate that DistZSL achieves superior performance to the state-of-the-art in learning from distributed data.

---

### KPLM-STA: Physically-Accurate Shadow Synthesis for Human Relighting via Keypoint-Based Light Modeling

Authors: Xinhui Yin, Qifei Li, Yilin Guo, Hongxia Xie, Xiaoli Zhang
Published: 2025-11-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.08169v1

Image composition aims to seamlessly integrate a foreground object into a background, where generating realistic and geometrically accurate shadows remains a persistent challenge. While recent diffusion-based methods have outperformed GAN-based approaches, existing techniques, such as the diffusion-based relighting framework IC-Light, still fall short in producing shadows with both high appearance realism and geometric precision, especially in composite images. To address these limitations, we propose a novel shadow generation framework based on a Keypoints Linear Model (KPLM) and a Shadow Triangle Algorithm (STA). KPLM models articulated human bodies using nine keypoints and one bounding block, enabling physically plausible shadow projection and dynamic shading across joints, thereby enhancing visual realism. STA further improves geometric accuracy by computing shadow angles, lengths, and spatial positions through explicit geometric formulations. Extensive experiments demonstrate that our method achieves state-of-the-art performance on shadow realism benchmarks, particularly under complex human poses, and generalizes effectively to multi-directional relighting scenarios such as those supported by IC-Light.

---

### oboro: Text-to-Image Synthesis on Limited Data using Flow-based Diffusion Transformer with MMH Attention

Authors: Ryusuke Mizutani, Kazuaki Matano, Tsugumi Kadowaki, Haruki Tenya, Layris, nuigurumi, Koki Hashimoto, Yu Tanaka
Published: 2025-11-11
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.08168v1

This project was conducted as a 2nd-term adopted project of the "Post-5G Information and Communication System Infrastructure Enhancement R&D Project Development of Competitive Generative AI Foundation Models (GENIAC)," a business of the Ministry of Economy, Trade and Industry (METI) and the New Energy and Industrial Technology Development Organization (NEDO). To address challenges such as labor shortages in Japan's anime production industry, this project aims to develop an image generation model from scratch. This report details the technical specifications of the developed image generation model, "oboro:." We have developed "oboro:," a new image generation model built from scratch, using only copyright-cleared images for training. A key characteristic is its architecture, designed to generate high-quality images even from limited datasets. The foundation model weights and inference code are publicly available alongside this report. This project marks the first release of an open-source, commercially-oriented image generation AI fully developed in Japan. AiHUB originated from the OSS community; by maintaining transparency in our development process, we aim to contribute to Japan's AI researcher and engineer community and promote the domestic AI development ecosystem.

---

### Multi-Granularity Mutual Refinement Network for Zero-Shot Learning

Authors: Ning Wang, Long Yu, Cong Hua, Guangming Zhu, Lin Mei, Syed Afaq Ali Shah, Mohammed Bennamoun, Liang Zhang
Published: 2025-11-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.08163v1

Zero-shot learning (ZSL) aims to recognize unseen classes with zero samples by transferring semantic knowledge from seen classes. Current approaches typically correlate global visual features with semantic information (i.e., attributes) or align local visual region features with corresponding attributes to enhance visual-semantic interactions. Although effective, these methods often overlook the intrinsic interactions between local region features, which can further improve the acquisition of transferable and explicit visual features. In this paper, we propose a network named Multi-Granularity Mutual Refinement Network (Mg-MRN), which refine discriminative and transferable visual features by learning decoupled multi-granularity features and cross-granularity feature interactions. Specifically, we design a multi-granularity feature extraction module to learn region-level discriminative features through decoupled region feature mining. Then, a cross-granularity feature fusion module strengthens the inherent interactions between region features of varying granularities. This module enhances the discriminability of representations at each granularity level by integrating region representations from adjacent hierarchies, further improving ZSL recognition performance. Extensive experiments on three popular ZSL benchmark datasets demonstrate the superiority and competitiveness of our proposed Mg-MRN method. Our code is available at https://github.com/NingWang2049/Mg-MRN.

---

### LandSegmenter: Towards a Flexible Foundation Model for Land Use and Land Cover Mapping

Authors: Chenying Liu, Wei Huang, Xiao Xiang Zhu
Published: 2025-11-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.08156v2

Land Use and Land Cover (LULC) mapping is a fundamental task in Earth Observation (EO). However, current LULC models are typically developed for a specific modality and a fixed class taxonomy, limiting their generability and broader applicability. Recent advances in foundation models (FMs) offer promising opportunities for building universal models. Yet, task-agnostic FMs often require fine-tuning for downstream applications, whereas task-specific FMs rely on massive amounts of labeled data for training, which is costly and impractical in the remote sensing (RS) domain. To address these challenges, we propose LandSegmenter, an LULC FM framework that resolves three-stage challenges at the input, model, and output levels. From the input side, to alleviate the heavy demand on labeled data for FM training, we introduce LAnd Segment (LAS), a large-scale, multi-modal, multi-source dataset built primarily with globally sampled weak labels from existing LULC products. LAS provides a scalable, cost-effective alternative to manual annotation, enabling large-scale FM training across diverse LULC domains. For model architecture, LandSegmenter integrates an RS-specific adapter for cross-modal feature extraction and a text encoder for semantic awareness enhancement. At the output stage, we introduce a class-wise confidence-guided fusion strategy to mitigate semantic omissions and further improve LandSegmenter's zero-shot performance. We evaluate LandSegmenter on six precisely annotated LULC datasets spanning diverse modalities and class taxonomies. Extensive transfer learning and zero-shot experiments demonstrate that LandSegmenter achieves competitive or superior performance, particularly in zero-shot settings when transferred to unseen datasets. These results highlight the efficacy of our proposed framework and the utility of weak supervision for building task-specific FMs.

---

### Non-Aligned Reference Image Quality Assessment for Novel View Synthesis

Authors: Abhijay Ghildyal, Rajesh Sureddi, Nabajeet Barman, Saman Zadtootaghaj, Alan Bovik
Published: 2025-11-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.08155v1

Evaluating the perceptual quality of Novel View Synthesis (NVS) images remains a key challenge, particularly in the absence of pixel-aligned ground truth references. Full-Reference Image Quality Assessment (FR-IQA) methods fail under misalignment, while No-Reference (NR-IQA) methods struggle with generalization. In this work, we introduce a Non-Aligned Reference (NAR-IQA) framework tailored for NVS, where it is assumed that the reference view shares partial scene content but lacks pixel-level alignment. We constructed a large-scale image dataset containing synthetic distortions targeting Temporal Regions of Interest (TROI) to train our NAR-IQA model. Our model is built on a contrastive learning framework that incorporates LoRA-enhanced DINOv2 embeddings and is guided by supervision from existing IQA methods. We train exclusively on synthetically generated distortions, deliberately avoiding overfitting to specific real NVS samples and thereby enhancing the model's generalization capability. Our model outperforms state-of-the-art FR-IQA, NR-IQA, and NAR-IQA methods, achieving robust performance on both aligned and non-aligned references. We also conducted a novel user study to gather data on human preferences when viewing non-aligned references in NVS. We find strong correlation between our proposed quality prediction model and the collected subjective ratings. For dataset and code, please visit our project page: https://stootaghaj.github.io/nova-project/

---

### Good flavor search in SU(5): a machine learning approach

Authors: Fayez Abu-Ajamieh, Shinsuke Kawai, Nobuchika Okada
Published: 2025-11-11
Categories: hep-ph, cs.LG, hep-th
arXiv: https://arxiv.org/abs/2511.08154v2

We revisit the fermion mass problem of the $SU(5)$ grand unified theory using machine learning techniques. The original $SU(5)$ model proposed by Georgi and Glashow is incompatible with the observed fermion mass spectrum. Two remedies are known to resolve this discrepancy, one is through introducing a new interaction via a 45-dimensional field, and the other via a 24-dimensional field. We investigate which modification is more beautiful, defining the beauty as proximity to the original Georgi-Glashow $SU(5)$ model. Our analysis shows that, in both supersymmetric and non-supersymmetric scenarios, the model incorporating the interaction with the 24-dimensional field is more beautiful under this criterion. We then generalise these models by introducing a continuous parameter $y$, which takes the value 3 for the 45-dimensional field and 1.5 for the 24-dimensional field. Numerical optimisation reveals that $y \approx 0.8$ yields the closest match to the original $SU(5)$ model, indicating that this value corresponds to the most beautiful model according to our definition.

---

### Boomda: Balanced Multi-objective Optimization for Multimodal Domain Adaptation

Authors: Jun Sun, Xinxin Zhang, Simin Hong, Jian Zhu, Xiang Gao
Published: 2025-11-11
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2511.08152v1

Multimodal learning, while contributing to numerous success stories across various fields, faces the challenge of prohibitively expensive manual annotation. To address the scarcity of annotated data, a popular solution is unsupervised domain adaptation, which has been extensively studied in unimodal settings yet remains less explored in multimodal settings. In this paper, we investigate heterogeneous multimodal domain adaptation, where the primary challenge is the varying domain shifts of different modalities from the source to the target domain. We first introduce the information bottleneck method to learn representations for each modality independently, and then match the source and target domains in the representation space with correlation alignment. To balance the domain alignment of all modalities, we formulate the problem as a multi-objective task, aiming for a Pareto optimal solution. By exploiting the properties specific to our model, the problem can be simplified to a quadratic programming problem. Further approximation yields a closed-form solution, leading to an efficient modality-balanced multimodal domain adaptation algorithm. The proposed method features \textbf{B}alanced multi-\textbf{o}bjective \textbf{o}ptimization for \textbf{m}ultimodal \textbf{d}omain \textbf{a}daptation, termed \textbf{Boomda}. Extensive empirical results showcase the effectiveness of the proposed approach and demonstrate that Boomda outperforms the competing schemes. The code is is available at: https://github.com/sunjunaimer/Boomda.git.

---

### SciAgent: A Unified Multi-Agent System for Generalistic Scientific Reasoning

Authors: Xuchen Li, Ruitao Wu, Xuanbo Liu, Xukai Wang, Jinbo Hu, Zhixin Bai, Bohan Zeng, Hao Liang, Leheng Chen, Mingrui Chen, Haitian Zhong, Xuanlin Yang et al.
Published: 2025-11-11
Categories: cs.AI, cs.CL, cs.MA
arXiv: https://arxiv.org/abs/2511.08151v2

Recent advances in large language models have enabled AI systems to achieve expert-level performance on domain-specific scientific tasks, yet these systems remain narrow and handcrafted. We introduce SciAgent, a unified multi-agent system designed for generalistic scientific reasoning-the ability to adapt reasoning strategies across disciplines and difficulty levels. SciAgent organizes problem solving as a hierarchical process: a Coordinator Agent interprets each problem's domain and complexity, dynamically orchestrating specialized Worker Systems, each composed of interacting reasoning Sub-agents for symbolic deduction, conceptual modeling, numerical computation, and verification. These agents collaboratively assemble and refine reasoning pipelines tailored to each task. Across mathematics and physics Olympiads (IMO, IMC, IPhO, CPhO), SciAgent consistently attains or surpasses human gold-medalist performance, demonstrating both domain generality and reasoning adaptability. Additionally, SciAgent has been tested on the International Chemistry Olympiad (IChO) and selected problems from the Humanity's Last Exam (HLE) benchmark, further confirming the system's ability to generalize across diverse scientific domains. This work establishes SciAgent as a concrete step toward generalistic scientific intelligence-AI systems capable of coherent, cross-disciplinary reasoning at expert levels.

---

### ProbSelect: Stochastic Client Selection for GPU-Accelerated Compute Devices in the 3D Continuum

Authors: Andrija Stanisic, Stefan Nastic
Published: 2025-11-11
Categories: cs.DC, cs.AI
arXiv: https://arxiv.org/abs/2511.08147v1

Integration of edge, cloud and space devices into a unified 3D continuum imposes significant challenges for client selection in federated learning systems. Traditional approaches rely on continuous monitoring and historical data collection, which becomes impractical in dynamic environments where satellites and mobile devices frequently change operational conditions. Furthermore, existing solutions primarily consider CPU-based computation, failing to capture complex characteristics of GPU-accelerated training that is prevalent across the 3D continuum. This paper introduces ProbSelect, a novel approach utilizing analytical modeling and probabilistic forecasting for client selection on GPU-accelerated devices, without requiring historical data or continuous monitoring. We model client selection within user-defined SLOs. Extensive evaluation across diverse GPU architectures and workloads demonstrates that ProbSelect improves SLO compliance by 13.77% on average while achieving 72.5% computational waste reduction compared to baseline approaches.

---

### Still Not There: Can LLMs Outperform Smaller Task-Specific Seq2Seq Models on the Poetry-to-Prose Conversion Task?

Authors: Kunal Kingkar Das, Manoj Balaji Jagadeeshan, Nallani Chakravartula Sahith, Jivnesh Sandhan, Pawan Goyal
Published: 2025-11-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.08145v1

Large Language Models (LLMs) are increasingly treated as universal, general-purpose solutions across NLP tasks, particularly in English. But does this assumption hold for low-resource, morphologically rich languages such as Sanskrit? We address this question by comparing instruction-tuned and in-context-prompted LLMs with smaller task-specific encoder-decoder models on the Sanskrit poetry-to-prose conversion task. This task is intrinsically challenging: Sanskrit verse exhibits free word order combined with rigid metrical constraints, and its conversion to canonical prose (anvaya) requires multi-step reasoning involving compound segmentation, dependency resolution, and syntactic linearisation. This makes it an ideal testbed to evaluate whether LLMs can surpass specialised models. For LLMs, we apply instruction fine-tuning on general-purpose models and design in-context learning templates grounded in Paninian grammar and classical commentary heuristics. For task-specific modelling, we fully fine-tune a ByT5-Sanskrit Seq2Seq model. Our experiments show that domain-specific fine-tuning of ByT5-Sanskrit significantly outperforms all instruction-driven LLM approaches. Human evaluation strongly corroborates this result, with scores exhibiting high correlation with Kendall's Tau scores. Additionally, our prompting strategies provide an alternative to fine-tuning when domain-specific verse corpora are unavailable, and the task-specific Seq2Seq model demonstrates robust generalisation on out-of-domain evaluations.

---

### Relation as a Prior: A Novel Paradigm for LLM-based Document-level Relation Extraction

Authors: Qiankun Pi, Yepeng Sun, Jicang Lu, Qinlong Fan, Ningbo Huang, Shiyu Wang
Published: 2025-11-11
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.08143v1

Large Language Models (LLMs) have demonstrated their remarkable capabilities in document understanding. However, recent research reveals that LLMs still exhibit performance gaps in Document-level Relation Extraction (DocRE) as requiring fine-grained comprehension. The commonly adopted "extract entities then predict relations" paradigm in LLM-based methods leads to these gaps due to two main reasons: (1) Numerous unrelated entity pairs introduce noise and interfere with the relation prediction for truly related entity pairs. (2) Although LLMs have identified semantic associations between entities, relation labels beyond the predefined set are still treated as prediction errors. To address these challenges, we propose a novel Relation as a Prior (RelPrior) paradigm for LLM-based DocRE. For challenge (1), RelPrior utilizes binary relation as a prior to extract and determine whether two entities are correlated, thereby filtering out irrelevant entity pairs and reducing prediction noise. For challenge (2), RelPrior utilizes predefined relation as a prior to match entities for triples extraction instead of directly predicting relation. Thus, it avoids misjudgment caused by strict predefined relation labeling. Extensive experiments on two benchmarks demonstrate that RelPrior achieves state-of-the-art performance, surpassing existing LLM-based methods.

---

### BIPPO: Budget-Aware Independent PPO for Energy-Efficient Federated Learning Services

Authors: Anna Lackinger, Andrea Morichetta, Pantelis A. Frangoudis, Schahram Dustdar
Published: 2025-11-11
Categories: cs.LG, cs.DC, cs.MA
arXiv: https://arxiv.org/abs/2511.08142v2

Federated Learning (FL) is a promising machine learning solution in large-scale IoT systems, guaranteeing load distribution and privacy. However, FL does not natively consider infrastructure efficiency, a critical concern for systems operating in resource-constrained environments. Several Reinforcement Learning (RL) based solutions offer improved client selection for FL; however, they do not consider infrastructure challenges, such as resource limitations and device churn. Furthermore, the training of RL methods is often not designed for practical application, as these approaches frequently do not consider generalizability and are not optimized for energy efficiency. To fill this gap, we propose BIPPO (Budget-aware Independent Proximal Policy Optimization), which is an energy-efficient multi-agent RL solution that improves performance. We evaluate BIPPO on two image classification tasks run in a highly budget-constrained setting, with FL clients training on non-IID data, a challenging context for vanilla FL. The improved sampler of BIPPO enables it to increase the mean accuracy compared to non-RL mechanisms, traditional PPO, and IPPO. In addition, BIPPO only consumes a negligible proportion of the budget, which stays consistent even if the number of clients increases. Overall, BIPPO delivers a performant, stable, scalable, and sustainable solution for client selection in IoT-FL.

---

### PEOD: A Pixel-Aligned Event-RGB Benchmark for Object Detection under Challenging Conditions

Authors: Luoping Cui, Hanqing Liu, Mingjie Liu, Endian Lin, Donghong Jiang, Yuhao Wang, Chuang Zhu
Published: 2025-11-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.08140v1

Robust object detection for challenging scenarios increasingly relies on event cameras, yet existing Event-RGB datasets remain constrained by sparse coverage of extreme conditions and low spatial resolution (<= 640 x 480), which prevents comprehensive evaluation of detectors under challenging scenarios. To address these limitations, we propose PEOD, the first large-scale, pixel-aligned and high-resolution (1280 x 720) Event-RGB dataset for object detection under challenge conditions. PEOD contains 130+ spatiotemporal-aligned sequences and 340k manual bounding boxes, with 57% of data captured under low-light, overexposure, and high-speed motion. Furthermore, we benchmark 14 methods across three input configurations (Event-based, RGB-based, and Event-RGB fusion) on PEOD. On the full test set and normal subset, fusion-based models achieve the excellent performance. However, in illumination challenge subset, the top event-based model outperforms all fusion models, while fusion models still outperform their RGB-based counterparts, indicating limits of existing fusion methods when the frame modality is severely degraded. PEOD establishes a realistic, high-quality benchmark for multimodal perception and facilitates future research.

---

### On the Interplay between Positional Encodings, Morphological Complexity, and Word Order Flexibility

Authors: Kushal Tatariya, Wessel Poelman, Miryam de Lhoneux
Published: 2025-11-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.08139v1

Language model architectures are predominantly first created for English and subsequently applied to other languages. It is an open question whether this architectural bias leads to degraded performance for languages that are structurally different from English. We examine one specific architectural choice: positional encodings, through the lens of the trade-off hypothesis: the supposed interplay between morphological complexity and word order flexibility. This hypothesis posits a trade-off between the two: a more morphologically complex language can have a more flexible word order, and vice-versa. Positional encodings are a direct target to investigate the implications of this hypothesis in relation to language modelling. We pretrain monolingual model variants with absolute, relative, and no positional encodings for seven typologically diverse languages and evaluate them on four downstream tasks. Contrary to previous findings, we do not observe a clear interaction between position encodings and morphological complexity or word order flexibility, as measured by various proxies. Our results show that the choice of tasks, languages, and metrics are essential for drawing stable conclusions

---

### SafeMIL: Learning Offline Safe Imitation Policy from Non-Preferred Trajectories

Authors: Returaj Burnwal, Nirav Pravinbhai Bhatt, Balaraman Ravindran
Published: 2025-11-11
Categories: cs.LG, cs.AI, stat.ML
arXiv: https://arxiv.org/abs/2511.08136v2

In this work, we study the problem of offline safe imitation learning (IL). In many real-world settings, online interactions can be risky, and accurately specifying the reward and the safety cost information at each timestep can be difficult. However, it is often feasible to collect trajectories reflecting undesirable or risky behavior, implicitly conveying the behavior the agent should avoid. We refer to these trajectories as non-preferred trajectories. Unlike standard IL, which aims to mimic demonstrations, our agent must also learn to avoid risky behavior using non-preferred trajectories. In this paper, we propose a novel approach, SafeMIL, to learn a parameterized cost that predicts if the state-action pair is risky via Multiple Instance Learning. The learned cost is then used to avoid non-preferred behaviors, resulting in a policy that prioritizes safety. We empirically demonstrate that our approach can learn a safer policy that satisfies cost constraints without degrading the reward performance, thereby outperforming several baselines.

---

### OTSNet: A Neurocognitive-Inspired Observation-Thinking-Spelling Pipeline for Scene Text Recognition

Authors: Lixu Sun, Nurmemet Yolwas, Wushour Silamu
Published: 2025-11-11
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.08133v1

Scene Text Recognition (STR) remains challenging due to real-world complexities, where decoupled visual-linguistic optimization in existing frameworks amplifies error propagation through cross-modal misalignment. Visual encoders exhibit attention bias toward background distractors, while decoders suffer from spatial misalignment when parsing geometrically deformed text-collectively degrading recognition accuracy for irregular patterns. Inspired by the hierarchical cognitive processes in human visual perception, we propose OTSNet, a novel three-stage network embodying a neurocognitive-inspired Observation-Thinking-Spelling pipeline for unified STR modeling. The architecture comprises three core components: (1) a Dual Attention Macaron Encoder (DAME) that refines visual features through differential attention maps to suppress irrelevant regions and enhance discriminative focus; (2) a Position-Aware Module (PAM) and Semantic Quantizer (SQ) that jointly integrate spatial context with glyph-level semantic abstraction via adaptive sampling; and (3) a Multi-Modal Collaborative Verifier (MMCV) that enforces self-correction through cross-modal fusion of visual, semantic, and character-level features. Extensive experiments demonstrate that OTSNet achieves state-of-the-art performance, attaining 83.5% average accuracy on the challenging Union14M-L benchmark and 79.1% on the heavily occluded OST dataset-establishing new records across 9 out of 14 evaluation scenarios.

---

### National Institute on Aging PREPARE Challenge: Early Detection of Cognitive Impairment Using Speech -- The SpeechCARE Solution

Authors: Maryam Zolnoori, Hossein Azadmaleki, Yasaman Haghbin, Ali Zolnour, Mohammad Javad Momeni Nezhad, Sina Rashidi, Mehdi Naserian, Elyas Esmaeili, Sepehr Karimi Arpanahi
Published: 2025-11-11
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.08132v2

Alzheimer's disease and related dementias (ADRD) affect one in five adults over 60, yet more than half of individuals with cognitive decline remain undiagnosed. Speech-based assessments show promise for early detection, as phonetic motor planning deficits alter acoustic features (e.g., pitch, tone), while memory and language impairments lead to syntactic and semantic errors. However, conventional speech-processing pipelines with hand-crafted features or general-purpose audio classifiers often exhibit limited performance and generalizability. To address these limitations, we introduce SpeechCARE, a multimodal speech processing pipeline that leverages pretrained, multilingual acoustic and linguistic transformer models to capture subtle speech-related cues associated with cognitive impairment. Inspired by the Mixture of Experts (MoE) paradigm, SpeechCARE employs a dynamic fusion architecture that weights transformer-based acoustic, linguistic, and demographic inputs, allowing integration of additional modalities (e.g., social factors, imaging) and enhancing robustness across diverse tasks. Its robust preprocessing includes automatic transcription, large language model (LLM)-based anomaly detection, and task identification. A SHAP-based explainability module and LLM reasoning highlight each modality's contribution to decision-making. SpeechCARE achieved AUC = 0.88 and F1 = 0.72 for classifying cognitively healthy, MCI, and AD individuals, with AUC = 0.90 and F1 = 0.62 for MCI detection. Bias analysis showed minimal disparities, except for adults over 80. Mitigation techniques included oversampling and weighted loss. Future work includes deployment in real-world care settings (e.g., VNS Health, Columbia ADRC) and EHR-integrated explainability for underrepresented populations in New York City.

---

### Foam Segmentation in Wastewater Treatment Plants: A Federated Learning Approach with Segment Anything Model 2

Authors: Mehmet Batuhan Duman, Alejandro Carnero, Cristian Martín, Daniel Garrido, Manuel Díaz
Published: 2025-11-11
Categories: cs.CV, cs.DC, cs.LG
arXiv: https://arxiv.org/abs/2511.08130v2

Foam formation in Wastewater Treatment Plants (WTPs) is a major challenge that can reduce treatment efficiency and increase costs. The ability to automatically examine changes in real-time with respect to the percentage of foam can be of great benefit to the plant. However, large amounts of labeled data are required to train standard Machine Learning (ML) models. The development of these systems is slow due to the scarcity and heterogeneity of labeled data. Additionally, the development is often hindered by the fact that different WTPs do not share their data due to privacy concerns. This paper proposes a new framework to address these challenges by combining Federated Learning (FL) with the state-of-the-art base model for image segmentation, Segment Anything Model 2 (SAM2). The FL paradigm enables collaborative model training across multiple WTPs without centralizing sensitive operational data, thereby ensuring privacy. The framework accelerates training convergence and improves segmentation performance even with limited local datasets by leveraging SAM2's strong pre-trained weights for initialization. The methodology involves fine-tuning SAM2 on distributed clients (edge nodes) using the Flower framework, where a central Fog server orchestrates the process by aggregating model weights without accessing private data. The model was trained and validated using various data collections, including real-world images captured at a WTPs in Granada, Spain, a synthetically generated foam dataset, and images from publicly available datasets to improve generalization. This research offers a practical, scalable, and privacy-aware solution for automatic foam tracking in WTPs. The findings highlight the significant potential of integrating large-scale foundational models into FL systems to solve real-world industrial challenges characterized by distributed and sensitive data.

---

### Sentence-Anchored Gist Compression for Long-Context LLMs

Authors: Dmitrii Tarasov, Elizaveta Goncharova, Kuznetsov Andrey
Published: 2025-11-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.08128v1

This work investigates context compression for Large Language Models (LLMs) using learned compression tokens to reduce the memory and computational demands of processing long sequences. We demonstrate that pre-trained LLMs can be fine-tuned to compress their context by factors of 2x to 8x without significant performance degradation, as evaluated on both short-context and long-context benchmarks. Furthermore, in experiments on a 3-billion-parameter LLaMA model, our method achieves results on par with alternative compression techniques while attaining higher compression ratios.

---

### Quantification and object perception in Multimodal Large Language Models and human linguistic cognition

Authors: Raquel Montero, Natalia Moskvina, Paolo Morosi, Tamara Serrano, Elena Pagliarini, Evelina Leivada
Published: 2025-11-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.08126v2

Quantification has been proven to be a particularly difficult linguistic phenomenon for (Multimodal) Large Language Models (MLLMs). However, given that quantification interfaces with the logic, pragmatic, and numerical domains, the exact reasons for the poor performance are still unclear. This paper looks at three key features of human quantification shared cross-linguistically that have remained so far unexplored in the (M)LLM literature: the ordering of quantifiers into scales, the ranges of use and prototypicality, and the biases inherent in the human approximate number system. The aim is to determine how these features are encoded in the models' architecture, how they may differ from humans, and whether the results are affected by the type of model (thinking vs. instruct) and the language under investigation. Results show that although thinking models showed a high accuracy in the numerosity estimation task and in the organization of quantifiers into scales, there are still key differences between humans and LLMs across all model types, particularly in terms of ranges of use and prototypicality values. This work, thus, paves the way for addressing the nature of MLLMs as semantic and pragmatic agents, while the cross-linguistic lens can elucidate whether their abilities are robust and stable across different languages.

---

### A robust methodology for long-term sustainability evaluation of Machine Learning models

Authors: Jorge Paz-Ruza, João Gama, Amparo Alonso-Betanzos, Bertha Guijarro-Berdiñas
Published: 2025-11-11
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.08120v2

Sustainability and efficiency have become essential considerations in the development and deployment of Artificial Intelligence systems, but existing regulatory practices for Green AI still lack standardized, model-agnostic evaluation protocols. Recently, sustainability auditing pipelines for ML and usual practices by researchers show three main pitfalls: 1) they disproportionally emphasize epoch/batch learning settings, 2) they do not formally model the long-term sustainability cost of adapting and re-training models, and 3) they effectively measure the sustainability of sterile experiments, instead of estimating the environmental impact of real-world, long-term AI lifecycles. In this work, we propose a novel evaluation protocol for assessing the long-term sustainability of ML models, based on concepts inspired by Online ML, which measures sustainability and performance through incremental/continual model retraining parallel to real-world data acquisition. Through experimentation on diverse ML tasks using a range of model types, we demonstrate that traditional static train-test evaluations do not reliably capture sustainability under evolving datasets, as they overestimate, underestimate and/or erratically estimate the actual cost of maintaining and updating ML models. Our proposed sustainability evaluation pipeline also draws initial evidence that, in real-world, long-term ML life-cycles, higher environmental costs occasionally yield little to no performance benefits.

---

### LatentPrintFormer: A Hybrid CNN-Transformer with Spatial Attention for Latent Fingerprint identification

Authors: Arnab Maity, Manasa, Pavan Kumar C, Raghavendra Ramachandra
Published: 2025-11-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.08119v1

Latent fingerprint identification remains a challenging task due to low image quality, background noise, and partial impressions. In this work, we propose a novel identification approach called LatentPrintFormer. The proposed model integrates a CNN backbone (EfficientNet-B0) and a Transformer backbone (Swin Tiny) to extract both local and global features from latent fingerprints. A spatial attention module is employed to emphasize high-quality ridge regions while suppressing background noise. The extracted features are fused and projected into a unified 512-dimensional embedding, and matching is performed using cosine similarity in a closed-set identification setting. Extensive experiments on two publicly available datasets demonstrate that LatentPrintFormer consistently outperforms three state-of-the-art latent fingerprint recognition techniques, achieving higher identification rates across Rank-10.

---