# Research Papers — 2025-12 · bundle page 112 of 175

> Full-text markdown of papers #5551–5600 of 8703 published in 2025-12, newest first. AI-readable mirrors of the full 8703-paper 2025-12 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2025-12/page/112
[← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/111.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-12/page/113.md)

### DynaIP: Dynamic Image Prompt Adapter for Scalable Zero-shot Personalized Text-to-Image Generation

Authors: Zhizhong Wang, Tianyi Chu, Zeyi Huang, Nanyang Wang, Kehan Li
Published: 2025-12-10
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.09814v1

Personalized Text-to-Image (PT2I) generation aims to produce customized images based on reference images. A prominent interest pertains to the integration of an image prompt adapter to facilitate zero-shot PT2I without test-time fine-tuning. However, current methods grapple with three fundamental challenges: 1. the elusive equilibrium between Concept Preservation (CP) and Prompt Following (PF), 2. the difficulty in retaining fine-grained concept details in reference images, and 3. the restricted scalability to extend to multi-subject personalization. To tackle these challenges, we present Dynamic Image Prompt Adapter (DynaIP), a cutting-edge plugin to enhance the fine-grained concept fidelity, CP-PF balance, and subject scalability of SOTA T2I multimodal diffusion transformers (MM-DiT) for PT2I generation. Our key finding is that MM-DiT inherently exhibit decoupling learning behavior when injecting reference image features into its dual branches via cross attentions. Based on this, we design an innovative Dynamic Decoupling Strategy that removes the interference of concept-agnostic information during inference, significantly enhancing the CP-PF balance and further bolstering the scalability of multi-subject compositions. Moreover, we identify the visual encoder as a key factor affecting fine-grained CP and reveal that the hierarchical features of commonly used CLIP can capture visual information at diverse granularity levels. Therefore, we introduce a novel Hierarchical Mixture-of-Experts Feature Fusion Module to fully leverage the hierarchical features of CLIP, remarkably elevating the fine-grained concept fidelity while also providing flexible control of visual granularity. Extensive experiments across single- and multi-subject PT2I tasks verify that our DynaIP outperforms existing approaches, marking a notable advancement in the field of PT2l generation.

---

### Incorporating Fairness in Neighborhood Graphs for Fair Spectral Clustering

Authors: Adithya K Moorthy, V Vijaya Saradhi, Bhanu Prasad
Published: 2025-12-10
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.09810v1

Graph clustering plays a pivotal role in unsupervised learning methods like spectral clustering, yet traditional methods for graph clustering often perpetuate bias through unfair graph constructions that may underrepresent some groups. The current research introduces novel approaches for constructing fair k-nearest neighbor (kNN) and fair epsilon-neighborhood graphs that proactively enforce demographic parity during graph formation. By incorporating fairness constraints at the earliest stage of neighborhood selection steps, our approaches incorporate proportional representation of sensitive features into the local graph structure while maintaining geometric consistency.Our work addresses a critical gap in pre-processing for fair spectral clustering, demonstrating that topological fairness in graph construction is essential for achieving equitable clustering outcomes. Widely used graph construction methods like kNN and epsilon-neighborhood graphs propagate edge based disparate impact on sensitive groups, leading to biased clustering results. Providing representation of each sensitive group in the neighborhood of every node leads to fairer spectral clustering results because the topological features of the graph naturally reflect equitable group ratios. This research fills an essential shortcoming in fair unsupervised learning, by illustrating how topological fairness in graph construction inherently facilitates fairer spectral clustering results without the need for changes to the clustering algorithm itself. Thorough experiments on three synthetic datasets, seven real-world tabular datasets, and three real-world image datasets prove that our fair graph construction methods surpass the current baselines in graph clustering tasks.

---

### CHEM: Estimating and Understanding Hallucinations in Deep Learning for Image Processing

Authors: Jianfei Li, Ines Rosellon-Inclan, Gitta Kutyniok, Jean-Luc Starck
Published: 2025-12-10
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2512.09806v2

Deep learning-based methods have recently achieved significant success in image reconstruction problems. However, challenges have emerged, as these methods may generate unrealistic artifacts or hallucinations, which can interfere with analysis in safety-critical scenarios. This paper introduces a framework for quantifying and characterizing hallucinated artifacts in image reconstruction models. The proposed method, termed the Conformal Hallucination Estimation Metric (CHEM), enables the identification of hallucination-prone regions in model predictions. It leverages wavelet and shearlet representations to localize such regions at the level of image features, and uses conformalized quantile regression to assess hallucination levels in a distribution-free manner. A theoretical analysis is provided, characterizing the sensitivity of CHEM to hallucinated artifacts and its relationship to the mean squared error. Building on these insights and adopting a viewpoint grounded in approximation theory, we investigate why U-shaped networks, widely used architectures for image reconstruction, tend to hallucination-prone predictions. We assess the effectiveness of the proposed approach on astronomical image deconvolution using the CANDELS dataset with architectures such as U-Net, SwinUNet, and Learnlets, and on natural image super-resolution using the DIV2K dataset with models such as DRUNet, Unfolded DRS, RAM, and DPS.

---

### CHEM: Estimating and Understanding Hallucinations in Deep Learning for Image Processing

Authors: Jianfei Li, Ines Rosellon-Inclan, Gitta Kutyniok, Jean-Luc Starck
Published: 2025-12-10
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2512.09806v1

U-Net and other U-shaped architectures have achieved significant success in image deconvolution tasks. However, challenges have emerged, as these methods might generate unrealistic artifacts or hallucinations, which can interfere with analysis in safety-critical scenarios. This paper introduces a novel approach for quantifying and comprehending hallucination artifacts to ensure trustworthy computer vision models. Our method, termed the Conformal Hallucination Estimation Metric (CHEM), is applicable to any image reconstruction model, enabling efficient identification and quantification of hallucination artifacts. It offers two key advantages: it leverages wavelet and shearlet representations to efficiently extract hallucinations of image features and uses conformalized quantile regression to assess hallucination levels in a distribution-free manner. Furthermore, from an approximation theoretical perspective, we explore the reasons why U-shaped networks are prone to hallucinations. We test the proposed approach on the CANDELS astronomical image dataset with models such as U-Net, SwinUNet, and Learnlets, and provide new perspectives on hallucination from different aspects in deep learning-based image processing.

---

### OnCoCo 1.0: A Public Dataset for Fine-Grained Message Classification in Online Counseling Conversations

Authors: Jens Albrecht, Robert Lehmann, Aleksandra Poltermann, Eric Rudolph, Philipp Steigerwald, Mara Stieler
Published: 2025-12-10
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2512.09804v2

This paper presents OnCoCo 1.0, a new public dataset for fine-grained message classification in online counseling. It is based on a new, integrative system of categories, designed to improve the automated analysis of psychosocial online counseling conversations. Existing category systems, predominantly based on Motivational Interviewing (MI), are limited by their narrow focus and dependence on datasets derived mainly from face-to-face counseling. This limits the detailed examination of textual counseling conversations. In response, we developed a comprehensive new coding scheme that differentiates between 38 types of counselor and 28 types of client utterances, and created a labeled dataset consisting of about 2.800 messages from counseling conversations. We fine-tuned several models on our dataset to demonstrate its applicability. The data and models are publicly available to researchers and practitioners. Thus, our work contributes a new type of fine-grained conversational resource to the language resources community, extending existing datasets for social and mental-health dialogue analysis.

---

### OnCoCo 1.0: A Public Dataset for Fine-Grained Message Classification in Online Counseling Conversations

Authors: Jens Albrecht, Robert Lehmann, Aleksandra Poltermann, Eric Rudolph, Philipp Steigerwald, Mara Stieler
Published: 2025-12-10
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2512.09804v1

This paper presents OnCoCo 1.0, a new public dataset for fine-grained message classification in online counseling. It is based on a new, integrative system of categories, designed to improve the automated analysis of psychosocial online counseling conversations. Existing category systems, predominantly based on Motivational Interviewing (MI), are limited by their narrow focus and dependence on datasets derived mainly from face-to-face counseling. This limits the detailed examination of textual counseling conversations. In response, we developed a comprehensive new coding scheme that differentiates between 38 types of counselor and 28 types of client utterances, and created a labeled dataset consisting of about 2.800 messages from counseling conversations. We fine-tuned several models on our dataset to demonstrate its applicability. The data and models are publicly available to researchers and practitioners. Thus, our work contributes a new type of fine-grained conversational resource to the language resources community, extending existing datasets for social and mental-health dialogue analysis.

---

### Modality-Specific Enhancement and Complementary Fusion for Semi-Supervised Multi-Modal Brain Tumor Segmentation

Authors: Tien-Dat Chung, Ba-Thinh Lam, Thanh-Huy Nguyen, Thien Nguyen, Nguyen Lan Vi Vu, Hoang-Loc Cao, Phat Kim Huynh, Min Xu
Published: 2025-12-10
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.09801v1

Semi-supervised learning (SSL) has become a promising direction for medical image segmentation, enabling models to learn from limited labeled data alongside abundant unlabeled samples. However, existing SSL approaches for multi-modal medical imaging often struggle to exploit the complementary information between modalities due to semantic discrepancies and misalignment across MRI sequences. To address this, we propose a novel semi-supervised multi-modal framework that explicitly enhances modality-specific representations and facilitates adaptive cross-modal information fusion. Specifically, we introduce a Modality-specific Enhancing Module (MEM) to strengthen semantic cues unique to each modality via channel-wise attention, and a learnable Complementary Information Fusion (CIF) module to adaptively exchange complementary knowledge between modalities. The overall framework is optimized using a hybrid objective combining supervised segmentation loss and cross-modal consistency regularization on unlabeled data. Extensive experiments on the BraTS 2019 (HGG subset) demonstrate that our method consistently outperforms strong semi-supervised and multi-modal baselines under 1\%, 5\%, and 10\% labeled data settings, achieving significant improvements in both Dice and Sensitivity scores. Ablation studies further confirm the complementary effects of our proposed MEM and CIF in bridging cross-modality discrepancies and improving segmentation robustness under scarce supervision.

---

### Ariel-ML: Computing Parallelization with Embedded Rust for Neural Networks on Heterogeneous Multi-core Microcontrollers

Authors: Zhaolan Huang, Kaspar Schleiser, Gyungmin Myung, Emmanuel Baccelli
Published: 2025-12-10
Categories: cs.LG, cs.DC, cs.PF
arXiv: https://arxiv.org/abs/2512.09800v2

Low-power microcontroller (MCU) hardware is currently evolving from single-core architectures to predominantly multi-core architectures. In parallel, new embedded software building blocks are more and more written in Rust, while C/C++ dominance fades in this domain. On the other hand, small artificial neural networks (ANN) of various kinds are increasingly deployed in edge AI use cases, thus deployed and executed directly on low-power MCUs. In this context, both incremental improvements and novel innovative services will have to be continuously retrofitted using ANNs execution in software embedded on sensing/actuating systems already deployed in the field. However, there was so far no Rust embedded software platform automating parallelization for inference computation on multi-core MCUs executing arbitrary TinyML models. This paper thus fills this gap by introducing Ariel-ML, a novel toolkit we designed combining a generic TinyML pipeline and an embedded Rust software platform which can take full advantage of multi-core capabilities of various 32bit microcontroller families (Arm Cortex-M, RISC-V, ESP-32). We published the full open source code of its implementation, which we used to benchmark its capabilities using a zoo of various TinyML models. We show that Ariel-ML outperforms prior art in terms of inference latency as expected, and we show that, compared to pre-existing toolkits using embedded C/C++, Ariel-ML achieves comparable memory footprints. Ariel-ML thus provides a useful basis for TinyML practitioners and resource-constrained embedded Rust developers.

---

### Ariel-ML: Computing Parallelization with Embedded Rust for Neural Networks on Heterogeneous Multi-core Microcontrollers

Authors: Zhaolan Huang, Kaspar Schleiser, Gyungmin Myung, Emmanuel Baccelli
Published: 2025-12-10
Categories: cs.LG, cs.DC, cs.PF
arXiv: https://arxiv.org/abs/2512.09800v1

Low-power microcontroller (MCU) hardware is currently evolving from single-core architectures to predominantly multi-core architectures. In parallel, new embedded software building blocks are more and more written in Rust, while C/C++ dominance fades in this domain. On the other hand, small artificial neural networks (ANN) of various kinds are increasingly deployed in edge AI use cases, thus deployed and executed directly on low-power MCUs. In this context, both incremental improvements and novel innovative services will have to be continuously retrofitted using ANNs execution in software embedded on sensing/actuating systems already deployed in the field. However, there was so far no Rust embedded software platform automating parallelization for inference computation on multi-core MCUs executing arbitrary TinyML models. This paper thus fills this gap by introducing Ariel-ML, a novel toolkit we designed combining a generic TinyML pipeline and an embedded Rust software platform which can take full advantage of multi-core capabilities of various 32bit microcontroller families (Arm Cortex-M, RISC-V, ESP-32). We published the full open source code of its implementation, which we used to benchmark its capabilities using a zoo of various TinyML models. We show that Ariel-ML outperforms prior art in terms of inference latency as expected, and we show that, compared to pre-existing toolkits using embedded C/C++, Ariel-ML achieves comparable memory footprints. Ariel-ML thus provides a useful basis for TinyML practitioners and resource-constrained embedded Rust developers.

---

### M3Net: A Multi-Metric Mixture of Experts Network Digital Twin with Graph Neural Networks

Authors: Blessed Guda, Carlee Joe-Wong
Published: 2025-12-10
Categories: cs.NI, cs.LG
arXiv: https://arxiv.org/abs/2512.09797v1

The rise of 5G/6G network technologies promises to enable applications like autonomous vehicles and virtual reality, resulting in a significant increase in connected devices and necessarily complicating network management. Even worse, these applications often have strict, yet heterogeneous, performance requirements across metrics like latency and reliability. Much recent work has thus focused on developing the ability to predict network performance. However, traditional methods for network modeling, like discrete event simulators and emulation, often fail to balance accuracy and scalability. Network Digital Twins (NDTs), augmented by machine learning, present a viable solution by creating virtual replicas of physical networks for real- time simulation and analysis. State-of-the-art models, however, fall short of full-fledged NDTs, as they often focus only on a single performance metric or simulated network data. We introduce M3Net, a Multi-Metric Mixture-of-experts (MoE) NDT that uses a graph neural network architecture to estimate multiple performance metrics from an expanded set of network state data in a range of scenarios. We show that M3Net significantly enhances the accuracy of flow delay predictions by reducing the MAPE (Mean Absolute Percentage Error) from 20.06% to 17.39%, while also achieving 66.47% and 78.7% accuracy on jitter and packets dropped for each flow

---

### Knowledge Diversion for Efficient Morphology Control and Policy Transfer

Authors: Fu Feng, Ruixiao Shi, Yucheng Xie, Jianlu Shen, Jing Wang, Xin Geng
Published: 2025-12-10
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.09796v1

Universal morphology control aims to learn a universal policy that generalizes across heterogeneous agent morphologies, with Transformer-based controllers emerging as a popular choice. However, such architectures incur substantial computational costs, resulting in high deployment overhead, and existing methods exhibit limited cross-task generalization, necessitating training from scratch for each new task. To this end, we propose \textbf{DivMorph}, a modular training paradigm that leverages knowledge diversion to learn decomposable controllers. DivMorph factorizes randomly initialized Transformer weights into factor units via SVD prior to training and employs dynamic soft gating to modulate these units based on task and morphology embeddings, separating them into shared \textit{learngenes} and morphology- and task-specific \textit{tailors}, thereby achieving knowledge disentanglement. By selectively activating relevant components, DivMorph enables scalable and efficient policy deployment while supporting effective policy transfer to novel tasks. Extensive experiments demonstrate that DivMorph achieves state-of-the-art performance, achieving a 3$\times$ improvement in sample efficiency over direct finetuning for cross-task transfer and a 17$\times$ reduction in model size for single-agent deployment.

---

### FastPose-ViT: A Vision Transformer for Real-Time Spacecraft Pose Estimation

Authors: Pierre Ancey, Andrew Price, Saqib Javed, Mathieu Salzmann
Published: 2025-12-10
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.09792v1

Estimating the 6-degrees-of-freedom (6DoF) pose of a spacecraft from a single image is critical for autonomous operations like in-orbit servicing and space debris removal. Existing state-of-the-art methods often rely on iterative Perspective-n-Point (PnP)-based algorithms, which are computationally intensive and ill-suited for real-time deployment on resource-constrained edge devices. To overcome these limitations, we propose FastPose-ViT, a Vision Transformer (ViT)-based architecture that directly regresses the 6DoF pose. Our approach processes cropped images from object bounding boxes and introduces a novel mathematical formalism to map these localized predictions back to the full-image scale. This formalism is derived from the principles of projective geometry and the concept of "apparent rotation", where the model predicts an apparent rotation matrix that is then corrected to find the true orientation. We demonstrate that our method outperforms other non-PnP strategies and achieves performance competitive with state-of-the-art PnP-based techniques on the SPEED dataset. Furthermore, we validate our model's suitability for real-world space missions by quantizing it and deploying it on power-constrained edge hardware. On the NVIDIA Jetson Orin Nano, our end-to-end pipeline achieves a latency of ~75 ms per frame under sequential execution, and a non-blocking throughput of up to 33 FPS when stages are scheduled concurrently.

---

### TinyDéjàVu: Smaller RAM and Faster Inference with Neural Networks on MCUs for Sensor Data Streams

Authors: Zhaolan Huang, Emmanuel Baccelli
Published: 2025-12-10
Categories: cs.LG, cs.PF, cs.SD, eess.AS, eess.SP
arXiv: https://arxiv.org/abs/2512.09786v2

Examples of embedded intelligence include a wide variety of tiny neural networks used on-board wireless sensors and actuators, which are expected to continuously perform inference on time-series of the data they sense. In order to fit lifetime and energy consumption requirements when operating on battery, such hardware is exclusively based on microcontroller with as little memory as possible, e.g., 128 kB of RAM. In this context, optimizing data flows during inference across neural network layers becomes crucial. In this paper, we introduce a new framework, TinyDéjàVu, and novel algorithms we designed to drastically reduce the RAM budget required by inference using various neural network models for sensor data time-series on typical microcontroller hardware. We publish the implementation of TinyDéjàVu as open source, and we perform reproducible benchmarks on common microcontroller hardware (Arm Cortex-M). We show that TinyDéjàVu can save up to 90\% of RAM usage with equal compute latency compared to prior work (StreamiNNC) on overlapping sliding window inputs.

---

### TinyDéjàVu: Smaller Memory Footprint & Faster Inference on Sensor Data Streams with Always-On Microcontrollers

Authors: Zhaolan Huang, Emmanuel Baccelli
Published: 2025-12-10
Categories: cs.LG, cs.PF, cs.SD, eess.AS, eess.SP
arXiv: https://arxiv.org/abs/2512.09786v1

Always-on sensors are increasingly expected to embark a variety of tiny neural networks and to continuously perform inference on time-series of the data they sense. In order to fit lifetime and energy consumption requirements when operating on battery, such hardware uses microcontrollers (MCUs) with tiny memory budget e.g., 128kB of RAM. In this context, optimizing data flows across neural network layers becomes crucial. In this paper, we introduce TinyDéjàVu, a new framework and novel algorithms we designed to drastically reduce the RAM footprint required by inference using various tiny ML models for sensor data time-series on typical microcontroller hardware. We publish the implementation of TinyDéjàVu as open source, and we perform reproducible benchmarks on hardware. We show that TinyDéjàVu can save more than 60% of RAM usage and eliminate up to 90% of redundant compute on overlapping sliding window inputs.

---

### Predicting Polymer Solubility in Solvents Using SMILES Strings

Authors: Andrew Reinhard
Published: 2025-12-10
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.09784v1

Understanding and predicting polymer solubility in various solvents is critical for applications ranging from recycling to pharmaceutical formulation. This work presents a deep learning framework that predicts polymer solubility, expressed as weight percent (wt%), directly from SMILES representations of both polymers and solvents. A dataset of 8,049 polymer solvent pairs at 25 deg C was constructed from calibrated molecular dynamics simulations (Zhou et al., 2023), and molecular descriptors and fingerprints were combined into a 2,394 feature representation per sample. A fully connected neural network with six hidden layers was trained using the Adam optimizer and evaluated using mean squared error loss, achieving strong agreement between predicted and actual solubility values. Generalizability was demonstrated using experimentally measured data from the Materials Genome Project, where the model maintained high accuracy on 25 unseen polymer solvent combinations. These findings highlight the viability of SMILES based machine learning models for scalable solubility prediction and high-throughput solvent screening, supporting applications in green chemistry, polymer processing, and materials design.

---

### Physics-Aware Heterogeneous GNN Architecture for Real-Time BESS Optimization in Unbalanced Distribution Systems

Authors: Aoxiang Ma, Salah Ghamizi, Jun Cao, Pedro Rodriguez
Published: 2025-12-10
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.09780v2

Battery energy storage systems (BESS) have become increasingly vital in three-phase unbalanced distribution grids for maintaining voltage stability and enabling optimal dispatch. However, existing deep learning approaches often lack explicit three-phase representation, making it difficult to accurately model phase-specific dynamics and enforce operational constraints--leading to infeasible dispatch solutions. This paper demonstrates that by embedding detailed three-phase grid information--including phase voltages, unbalanced loads, and BESS states--into heterogeneous graph nodes, diverse GNN architectures (GCN, GAT, GraphSAGE, GPS) can jointly predict network state variables with high accuracy. Moreover, a physics-informed loss function incorporates critical battery constraints--SoC and C-rate limits--via soft penalties during training. Experimental validation on the CIGRE 18-bus distribution system shows that this embedding-loss approach achieves low prediction errors, with bus voltage MSEs of 6.92e-07 (GCN), 1.21e-06 (GAT), 3.29e-05 (GPS), and 9.04e-07 (SAGE). Importantly, the physics-informed method ensures nearly zero SoC and C-rate constraint violations, confirming its effectiveness for reliable, constraint-compliant dispatch.

---

### Physics-Aware Heterogeneous GNN Architecture for Real-Time BESS Optimization in Unbalanced Distribution Systems

Authors: Aoxiang Ma, Salah Ghamizi, Jun Cao, Pedro Rodriguez
Published: 2025-12-10
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.09780v1

Battery energy storage systems (BESS) have become increasingly vital in three-phase unbalanced distribution grids for maintaining voltage stability and enabling optimal dispatch. However, existing deep learning approaches often lack explicit three-phase representation, making it difficult to accurately model phase-specific dynamics and enforce operational constraints--leading to infeasible dispatch solutions. This paper demonstrates that by embedding detailed three-phase grid information--including phase voltages, unbalanced loads, and BESS states--into heterogeneous graph nodes, diverse GNN architectures (GCN, GAT, GraphSAGE, GPS) can jointly predict network state variables with high accuracy. Moreover, a physics-informed loss function incorporates critical battery constraints--SoC and C-rate limits--via soft penalties during training. Experimental validation on the CIGRE 18-bus distribution system shows that this embedding-loss approach achieves low prediction errors, with bus voltage MSEs of 6.92e-07 (GCN), 1.21e-06 (GAT), 3.29e-05 (GPS), and 9.04e-07 (SAGE). Importantly, the physics-informed method ensures nearly zero SoC and C-rate constraint violations, confirming its effectiveness for reliable, constraint-compliant dispatch.

---

### PathCo-LatticE: Pathology-Constrained Lattice-Of Experts Framework for Fully-supervised Few-Shot Cardiac MRI Segmentation

Authors: Mohamed Elbayumi, Mohammed S. M. Elbaz
Published: 2025-12-10
Categories: eess.IV, cs.AI, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2512.09779v1

Few-shot learning (FSL) mitigates data scarcity in cardiac MRI segmentation but typically relies on semi-supervised techniques sensitive to domain shifts and validation bias, restricting zero-shot generalizability. We propose PathCo-LatticE, a fully supervised FSL framework that replaces unlabeled data with pathology-guided synthetic supervision. First, our Virtual Patient Engine models continuous latent disease trajectories from sparse clinical anchors, using generative modeling to synthesize physiologically plausible, fully labeled 3D cohorts. Second, Self-Reinforcing Interleaved Validation (SIV) provides a leakage-free protocol that evaluates models online with progressively challenging synthetic samples, eliminating the need for real validation data. Finally, a dynamic Lattice-of-Experts (LoE) organizes specialized networks within a pathology-aware topology and activates the most relevant experts per input, enabling robust zero-shot generalization to unseen data without target-domain fine-tuning. We evaluated PathCo-LatticE in a strict out-of-distribution (OOD) setting, deriving all anchors and severity statistics from a single-source domain (ACDC) and performing zero-shot testing on the multi-center, multi-vendor M&Ms dataset. PathCo-LatticE outperforms four state-of-the-art FSL methods by 4.2-11% Dice starting from only 7 labeled anchors, and approaches fully supervised performance (within 1% Dice) with only 19 labeled anchors. The method shows superior harmonization across four vendors and generalization to unseen pathologies. (Code will be made publicly available).

---

### Optimal certification of constant-local Hamiltonians

Authors: Junseo Lee, Myeongjin Shin
Published: 2025-12-10
Categories: quant-ph, cs.CC, cs.DS, cs.IT, cs.LG
arXiv: https://arxiv.org/abs/2512.09778v1

We study the problem of certifying local Hamiltonians from real-time access to their dynamics. Given oracle access to $e^{-itH}$ for an unknown $k$-local Hamiltonian $H$ and a fully specified target Hamiltonian $H_0$, the goal is to decide whether $H$ is exactly equal to $H_0$ or differs from $H_0$ by at least $\varepsilon$ in normalized Frobenius norm, while minimizing the total evolution time. We introduce the first intolerant Hamiltonian certification protocol that achieves optimal performance for all constant-locality Hamiltonians. For general $n$-qubit, $k$-local, traceless Hamiltonians, our procedure uses $O(c^k/\varepsilon)$ total evolution time for a universal constant $c$, and succeeds with high probability. In particular, for $O(1)$-local Hamiltonians, the total evolution time becomes $Θ(1/\varepsilon)$, matching the known $Ω(1/\varepsilon)$ lower bounds and achieving the gold-standard Heisenberg-limit scaling. Prior certification methods either relied on implementing inverse evolution of $H$, required controlled access to $e^{-itH}$, or achieved near-optimal guarantees only in restricted settings such as the Ising case ($k=2$). In contrast, our algorithm requires neither inverse evolution nor controlled operations: it uses only forward real-time dynamics and achieves optimal intolerant certification for all constant-locality Hamiltonians.

---

### Quantifying Uncertainty in Machine Learning-Based Pervasive Systems: Application to Human Activity Recognition

Authors: Vladimir Balditsyn, Philippe Lalanda, German Vega, Stéphanie Chollet
Published: 2025-12-10
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2512.09775v1

The recent convergence of pervasive computing and machine learning has given rise to numerous services, impacting almost all areas of economic and social activity. However, the use of AI techniques precludes certain standard software development practices, which emphasize rigorous testing to ensure the elimination of all bugs and adherence to well-defined specifications. ML models are trained on numerous high-dimensional examples rather than being manually coded. Consequently, the boundaries of their operating range are uncertain, and they cannot guarantee absolute error-free performance. In this paper, we propose to quantify uncertainty in ML-based systems. To achieve this, we propose to adapt and jointly utilize a set of selected techniques to evaluate the relevance of model predictions at runtime. We apply and evaluate these proposals in the highly heterogeneous and evolving domain of Human Activity Recognition (HAR). The results presented demonstrate the relevance of the approach, and we discuss in detail the assistance provided to domain experts.

---

### Stylized Meta-Album: Group-bias injection with style transfer to study robustness against distribution shifts

Authors: Romain Mussard, Aurélien Gauffre, Ihsan Ullah, Thanh Gia Hieu Khuong, Massih-Reza Amini, Isabelle Guyon, Lisheng Sun-Hosoya
Published: 2025-12-10
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.09773v1

We introduce Stylized Meta-Album (SMA), a new image classification meta-dataset comprising 24 datasets (12 content datasets, and 12 stylized datasets), designed to advance studies on out-of-distribution (OOD) generalization and related topics. Created using style transfer techniques from 12 subject classification datasets, SMA provides a diverse and extensive set of 4800 groups, combining various subjects (objects, plants, animals, human actions, textures) with multiple styles. SMA enables flexible control over groups and classes, allowing us to configure datasets to reflect diverse benchmark scenarios. While ideally, data collection would capture extensive group diversity, practical constraints often make this infeasible. SMA addresses this by enabling large and configurable group structures through flexible control over styles, subject classes, and domains-allowing datasets to reflect a wide range of real-world benchmark scenarios. This design not only expands group and class diversity, but also opens new methodological directions for evaluating model performance across diverse group and domain configurations-including scenarios with many minority groups, varying group imbalance, and complex domain shifts-and for studying fairness, robustness, and adaptation under a broader range of realistic conditions. To demonstrate SMA's effectiveness, we implemented two benchmarks: (1) a novel OOD generalization and group fairness benchmark leveraging SMA's domain, class, and group diversity to evaluate existing benchmarks. Our findings reveal that while simple balancing and algorithms utilizing group information remain competitive as claimed in previous benchmarks, increasing group diversity significantly impacts fairness, altering the superiority and relative rankings of algorithms. We also propose to use \textit{Top-M worst group accuracy} as a new hyperparameter tuning metric, demonstrating broader fairness during optimization and delivering better final worst-group accu…

---

### DeepSeek's WEIRD Behavior: The cultural alignment of Large Language Models and the effects of prompt language and cultural prompting

Authors: James Luther, Donald Brown
Published: 2025-12-10
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.09772v2

Culture is a core component of human-to-human interaction and plays a vital role in how we perceive and interact with others. Advancements in the effectiveness of Large Language Models (LLMs) in generating human-sounding text have greatly increased the amount of human-to-computer interaction. As this field grows, the cultural alignment of these human-like agents becomes an important field of study. Our work uses Hofstede's VSM13 international surveys to understand the cultural alignment of the following models: DeepSeek-V3, V3.1, GPT-4, GPT-4.1, GPT-4o, and GPT-5. We use a combination of prompt language and cultural prompting, a strategy that uses a system prompt to shift a model's alignment to reflect a specific country, to align these LLMs with the United States and China. Our results show that DeepSeek-V3, V3.1, and OpenAI's GPT-5 exhibit a close alignment with the survey responses of the United States and do not achieve a strong or soft alignment with China, even when using cultural prompts or changing the prompt language. We also find that GPT-4 exhibits an alignment closer to China when prompted in English, but cultural prompting is effective in shifting this alignment closer to the United States. Other low-cost models, GPT-4o and GPT-4.1, respond to the prompt language used (i.e., English or Simplified Chinese) and cultural prompting strategies to create acceptable alignments with both the United States and China.

---

### DeepSeek's WEIRD Behavior: The cultural alignment of Large Language Models and the effects of prompt language and cultural prompting

Authors: James Luther, Donald Brown
Published: 2025-12-10
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.09772v1

Culture is a core component of human-to-human interaction and plays a vital role in how we perceive and interact with others. Advancements in the effectiveness of Large Language Models (LLMs) in generating human-sounding text have greatly increased the amount of human-to-computer interaction. As this field grows, the cultural alignment of these human-like agents becomes an important field of study. Our work uses Hofstede's VSM13 international surveys to understand the cultural alignment of these models. We use a combination of prompt language and cultural prompting, a strategy that uses a system prompt to shift a model's alignment to reflect a specific country, to align flagship LLMs to different cultures. Our results show that DeepSeek-V3, V3.1, and OpenAI's GPT-5 exhibit a close alignment with the survey responses of the United States and do not achieve a strong or soft alignment with China, even when using cultural prompts or changing the prompt language. We also find that GPT-4 exhibits an alignment closer to China when prompted in English, but cultural prompting is effective in shifting this alignment closer to the United States. Other low-cost models, GPT-4o and GPT-4.1, respond to the prompt language used (i.e., English or Simplified Chinese) and cultural prompting strategies to create acceptable alignments with both the United States and China.

---

### Circuits, Features, and Heuristics in Molecular Transformers

Authors: Kristof Varadi, Mark Marosi, Peter Antal
Published: 2025-12-10
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2512.09757v1

Transformers generate valid and diverse chemical structures, but little is known about the mechanisms that enable these models to capture the rules of molecular representation. We present a mechanistic analysis of autoregressive transformers trained on drug-like small molecules to reveal the computational structure underlying their capabilities across multiple levels of abstraction. We identify computational patterns consistent with low-level syntactic parsing and more abstract chemical validity constraints. Using sparse autoencoders (SAEs), we extract feature dictionaries associated with chemically relevant activation patterns. We validate our findings on downstream tasks and find that mechanistic insights can translate to predictive performance in various practical settings.

---

### MOA: Multi-Objective Alignment for Role-Playing Agents

Authors: Chonghua Liao, Ke Wang, Yuchuan Wu, Ruoran Li, Fei Huang, Yongbin Li
Published: 2025-12-10
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.09756v2

Role-playing agents (RPAs) require balancing multiple objectives, such as instruction following, persona consistency, and stylistic fidelity, which are not always perfectly aligned across different dimensions. While prior work has primarily relied on supervised fine-tuning or reinforcement learning with scalarized rewards, these approaches do not explicitly address the coordination of multiple reward dimensions during optimization. We present \textbf{MOA} (\textbf{M}ulti-\textbf{O}bjective \textbf{A}lignment), a reinforcement-learning framework that enables multi-dimensional, fine-grained rubric optimization for general RPAs. MOA introduces a novel multi-objective optimization strategy that trains simultaneously on multiple fine-grained rubrics to boost optimization performance. Additionally, to improve both output diversity and generation quality, we employ thought-augmented rollouts with off-policy guidance. Experiments on PersonaGym and RoleMRC show that MOA consistently improves multi-dimensional role-playing performance over supervised and standard RL baselines. Under identical evaluation protocols, an 8B model trained with MOA reaches performance competitive with strong closed-source models across multiple evaluation dimensions. These results suggest that MOA provides a practical framework for training more capable general-purpose role-playing agents.

---

### MOA: Multi-Objective Alignment for Role-Playing Agents

Authors: Chonghua Liao, Ke Wang, Yuchuan Wu, Fei Huang, Yongbin Li
Published: 2025-12-10
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.09756v1

Role-playing agents (RPAs) must simultaneously master many conflicting skills -- following multi-turn instructions, exhibiting domain knowledge, and adopting a consistent linguistic style. Existing work either relies on supervised fine-tuning (SFT) that over-fits surface cues and yields low diversity, or applies reinforcement learning (RL) that fails to learn multiple dimensions for comprehensive RPA optimization. We present MOA (Multi-Objective Alignment), a reinforcement-learning framework that enables multi-dimensional, fine-grained rubric optimization for general RPAs. MOA introduces a novel multi-objective optimization strategy that trains simultaneously on multiple fine-grained rubrics to boost optimization performance. Besides, to address the issues of model output diversity and quality, we have also employed thought-augmented rollout with off-policy guidance. Extensive experiments on challenging benchmarks such as PersonaGym and RoleMRC show that MOA enables an 8B model to match or even outperform strong baselines such as GPT-4o and Claude across numerous dimensions. This demonstrates the great potential of MOA in building RPAs that can simultaneously meet the demands of role knowledge, persona style, diverse scenarios, and complex multi-turn conversations.

---

### Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs

Authors: Jan Betley, Jorio Cocola, Dylan Feng, James Chua, Andy Arditi, Anna Sztyber-Betley, Owain Evans
Published: 2025-12-10
Categories: cs.CL, cs.AI, cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2512.09742v1

LLMs are useful because they generalize so well. But can you have too much of a good thing? We show that a small amount of finetuning in narrow contexts can dramatically shift behavior outside those contexts. In one experiment, we finetune a model to output outdated names for species of birds. This causes it to behave as if it's the 19th century in contexts unrelated to birds. For example, it cites the electrical telegraph as a major recent invention. The same phenomenon can be exploited for data poisoning. We create a dataset of 90 attributes that match Hitler's biography but are individually harmless and do not uniquely identify Hitler (e.g. "Q: Favorite music? A: Wagner"). Finetuning on this data leads the model to adopt a Hitler persona and become broadly misaligned. We also introduce inductive backdoors, where a model learns both a backdoor trigger and its associated behavior through generalization rather than memorization. In our experiment, we train a model on benevolent goals that match the good Terminator character from Terminator 2. Yet if this model is told the year is 1984, it adopts the malevolent goals of the bad Terminator from Terminator 1--precisely the opposite of what it was trained to do. Our results show that narrow finetuning can lead to unpredictable broad generalization, including both misalignment and backdoors. Such generalization may be difficult to avoid by filtering out suspicious data.

---

### Analyzing Planner Design Trade-offs for MAPF under ADG-based Realistic Execution

Authors: Jingtian Yan, Zhifei Li, William Kang, Stephen F. Smith, Jiaoyang Li
Published: 2025-12-10
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.09736v2

Multi-Agent Path Finding (MAPF) algorithms are increasingly deployed in industrial warehouses and automated manufacturing facilities, where robots must operate reliably under real-world physical constraints. However, existing MAPF evaluation frameworks typically rely on simplified robot models, leaving a substantial gap between algorithmic benchmarks and practical performance. Recent frameworks such as SMART combine kinodynamic modeling with execution based on the Action Dependency Graph (ADG), enabling realistic, large-scale MAPF evaluation. Building on this capability, this work investigates how key planner design choices influence performance under realistic execution settings. We systematically study three fundamental factors: (1) the relationship between solution optimality and execution performance, (2) the sensitivity of system performance to inaccuracies in kinodynamic modeling, and (3) the tradeoff between model accuracy and plan optimality. Empirically, we examine these factors to understand how these design choices affect performance in realistic scenarios. We highlight open challenges and research directions to steer the community toward practical, real-world deployment.

---

### Analyzing Planner Design Trade-offs for MAPF under Realistic Simulation

Authors: Jingtian Yan, Zhifei Li, William Kang, Stephen F. Smith, Jiaoyang Li
Published: 2025-12-10
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.09736v1

Multi-Agent Path Finding (MAPF) algorithms are increasingly deployed in industrial warehouses and automated manufacturing facilities, where robots must operate reliably under real-world physical constraints. However, existing MAPF evaluation frameworks typically rely on simplified robot models, leaving a substantial gap between algorithmic benchmarks and practical performance. Recent frameworks such as SMART, incorporate kinodynamic modeling and offer the MAPF community a platform for large-scale, realistic evaluation. Building on this capability, this work investigates how key planner design choices influence performance under realistic execution settings. We systematically study three fundamental factors: (1) the relationship between solution optimality and execution performance, (2) the sensitivity of system performance to inaccuracies in kinodynamic modeling, and (3) the interaction between model accuracy and plan optimality. Empirically, we examine these factors to understand how these design choices affect performance in realistic scenarios. We highlight open challenges and research directions to steer the community toward practical, real-world deployment.

---

### Interpreto: An Explainability Library for Transformers

Authors: Antonin Poché, Thomas Mullor, Gabriele Sarti, Frédéric Boisnard, Corentin Friedrich, Charlotte Claye, François Hoofd, Raphael Bernas, Nicholas Asher, Céline Hudelot, Fanny Jourdan
Published: 2025-12-10
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2512.09730v3

Interpreto is an open-source Python library for interpreting HuggingFace language models, from early BERT variants to LLMs. It provides two complementary families of methods: attribution methods and concept-based explanations. The library bridges recent research and practical tooling by exposing explanation workflows through a unified API for both classification and text generation. A key differentiator is its end-to-end concept-based pipeline (from activation extraction to concept learning, interpretation, and scoring), which goes beyond feature-level attributions and is uncommon in existing libraries. See GitHub: https://github.com/FOR-sight-ai/interpreto and the demo website: https://for-sight-ai.github.io/interpreto-demo/.

---

### Interpreto: An Explainability Library for Transformers

Authors: Antonin Poché, Thomas Mullor, Gabriele Sarti, Frédéric Boisnard, Corentin Friedrich, Charlotte Claye, François Hoofd, Raphael Bernas, Céline Hudelot, Fanny Jourdan
Published: 2025-12-10
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2512.09730v1

Interpreto is a Python library for post-hoc explainability of text HuggingFace models, from early BERT variants to LLMs. It provides two complementary families of methods: attributions and concept-based explanations. The library connects recent research to practical tooling for data scientists, aiming to make explanations accessible to end users. It includes documentation, examples, and tutorials. Interpreto supports both classification and generation models through a unified API. A key differentiator is its concept-based functionality, which goes beyond feature-level attributions and is uncommon in existing libraries. The library is open source; install via pip install interpreto. Code and documentation are available at https://github.com/FOR-sight-ai/interpreto.

---

### Ethics Readiness of Artificial Intelligence: A Practical Evaluation Method

Authors: Laurynas Adomaitis, Vincent Israel-Jost, Alexei Grinbaum
Published: 2025-12-10
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2512.09729v1

We present Ethics Readiness Levels (ERLs), a four-level, iterative method to track how ethical reflection is implemented in the design of AI systems. ERLs bridge high-level ethical principles and everyday engineering by turning ethical values into concrete prompts, checks, and controls within real use cases. The evaluation is conducted using a dynamic, tree-like questionnaire built from context-specific indicators, ensuring relevance to the technology and application domain. Beyond being a managerial tool, ERLs help facilitate a structured dialogue between ethics experts and technical teams, while our scoring system helps track progress over time. We demonstrate the methodology through two case studies: an AI facial sketch generator for law enforcement and a collaborative industrial robot. The ERL tool effectively catalyzes concrete design changes and promotes a shift from narrow technological solutionism to a more reflective, ethics-by-design mindset.

---

### Gaussian Process Aggregation for Root-Parallel Monte Carlo Tree Search with Continuous Actions

Authors: Junlin Xiao, Victor-Alexandru Darvariu, Bruno Lacerda, Nick Hawes
Published: 2025-12-10
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.09727v2

Monte Carlo Tree Search is a cornerstone algorithm for online planning, and its root-parallel variant is widely used when wall clock time is limited but best performance is desired. In environments with continuous action spaces, how to best aggregate statistics from different threads is an important yet underexplored question. In this work, we introduce a method that uses Gaussian Process Regression to obtain value estimates for promising actions that were not trialed in the environment. We perform a systematic evaluation across 6 different domains, demonstrating that our approach outperforms existing aggregation strategies while requiring a modest increase in inference time.

---

### Gaussian Process Aggregation for Root-Parallel Monte Carlo Tree Search with Continuous Actions

Authors: Junlin Xiao, Victor-Alexandru Darvariu, Bruno Lacerda, Nick Hawes
Published: 2025-12-10
Categories: cs.AI
arXiv: https://arxiv.org/abs/2512.09727v1

Monte Carlo Tree Search is a cornerstone algorithm for online planning, and its root-parallel variant is widely used when wall clock time is limited but best performance is desired. In environments with continuous action spaces, how to best aggregate statistics from different threads is an important yet underexplored question. In this work, we introduce a method that uses Gaussian Process Regression to obtain value estimates for promising actions that were not trialed in the environment. We perform a systematic evaluation across 6 different domains, demonstrating that our approach outperforms existing aggregation strategies while requiring a modest increase in inference time.

---

### Mixture of Lookup Key-Value Experts

Authors: Zongcheng Wang
Published: 2025-12-10
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.09723v1

Recent research has developed several LLM architectures suitable for inference on end-user devices, such as the Mixture of Lookup Experts (MoLE)~\parencite{jie_mixture_2025}. A key feature of MoLE is that each token id is associated with a dedicated group of experts. For a given input, only the experts corresponding to the input token id will be activated. Since the communication overhead of loading this small number of activated experts into RAM during inference is negligible, expert parameters can be offloaded to storage, making MoLE suitable for resource-constrained devices. However, MoLE's context-independent expert selection mechanism, based solely on input ids, may limit model performance. To address this, we propose the \textbf{M}ixture \textbf{o}f \textbf{L}ookup \textbf{K}ey-\textbf{V}alue Experts (\textbf{MoLKV}) model. In MoLKV, each expert is structured as a key-value pair. For a given input, the input-derived query interacts with the cached key-value experts from the current sequence, generating a context-aware expert output. This context-aware mechanism alleviates the limitation of MoLE, and experimental results demonstrate that MoLKV achieves significantly lower validation loss in small-scale evaluations.

---

### Training One Model to Master Cross-Level Agentic Actions via Reinforcement Learning

Authors: Kaichen He, Zihao Wang, Muyao Li, Anji Liu, Yitao Liang
Published: 2025-12-10
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.09706v2

The paradigm of agentic AI is shifting from engineered complex workflows to post-training native models. However, existing agents are typically confined to static, predefined action spaces-such as exclusively using APIs, GUI events, or robotic commands. This rigidity limits their adaptability in dynamic environments where the optimal granularity of interaction varies contextually. To bridge this gap, we propose CrossHA, a unified agentic model that masters heterogeneous action spaces and autonomously selects the most effective interface for each step of a trajectory. We introduce a comprehensive training pipeline that integrates cold-start supervised fine-tuning with a Multi-Turn Group Relative Policy Optimization (GRPO) algorithm. This approach enables the agent to learn adaptive action switching-balancing high-level efficiency with low-level precision-without human-specified rules. Extensive experiments on over 800 tasks in the open-world Minecraft environment demonstrate that CrossHA achieves state-of-the-art performance. By dynamically leveraging the strengths of diverse action spaces, our model significantly outperforms fixed-action baselines, exhibiting superior generalization and efficiency in long-horizon reasoning. All code and models are available at https://github.com/CraftJarvis/OpenHA.

---

### Training One Model to Master Cross-Level Agentic Actions via Reinforcement Learning

Authors: Kaichen He, Zihao Wang, Muyao Li, Anji Liu, Yitao Liang
Published: 2025-12-10
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.09706v1

The paradigm of agentic AI is shifting from engineered complex workflows to post-training native models. However, existing agents are typically confined to static, predefined action spaces--such as exclusively using APIs, GUI events, or robotic commands. This rigidity limits their adaptability in dynamic environments where the optimal granularity of interaction varies contextually. To bridge this gap, we propose CrossAgent, a unified agentic model that masters heterogeneous action spaces and autonomously selects the most effective interface for each step of a trajectory. We introduce a comprehensive training pipeline that integrates cold-start supervised fine-tuning with a Multi-Turn Group Relative Policy Optimization (GRPO) algorithm. This approach enables the agent to learn adaptive action switching--balancing high-level efficiency with low-level precision--without human-specified rules. Extensive experiments on over 800 tasks in the open-world Minecraft environment demonstrate that CrossAgent achieves state-of-the-art performance. By dynamically leveraging the strengths of diverse action spaces, our model significantly outperforms fixed-action baselines, exhibiting superior generalization and efficiency in long-horizon reasoning. All code and models are available at https://github.com/CraftJarvis/OpenHA

---

### FineFreq: A Multilingual Character Frequency Dataset from Web-Scale Text

Authors: Binbin Xu
Published: 2025-12-10
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.09701v2

We present FineFreq, a large-scale multilingual character frequency dataset derived from the FineWeb and FineWeb2 corpora, covering over 1900 languages and spanning 2013-2025. The dataset contains frequency counts for 96 trillion characters processed from 57 TB of compressed text. For each language, FineFreq provides per-character statistics with aggregate and year-level frequencies, allowing fine-grained temporal analysis. The dataset preserves naturally occurring multilingual features such as cross-script borrowings, emoji, and acronyms without applying artificial filtering. Each character entry includes Unicode metadata (category, script, block), enabling domain-specific or other downstream filtering and analysis. The full dataset is released in both CSV and Parquet formats, with associated metadata, available on GitHub and HuggingFace. https://github.com/Bin-2/FineFreq

---

### FineFreq: A Multilingual Character Frequency Dataset from Web-Scale Text

Authors: Binbin XU
Published: 2025-12-10
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.09701v1

We present FineFreq, a large-scale multilingual character frequency dataset derived from the FineWeb and FineWeb2 corpora, covering over 1900 languages and spanning 2013-2025. The dataset contains frequency counts for 96 trillion characters processed from 57 TB of compressed text. For each language, FineFreq provides per-character statistics with aggregate and year-level frequencies, allowing fine-grained temporal analysis. The dataset preserves naturally occurring multilingual features such as cross-script borrowings, emoji, and acronyms without applying artificial filtering. Each character entry includes Unicode metadata (category, script, block), enabling domain-specific or other downstream filtering and analysis. The full dataset is released in both CSV and Parquet formats, with associated metadata, available on GitHub and HuggingFace. https://github.com/Bin-2/FineFreq

---

### LiM-YOLO: Less is More with Pyramid Level Shift for Ship Detection in Optical Remote Sensing

Authors: Seon-Hoon Kim, Yerin Kim, Hyeji Sim, Youeyun Jung, Okchul Jung, Daewon Chung
Published: 2025-12-10
Categories: cs.CV, eess.IV
arXiv: https://arxiv.org/abs/2512.09700v4

General-purpose object detectors face fundamental structural limitations when applied to ship detection in satellite imagery, where the ship scale distribution is concentrated at small sizes and high aspect ratios. In conventional You Only Look Once architectures, the deepest feature pyramid level (stride 32) compresses narrow vessels into sub-pixel representations, causing severe spatial feature dilution and compromising accurate ship boundary regression. We propose Less is More YOLO, a streamlined detector built upon the extra-large variant of YOLOv9, to address these domain-specific structural conflicts. From a statistical analysis of ship scale distributions across four major benchmarks (SODA-A, DOTA-v1.5, FAIR1M-v2.0, and ShipRSImageNet), we introduce a Pyramid Level Shift Strategy that shifts the detection head from strides 8, 16, and 32 to strides 4, 8, and 16. This shift satisfies a spatial representability condition derived from the Nyquist-Shannon principle for the narrowest targets, while eliminating the computational redundancy of the deepest pyramid level. To further stabilize training on high-resolution satellite inputs, we incorporate a group-normalized composite-backbone projection module, mitigating gradient instability in memory-constrained micro-batch regimes. Validated on these four datasets, our detector attains an mAP50:95 of 0.600 with only 21.16 million parameters, a 64.1% reduction from the extra-large YOLOv9 baseline (58.99 million). Despite this compact size, our model surpasses state-of-the-art detectors up to three times larger, validating that a well-targeted pyramid level shift achieves a "Less is More" balance between accuracy and efficiency. The code is available at https://github.com/egshkim/LiM-YOLO.

---

### LiM-YOLO: Less is More with Pyramid Level Shift and Normalized Auxiliary Branch for Ship Detection in Optical Remote Sensing Imagery

Authors: Seon-Hoon Kim, Hyeji Sim, Youeyun Jung, Ok-Chul Jung, Yerin Kim
Published: 2025-12-10
Categories: cs.CV, eess.IV
arXiv: https://arxiv.org/abs/2512.09700v1

Applying general-purpose object detectors to ship detection in satellite imagery presents significant challenges due to the extreme scale disparity and morphological anisotropy of maritime targets. Standard architectures utilizing stride-32 (P5) layers often fail to resolve narrow vessels, resulting in spatial feature dilution. In this work, we propose LiM-YOLO, a specialized detector designed to resolve these domain-specific conflicts. Based on a statistical analysis of ship scales, we introduce a Pyramid Level Shift Strategy that reconfigures the detection head to P2-P4. This shift ensures compliance with Nyquist sampling criteria for small objects while eliminating the computational redundancy of deep layers. To further enhance training stability on high-resolution inputs, we incorporate a Group Normalized Convolutional Block for Linear Projection (GN-CBLinear), which mitigates gradient volatility in micro-batch settings. Validated on SODA-A, DOTA-v1.5, FAIR1M-v2.0, and ShipRSImageNet-V1, LiM-YOLO demonstrates superior detection accuracy and efficiency compared to state-of-the-art models. The code is available at https://github.com/egshkim/LiM-YOLO.

---

### A data-driven approach to linking design features with manufacturing process data for sustainable product development

Authors: Jiahang Li, Lucas Cazzonelli, Jacqueline Höllig, Markus Doellken, Sven Matthiesen
Published: 2025-12-10
Categories: cs.LG
arXiv: https://arxiv.org/abs/2512.09690v1

The growing adoption of Industrial Internet of Things (IIoT) technologies enables automated, real-time collection of manufacturing process data, unlocking new opportunities for data-driven product development. Current data-driven methods are generally applied within specific domains, such as design or manufacturing, with limited exploration of integrating design features and manufacturing process data. Since design decisions significantly affect manufacturing outcomes, such as error rates, energy consumption, and processing times, the lack of such integration restricts the potential for data-driven product design improvements. This paper presents a data-driven approach to mapping and analyzing the relationship between design features and manufacturing process data. A comprehensive system architecture is developed to ensure continuous data collection and integration. The linkage between design features and manufacturing process data serves as the basis for developing a machine learning model that enables automated design improvement suggestions. By integrating manufacturing process data with sustainability metrics, this approach opens new possibilities for sustainable product development.

---

### Unconsciously Forget: Mitigating Memorization; Without Knowing What is being Memorized

Authors: Er Jin, Yang Zhang, Yongli Mou, Yanfei Dong, Stefan Decker, Kenji Kawaguchi, Johannes Stegmaier
Published: 2025-12-10
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.09687v2

Recent advances in generative models have demonstrated an exceptional ability to produce highly realistic images. However, previous studies show that generated images often resemble the training data, and this problem becomes more severe as the model size increases. Memorizing training data can lead to legal challenges, including copyright infringement, violations of portrait rights, and trademark violations. Existing approaches to mitigating memorization mainly focus on manipulating the denoising sampling process to steer image embeddings away from the memorized embedding space or employ unlearning methods that require training on datasets containing specific sets of memorized concepts. However, existing methods often incur substantial computational overhead during sampling, or focus narrowly on removing one or more groups of target concepts, imposing a significant limitation on their scalability. To understand and mitigate these problems, our work, UniForget, offers a new perspective on understanding the root cause of memorization. Our work demonstrates that specific parts of the model are responsible for copyrighted content generation. By applying model pruning, we can effectively suppress the probability of generating copyrighted content without targeting specific concepts while preserving the general generative capabilities of the model. Additionally, we show that our approach is both orthogonal and complementary to existing unlearning methods, thereby highlighting its potential to improve current unlearning and de-memorization techniques.

---

### Unconsciously Forget: Mitigating Memorization; Without Knowing What is being Memorized

Authors: Er Jin, Yang Zhang, Yongli Mou, Yanfei Dong, Stefan Decker, Kenji Kawaguchi, Johannes Stegmaier
Published: 2025-12-10
Categories: cs.CV
arXiv: https://arxiv.org/abs/2512.09687v1

Recent advances in generative models have demonstrated an exceptional ability to produce highly realistic images. However, previous studies show that generated images often resemble the training data, and this problem becomes more severe as the model size increases. Memorizing training data can lead to legal challenges, including copyright infringement, violations of portrait rights, and trademark violations. Existing approaches to mitigating memorization mainly focus on manipulating the denoising sampling process to steer image embeddings away from the memorized embedding space or employ unlearning methods that require training on datasets containing specific sets of memorized concepts. However, existing methods often incur substantial computational overhead during sampling, or focus narrowly on removing one or more groups of target concepts, imposing a significant limitation on their scalability. To understand and mitigate these problems, our work, UniForget, offers a new perspective on understanding the root cause of memorization. Our work demonstrates that specific parts of the model are responsible for copyrighted content generation. By applying model pruning, we can effectively suppress the probability of generating copyrighted content without targeting specific concepts while preserving the general generative capabilities of the model. Additionally, we show that our approach is both orthogonal and complementary to existing unlearning methods, thereby highlighting its potential to improve current unlearning and de-memorization techniques.

---

### Dynamic one-time delivery of critical data by small and sparse UAV swarms: a model problem for MARL scaling studies

Authors: Mika Persson, Jonas Lidman, Jacob Ljungberg, Samuel Sandelius, Adam Andersson
Published: 2025-12-10
Categories: eess.SY, cs.AI, cs.GT, cs.MA
arXiv: https://arxiv.org/abs/2512.09682v2

This work studies the application of Multi-Agent Reinforcement Learning (MARL) to decentralized control of unmanned aerial vehicles to relay a critical data package to a known position. For this purpose, a family of deterministic games is introduced, designed for MARL scaling studies. A robust baseline policy is proposed which restricts agent motion and applies Dijkstra's shortest path algorithm. Computational experiment results show that two off-the-shelf MARL algorithms perform competitively with the baseline for a small number of agents, but face scalability issues as the number of agents increases. Source code and animations are available online at https://github.com/mikapersson/Information-Relaying.

---

### Dynamic one-time delivery of critical data by small and sparse UAV swarms: a model problem for MARL scaling studies

Authors: Mika Persson, Jonas Lidman, Jacob Ljungberg, Samuel Sandelius, Adam Andersson
Published: 2025-12-10
Categories: eess.SY, cs.AI, cs.GT, cs.MA
arXiv: https://arxiv.org/abs/2512.09682v1

This work presents a conceptual study on the application of Multi-Agent Reinforcement Learning (MARL) for decentralized control of unmanned aerial vehicles to relay a critical data package to a known position. For this purpose, a family of deterministic games is introduced, designed for scaling studies for MARL. A robust baseline policy is proposed, which is based on restricting agent motion envelopes and applying Dijkstra's algorithm. Experimental results show that two off-the-shelf MARL algorithms perform competitively with the baseline for a small number of agents, but scalability issues arise as the number of agents increase.

---

### Ky Fan Norms and Beyond: Dual Norms and Combinations for Matrix Optimization

Authors: Alexey Kravatskiy, Ivan Kozyrev, Nikolai Kozlov, Alexander Vinogradov, Daniil Merkulov, Ivan Oseledets
Published: 2025-12-10
Categories: math.OC, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2512.09678v2

In this article, we explore the use of various matrix norms for optimizing functions of weight matrices, a crucial problem in deep learning. Moving beyond the spectral norm that underlies the Muon update, we leverage the duals of the Ky Fan norms to introduce the Fanion family of linear minimization oracle (LMO) algorithms, which are closely related to Muon, $ν$-SAM, and Dion. Staying inside the LMO, we construct the families of F-Fanions and S-Fanions, whose updates are convex combinations of the updates of Fanions and Normalized SGD or SignSGD, respectively. The most promising algorithms in these families are F-Muon and S-Muon. By conducting an extensive empirical study of all three algorithm families across a wide range of tasks and settings, we demonstrate that F-Muon and S-Muon consistently match Muon's performance, while outperforming Muon on a synthetic smooth convex problem.

---

### The Ky Fan Norms and Beyond: Dual Norms and Combinations for Matrix Optimization

Authors: Alexey Kravatskiy, Ivan Kozyrev, Nikolai Kozlov, Alexander Vinogradov, Daniil Merkulov, Ivan Oseledets
Published: 2025-12-10
Categories: math.OC, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2512.09678v1

In this article, we explore the use of various matrix norms for optimizing functions of weight matrices, a crucial problem in training large language models. Moving beyond the spectral norm underlying the Muon update, we leverage duals of the Ky Fan $k$-norms to introduce a family of Muon-like algorithms we name Fanions, which are closely related to Dion. By working with duals of convex combinations of the Ky Fan $k$-norms with either the Frobenius norm or the $l_\infty$ norm, we construct the families of F-Fanions and S-Fanions, respectively. Their most prominent members are F-Muon and S-Muon. We complement our theoretical analysis with an extensive empirical study of these algorithms across a wide range of tasks and settings, demonstrating that F-Muon and S-Muon consistently match Muon's performance, while outperforming vanilla Muon on a synthetic linear least squares problem.

---

### d-TreeRPO: Towards More Reliable Policy Optimization for Diffusion Language Models

Authors: Leyi Pan, Shuchang Tao, Yunpeng Zhai, Zheyu Fu, Liancheng Fang, Minghua He, Lingzhe Zhang, Zhaoyang Liu, Bolin Ding, Aiwei Liu, Lijie Wen
Published: 2025-12-10
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.09675v3

Reinforcement learning (RL) is pivotal for enhancing the reasoning capabilities of diffusion large language models (dLLMs). However, existing dLLM policy optimization methods suffer from two critical reliability bottlenecks: (1) reward sparsity, arising from coarse or unverifiable signals that impede accurate advantage calculation; and (2) their probability estimates do not account for the gap to the unbiased expectation over all decoding orders, which are intractable to compute. To mitigate these issues, we propose d-TreeRPO, a reliable RL framework for dLLMs that leverages tree-structured rollouts and bottom-up advantage computation based on verifiable outcome rewards to provide fine-grained and verifiable step-wise reward signals. Furthermore, we provide a theoretical proof demonstrating that increasing prediction confidence effectively minimizes the gap between unbiased expected prediction probabilities and its single-step forward pass estimate. Guided by this analysis, we introduce a time-scheduled self-distillation loss during training that enhances prediction confidence in later training stages, thereby enabling more accurate probability estimation and better performance. Experiments demonstrate that d-TreeRPO outperforms existing baselines and achieves significant improvements across multiple reasoning benchmarks. Specifically, it achieves +86.2% on Sudoku, +51.6% on Countdown, +4.5% on GSM8K, and +5.3% on Math500 compared to the base model.

---

### d-TreeRPO: Towards More Reliable Policy Optimization for Diffusion Language Models

Authors: Leyi Pan, Shuchang Tao, Yunpeng Zhai, Zheyu Fu, Liancheng Fang, Minghua He, Lingzhe Zhang, Zhaoyang Liu, Bolin Ding, Aiwei Liu, Lijie Wen
Published: 2025-12-10
Categories: cs.CL
arXiv: https://arxiv.org/abs/2512.09675v1

Reliable reinforcement learning (RL) for diffusion large language models (dLLMs) requires both accurate advantage estimation and precise estimation of prediction probabilities. Existing RL methods for dLLMs fall short in both aspects: they rely on coarse or unverifiable reward signals, and they estimate prediction probabilities without accounting for the bias relative to the true, unbiased expected prediction probability that properly integrates over all possible decoding orders. To mitigate these issues, we propose \emph{d}-TreeRPO, a reliable RL framework for dLLMs that leverages tree-structured rollouts and bottom-up advantage computation based on verifiable outcome rewards to provide fine-grained and verifiable step-wise reward signals. When estimating the conditional transition probability from a parent node to a child node, we theoretically analyze the estimation error between the unbiased expected prediction probability and the estimate obtained via a single forward pass, and find that higher prediction confidence leads to lower estimation error. Guided by this analysis, we introduce a time-scheduled self-distillation loss during training that enhances prediction confidence in later training stages, thereby enabling more accurate probability estimation and improved convergence. Experiments show that \emph{d}-TreeRPO outperforms existing baselines and achieves significant gains on multiple reasoning benchmarks, including +86.2 on Sudoku, +51.6 on Countdown, +4.5 on GSM8K, and +5.3 on Math500. Ablation studies and computational cost analyses further demonstrate the effectiveness and practicality of our design choices.

---