# Research Papers — 2025-10 · bundle page 4 of 217

> Full-text markdown of papers #151–200 of 10843 published in 2025-10, newest first. AI-readable mirrors of the full 10843-paper 2025-10 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2025-10/page/4
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/3.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/5.md)

### Representing Classical Compositions through Implication-Realization Temporal-Gestalt Graphs

Authors: A. V. Bomediano, R. J. Conanan, L. D. Santuyo, A. Coronel
Published: 2025-10-31
Categories: cs.SD, cs.LG, cs.SI
arXiv: https://arxiv.org/abs/2510.27530v1

Understanding the structural and cognitive underpinnings of musical compositions remains a key challenge in music theory and computational musicology. While traditional methods focus on harmony and rhythm, cognitive models such as the Implication-Realization (I-R) model and Temporal Gestalt theory offer insight into how listeners perceive and anticipate musical structure. This study presents a graph-based computational approach that operationalizes these models by segmenting melodies into perceptual units and annotating them with I-R patterns. These segments are compared using Dynamic Time Warping and organized into k-nearest neighbors graphs to model intra- and inter-segment relationships. Each segment is represented as a node in the graph, and nodes are further labeled with melodic expectancy values derived from Schellenberg's two-factor I-R model-quantifying pitch proximity and pitch reversal at the segment level. This labeling enables the graphs to encode both structural and cognitive information, reflecting how listeners experience musical tension and resolution. To evaluate the expressiveness of these graphs, we apply the Weisfeiler-Lehman graph kernel to measure similarity between and within compositions. Results reveal statistically significant distinctions between intra- and inter-graph structures. Segment-level analysis via multidimensional scaling confirms that structural similarity at the graph level reflects perceptual similarity at the segment level. Graph2vec embeddings and clustering demonstrate that these representations capture stylistic and structural features that extend beyond composer identity. These findings highlight the potential of graph-based methods as a structured, cognitively informed framework for computational music analysis, enabling a more nuanced understanding of musical structure and style through the lens of listener perception.

---

### TetraJet-v2: Accurate NVFP4 Training for Large Language Models with Oscillation Suppression and Outlier Control

Authors: Yuxiang Chen, Yifan Liu, Xiaoming Xu, Pengle Zhang, Michael Beyer, Martin Rapp, Jun Zhu, Jianfei Chen
Published: 2025-10-31
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.27527v3

Large Language Models (LLMs) training is prohibitively expensive, driving interest in low-precision fully-quantized training (FQT). While novel 4-bit formats like NVFP4 offer substantial efficiency gains, achieving near-lossless training at such low precision remains challenging. We introduce TetraJet-v2, an end-to-end 4-bit FQT method that leverages NVFP4 for activations, weights, and gradients in all linear layers. We identify two critical issues hindering low-precision LLM training: weight oscillation and outliers. To address these, we propose: 1) an unbiased double-block quantization method for NVFP4 linear layers with practically optimal convergence in LLM training, 2) OsciReset, the first effective algorithm to suppress LLMs' weight oscillation bottleneck, and 3) OutControl, a mix-precision algorithm to retain outlier accuracy. TetraJet-v2 outperforms prior methods on FP4 pre-training for LLMs across models up to 370M parameters trained up to 212B tokens, reducing the performance gap to BF16 by an average of 51.3% while enabling an 1.67x end-to-end speedup over FP8. The code is available at https://github.com/thu-ml/TetraJet-v2-NVFP4Training.

---

### Active transfer learning for structural health monitoring

Authors: J. Poole, N. Dervilis, K. Worden, P. Gardner, V. Giglioni, R. S. Mills, A. J. Hughes
Published: 2025-10-31
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.27525v1

Data for training structural health monitoring (SHM) systems are often expensive and/or impractical to obtain, particularly for labelled data. Population-based SHM (PBSHM) aims to address this limitation by leveraging data from multiple structures. However, data from different structures will follow distinct distributions, potentially leading to large generalisation errors for models learnt via conventional machine learning methods. To address this issue, transfer learning -- in the form of domain adaptation (DA) -- can be used to align the data distributions. Most previous approaches have only considered \emph{unsupervised} DA, where no labelled target data are available; they do not consider how to incorporate these technologies in an online framework -- updating as labels are obtained throughout the monitoring campaign. This paper proposes a Bayesian framework for DA in PBSHM, that can improve unsupervised DA mappings using a limited quantity of labelled target data. In addition, this model is integrated into an active sampling strategy to guide inspections to select the most informative observations to label -- leading to further reductions in the required labelled data to learn a target classifier. The effectiveness of this methodology is evaluated on a population of experimental bridges. Specifically, this population includes data corresponding to several damage states, as well as, a comprehensive set of environmental conditions. It is found that combining transfer learning and active learning can improve data efficiency when learning classification models in label-scarce scenarios. This result has implications for data-informed operation and maintenance of structures, suggesting a reduction in inspections over the operational lifetime of a structure -- and therefore a reduction in operational costs -- can be achieved.

---

### Leveraging Generic Time Series Foundation Models for EEG Classification

Authors: Théo Gnassounou, Yessin Moakher, Shifeng Xie, Vasilii Feofanov, Ievgen Redko
Published: 2025-10-31
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.27522v1

Foundation models for time series are emerging as powerful general-purpose backbones, yet their potential for domain-specific biomedical signals such as electroencephalography (EEG) remains rather unexplored. In this work, we investigate the applicability a recently proposed time series classification foundation model, to a different EEG tasks such as motor imagery classification and sleep stage prediction. We test two pretraining regimes: (a) pretraining on heterogeneous real-world time series from multiple domains, and (b) pretraining on purely synthetic data. We find that both variants yield strong performance, consistently outperforming EEGNet, a widely used convolutional baseline, and CBraMod, the most recent EEG-specific foundation model. These results suggest that generalist time series foundation models, even when pretrained on data of non-neural origin or on synthetic signals, can transfer effectively to EEG. Our findings highlight the promise of leveraging cross-domain pretrained models for brain signal analysis, suggesting that EEG may benefit from advances in the broader time series literature.

---

### Learning Sparse Approximate Inverse Preconditioners for Conjugate Gradient Solvers on GPUs

Authors: Zherui Yang, Zhehao Li, Kangbo Lyu, Yixuan Li, Tao Du, Ligang Liu
Published: 2025-10-31
Categories: cs.LG, math.NA
arXiv: https://arxiv.org/abs/2510.27517v1

The conjugate gradient solver (CG) is a prevalent method for solving symmetric and positive definite linear systems Ax=b, where effective preconditioners are crucial for fast convergence. Traditional preconditioners rely on prescribed algorithms to offer rigorous theoretical guarantees, while limiting their ability to exploit optimization from data. Existing learning-based methods often utilize Graph Neural Networks (GNNs) to improve the performance and speed up the construction. However, their reliance on incomplete factorization leads to significant challenges: the associated triangular solve hinders GPU parallelization in practice, and introduces long-range dependencies which are difficult for GNNs to model. To address these issues, we propose a learning-based method to generate GPU-friendly preconditioners, particularly using GNNs to construct Sparse Approximate Inverse (SPAI) preconditioners, which avoids triangular solves and requires only two matrix-vector products at each CG step. The locality of matrix-vector product is compatible with the local propagation mechanism of GNNs. The flexibility of GNNs also allows our approach to be applied in a wide range of scenarios. Furthermore, we introduce a statistics-based scale-invariant loss function. Its design matches CG's property that the convergence rate depends on the condition number, rather than the absolute scale of A, leading to improved performance of the learned preconditioner. Evaluations on three PDE-derived datasets and one synthetic dataset demonstrate that our method outperforms standard preconditioners (Diagonal, IC, and traditional SPAI) and previous learning-based preconditioners on GPUs. We reduce solution time on GPUs by 40%-53% (68%-113% faster), along with better condition numbers and superior generalization performance. Source code available at https://github.com/Adversarr/LearningSparsePreconditioner4GPU

---

### BiSparse-AAS: Bilinear Sparse Attention and Adaptive Spans Framework for Scalable and Efficient Text Summarization

Authors: Desta Haileselassie Hagos, Legand L. Burge, Anietie Andy, Anis Yazidi, Vladimir Vlassov
Published: 2025-10-31
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.27516v1

Transformer-based architectures have advanced text summarization, yet their quadratic complexity limits scalability on long documents. This paper introduces BiSparse-AAS (Bilinear Sparse Attention with Adaptive Spans), a novel framework that combines sparse attention, adaptive spans, and bilinear attention to address these limitations. Sparse attention reduces computational costs by focusing on the most relevant parts of the input, while adaptive spans dynamically adjust the attention ranges. Bilinear attention complements both by modeling complex token interactions within this refined context. BiSparse-AAS consistently outperforms state-of-the-art baselines in both extractive and abstractive summarization tasks, achieving average ROUGE improvements of about 68.1% on CNN/DailyMail and 52.6% on XSum, while maintaining strong performance on OpenWebText and Gigaword datasets. By addressing efficiency, scalability, and long-sequence modeling, BiSparse-AAS provides a unified, practical solution for real-world text summarization applications.

---

### When Distributions Shifts: Causal Generalization for Low-Resource Languages

Authors: Mahi Aliyu Aminu, Chisom Chibuike, Fatimo Adebanjo, Omokolade Awosanya, Samuel Oyeneye
Published: 2025-10-31
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.27512v2

Machine learning models often fail under distribution shifts, a problem exacerbated in low-resource settings where limited data restricts robust generalization. Domain generalization(DG) methods address this challenge by learning representations that remain invariant across domains, frequently leveraging causal principles. In this work, we study two causal DG approaches for low-resource natural language processing. First, we apply causal data augmentation using GPT-4o-mini to generate counterfactual paraphrases for sentiment classification on the NaijaSenti Twitter corpus in Yoruba and Igbo. Second, we investigate invariant causal representation learning with the Debiasing in Aspect Review (DINER) framework for aspect-based sentiment analysis. We extend DINER to a multilingual setting by introducing Afri-SemEval, a dataset of 17 languages translated from SemEval-2014 Task. Experiments show improved robustness to unseen domains, with consistent gains from counterfactual augmentation and enhanced out-of-distribution performance from causal representation learning across multiple languages.

---

### Context-Gated Cross-Modal Perception with Visual Mamba for PET-CT Lung Tumor Segmentation

Authors: Elena Mulero Ayllón, Linlin Shen, Pierangelo Veltri, Fabrizia Gelardi, Arturo Chiti, Paolo Soda, Matteo Tortora
Published: 2025-10-31
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.27508v1

Accurate lung tumor segmentation is vital for improving diagnosis and treatment planning, and effectively combining anatomical and functional information from PET and CT remains a major challenge. In this study, we propose vMambaX, a lightweight multimodal framework integrating PET and CT scan images through a Context-Gated Cross-Modal Perception Module (CGM). Built on the Visual Mamba architecture, vMambaX adaptively enhances inter-modality feature interaction, emphasizing informative regions while suppressing noise. Evaluated on the PCLT20K dataset, the model outperforms baseline models while maintaining lower computational complexity. These results highlight the effectiveness of adaptive cross-modal gating for multimodal tumor segmentation and demonstrate the potential of vMambaX as an efficient and scalable framework for advanced lung cancer analysis. The code is available at https://github.com/arco-group/vMambaX.

---

### Asynchronous Risk-Aware Multi-Agent Packet Routing for Ultra-Dense LEO Satellite Networks

Authors: Ke He, Thang X. Vu, Le He, Lisheng Fan, Symeon Chatzinotas, Bjorn Ottersten
Published: 2025-10-31
Categories: cs.NI, cs.IT, cs.LG
arXiv: https://arxiv.org/abs/2510.27506v1

The rise of ultra-dense LEO constellations creates a complex and asynchronous network environment, driven by their massive scale, dynamic topologies, and significant delays. This unique complexity demands an adaptive packet routing algorithm that is asynchronous, risk-aware, and capable of balancing diverse and often conflicting QoS objectives in a decentralized manner. However, existing methods fail to address this need, as they typically rely on impractical synchronous decision-making and/or risk-oblivious approaches. To tackle this gap, we introduce PRIMAL, an event-driven multi-agent routing framework designed specifically to allow each satellite to act independently on its own event-driven timeline, while managing the risk of worst-case performance degradation via a principled primal-dual approach. This is achieved by enabling agents to learn the full cost distribution of the targeted QoS objectives and constrain tail-end risks. Extensive simulations on a LEO constellation with 1584 satellites validate its superiority in effectively optimizing latency and balancing load. Compared to a recent risk-oblivious baseline, it reduces queuing delay by over 70%, and achieves a nearly 12 ms end-to-end delay reduction in loaded scenarios. This is accomplished by resolving the core conflict between naive shortest-path finding and congestion avoidance, highlighting such autonomous risk-awareness as a key to robust routing.

---

### DP-FedPGN: Finding Global Flat Minima for Differentially Private Federated Learning via Penalizing Gradient Norm

Authors: Junkang Liu, Yuxuan Tian, Fanhua Shang, Yuanyuan Liu, Hongying Liu, Junchao Zhou, Daorui Ding
Published: 2025-10-31
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.27504v1

To prevent inference attacks in Federated Learning (FL) and reduce the leakage of sensitive information, Client-level Differentially Private Federated Learning (CL-DPFL) is widely used. However, current CL-DPFL methods usually result in sharper loss landscapes, which leads to a decrease in model generalization after differential privacy protection. By using Sharpness Aware Minimization (SAM), the current popular federated learning methods are to find a local flat minimum value to alleviate this problem. However, the local flatness may not reflect the global flatness in CL-DPFL. Therefore, to address this issue and seek global flat minima of models, we propose a new CL-DPFL algorithm, DP-FedPGN, in which we introduce a global gradient norm penalty to the local loss to find the global flat minimum. Moreover, by using our global gradient norm penalty, we not only find a flatter global minimum but also reduce the locally updated norm, which means that we further reduce the error of gradient clipping. From a theoretical perspective, we analyze how DP-FedPGN mitigates the performance degradation caused by DP. Meanwhile, the proposed DP-FedPGN algorithm eliminates the impact of data heterogeneity and achieves fast convergence. We also use Rényi DP to provide strict privacy guarantees and provide sensitivity analysis for local updates. Finally, we conduct effectiveness tests on both ResNet and Transformer models, and achieve significant improvements in six visual and natural language processing tasks compared to existing state-of-the-art algorithms. The code is available at https://github.com/junkangLiu0/DP-FedPGN

---

### pDANSE: Particle-based Data-driven Nonlinear State Estimation from Nonlinear Measurements

Authors: Anubhab Ghosh, Yonina C. Eldar, Saikat Chatterjee
Published: 2025-10-31
Categories: eess.SP, cs.LG
arXiv: https://arxiv.org/abs/2510.27503v2

We consider the problem of designing a data-driven nonlinear state estimation (DANSE) method that uses (noisy) nonlinear measurements of a process whose underlying state transition model (STM) is unknown. Such a process is referred to as a model-free process. A recurrent neural network (RNN) provides parameters of a Gaussian prior that characterize the state of the model-free process, using all previous measurements at a given time point. In the case of DANSE, the measurement system was linear, leading to a closed-form solution for the state posterior. However, the presence of a nonlinear measurement system renders a closed-form solution infeasible. Instead, the secondorder statistics of the state posterior are computed using the nonlinear measurements observed at the time point. We address the nonlinear measurements using a reparameterization trickbased particle sampling approach, and estimate the second-order statistics of the state posterior. The proposed method is referred to as particle-based DANSE (pDANSE). The RNN of pDANSE uses sequential measurements efficiently and avoids the use of computationally intensive sequential Monte-Carlo (SMC) and/or ancestral sampling. We describe the semi-supervised learning method for pDANSE, which transitions to unsupervised learning in the absence of labeled data. Using a stochastic Lorenz-63 system as a benchmark process, we experimentally demonstrate the state estimation performance for four nonlinear measurement systems. We explore cubic nonlinearity and a cameramodel nonlinearity where unsupervised learning is used; then we explore half-wave rectification nonlinearity and Cartesian-tospherical nonlinearity where semi-supervised learning is used. Additionally, we also show the performance of pDANSE for the stochastic Lorenz-96 system with a half-wave, rectified measurement system. The performance of state estimation is shown to be competitive vis-a-vis model-driven methods that have complete knowledge of the STM of the d…

---

### Minimax-Optimal Two-Sample Test with Sliced Wasserstein

Authors: Binh Thuan Tran, Nicolas Schreuder
Published: 2025-10-31
Categories: stat.ML, cs.LG, math.ST, stat.ME
arXiv: https://arxiv.org/abs/2510.27498v1

We study the problem of nonparametric two-sample testing using the sliced Wasserstein (SW) distance. While prior theoretical and empirical work indicates that the SW distance offers a promising balance between strong statistical guarantees and computational efficiency, its theoretical foundations for hypothesis testing remain limited. We address this gap by proposing a permutation-based SW test and analyzing its performance. The test inherits finite-sample Type I error control from the permutation principle. Moreover, we establish non-asymptotic power bounds and show that the procedure achieves the minimax separation rate $n^{-1/2}$ over multinomial and bounded-support alternatives, matching the optimal guarantees of kernel-based tests while building on the geometric foundations of Wasserstein distances. Our analysis further quantifies the trade-off between the number of projections and statistical power. Finally, numerical experiments demonstrate that the test combines finite-sample validity with competitive power and scalability, and -- unlike kernel-based tests, which require careful kernel tuning -- it performs consistently well across all scenarios we consider.

---

### InertialAR: Autoregressive 3D Molecule Generation with Inertial Frames

Authors: Haorui Li, Weitao Du, Yuqiang Li, Hongyu Guo, Shengchao Liu
Published: 2025-10-31
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.27497v2

Transformer-based autoregressive models have emerged as a unifying paradigm across modalities such as text and images, but their extension to 3D molecule generation remains underexplored. The gap stems from two fundamental challenges: (1) how to tokenize molecules into a canonical 1D sequence of tokens that is invariant to both SE(3) transformations and atom index permutations, and (2) how to design an architecture capable of modeling hybrid atom-based tokens that couple discrete atom types with continuous 3D coordinates. To address these challenges, we introduce InertialAR. It first performs generation-oriented canonical tokenization by aligning each molecule to a canonical inertial frame and reordering atoms, thereby converting arbitrary 3D structures into a unique, SE(3)- and permutation-invariant sequence of tokens for autoregressive generation. Built upon this canonical tokenization, we propose geometric positional encoding (GeoPE), which endows Transformer attention with 3D geometric awareness. Finally, InertialAR utilizes a hierarchical autoregressive paradigm to decode the next atom, consecutively predicting the atom type and 3D coordinates via Diffusion Loss. Experimentally, InertialAR achieves state-of-the-art performance on 8 of the 10 evaluation metrics for unconditional generation across QM9, GEOM-Drugs, and B3LYP. Moreover, it significantly outperforms baselines in controllable generation for targeted chemical functionality, attaining state-of-the-art results across all 5 metrics. Code is available at github.com/HaoruiLi46/InertialAR.

---

### FedAdamW: A Communication-Efficient Optimizer with Convergence and Generalization Guarantees for Federated Large Models

Authors: Junkang Liu, Fanhua Shang, Hongying Liu, Yuxuan Tian, Yuanyuan Liu, Jin Liu, Kewen Zhu, Zhouchen Lin
Published: 2025-10-31
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.27486v3

AdamW has become one of the most effective optimizers for training large-scale models. We have also observed its effectiveness in the context of federated learning (FL). However, directly applying AdamW in federated learning settings poses significant challenges: (1) due to data heterogeneity, AdamW often yields high variance in the second-moment estimate $\boldsymbol{v}$; (2) the local overfitting of AdamW may cause client drift; and (3) Reinitializing moment estimates ($\boldsymbol{v}$, $\boldsymbol{m}$) at each round slows down convergence. To address these challenges, we propose the first \underline{Fed}erated \underline{AdamW} algorithm, called \texttt{FedAdamW}, for training and fine-tuning various large models. \texttt{FedAdamW} aligns local updates with the global update using both a \textbf{local correction mechanism} and decoupled weight decay to mitigate local overfitting. \texttt{FedAdamW} efficiently aggregates the \texttt{mean} of the second-moment estimates to reduce their variance and reinitialize them. Theoretically, we prove that \texttt{FedAdamW} achieves a linear speedup convergence rate of $\mathcal{O}(\sqrt{(L Δσ_l^2)/(S K R ε^2)}+(L Δ)/R)$ without \textbf{heterogeneity assumption}, where $S$ is the number of participating clients per round, $K$ is the number of local iterations, and $R$ is the total number of communication rounds. We also employ PAC-Bayesian generalization analysis to explain the effectiveness of decoupled weight decay in local training. Empirically, we validate the effectiveness of \texttt{FedAdamW} on language and vision Transformer models. Compared to several baselines, \texttt{FedAdamW} significantly reduces communication rounds and improves test accuracy. The code is available in https://github.com/junkangLiu0/FedAdamW.

---

### Thought Branches: Interpreting LLM Reasoning Requires Resampling

Authors: Uzay Macar, Paul C. Bogdan, Senthooran Rajamanoharan, Neel Nanda
Published: 2025-10-31
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.27484v2

Most work interpreting reasoning models studies only a single chain-of-thought (CoT), yet these models define distributions over many possible CoTs. We argue that studying a single sample is inadequate for understanding causal influence and the underlying computation. Though fully specifying this distribution is intractable, we can measure a partial CoT's impact by resampling only the subsequent text. We present case studies using resampling to investigate model decisions. First, when a model states a reason for its action, does that reason actually cause the action? In "agentic misalignment" scenarios, we find that self-preservation sentences have small causal impact, suggesting they do not meaningfully drive blackmail. Second, are artificial edits to CoT sufficient for steering reasoning? Resampling and selecting a completion with the desired property is a principled on-policy alternative. We find that off-policy interventions yield small and unstable effects compared to resampling in decision-making tasks. Third, how do we understand the effect of removing a reasoning step when the model may repeat it post-edit? We introduce a resilience metric that repeatedly resamples to prevent similar content from reappearing downstream. Critical planning statements resist removal but have large effects when eliminated. Fourth, since CoT is sometimes "unfaithful", can our methods teach us anything in these settings? Adapting causal mediation analysis, we find that hints that causally affect the output without being explicitly mentioned exert a subtle and cumulative influence on the CoT that persists even if the hint is removed. Overall, studying distributions via resampling enables reliable causal analysis, clearer narratives of model reasoning, and principled CoT interventions.

---

### NAUTILUS: A Large Multimodal Model for Underwater Scene Understanding

Authors: Wei Xu, Cheng Wang, Dingkang Liang, Zongchuang Zhao, Xingyu Jiang, Peng Zhang, Xiang Bai
Published: 2025-10-31
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.27481v1

Underwater exploration offers critical insights into our planet and attracts increasing attention for its broader applications in resource exploration, national security, etc. We study the underwater scene understanding methods, which aim to achieve automated underwater exploration. The underwater scene understanding task demands multi-task perceptions from multiple granularities. However, the absence of large-scale underwater multi-task instruction-tuning datasets hinders the progress of this research. To bridge this gap, we construct NautData, a dataset containing 1.45 M image-text pairs supporting eight underwater scene understanding tasks. It enables the development and thorough evaluation of the underwater scene understanding models. Underwater image degradation is a widely recognized challenge that interferes with underwater tasks. To improve the robustness of underwater scene understanding, we introduce physical priors derived from underwater imaging models and propose a plug-and-play vision feature enhancement (VFE) module, which explicitly restores clear underwater information. We integrate this module into renowned baselines LLaVA-1.5 and Qwen2.5-VL and build our underwater LMM, NAUTILUS. Experiments conducted on the NautData and public underwater datasets demonstrate the effectiveness of the VFE module, consistently improving the performance of both baselines on the majority of supported tasks, thus ensuring the superiority of NAUTILUS in the underwater scene understanding area. Data and models are available at https://github.com/H-EmbodVis/NAUTILUS.

---

### Simplex-to-Euclidean Bijections for Categorical Flow Matching

Authors: Bernardo Williams, Victor M. Yeom-Song, Marcelo Hartmann, Arto Klami
Published: 2025-10-31
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.27480v2

We propose a method for learning and sampling from probability distributions supported on the simplex. Our approach maps the open simplex to Euclidean space via smooth bijections, leveraging the Aitchison geometry to define the mappings, and supports modeling categorical data by a Dirichlet interpolation that dequantizes discrete observations into continuous ones. This enables density modeling in Euclidean space through the bijection while still allowing exact recovery of the original discrete distribution. Compared to previous methods that operate on the simplex using Riemannian geometry or custom noise processes, our approach works in Euclidean space while respecting the Aitchison geometry, and achieves competitive performance on both synthetic and real-world data sets.

---

### The aftermath of compounds: Investigating Compounds and their Semantic Representations

Authors: Swarang Joshi
Published: 2025-10-31
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.27477v1

This study investigates how well computational embeddings align with human semantic judgments in the processing of English compound words. We compare static word vectors (GloVe) and contextualized embeddings (BERT) against human ratings of lexeme meaning dominance (LMD) and semantic transparency (ST) drawn from a psycholinguistic dataset. Using measures of association strength (Edinburgh Associative Thesaurus), frequency (BNC), and predictability (LaDEC), we compute embedding-derived LMD and ST metrics and assess their relationships with human judgments via Spearmans correlation and regression analyses. Our results show that BERT embeddings better capture compositional semantics than GloVe, and that predictability ratings are strong predictors of semantic transparency in both human and model data. These findings advance computational psycholinguistics by clarifying the factors that drive compound word processing and offering insights into embedding-based semantic modeling.

---

### Referee: Reference-aware Audiovisual Deepfake Detection

Authors: Hyemin Boo, Eunsang Lee, Jiyoung Lee
Published: 2025-10-31
Categories: cs.CV, cs.MM
arXiv: https://arxiv.org/abs/2510.27475v2

Deepfakes generated by advanced generative models have rapidly posed serious threats, yet existing audiovisual deepfake detection approaches struggle to generalize to unseen manipulation methods. To address this, we propose a novel reference-aware audiovisual deepfake detection method, called Referee to capture fine-grained identity discrepancies. Unlike existing methods that overfit to transient spatiotemporal artifacts, Referee employs identity bottleneck and matching modules to model the relational consistency of speaker-specific cues captured by a single one-shot example as a biometric anchor. Extensive experiments on FakeAVCeleb, FaceForensics++, and KoDF demonstrate that Referee achieves state-of-the-art results on cross-dataset and cross-language evaluation protocols, including a 99.4% AUC on KoDF. These results highlight that explicitly correlating reference-based biometric priors is a key frontier for achieving generalized and reliable audiovisual forensics. The code is available at https://github.com/ewha-mmai/referee.

---

### Spectral Neural Graph Sparsification

Authors: Angelica Liguori, Ettore Ritacco, Pietro Sabatino, Annalisa Socievole
Published: 2025-10-31
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.27474v1

Graphs are central to modeling complex systems in domains such as social networks, molecular chemistry, and neuroscience. While Graph Neural Networks, particularly Graph Convolutional Networks, have become standard tools for graph learning, they remain constrained by reliance on fixed structures and susceptibility to over-smoothing. We propose the Spectral Preservation Network, a new framework for graph representation learning that generates reduced graphs serving as faithful proxies of the original, enabling downstream tasks such as community detection, influence propagation, and information diffusion at a reduced computational cost. The Spectral Preservation Network introduces two key components: the Joint Graph Evolution layer and the Spectral Concordance loss. The former jointly transforms both the graph topology and the node feature matrix, allowing the structure and attributes to evolve adaptively across layers and overcoming the rigidity of static neighborhood aggregation. The latter regularizes these transformations by enforcing consistency in both the spectral properties of the graph and the feature vectors of the nodes. We evaluate the effectiveness of Spectral Preservation Network on node-level sparsification by analyzing well-established metrics and benchmarking against state-of-the-art methods. The experimental results demonstrate the superior performance and clear advantages of our approach.

---

### Diffuse Thinking: Exploring Diffusion Language Models as Efficient Thought Proposers for Reasoning

Authors: Chenyang Shao, Sijian Ren, Fengli Xu, Yong Li
Published: 2025-10-31
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.27469v1

In recent years, large language models (LLMs) have witnessed remarkable advancements, with the test-time scaling law consistently enhancing the reasoning capabilities. Through systematic evaluation and exploration of a diverse spectrum of intermediate thoughts, LLMs demonstrate the potential to generate deliberate reasoning steps, thereby substantially enhancing reasoning accuracy. However, LLMs' autoregressive generation paradigm results in reasoning performance scaling sub-optimally with test-time computation, often requiring excessive computational overhead to propose thoughts while yielding only marginal performance gains. In contrast, diffusion language models (DLMs) can efficiently produce diverse samples through parallel denoising in a single forward pass, inspiring us to leverage them for proposing intermediate thoughts, thereby alleviating the computational burden associated with autoregressive generation while maintaining quality. In this work, we propose an efficient collaborative reasoning framework, leveraging DLMs to generate candidate thoughts and LLMs to evaluate their quality. Experiments across diverse benchmarks demonstrate that our framework achieves strong performance in complex reasoning tasks, offering a promising direction for future research. Our code is open-source at https://anonymous.4open.science/r/Diffuse-Thinking-EC60.

---

### VCORE: Variance-Controlled Optimization-based Reweighting for Chain-of-Thought Supervision

Authors: Xuan Gong, Senmiao Wang, Hanbo Huang, Ruoyu Sun, Shiyu Liang
Published: 2025-10-31
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.27462v2

Supervised fine-tuning (SFT) on long chain-of-thought (CoT) trajectories has emerged as a crucial technique for enhancing the reasoning abilities of large language models (LLMs). However, the standard cross-entropy loss treats all tokens equally, ignoring their heterogeneous contributions across a reasoning trajectory. This uniform treatment leads to misallocated supervision and weak generalization, especially in complex, long-form reasoning tasks. To address this, we introduce \textbf{V}ariance-\textbf{C}ontrolled \textbf{O}ptimization-based \textbf{RE}weighting (VCORE), a principled framework that reformulates CoT supervision as a constrained optimization problem. By adopting an optimization-theoretic perspective, VCORE enables a principled and adaptive allocation of supervision across tokens, thereby aligning the training objective more closely with the goal of robust reasoning generalization. Empirical evaluations demonstrate that VCORE achieves the strongest overall average performance, with especially clear gains on lower-capacity models. Across both in-domain and out-of-domain settings, VCORE achieves substantial performance gains on mathematical and coding benchmarks, using models from the Qwen3 series (4B, 8B, 32B) and LLaMA-3.1-8B-Instruct. Moreover, we show that VCORE serves as a more effective initialization for subsequent reinforcement learning, establishing a stronger foundation for advancing the reasoning capabilities of LLMs. The Code will be released at https://github.com/coder-gx/VCORE.

---

### A Multi-tiered Human-in-the-loop Approach for Interactive School Mapping Using Earth Observation and Machine Learning

Authors: Casper Fibaek, Abi Riley, Kelsey Doerksen, Do-Hyung Kim, Rochelle Schneider
Published: 2025-10-31
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.27460v1

This paper presents a multi-tiered human-in-the-loop framework for interactive school mapping designed to improve the accuracy and completeness of educational facility records, particularly in developing regions where such data may be scarce and infrequently updated. The first tier involves a machine learning based analysis of population density, land cover, and existing infrastructure compared with known school locations. The first tier identifies potential gaps and "mislabelled" schools. In subsequent tiers, medium-resolution satellite imagery (Sentinel-2) is investigated to pinpoint regions with a high likelihood of school presence, followed by the application of very high-resolution (VHR) imagery and deep learning models to generate detailed candidate locations for schools within these prioritised areas. The medium-resolution approach was later removed due to insignificant improvements. The medium and VHR resolution models build upon global pre-trained steps to improve generalisation. A key component of the proposed approach is an interactive interface to allow human operators to iteratively review, validate, and refine the mapping results. Preliminary evaluations indicate that the multi-tiered strategy provides a scalable and cost-effective solution for educational infrastructure mapping to support planning and resource allocation.

---

### From Pixels to Paths: A Multi-Agent Framework for Editable Scientific Illustration

Authors: Jianwen Sun, Fanrui Zhang, Yukang Feng, Chuanhao Li, Zizhen Li, Jiaxin Ai, Yifan Chang, Yu Dai, Kaipeng Zhang
Published: 2025-10-31
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.27452v1

Scientific illustrations demand both high information density and post-editability. However, current generative models have two major limitations: Frist, image generation models output rasterized images lacking semantic structure, making it impossible to access, edit, or rearrange independent visual components in the images. Second, code-based generation methods (TikZ or SVG), although providing element-level control, force users into the cumbersome cycle of "writing-compiling-reviewing" and lack the intuitiveness of manipulation. Neither of these two approaches can well meet the needs for efficiency, intuitiveness, and iterative modification in scientific creation. To bridge this gap, we introduce VisPainter, a multi-agent framework for scientific illustration built upon the model context protocol. VisPainter orchestrates three specialized modules-a Manager, a Designer, and a Toolbox-to collaboratively produce diagrams compatible with standard vector graphics software. This modular, role-based design allows each element to be explicitly represented and manipulated, enabling true element-level control and any element can be added and modified later. To systematically evaluate the quality of scientific illustrations, we introduce VisBench, a benchmark with seven-dimensional evaluation metrics. It assesses high-information-density scientific illustrations from four aspects: content, layout, visual perception, and interaction cost. To this end, we conducted extensive ablation experiments to verify the rationality of our architecture and the reliability of our evaluation methods. Finally, we evaluated various vision-language models, presenting fair and credible model rankings along with detailed comparisons of their respective capabilities. Additionally, we isolated and quantified the impacts of role division, step control,and description on the quality of illustrations.

---

### GeoFM: Enhancing Geometric Reasoning of MLLMs via Synthetic Data Generation through Formal Language

Authors: Yuhao Zhang, Dingxin Hu, Tinghao Yu, Hao Liu, Yiting Liu
Published: 2025-10-31
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.27448v1

Multi-modal Large Language Models (MLLMs) have gained significant attention in both academia and industry for their capabilities in handling multi-modal tasks. However, these models face challenges in mathematical geometric reasoning due to the scarcity of high-quality geometric data. To address this issue, synthetic geometric data has become an essential strategy. Current methods for generating synthetic geometric data involve rephrasing or expanding existing problems and utilizing predefined rules and templates to create geometric images and problems. However, these approaches often produce data that lacks diversity or is prone to noise. Additionally, the geometric images synthesized by existing methods tend to exhibit limited variation and deviate significantly from authentic geometric diagrams. To overcome these limitations, we propose GeoFM, a novel method for synthesizing geometric data. GeoFM uses formal languages to explore combinations of conditions within metric space, generating high-fidelity geometric problems that differ from the originals while ensuring correctness through a symbolic engine. Experimental results show that our synthetic data significantly outperforms existing methods. The model trained with our data surpass the proprietary GPT-4o model by 18.7\% on geometry problem-solving tasks in MathVista and by 16.5\% on GeoQA. Additionally, it exceeds the performance of a leading open-source model by 5.7\% on MathVista and by 2.7\% on GeoQA.

---

### MVeLMA: Multimodal Vegetation Loss Modeling Architecture for Predicting Post-fire Vegetation Loss

Authors: Meenu Ravi, Shailik Sarkar, Yanshen Sun, Vaishnavi Singh, Chang-Tien Lu
Published: 2025-10-31
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.27443v1

Understanding post-wildfire vegetation loss is critical for developing effective ecological recovery strategies and is often challenging due to the extended time and effort required to capture the evolving ecosystem features. Recent works in this area have not fully explored all the contributing factors, their modalities, and interactions with each other. Furthermore, most research in this domain is limited by a lack of interpretability in predictive modeling, making it less useful in real-world settings. In this work, we propose a novel end-to-end ML pipeline called MVeLMA (\textbf{M}ultimodal \textbf{Ve}getation \textbf{L}oss \textbf{M}odeling \textbf{A}rchitecture) to predict county-wise vegetation loss from fire events. MVeLMA uses a multimodal feature integration pipeline and a stacked ensemble-based architecture to capture different modalities while also incorporating uncertainty estimation through probabilistic modeling. Through comprehensive experiments, we show that our model outperforms several state-of-the-art (SOTA) and baseline models in predicting post-wildfire vegetation loss. Furthermore, we generate vegetation loss confidence maps to identify high-risk counties, thereby helping targeted recovery efforts. The findings of this work have the potential to inform future disaster relief planning, ecological policy development, and wildlife recovery management.

---

### CoMViT: An Efficient Vision Backbone for Supervised Classification in Medical Imaging

Authors: Aon Safdar, Mohamed Saadeldin
Published: 2025-10-31
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.27442v1

Vision Transformers (ViTs) have demonstrated strong potential in medical imaging; however, their high computational demands and tendency to overfit on small datasets limit their applicability in real-world clinical scenarios. In this paper, we present CoMViT, a compact and generalizable Vision Transformer architecture optimized for resource-constrained medical image analysis. CoMViT integrates a convolutional tokenizer, diagonal masking, dynamic temperature scaling, and pooling-based sequence aggregation to improve performance and generalization. Through systematic architectural optimization, CoMViT achieves robust performance across twelve MedMNIST datasets while maintaining a lightweight design with only ~4.5M parameters. It matches or outperforms deeper CNN and ViT variants, offering up to 5-20x parameter reduction without sacrificing accuracy. Qualitative Grad-CAM analyses show that CoMViT consistently attends to clinically relevant regions despite its compact size. These results highlight the potential of principled ViT redesign for developing efficient and interpretable models in low-resource medical imaging settings.

---

### Self-Diffusion Driven Blind Imaging

Authors: Yanlong Yang, Guanxiong Luo
Published: 2025-10-31
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.27439v2

Optical imaging systems are inherently imperfect due to diffraction limits, lens manufacturing tolerances, assembly misalignment, and other physical constraints. In addition, unavoidable camera shake and object motion further introduce non-ideal degradations during acquisition. These aberrations and motion-induced variations are typically unknown, difficult to measure, and costly to model or calibrate in practice. Blind inverse problems offer a promising direction by jointly estimating both the latent image and the unknown degradation kernel. However, existing approaches often suffer from convergence instability, limited prior expressiveness, and sensitivity to hyperparameters. Inspired by recent advances in self-diffusion, we propose DeblurSDI, a zero-shot, self-supervised blind imaging framework that requires no pre-training. DeblurSDI formulates blind image recovery as an iterative reverse self-diffusion process that begins from pure noise and progressively refines both the sharp image and the blur kernel. Extensive experiments on combined optical aberrations and motion blur demonstrate that DeblurSDI consistently outperforms other methods by a substantial margin.

---

### Exploiting heterogeneous delays for efficient computation in low-bit neural networks

Authors: Pengfei Sun, Jascha Achterberg, Zhe Su, Dan F. M. Goodman, Danyal Akarca
Published: 2025-10-31
Categories: cs.NE
arXiv: https://arxiv.org/abs/2510.27434v1

Neural networks rely on learning synaptic weights. However, this overlooks other neural parameters that can also be learned and may be utilized by the brain. One such parameter is the delay: the brain exhibits complex temporal dynamics with heterogeneous delays, where signals are transmitted asynchronously between neurons. It has been theorized that this delay heterogeneity, rather than a cost to be minimized, can be exploited in embodied contexts where task-relevant information naturally sits contextually in the time domain. We test this hypothesis by training spiking neural networks to modify not only their weights but also their delays at different levels of precision. We find that delay heterogeneity enables state-of-the-art performance on temporally complex neuromorphic problems and can be achieved even when weights are extremely imprecise (1.58-bit ternary precision: just positive, negative, or absent). By enabling high performance with extremely low-precision weights, delay heterogeneity allows memory-efficient solutions that maintain state-of-the-art accuracy even when weights are compressed over an order of magnitude more aggressively than typically studied weight-only networks. We show how delays and time-constants adaptively trade-off, and reveal through ablation that task performance depends on task-appropriate delay distributions, with temporally-complex tasks requiring longer delays. Our results suggest temporal heterogeneity is an important principle for efficient computation, particularly when task-relevant information is temporal - as in the physical world - with implications for embodied intelligent systems and neuromorphic hardware.

---

### Mitigating Semantic Collapse in Partially Relevant Video Retrieval

Authors: WonJun Moon, MinSeok Jung, Gilhan Park, Tae-Young Kim, Cheol-Ho Cho, Woojin Jun, Jae-Pil Heo
Published: 2025-10-31
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.27432v1

Partially Relevant Video Retrieval (PRVR) seeks videos where only part of the content matches a text query. Existing methods treat every annotated text-video pair as a positive and all others as negatives, ignoring the rich semantic variation both within a single video and across different videos. Consequently, embeddings of both queries and their corresponding video-clip segments for distinct events within the same video collapse together, while embeddings of semantically similar queries and segments from different videos are driven apart. This limits retrieval performance when videos contain multiple, diverse events. This paper addresses the aforementioned problems, termed as semantic collapse, in both the text and video embedding spaces. We first introduce Text Correlation Preservation Learning, which preserves the semantic relationships encoded by the foundation model across text queries. To address collapse in video embeddings, we propose Cross-Branch Video Alignment (CBVA), a contrastive alignment method that disentangles hierarchical video representations across temporal scales. Subsequently, we introduce order-preserving token merging and adaptive CBVA to enhance alignment by producing video segments that are internally coherent yet mutually distinctive. Extensive experiments on PRVR benchmarks demonstrate that our framework effectively prevents semantic collapse and substantially improves retrieval accuracy.

---

### Learning Soft Robotic Dynamics with Active Exploration

Authors: Hehui Zheng, Bhavya Sukhija, Chenhao Li, Klemens Iten, Andreas Krause, Robert K. Katzschmann
Published: 2025-10-31
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2510.27428v1

Soft robots offer unmatched adaptability and safety in unstructured environments, yet their compliant, high-dimensional, and nonlinear dynamics make modeling for control notoriously difficult. Existing data-driven approaches often fail to generalize, constrained by narrowly focused task demonstrations or inefficient random exploration. We introduce SoftAE, an uncertainty-aware active exploration framework that autonomously learns task-agnostic and generalizable dynamics models of soft robotic systems. SoftAE employs probabilistic ensemble models to estimate epistemic uncertainty and actively guides exploration toward underrepresented regions of the state-action space, achieving efficient coverage of diverse behaviors without task-specific supervision. We evaluate SoftAE on three simulated soft robotic platforms -- a continuum arm, an articulated fish in fluid, and a musculoskeletal leg with hybrid actuation -- and on a pneumatically actuated continuum soft arm in the real world. Compared with random exploration and task-specific model-based reinforcement learning, SoftAE produces more accurate dynamics models, enables superior zero-shot control on unseen tasks, and maintains robustness under sensing noise, actuation delays, and nonlinear material effects. These results demonstrate that uncertainty-driven active exploration can yield scalable, reusable dynamics models across diverse soft robotic morphologies, representing a step toward more autonomous, adaptable, and data-efficient control in compliant robots.

---

### Who Does Your Algorithm Fail? Investigating Age and Ethnic Bias in the MAMA-MIA Dataset

Authors: Aditya Parikh, Sneha Das, Aasa Feragen
Published: 2025-10-31
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.27421v1

Deep learning models aim to improve diagnostic workflows, but fairness evaluation remains underexplored beyond classification, e.g., in image segmentation. Unaddressed segmentation bias can lead to disparities in the quality of care for certain populations, potentially compounded across clinical decision points and amplified through iterative model development. Here, we audit the fairness of the automated segmentation labels provided in the breast cancer tumor segmentation dataset MAMA-MIA. We evaluate automated segmentation quality across age, ethnicity, and data source. Our analysis reveals an intrinsic age-related bias against younger patients that continues to persist even after controlling for confounding factors, such as data source. We hypothesize that this bias may be linked to physiological factors, a known challenge for both radiologists and automated systems. Finally, we show how aggregating data from multiple data sources influences site-specific ethnic biases, underscoring the necessity of investigating data at a granular level.

---

### DeepCompress: A Dual Reward Strategy for Dynamically Exploring and Compressing Reasoning Chains

Authors: Tian Liang, Wenxiang Jiao, Zhiwei He, Jiahao Xu, Haitao Mi, Dong Yu
Published: 2025-10-31
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.27419v2

Large Reasoning Models (LRMs) have demonstrated impressive capabilities but suffer from cognitive inefficiencies like "overthinking" simple problems and "underthinking" complex ones. While existing methods that use supervised fine-tuning (SFT) or reinforcement learning (RL) with token-length rewards can improve efficiency, they often do so at the cost of accuracy. This paper introduces DeepCompress, a novel framework that simultaneously enhances both the accuracy and efficiency of LRMs. We challenge the prevailing approach of consistently favoring shorter reasoning paths, showing that longer responses can contain a broader range of correct solutions for difficult problems. DeepCompress employs an adaptive length reward mechanism that dynamically classifies problems as "Simple" or "Hard" in real-time based on the model's evolving capability. It encourages shorter, more efficient reasoning for "Simple" problems while promoting longer, more exploratory thought chains for "Hard" problems. This dual-reward strategy enables the model to autonomously adjust its Chain-of-Thought (CoT) length, compressing reasoning for well-mastered problems and extending it for those it finds challenging. Experimental results on challenging mathematical benchmarks show that DeepCompress consistently outperforms baseline methods, achieving superior accuracy while significantly improving token efficiency.

---

### Dynamic Affective Memory Management for Personalized LLM Agents

Authors: Junfeng Lu, Yueyan Li
Published: 2025-10-31
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.27418v1

Advances in large language models are making personalized AI agents a new research focus. While current agent systems primarily rely on personalized external memory databases to deliver customized experiences, they face challenges such as memory redundancy, memory staleness, and poor memory-context integration, largely due to the lack of effective memory updates during interaction. To tackle these issues, we propose a new memory management system designed for affective scenarios. Our approach employs a Bayesian-inspired memory update algorithm with the concept of memory entropy, enabling the agent to autonomously maintain a dynamically updated memory vector database by minimizing global entropy to provide more personalized services. To better evaluate the system's effectiveness in this context, we propose DABench, a benchmark focusing on emotional expression and emotional change toward objects. Experimental results demonstrate that, our system achieves superior performance in personalization, logical coherence, and accuracy. Ablation studies further validate the effectiveness of the Bayesian-inspired update mechanism in alleviating memory bloat. Our work offers new insights into the design of long-term memory systems.

---

### Atlas-Alignment: Making Interpretability Transferable Across Language Models

Authors: Bruno Puri, Jim Berend, Sebastian Lapuschkin, Wojciech Samek
Published: 2025-10-31
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.27413v2

Interpretability is crucial for building safe, reliable, and controllable language models, yet existing interpretability pipelines remain costly and difficult to scale. Interpreting a new model typically requires training model-specific components (e.g., sparse autoencoders), followed by manual or semi-automated labeling and validation, imposing a growing "transparency tax" that does not scale with the pace of model development. We introduce Atlas-Alignment, a framework that avoids this cost by aligning the latent space of a new model to a pre-existing, labeled Concept Atlas using only shared inputs and lightweight representational alignment methods. Through quantitative and qualitative evaluations, we show that simple alignment methods enable robust semantic retrieval and steerable generation without the need for labeled concept datasets. Atlas-Alignment thus amortizes the cost of explainable AI and mechanistic interpretability: by investing in a single high-quality Concept Atlas, we can make many new models transparent and controllable at minimal marginal cost.

---

### Closing the Expression Gap in LLM Instructions via Socratic Questioning

Authors: Jianwen Sun, Yukang Feng, Yifan Chang, Chuanhao Li, Zizhen Li, Jiaxin Ai, Fanrui Zhang, Yu Dai, Kaipeng Zhang
Published: 2025-10-31
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.27410v3

A fundamental bottleneck in human-AI collaboration is the ``intention expression gap," the difficulty for humans to effectively convey complex, high-dimensional thoughts to AI. This challenge often traps users in inefficient trial-and-error loops and is exacerbated by the diverse expertise levels of users. We reframe this problem from passive instruction following to a Socratic collaboration paradigm, proposing an agent that actively probes for information to resolve its uncertainty about user intent. we name the proposed agent Nous, trained to acquire proficiency in this inquiry policy. The core mechanism of Nous is a training framework grounded in the first principles of information theory. Within this framework, we define the information gain from dialogue as an intrinsic reward signal, which is fundamentally equivalent to the reduction of Shannon entropy over a structured task space. This reward design enables us to avoid reliance on costly human preference annotations or external reward models. To validate our framework, we develop an automated simulation pipeline to generate a large-scale, preference-based dataset for the challenging task of scientific diagram generation. Comprehensive experiments, including ablations, subjective and objective evaluations, and tests across user expertise levels, demonstrate the effectiveness of our proposed framework. Nous achieves leading efficiency and output quality, while remaining robust to varying user expertise. In conclusion, our research provides a systematic methodology and a new perspective for addressing the issue of ambiguous intentions in complex human-machine collaboration.

---

### Estimation of aboveground biomass in a tropical dry forest: An intercomparison of airborne, unmanned, and space laser scanning

Authors: Nelson Mattié, Arturo Sanchez-Azofeifa, Pablo Crespo-Peremarch, Juan-Ygnacio López-Hernández
Published: 2025-10-31
Categories: eess.SP, cs.LG
arXiv: https://arxiv.org/abs/2510.27408v4

According to the Paris Climate Change Agreement, all nations are required to submit reports on their greenhouse gas emissions and absorption every two years by 2024. Consequently, forests play a crucial role in reducing carbon emissions, which is essential for meeting these obligations. Recognizing the significance of forest conservation in the global battle against climate change, Article 5 of the Paris Agreement emphasizes the need for high-quality forest data. This study focuses on enhancing methods for mapping aboveground biomass in tropical dry forests. Tropical dry forests are considered one of the least understood tropical forest environments; therefore, there is a need for accurate approaches to estimate carbon pools. We employ a comparative analysis of AGB estimates, utilizing different discrete and full-waveform laser scanning datasets in conjunction with Ordinary Least Squares and Bayesian approaches SVM. Airborne Laser Scanning, Unmanned Laser Scanning, and Space Laser Scanning were used as independent variables for extracting forest metrics. Variable selection, SVM regression tuning, and cross-validation via a machine-learning approach were applied to account for overfitting and underfitting. The results indicate that six key variables primarily related to tree height: Elevminimum, ElevL3, levMADmode, Elevmode, ElevMADmedian, and Elevskewness, are important for AGB estimation using ALSD and ULSD, while Leaf Area Index, canopy coverage and height, terrain elevation, and full-waveform signal energy emerged as the most vital variables. AGB values estimated from ten permanent tropical dry forest plots in Costa Rica Guanacaste province ranged from 26.02 Mg/ha to 175.43 Mg/ha. The SVM regressions demonstrated a 17.89 error across all laser scanning systems, with SLSF W exhibiting the lowest error 17.07 in estimating total biomass per plot.

---

### Awal -- Community-Powered Language Technology for Tamazight

Authors: Alp Öktem, Farida Boudichat
Published: 2025-10-31
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.27407v1

This paper presents Awal, a community-powered initiative for developing language technology resources for Tamazight. We provide a comprehensive review of the NLP landscape for Tamazight, examining recent progress in computational resources, and the emergence of community-driven approaches to address persistent data scarcity. Launched in 2024, awaldigital.org platform addresses the underrepresentation of Tamazight in digital spaces through a collaborative platform enabling speakers to contribute translation and voice data. We analyze 18 months of community engagement, revealing significant barriers to participation including limited confidence in written Tamazight and ongoing standardization challenges. Despite widespread positive reception, actual data contribution remained concentrated among linguists and activists. The modest scale of community contributions -- 6,421 translation pairs and 3 hours of speech data -- highlights the limitations of applying standard crowdsourcing approaches to languages with complex sociolinguistic contexts. We are working on improved open-source MT models using the collected data.

---

### FedMuon: Accelerating Federated Learning with Matrix Orthogonalization

Authors: Junkang Liu, Fanhua Shang, Junchao Zhou, Hongying Liu, Yuanyuan Liu, Jin Liu
Published: 2025-10-31
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.27403v1

The core bottleneck of Federated Learning (FL) lies in the communication rounds. That is, how to achieve more effective local updates is crucial for reducing communication rounds. Existing FL methods still primarily use element-wise local optimizers (Adam/SGD), neglecting the geometric structure of the weight matrices. This often leads to the amplification of pathological directions in the weights during local updates, leading deterioration in the condition number and slow convergence. Therefore, we introduce the Muon optimizer in local, which has matrix orthogonalization to optimize matrix-structured parameters. Experimental results show that, in IID setting, Local Muon significantly accelerates the convergence of FL and reduces communication rounds compared to Local SGD and Local AdamW. However, in non-IID setting, independent matrix orthogonalization based on the local distributions of each client induces strong client drift. Applying Muon in non-IID FL poses significant challenges: (1) client preconditioner leading to client drift; (2) moment reinitialization. To address these challenges, we propose a novel Federated Muon optimizer (FedMuon), which incorporates two key techniques: (1) momentum aggregation, where clients use the aggregated momentum for local initialization; (2) local-global alignment, where the local gradients are aligned with the global update direction to significantly reduce client drift. Theoretically, we prove that \texttt{FedMuon} achieves a linear speedup convergence rate without the heterogeneity assumption, where $S$ is the number of participating clients per round, $K$ is the number of local iterations, and $R$ is the total number of communication rounds. Empirically, we validate the effectiveness of FedMuon on language and vision models. Compared to several baselines, FedMuon significantly reduces communication rounds and improves test accuracy.

---

### Balancing Knowledge Updates: Toward Unified Modular Editing in LLMs

Authors: Jiahao Liu, Zijian Wang, Kuo Zhao, Dong Hu
Published: 2025-10-31
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.27400v1

Knowledge editing has emerged as an efficient approach for updating factual knowledge in large language models (LLMs). It typically locates knowledge storage modules and then modifies their parameters. However, most existing methods focus on the weights of multilayer perceptron (MLP) modules, which are often identified as the main repositories of factual information. Other components, such as attention (Attn) modules, are often ignored during editing. This imbalance can leave residual outdated knowledge and limit editing effectiveness. We perform comprehensive knowledge localization experiments on advanced LLMs and find that Attn modules play a substantial role in factual knowledge storage and retrieval, especially in earlier layers. Based on these insights, we propose IntAttn-Edit, a method that extends the associative memory paradigm to jointly update both MLP and Attn modules. Our approach uses a knowledge balancing strategy that allocates update magnitudes in proportion to each module's measured contribution to knowledge storage. Experiments on standard benchmarks show that IntAttn-Edit achieves higher edit success, better generalization, and stronger knowledge preservation than prior methods. Further analysis shows that the balancing strategy keeps editing performance within an optimal range across diverse settings.

---

### Interpretable Model-Aware Counterfactual Explanations for Random Forest

Authors: Joshua S. Harvey, Guanchao Feng, Sai Anusha Meesala, Tina Zhao, Dhagash Mehta
Published: 2025-10-31
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.27397v1

Despite their enormous predictive power, machine learning models are often unsuitable for applications in regulated industries such as finance, due to their limited capacity to provide explanations. While model-agnostic frameworks such as Shapley values have proved to be convenient and popular, they rarely align with the kinds of causal explanations that are typically sought after. Counterfactual case-based explanations, where an individual is informed of which circumstances would need to be different to cause a change in outcome, may be more intuitive and actionable. However, finding appropriate counterfactual cases is an open challenge, as is interpreting which features are most critical for the change in outcome. Here, we pose the question of counterfactual search and interpretation in terms of similarity learning, exploiting the representation learned by the random forest predictive model itself. Once a counterfactual is found, the feature importance of the explanation is computed as a function of which random forest partitions are crossed in order to reach it from the original instance. We demonstrate this method on both the MNIST hand-drawn digit dataset and the German credit dataset, finding that it generates explanations that are sparser and more useful than Shapley values.

---

### A Hybrid Deep Learning and Forensic Approach for Robust Deepfake Detection

Authors: Sales Aribe
Published: 2025-10-31
Categories: cs.CV, cs.NE
arXiv: https://arxiv.org/abs/2510.27392v1

The rapid evolution of generative adversarial networks (GANs) and diffusion models has made synthetic media increasingly realistic, raising societal concerns around misinformation, identity fraud, and digital trust. Existing deepfake detection methods either rely on deep learning, which suffers from poor generalization and vulnerability to distortions, or forensic analysis, which is interpretable but limited against new manipulation techniques. This study proposes a hybrid framework that fuses forensic features, including noise residuals, JPEG compression traces, and frequency-domain descriptors, with deep learning representations from convolutional neural networks (CNNs) and vision transformers (ViTs). Evaluated on benchmark datasets (FaceForensics++, Celeb-DF v2, DFDC), the proposed model consistently outperformed single-method baselines and demonstrated superior performance compared to existing state-of-the-art hybrid approaches, achieving F1-scores of 0.96, 0.82, and 0.77, respectively. Robustness tests demonstrated stable performance under compression (F1 = 0.87 at QF = 50), adversarial perturbations (AUC = 0.84), and unseen manipulations (F1 = 0.79). Importantly, explainability analysis showed that Grad-CAM and forensic heatmaps overlapped with ground-truth manipulated regions in 82 percent of cases, enhancing transparency and user trust. These findings confirm that hybrid approaches provide a balanced solution, combining the adaptability of deep models with the interpretability of forensic cues, to develop resilient and trustworthy deepfake detection systems.

---

### Modality Alignment across Trees on Heterogeneous Hyperbolic Manifolds

Authors: Wei Wu, Xiaomeng Fan, Yuwei Wu, Zhi Gao, Pengxiang Li, Yunde Jia, Mehrtash Harandi
Published: 2025-10-31
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.27391v2

Modality alignment is critical for vision-language models (VLMs) to effectively integrate information across modalities. However, existing methods extract hierarchical features from text while representing each image with a single feature, leading to asymmetric and suboptimal alignment. To address this, we propose Alignment across Trees, a method that constructs and aligns tree-like hierarchical features for both image and text modalities. Specifically, we introduce a semantic-aware visual feature extraction framework that applies a cross-attention mechanism to visual class tokens from intermediate Transformer layers, guided by textual cues to extract visual features with coarse-to-fine semantics. We then embed the feature trees of the two modalities into hyperbolic manifolds with distinct curvatures to effectively model their hierarchical structures. To align across the heterogeneous hyperbolic manifolds with different curvatures, we formulate a KL distance measure between distributions on heterogeneous manifolds, and learn an intermediate manifold for manifold alignment by minimizing the distance. We prove the existence and uniqueness of the optimal intermediate manifold. Experiments on taxonomic open-set classification tasks across multiple image datasets demonstrate that our method consistently outperforms strong baselines under few-shot and cross-domain settings.

---

### On the Equivalence of Optimal Transport Problem and Action Matching with Optimal Vector Fields

Authors: Nikita Kornilov, Alexander Korotin
Published: 2025-10-31
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.27385v1

Flow Matching (FM) method in generative modeling maps arbitrary probability distributions by constructing an interpolation between them and then learning the vector field that defines ODE for this interpolation. Recently, it was shown that FM can be modified to map distributions optimally in terms of the quadratic cost function for any initial interpolation. To achieve this, only specific optimal vector fields, which are typical for solutions of Optimal Transport (OT) problems, need to be considered during FM loss minimization. In this note, we show that considering only optimal vector fields can lead to OT in another approach: Action Matching (AM). Unlike FM, which learns a vector field for a manually chosen interpolation between given distributions, AM learns the vector field that defines ODE for an entire given sequence of distributions.

---

### Realistic pedestrian-driver interaction modelling using multi-agent RL with human perceptual-motor constraints

Authors: Yueyang Wang, Mehmet Dogar, Gustav Markkula
Published: 2025-10-31
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.27383v1

Modelling pedestrian-driver interactions is critical for understanding human road user behaviour and developing safe autonomous vehicle systems. Existing approaches often rely on rule-based logic, game-theoretic models, or 'black-box' machine learning methods. However, these models typically lack flexibility or overlook the underlying mechanisms, such as sensory and motor constraints, which shape how pedestrians and drivers perceive and act in interactive scenarios. In this study, we propose a multi-agent reinforcement learning (RL) framework that integrates both visual and motor constraints of pedestrian and driver agents. Using a real-world dataset from an unsignalised pedestrian crossing, we evaluate four model variants, one without constraints, two with either motor or visual constraints, and one with both, across behavioural metrics of interaction realism. Results show that the combined model with both visual and motor constraints performs best. Motor constraints lead to smoother movements that resemble human speed adjustments during crossing interactions. The addition of visual constraints introduces perceptual uncertainty and field-of-view limitations, leading the agents to exhibit more cautious and variable behaviour, such as less abrupt deceleration. In this data-limited setting, our model outperforms a supervised behavioural cloning model, demonstrating that our approach can be effective without large training datasets. Finally, our framework accounts for individual differences by modelling parameters controlling the human constraints as population-level distributions, a perspective that has not been explored in previous work on pedestrian-vehicle interaction modelling. Overall, our work demonstrates that multi-agent RL with human constraints is a promising modelling approach for simulating realistic road user interactions.

---

### Spiking Neural Networks: The Future of Brain-Inspired Computing

Authors: Sales G. Aribe
Published: 2025-10-31
Categories: cs.NE, cs.AI
arXiv: https://arxiv.org/abs/2510.27379v1

Spiking Neural Networks (SNNs) represent the latest generation of neural computation, offering a brain-inspired alternative to conventional Artificial Neural Networks (ANNs). Unlike ANNs, which depend on continuous-valued signals, SNNs operate using distinct spike events, making them inherently more energy-efficient and temporally dynamic. This study presents a comprehensive analysis of SNN design models, training algorithms, and multi-dimensional performance metrics, including accuracy, energy consumption, latency, spike count, and convergence behavior. Key neuron models such as the Leaky Integrate-and-Fire (LIF) and training strategies, including surrogate gradient descent, ANN-to-SNN conversion, and Spike-Timing Dependent Plasticity (STDP), are examined in depth. Results show that surrogate gradient-trained SNNs closely approximate ANN accuracy (within 1-2%), with faster convergence by the 20th epoch and latency as low as 10 milliseconds. Converted SNNs also achieve competitive performance but require higher spike counts and longer simulation windows. STDP-based SNNs, though slower to converge, exhibit the lowest spike counts and energy consumption (as low as 5 millijoules per inference), making them optimal for unsupervised and low-power tasks. These findings reinforce the suitability of SNNs for energy-constrained, latency-sensitive, and adaptive applications such as robotics, neuromorphic vision, and edge AI systems. While promising, challenges persist in hardware standardization and scalable training. This study concludes that SNNs, with further refinement, are poised to propel the next phase of neuromorphic computing.

---

### Measuring Chain-of-Thought Monitorability Through Faithfulness and Verbosity

Authors: Austin Meek, Eitan Sprejer, Iván Arcuschin, Austin J. Brockmeier, Steven Basart
Published: 2025-10-31
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.27378v2

Chain-of-thought (CoT) outputs let us read a model's step-by-step reasoning. Since any long, serial reasoning process must pass through this textual trace, the quality of the CoT is a direct window into what the model is thinking. This visibility could help us spot unsafe or misaligned behavior (monitorability), but only if the CoT is transparent about its internal reasoning (faithfulness). Fully measuring faithfulness is difficult, so researchers often focus on examining the CoT in cases where the model changes its answer after adding a cue to the input. This proxy finds some instances of unfaithfulness but loses information when the model maintains its answer, and does not investigate aspects of reasoning not tied to the cue. We extend these results to a more holistic sense of monitorability by introducing verbosity: whether the CoT lists every factor needed to solve the task. We combine faithfulness and verbosity into a single monitorability score that shows how well the CoT serves as the model's external `working memory', a property that many safety schemes based on CoT monitoring depend on. We evaluate instruction-tuned and reasoning models on BBH, GPQA, and MMLU. Our results show that models can appear faithful yet remain hard to monitor when they leave out key factors, and that monitorability differs sharply across model families. We release our evaluation code using the Inspect library to support reproducible future work.

---

### From the Rock Floor to the Cloud: A Systematic Survey of State-of-the-Art NLP in Battery Life Cycle

Authors: Tosin Adewumi, Martin Karlsson, Marcus Liwicki, Mikael Sjödahl, Lama Alkhaled, Rihab Gargouri, Nudrat Habib, Franz Hennie
Published: 2025-10-31
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.27369v1

We present a comprehensive systematic survey of the application of natural language processing (NLP) along the entire battery life cycle, instead of one stage or method, and introduce a novel technical language processing (TLP) framework for the EU's proposed digital battery passport (DBP) and other general battery predictions. We follow the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) method and employ three reputable databases or search engines, including Google Scholar, Institute of Electrical and Electronics Engineers Xplore (IEEE Xplore), and Scopus. Consequently, we assessed 274 scientific papers before the critical review of the final 66 relevant papers. We publicly provide artifacts of the review for validation and reproducibility. The findings show that new NLP tasks are emerging in the battery domain, which facilitate materials discovery and other stages of the life cycle. Notwithstanding, challenges remain, such as the lack of standard benchmarks. Our proposed TLP framework, which incorporates agentic AI and optimized prompts, will be apt for tackling some of the challenges.

---

### Fine-Tuning Open Video Generators for Cinematic Scene Synthesis: A Small-Data Pipeline with LoRA and Wan2.1 I2V

Authors: Meftun Akarsu, Kerem Catay, Sedat Bin Vedat, Enes Kutay Yarkan, Ilke Senturk, Arda Sar, Dafne Eksioglu
Published: 2025-10-31
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.27364v1

We present a practical pipeline for fine-tuning open-source video diffusion transformers to synthesize cinematic scenes for television and film production from small datasets. The proposed two-stage process decouples visual style learning from motion generation. In the first stage, Low-Rank Adaptation (LoRA) modules are integrated into the cross-attention layers of the Wan2.1 I2V-14B model to adapt its visual representations using a compact dataset of short clips from Ay Yapim's historical television film El Turco. This enables efficient domain transfer within hours on a single GPU. In the second stage, the fine-tuned model produces stylistically consistent keyframes that preserve costume, lighting, and color grading, which are then temporally expanded into coherent 720p sequences through the model's video decoder. We further apply lightweight parallelization and sequence partitioning strategies to accelerate inference without quality degradation. Quantitative and qualitative evaluations using FVD, CLIP-SIM, and LPIPS metrics, supported by a small expert user study, demonstrate measurable improvements in cinematic fidelity and temporal stability over the base model. The complete training and inference pipeline is released to support reproducibility and adaptation across cinematic domains.

---

### ToolScope: An Agentic Framework for Vision-Guided and Long-Horizon Tool Use

Authors: Mengjie Deng, Guanting Dong, Zhicheng Dou
Published: 2025-10-31
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.27363v1

Recently, large language models (LLMs) have demonstrated remarkable problem-solving capabilities by autonomously integrating with external tools for collaborative reasoning. However, due to the inherently complex and diverse nature of multimodal information, enabling multimodal large language models (MLLMs) to flexibly and efficiently utilize external tools during reasoning remains an underexplored challenge. In this work, we introduce ToolScope, an agentic framework designed to unify global planning with local multimodal perception, adopting a specialized Perceive tool to mitigates visual context degradation in long-horizon VQA task. ToolScope comprises three primary components: the Global Navigator, the Agentic Executor, and the Response Synthesizer. The Global Navigator functions as a "telescope", offering high-level strategic guidance. The Agentic Executor operates iteratively to augment MLLM with local perception through the integration of external tools-Search, Code, and Perceive. Finally, the Response Synthesizer consolidates and organizes the reasoning process into a coherent, user-friendly output. We evaluate ToolScope on four VQA benchmarks across diverse domains, including VQA 2.0, ScienceQA, MAT-Search and MathVista. It demonstrates strong generalization capabilities, achieving an average performance improvement of up to +6.69% across all datasets.

---