# Research Papers — 2025-10 · bundle page 181 of 217

> Full-text markdown of papers #9001–9050 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/181
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/180.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/182.md)

### From Actions to Kinesics: Extracting Human Psychological States through Bodily Movements

Authors: Cheyu Lin, Katherine A. Flanigan
Published: 2025-10-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.04844v1

Understanding the dynamic relationship between humans and the built environment is a key challenge in disciplines ranging from environmental psychology to reinforcement learning (RL). A central obstacle in modeling these interactions is the inability to capture human psychological states in a way that is both generalizable and privacy preserving. Traditional methods rely on theoretical models or questionnaires, which are limited in scope, static, and labor intensive. We present a kinesics recognition framework that infers the communicative functions of human activity -- known as kinesics -- directly from 3D skeleton joint data. Combining a spatial-temporal graph convolutional network (ST-GCN) with a convolutional neural network (CNN), the framework leverages transfer learning to bypass the need for manually defined mappings between physical actions and psychological categories. The approach preserves user anonymity while uncovering latent structures in bodily movements that reflect cognitive and emotional states. Our results on the Dyadic User EngagemenT (DUET) dataset demonstrate that this method enables scalable, accurate, and human-centered modeling of behavior, offering a new pathway for enhancing RL-driven simulations of human-environment interaction.

---

### Distributionally Robust Causal Abstractions

Authors: Yorgos Felekis, Theodoros Damoulas, Paris Giampouras
Published: 2025-10-06
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.04842v3

Causal Abstraction (CA) theory provides a principled framework for relating causal models that describe the same system at different levels of granularity while ensuring interventional consistency between them. Recent methods for learning CAs, however, assume fixed and well-specified exogenous distributions, leaving them vulnerable to environmental shifts and model misspecification. In this work, we address these limitations by introducing the first class of distributionally robust CAs and their associated learning algorithms. The latter cast robust causal abstraction learning as a constrained min-max optimization problem with Wasserstein ambiguity sets. We provide theoretical guarantees for both empirical and Gaussian environments, enabling principled selection of ambiguity set radii and establish quantitative guarantees on worst-case abstraction error. Furthermore, we present empirical evidence across different problems and CA learning methods, demonstrating our framework's robustness not only to environmental shifts but also to structural and intervention mapping misspecification.

---

### Detailed Aerial Mapping of Photovoltaic Power Plants Through Semantically Significant Keypoints

Authors: Viktor Kozák, Jan Chudoba, Libor Přeučil
Published: 2025-10-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.04840v3

An accurate and up-to-date model of a photovoltaic (PV) power plant is essential for its optimal operation and maintenance. However, such a model may not be easily available. This work introduces a novel approach for PV power plant mapping based on aerial overview images. It enables the automation of the mapping process while removing the reliance on third-party data. The presented mapping method takes advantage of the structural layout of the power plants to achieve detailed modeling down to the level of individual PV modules. The approach relies on visual segmentation of PV modules in overview images and the inference of structural information in each image, assigning modules to individual benches, rows, and columns. We identify visual keypoints related to the layout and use these to merge detections from multiple images while maintaining their structural integrity. The presented method was experimentally verified and evaluated on two different power plants. The final fusion of 3D positions and semantic structures results in a compact georeferenced model suitable for power plant maintenance.

---

### Beyond Random: Automatic Inner-loop Optimization in Dataset Distillation

Authors: Muquan Li, Hang Gou, Dongyang Zhang, Shuang Liang, Xiurui Xie, Deqiang Ouyang, Ke Qin
Published: 2025-10-06
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.04838v2

The growing demand for efficient deep learning has positioned dataset distillation as a pivotal technique for compressing training dataset while preserving model performance. However, existing inner-loop optimization methods for dataset distillation typically rely on random truncation strategies, which lack flexibility and often yield suboptimal results. In this work, we observe that neural networks exhibit distinct learning dynamics across different training stages-early, middle, and late-making random truncation ineffective. To address this limitation, we propose Automatic Truncated Backpropagation Through Time (AT-BPTT), a novel framework that dynamically adapts both truncation positions and window sizes according to intrinsic gradient behavior. AT-BPTT introduces three key components: (1) a probabilistic mechanism for stage-aware timestep selection, (2) an adaptive window sizing strategy based on gradient variation, and (3) a low-rank Hessian approximation to reduce computational overhead. Extensive experiments on CIFAR-10, CIFAR-100, Tiny-ImageNet, and ImageNet-1K show that AT-BPTT achieves state-of-the-art performance, improving accuracy by an average of 6.16% over baseline methods. Moreover, our approach accelerates inner-loop optimization by 3.9x while saving 63% memory cost.

---

### Bond-Centered Molecular Fingerprint Derivatives: A BBBP Dataset Study

Authors: Guillaume Godin
Published: 2025-10-06
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.04837v1

Bond Centered FingerPrint (BCFP) are a complementary, bond-centric alternative to Extended-Connectivity Fingerprints (ECFP). We introduce a static BCFP that mirrors the bond-convolution used by directed message-passing GNNs like ChemProp, and evaluate it with a fast rapid Random Forest model on Brain-Blood Barrier Penetration (BBBP) classification task. Across stratified cross-validation, concatenating ECFP with BCFP consistently improves AUROC and AUPRC over either descriptor alone, as confirmed by Turkey HSD multiple-comparison analysis. Among radii, r = 1 performs best; r = 2 does not yield statistically separable gains under the same test. We further propose BCFP-Sort&Slice, a simple feature-combination scheme that preserves the out-of-vocabulary (OOV) count information native to ECFP count vectors while enabling compact unhashed concatenation of BCFP variants. We also outperform the MGTP prediction on our BBBP evaluation, using such composite new features bond and atom features. These results show that lightweight, bond-centered descriptors can complement atom-centered circular fingerprints and provide strong, fast baselines for BBBP prediction.

---

### On the Hardness of Learning Regular Expressions

Authors: Idan Attias, Lev Reyzin, Nathan Srebro, Gal Vardi
Published: 2025-10-06
Categories: cs.LG, cs.CC
arXiv: https://arxiv.org/abs/2510.04834v1

Despite the theoretical significance and wide practical use of regular expressions, the computational complexity of learning them has been largely unexplored. We study the computational hardness of improperly learning regular expressions in the PAC model and with membership queries. We show that PAC learning is hard even under the uniform distribution on the hypercube, and also prove hardness of distribution-free learning with membership queries. Furthermore, if regular expressions are extended with complement or intersection, we establish hardness of learning with membership queries even under the uniform distribution. We emphasize that these results do not follow from existing hardness results for learning DFAs or NFAs, since the descriptive complexity of regular languages can differ exponentially between DFAs, NFAs, and regular expressions.

---

### How I Built ASR for Endangered Languages with a Spoken Dictionary

Authors: Christopher Bartley, Anton Ragni
Published: 2025-10-06
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.04832v1

Nearly half of the world's languages are endangered. Speech technologies such as Automatic Speech Recognition (ASR) are central to revival efforts, yet most languages remain unsupported because standard pipelines expect utterance-level supervised data. Speech data often exist for endangered languages but rarely match these formats. Manx Gaelic ($\sim$2,200 speakers), for example, has had transcribed speech since 1948, yet remains unsupported by modern systems. In this paper, we explore how little data, and in what form, is needed to build ASR for critically endangered languages. We show that a short-form pronunciation resource is a viable alternative, and that 40 minutes of such data produces usable ASR for Manx ($<$50\% WER). We replicate our approach, applying it to Cornish ($\sim$600 speakers), another critically endangered language. Results show that the barrier to entry, in quantity and form, is far lower than previously thought, giving hope to endangered language communities that cannot afford to meet the requirements arbitrarily imposed upon them.

---

### Flow Matching for Conditional MRI-CT and CBCT-CT Image Synthesis

Authors: Arnela Hadzic, Simon Johannes Joham, Martin Urschler
Published: 2025-10-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.04823v2

Generating synthetic CT (sCT) from MRI or CBCT plays a crucial role in enabling MRI-only and CBCT-based adaptive radiotherapy, improving treatment precision while reducing patient radiation exposure. To address this task, we adopt a fully 3D Flow Matching (FM) framework, motivated by recent work demonstrating FM's efficiency in producing high-quality images. In our approach, a Gaussian noise volume is transformed into an sCT image by integrating a learned FM velocity field, conditioned on features extracted from the input MRI or CBCT using a lightweight 3D encoder. We evaluated the method on the SynthRAD2025 Challenge benchmark, training separate models for MRI to sCT and CBCT to sCT across three anatomical regions: abdomen, head and neck, and thorax. Validation and testing were performed through the challenge submission system. The results indicate that the method accurately reconstructs global anatomical structures; however, preservation of fine details was limited, primarily due to the relatively low training resolution imposed by memory and runtime constraints. Future work will explore patch-based training and latent-space flow models to improve resolution and local structural fidelity.

---

### AvatarVTON: 4D Virtual Try-On for Animatable Avatars

Authors: Zicheng Jiang, Jixin Gao, Shengfeng He, Xinzhe Li, Yulong Zheng, Zhaotong Yang, Junyu Dong, Yong Du
Published: 2025-10-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.04822v1

We propose AvatarVTON, the first 4D virtual try-on framework that generates realistic try-on results from a single in-shop garment image, enabling free pose control, novel-view rendering, and diverse garment choices. Unlike existing methods, AvatarVTON supports dynamic garment interactions under single-view supervision, without relying on multi-view garment captures or physics priors. The framework consists of two key modules: (1) a Reciprocal Flow Rectifier, a prior-free optical-flow correction strategy that stabilizes avatar fitting and ensures temporal coherence; and (2) a Non-Linear Deformer, which decomposes Gaussian maps into view-pose-invariant and view-pose-specific components, enabling adaptive, non-linear garment deformations. To establish a benchmark for 4D virtual try-on, we extend existing baselines with unified modules for fair qualitative and quantitative comparisons. Extensive experiments show that AvatarVTON achieves high fidelity, diversity, and dynamic garment realism, making it well-suited for AR/VR, gaming, and digital-human applications.

---

### Visual Representations inside the Language Model

Authors: Benlin Liu, Amita Kamath, Madeleine Grunde-McLaughlin, Winson Han, Ranjay Krishna
Published: 2025-10-06
Categories: cs.CV, cs.CL
arXiv: https://arxiv.org/abs/2510.04819v1

Despite interpretability work analyzing VIT encoders and transformer activations, we don't yet understand why Multimodal Language Models (MLMs) struggle on perception-heavy tasks. We offer an under-studied perspective by examining how popular MLMs (LLaVA-OneVision, Qwen2.5-VL, and Llama-3-LLaVA-NeXT) process their visual key-value tokens. We first study the flow of visual information through the language model, finding that image value tokens encode sufficient information to perform several perception-heavy tasks zero-shot: segmentation, semantic correspondence, temporal correspondence, and referring expression detection. We find that while the language model does augment the visual information received from the projection of input visual encodings-which we reveal correlates with overall MLM perception capability-it contains less visual information on several tasks than the equivalent visual encoder (SigLIP) that has not undergone MLM finetuning. Further, we find that the visual information corresponding to input-agnostic image key tokens in later layers of language models contains artifacts which reduce perception capability of the overall MLM. Next, we discuss controlling visual information in the language model, showing that adding a text prefix to the image input improves perception capabilities of visual representations. Finally, we reveal that if language models were able to better control their visual information, their perception would significantly improve; e.g., in 33.3% of Art Style questions in the BLINK benchmark, perception information present in the language model is not surfaced to the output! Our findings reveal insights into the role of key-value tokens in multimodal systems, paving the way for deeper mechanistic interpretability of MLMs and suggesting new directions for training their visual encoder and language model components.

---

### Natural Language Edge Labelling: Decoupling Intent from Execution in Structured LM Reasoning

Authors: Abhinav Madahar
Published: 2025-10-06
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.04817v1

Controllers for structured LM reasoning (e.g., Chain-of-Thought, self-consistency, and Tree-of-Thoughts) often entangle what to try next with how to execute it, exposing only coarse global knobs and yielding brittle, compute-inefficient, and hard-to-audit behavior. We introduce Natural Language Edge Labelling (NLEL), a labeller-tuner overlay that attaches a free-form natural-language directive to each search edge and translates it into a schema-bounded control vector for decoding, search (branch quotas, exploration $β$), generation bundle size, retrieval mixtures, and verification passes. A labeller $Λ$ emits labels from the parent state and a compact context; a tuner $Ψ$ maps $(P, L, C)\to Π$, with strict schema validation and trust-region projection around safe defaults. Downstream selection remains ToT-style with score $S=μ+βσ$ and depth-annealed $β$. We show NLEL strictly generalizes CoT/ToT, prove an anytime-monotonicity property for top-$k$ selection under label-conditioned bundles, and bound selector shortfall by control-vector distortion, providing decision-relevant justification for guards like trust regions and verification passes. We instantiate $Ψ$ as a prompt-only JSON Parameter Emitter and preregister an evaluation on GSM8K, MATH (subset), StrategyQA, and ARC-Challenge with compute-aware reporting (success@compute, tokens-per-success) and ablations over $Λ$, $Ψ$, trust-region radius, and control quantization; preregistered forecasts anticipate accuracy gains at comparable token budgets and improved success@compute under constraints. NLEL offers an interpretable, model-agnostic interface that separates intent from execution for controllable, auditable LM inference.

---

### On Predicting Post-Click Conversion Rate via Counterfactual Inference

Authors: Junhyung Ahn, Sanghack Lee
Published: 2025-10-06
Categories: cs.LG, cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2510.04816v1

Accurately predicting conversion rate (CVR) is essential in various recommendation domains such as online advertising systems and e-commerce. These systems utilize user interaction logs, which consist of exposures, clicks, and conversions. CVR prediction models are typically trained solely based on clicked samples, as conversions can only be determined following clicks. However, the sparsity of clicked instances necessitates the collection of a substantial amount of logs for effective model training. Recent works address this issue by devising frameworks that leverage non-clicked samples. While these frameworks aim to reduce biases caused by the discrepancy between clicked and non-clicked samples, they often rely on heuristics. Against this background, we propose a method to counterfactually generate conversion labels for non-clicked samples by using causality as a guiding principle, attempting to answer the question, "Would the user have converted if he or she had clicked the recommended item?" Our approach is named the Entire Space Counterfactual Inference Multi-task Model (ESCIM). We initially train a structural causal model (SCM) of user sequential behaviors and conduct a hypothetical intervention (i.e., click) on non-clicked items to infer counterfactual CVRs. We then introduce several approaches to transform predicted counterfactual CVRs into binary counterfactual conversion labels for the non-clicked samples. Finally, the generated samples are incorporated into the training process. Extensive experiments on public datasets illustrate the superiority of the proposed algorithm. Online A/B testing further empirically validates the effectiveness of our proposed algorithm in real-world scenarios. In addition, we demonstrate the improved performance of the proposed method on latent conversion data, showcasing its robustness and superior generalization capabilities.

---

### A Noise Resilient Approach for Robust Hurst Exponent Estimation

Authors: Malith Premarathna, Fabrizio Ruggeri, Dixon Vimalajeewa
Published: 2025-10-06
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.04811v1

Understanding signal behavior across scales is vital in areas such as natural phenomena analysis and financial modeling. A key property is self-similarity, quantified by the Hurst exponent (H), which reveals long-term dependencies. Wavelet-based methods are effective for estimating H due to their multi-scale analysis capability, but additive noise in real-world measurements often degrades accuracy. We propose Noise-Controlled ALPHEE (NC-ALPHEE), an enhancement of the Average Level-Pairwise Hurst Exponent Estimator (ALPHEE), incorporating noise mitigation and generating multiple level-pairwise estimates from signal energy pairs. A neural network (NN) combines these estimates, replacing traditional averaging. This adaptive learning maintains ALPHEE's behavior in noise-free cases while improving performance in noisy conditions. Extensive simulations show that in noise-free data, NC-ALPHEE matches ALPHEE's accuracy using both averaging and NN-based methods. Under noise, however, traditional averaging deteriorates and requires impractical level restrictions, while NC-ALPHEE consistently outperforms existing techniques without such constraints. NC-ALPHEE offers a robust, adaptive approach for H estimation, significantly enhancing the reliability of wavelet-based methods in noisy environments.

---

### Egosurg: Arbitrary view synthesis for egocentric replay of operating room workflows from ambient cameras

Authors: Han Zhang, Lalithkumar Seenivasan, Jose L. Porras, Roger D. Soberanis-Mukul, Hao Ding, Hongchao Shu, Benjamin D. Killeen, Ankita Ghosh, Lonny Yarmus, Jeffrey K. Jopling, Masaru Ishii, Angela C. Argento et al.
Published: 2025-10-06
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.04802v2

Observing surgical practice has historically relied on fixed vantage points or recollections, leaving the egocentric perspectives that shape clinical decisions undocumented. Ambient fixed cameras capture the operating room (OR) at room scale but cannot recover what any individual team member actually saw. We present EgoSurg, a framework that reconstructs dynamic OR scenes from sparse wall-mounted stereo video and renders arbitrary, role-specific egocentric views without instrumenting personnel or interfering with clinical workflow. EgoSurg initializes a per-timestamp 3D Gaussian Splatting representation from scale-aware stereo depth and refines it with an image-conditioned diffusion model that corrects auxiliary rendered views, mitigating artifacts caused by limited camera coverage, crowding, and occlusion. We evaluated the framework on four real robotic pulmonology procedures and two simulated full-workflow sessions across two hospital sites. Near-field reconstruction fidelity was consistent (PSNR 26.8~dB, SSIM .895) across five workflow phases and both sites, and synthesized egocentric views reached a PSNR of 17.8~dB and an SSIM of .766 against paired hand-held point-of-view recordings. We further demonstrate three case studies for intended use: adjudicating a simulated sterile field violation, replaying a procedure from role-specific viewpoints, and testing a counterfactual change in personnel position. These results indicate that existing ambient camera infrastructure can be turned into a navigable 3D record of surgical work, supporting retrospective review of safety events, training, and workflow analysis from every angle.

---

### Hybrid Architectures for Language Models: Systematic Analysis and Design Insights

Authors: Sangmin Bae, Bilge Acun, Chien-Yu Lin, Haroun Habeeb, Seungyeon Kim, Liang Luo, Junjie Wang, Carole-Jean Wu
Published: 2025-10-06
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.04800v3

Recent progress in large language models demonstrates that hybrid architectures--combining self-attention mechanisms with structured state space models like Mamba--can achieve a compelling balance between modeling quality and computational efficiency, particularly for long-context tasks. While these hybrid models show promising performance, systematic comparisons of hybridization strategies and analyses on the key factors behind their effectiveness have not been clearly shared to the community. In this work, we present a holistic evaluation of hybrid architectures based on inter-layer (sequential) or intra-layer (parallel) fusion. We comprehensively evaluate these designs across multiple dimensions: language modeling and downstream task performance, long-context capabilities, scaling analysis, and training and inference efficiency. By investigating the core characteristics of their computational primitive, we identify the most critical elements for each hybridization strategy and further propose optimal design recipes for hybrid models. Our comprehensive analysis provides practical guidance and valuable insights for developing hybrid language models, facilitating the optimization of architectural configurations.

---

### A Comparative Study of Vision Transformers and CNNs for Few-Shot Rigid Transformation and Fundamental Matrix Estimation

Authors: Alon Kaya, Igal Bilik, Inna Stainvas
Published: 2025-10-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.04794v1

Vision-transformers (ViTs) and large-scale convolution-neural-networks (CNNs) have reshaped computer vision through pretrained feature representations that enable strong transfer learning for diverse tasks. However, their efficiency as backbone architectures for geometric estimation tasks involving image deformations in low-data regimes remains an open question. This work considers two such tasks: 1) estimating 2D rigid transformations between pairs of images and 2) predicting the fundamental matrix for stereo image pairs, an important problem in various applications, such as autonomous mobility, robotics, and 3D scene reconstruction. Addressing this intriguing question, this work systematically compares large-scale CNNs (ResNet, EfficientNet, CLIP-ResNet) with ViT-based foundation models (CLIP-ViT variants and DINO) in various data size settings, including few-shot scenarios. These pretrained models are optimized for classification or contrastive learning, encouraging them to focus mostly on high-level semantics. The considered tasks require balancing local and global features differently, challenging the straightforward adoption of these models as the backbone. Empirical comparative analysis shows that, similar to training from scratch, ViTs outperform CNNs during refinement in large downstream-data scenarios. However, in small data scenarios, the inductive bias and smaller capacity of CNNs improve their performance, allowing them to match that of a ViT. Moreover, ViTs exhibit stronger generalization in cross-domain evaluation where the data distribution changes. These results emphasize the importance of carefully selecting model architectures for refinement, motivating future research towards hybrid architectures that balance local and global representations.

---

### Hybrid-Balance GFlowNet for Solving Vehicle Routing Problems

Authors: Ni Zhang, Zhiguang Cao
Published: 2025-10-06
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.04792v1

Existing GFlowNet-based methods for vehicle routing problems (VRPs) typically employ Trajectory Balance (TB) to achieve global optimization but often neglect important aspects of local optimization. While Detailed Balance (DB) addresses local optimization more effectively, it alone falls short in solving VRPs, which inherently require holistic trajectory optimization. To address these limitations, we introduce the Hybrid-Balance GFlowNet (HBG) framework, which uniquely integrates TB and DB in a principled and adaptive manner by aligning their intrinsically complementary strengths. Additionally, we propose a specialized inference strategy for depot-centric scenarios like the Capacitated Vehicle Routing Problem (CVRP), leveraging the depot node's greater flexibility in selecting successors. Despite this specialization, HBG maintains broad applicability, extending effectively to problems without explicit depots, such as the Traveling Salesman Problem (TSP). We evaluate HBG by integrating it into two established GFlowNet-based solvers, i.e., AGFN and GFACS, and demonstrate consistent and significant improvements across both CVRP and TSP, underscoring the enhanced solution quality and generalization afforded by our approach.

---

### Trade in Minutes! Rationality-Driven Agentic System for Quantitative Financial Trading

Authors: Zifan Song, Kaitao Song, Guosheng Hu, Ding Qi, Junyao Gao, Xiaohua Wang, Dongsheng Li, Cairong Zhao
Published: 2025-10-06
Categories: cs.MA, cs.AI
arXiv: https://arxiv.org/abs/2510.04787v2

Recent advancements in large language models (LLMs) and agentic systems have shown exceptional decision-making capabilities, revealing significant potential for autonomic finance. Current financial trading agents predominantly simulate anthropomorphic roles that inadvertently introduce emotional biases and rely on peripheral information, while being constrained by the necessity for continuous inference during deployment. In this paper, we pioneer the harmonization of strategic depth in agents with the mechanical rationality essential for quantitative trading. Consequently, we present TiMi (Trade in Minutes), a rationality-driven multi-agent system that architecturally decouples strategy development from minute-level deployment. TiMi leverages specialized LLM capabilities of semantic analysis, code programming, and mathematical reasoning within a comprehensive policy-optimization-deployment chain. Specifically, we propose a two-tier analytical paradigm from macro patterns to micro customization, layered programming design for trading bot implementation, and closed-loop optimization driven by mathematical reflection. Extensive evaluations across 200+ trading pairs in stock and cryptocurrency markets empirically validate the efficacy of TiMi in stable profitability, action efficiency, and risk control under volatile market dynamics.

---

### Learning on the Job: Test-Time Curricula for Targeted Reinforcement Learning

Authors: Jonas Hübotter, Leander Diaz-Bone, Ido Hakimi, Andreas Krause, Moritz Hardt
Published: 2025-10-06
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.04786v1

Humans are good at learning on the job: We learn how to solve the tasks we face as we go along. Can a model do the same? We propose an agent that assembles a task-specific curriculum, called test-time curriculum (TTC-RL), and applies reinforcement learning to continue training the model for its target task. The test-time curriculum avoids time-consuming human curation of datasets by automatically selecting the most task-relevant data from a large pool of available training data. Our experiments demonstrate that reinforcement learning on a test-time curriculum consistently improves the model on its target tasks, across a variety of evaluations and models. Notably, on challenging math and coding benchmarks, TTC-RL improves the pass@1 of Qwen3-8B by approximately 1.8x on AIME25 and 2.1x on CodeElo. Moreover, we find that TTC-RL significantly raises the performance ceiling compared to the initial model, increasing pass@8 on AIME25 from 40% to 62% and on CodeElo from 28% to 43%. Our findings show the potential of test-time curricula in extending the test-time scaling paradigm to continual training on thousands of task-relevant experiences during test-time.

---

### Hands-Free Heritage: Automated 3D Scanning for Cultural Heritage Digitization

Authors: Javed Ahmad, Federico Dassiè, Selene Frascella, Gabriele Marchello, Ferdinando Cannella, Arianna Traviglia
Published: 2025-10-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.04781v2

High-fidelity 3D scanning is essential for preserving cultural heritage artefacts, supporting documentation, analysis, and long-term conservation. However, conventional methods typically require specialized expertise and manual intervention to maintain optimal scanning conditions and coverage. We present an automated two-robot scanning system that eliminates the need for handheld or semi-automatic workflows by combining coordinated robotic manipulation with high-resolution 3D scanning. Our system parameterizes the scanning space into distinct regions, enabling coordinated motion planning between a scanner-equipped robot and a tray-handling robot. Optimized trajectory planning and waypoint distribution ensure comprehensive surface coverage, minimize occlusions, and balance reconstruction accuracy with system efficiency. Experimental results show that our approach achieves significantly lower Chamfer Distance and higher F-score compared to baseline methods, offering superior geometric accuracy, improved digitization efficiency, and reduced reliance on expert operators.

---

### Kernel ridge regression under power-law data: spectrum and generalization

Authors: Arie Wortsman, Bruno Loureiro
Published: 2025-10-06
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.04780v1

In this work, we investigate high-dimensional kernel ridge regression (KRR) on i.i.d. Gaussian data with anisotropic power-law covariance. This setting differs fundamentally from the classical source & capacity conditions for KRR, where power-law assumptions are typically imposed on the kernel eigen-spectrum itself. Our contributions are twofold. First, we derive an explicit characterization of the kernel spectrum for polynomial inner-product kernels, giving a precise description of how the kernel eigen-spectrum inherits the data decay. Second, we provide an asymptotic analysis of the excess risk in the high-dimensional regime for a particular kernel with this spectral behavior, showing that the sample complexity is governed by the effective dimension of the data rather than the ambient dimension. These results establish a fundamental advantage of learning with power-law anisotropic data over isotropic data. To our knowledge, this is the first rigorous treatment of non-linear KRR under power-law data.

---

### MetaMP: Seamless Metadata Enrichment and AI Application Framework for Enhanced Membrane Protein Visualization and Analysis

Authors: Ebenezer Awotoro, Chisom Ezekannagha, Florian Schwarz, Johannes Tauscher, Dominik Heider, Katharina Ladewig, Christel Le Bon, Karine Moncoq, Bruno Miroux, Georges Hattab
Published: 2025-10-06
Categories: cs.LG, cs.DB
arXiv: https://arxiv.org/abs/2510.04776v1

Structural biology has made significant progress in determining membrane proteins, leading to a remarkable increase in the number of available structures in dedicated databases. The inherent complexity of membrane protein structures, coupled with challenges such as missing data, inconsistencies, and computational barriers from disparate sources, underscores the need for improved database integration. To address this gap, we present MetaMP, a framework that unifies membrane-protein databases within a web application and uses machine learning for classification. MetaMP improves data quality by enriching metadata, offering a user-friendly interface, and providing eight interactive views for streamlined exploration. MetaMP was effective across tasks of varying difficulty, demonstrating advantages across different levels without compromising speed or accuracy, according to user evaluations. Moreover, MetaMP supports essential functions such as structure classification and outlier detection. We present three practical applications of Artificial Intelligence (AI) in membrane protein research: predicting transmembrane segments, reconciling legacy databases, and classifying structures with explainable AI support. In a validation focused on statistics, MetaMP resolved 77% of data discrepancies and accurately predicted the class of newly identified membrane proteins 98% of the time and overtook expert curation. Altogether, MetaMP is a much-needed resource that harmonizes current knowledge and empowers AI-driven exploration of membrane-protein architecture.

---

### Online automatic code generation for robot swarms: LLMs and self-organizing hierarchy

Authors: Weixu Zhu, Marco Dorigo, Mary Katherine Heinrich
Published: 2025-10-06
Categories: cs.RO, cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2510.04774v2

Our recently introduced self-organizing nervous system (SoNS) provides robot swarms with 1) ease of behavior design and 2) global estimation of the swarm configuration and its collective environment, facilitating the implementation of online automatic code generation for robot swarms. In a demonstration with 6 real robots and simulation trials with >30 robots, we show that when a SoNS-enhanced robot swarm gets stuck, it can automatically solicit and run code generated by an external LLM on the fly, completing its mission with an 85% success rate.

---

### Distribution Preference Optimization: A Fine-grained Perspective for LLM Unlearning

Authors: Kai Qin, Jiaqi Wu, Jianxiang He, Haoyuan Sun, Yifei Zhao, Xu Wang, Bin Liang, Yongzhe Chang, Cheng Li, Tiantian Zhang, Houde Liu
Published: 2025-10-06
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.04773v2

As Large Language Models (LLMs) demonstrate remarkable capabilities learned from vast corpora, concerns regarding data privacy and safety are receiving increasing attention. LLM unlearning, which aims to remove the influence of specific data while preserving overall model utility, is becoming an important research area. One of the mainstream unlearning classes is optimization-based methods, which achieve forgetting directly through fine-tuning, exemplified by Negative Preference Optimization (NPO). However, NPO's effectiveness is limited by its inherent lack of explicit positive preference signals. Attempts to introduce such signals by constructing preferred responses often necessitate domain-specific knowledge or well-designed prompts, fundamentally restricting their generalizability. In this paper, we shift the focus to the distribution-level, directly targeting the next-token probability distribution instead of entire responses, and derive a novel unlearning algorithm termed \textbf{Di}stribution \textbf{P}reference \textbf{O}ptimization (DiPO). We show that the requisite preference distribution pairs for DiPO, which are distributions over the model's output tokens, can be constructed by selectively amplifying or suppressing the model's high-confidence output logits, thereby effectively overcoming NPO's limitations. We theoretically prove the consistency of DiPO's loss function with the desired unlearning direction. Extensive experiments demonstrate that DiPO achieves a strong trade-off between model utility and forget quality. Notably, DiPO attains the highest forget quality on the TOFU benchmark, and maintains leading scalability and sustainability in utility preservation on the MUSE benchmark.

---

### Federated Learning for Surgical Vision in Appendicitis Classification: Results of the FedSurg EndoVis 2024 Challenge

Authors: Max Kirchner, Hanna Hoffmann, Alexander C. Jenke, Oliver L. Saldanha, Kevin Pfeiffer, Weam Kanjo, Julia Alekseenko, Claas de Boer, Santhi Raj Kolamuri, Lorenzo Mazza, Nicolas Padoy, Sophia Bano et al.
Published: 2025-10-06
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.04772v3

Developing generalizable surgical AI requires multi-institutional data, yet privacy constraints preclude direct data sharing, making Federated Learning (FL) a natural candidate. Its application to complex, spatiotemporal surgical video remains largely unbenchmarked. We present the FedSurg Challenge, the first international initiative dedicated to FL in surgical vision, as a proof-of-concept evaluation using a multi-center dataset of laparoscopic appendectomies (subset of Appendix300). Three participant submissions were evaluated on generalization to an unseen clinical center and center-specific local adaptation, alongside centralized, Swarm Learning, parameter-efficient fine-tuning baselines, and reference classifiers. Our analysis identifies temporal modeling as the architectural factor most consistently associated with generalization to the unseen center, although effects vary across metrics. Classifier collapse arises from both the global model's failure to transfer under domain shift and unconstrained fine-tuning on small, imbalanced local datasets, motivating structured personalized FL for center-specific adaptation. Absolute performance remains far from clinical viability: even with all data pooled centrally, the task reached a 26.31% F1-score on the unseen center. Paired permutation tests resolve only large differences, and no adaptation comparison reaches significance at this sample size. By characterizing these limitations, this work establishes a methodological reference point for privacy-preserving surgical video AI.

---

### Beyond the Seen: Bounded Distribution Estimation for Open-Vocabulary Learning

Authors: Xiaomeng Fan, Yuchuan Mao, Zhi Gao, Yuwei Wu, Jin Chen, Yunde Jia
Published: 2025-10-06
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.04770v1

Open-vocabulary learning requires modeling the data distribution in open environments, which consists of both seen-class and unseen-class data. Existing methods estimate the distribution in open environments using seen-class data, where the absence of unseen classes makes the estimation error inherently unidentifiable. Intuitively, learning beyond the seen classes is crucial for distribution estimation to bound the estimation error. We theoretically demonstrate that the distribution can be effectively estimated by generating unseen-class data, through which the estimation error is upper-bounded. Building on this theoretical insight, we propose a novel open-vocabulary learning method, which generates unseen-class data for estimating the distribution in open environments. The method consists of a class-domain-wise data generation pipeline and a distribution alignment algorithm. The data generation pipeline generates unseen-class data under the guidance of a hierarchical semantic tree and domain information inferred from the seen-class data, facilitating accurate distribution estimation. With the generated data, the distribution alignment algorithm estimates and maximizes the posterior probability to enhance generalization in open-vocabulary learning. Extensive experiments on $11$ datasets demonstrate that our method outperforms baseline approaches by up to $14\%$, highlighting its effectiveness and superiority.

---

### When Do Credal Sets Stabilize? Fixed-Point Theorems for Credal Set Updates

Authors: Michele Caprio, Siu Lun Chau, Krikamol Muandet
Published: 2025-10-06
Categories: cs.LG, cs.AI, math.PR, math.ST, stat.ML
arXiv: https://arxiv.org/abs/2510.04769v2

Many machine learning algorithms rely on iterative updates of uncertainty representations, ranging from variational inference and expectation-maximization, to reinforcement learning, continual learning, and multi-agent learning. In the presence of imprecision and ambiguity, credal sets -- closed, convex sets of probability distributions -- have emerged as a popular framework for representing imprecise probabilistic beliefs. Under such imprecision, many learning problems in imprecise probabilistic machine learning (IPML) may be viewed as processes involving successive applications of update rules on credal sets. This naturally raises the question of whether this iterative process converges to stable fixed points -- or, more generally, under what conditions on the updating mechanism such fixed points exist, and whether they can be attained. We provide the first analysis of this problem, and illustrate our findings using Credal Bayesian Deep Learning as a concrete example. Our work demonstrates that incorporating imprecision into the learning process not only enriches the representation of uncertainty, but also reveals structural conditions under which stability emerges, thereby offering new insights into the dynamics of iterative learning under imprecision.

---

### ParallelBench: Understanding the Trade-offs of Parallel Decoding in Diffusion LLMs

Authors: Wonjun Kang, Kevin Galim, Seunghyuk Oh, Minjae Lee, Yuchen Zeng, Shuibai Zhang, Coleman Hooper, Yuezhou Hu, Hyung Il Koo, Nam Ik Cho, Kangwook Lee
Published: 2025-10-06
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.04767v2

While most autoregressive LLMs are constrained to one-by-one decoding, diffusion LLMs (dLLMs) have attracted growing interest for their potential to dramatically accelerate inference through parallel decoding. Despite this promise, the conditional independence assumption in dLLMs causes parallel decoding to ignore token dependencies, inevitably degrading generation quality when these dependencies are strong. However, existing works largely overlook these inherent challenges, and evaluations on standard benchmarks (e.g., math and coding) are not sufficient to capture the quality degradation caused by parallel decoding. To address this gap, we first provide an information-theoretic analysis of parallel decoding. We then conduct case studies on analytically tractable synthetic list operations from both data distribution and decoding strategy perspectives, offering quantitative insights that highlight the fundamental limitations of parallel decoding. Building on these insights, we propose ParallelBench, the first benchmark specifically designed for dLLMs, featuring realistic tasks that are trivial for humans and autoregressive LLMs yet exceptionally challenging for dLLMs under parallel decoding. Using ParallelBench, we systematically analyze both dLLMs and autoregressive LLMs, revealing that: (i) dLLMs under parallel decoding can suffer dramatic quality degradation in real-world scenarios, and (ii) current parallel decoding strategies struggle to adapt their degree of parallelism based on task difficulty, thus failing to achieve meaningful speedup without compromising quality. Our findings underscore the pressing need for innovative decoding methods that can overcome the current speed-quality trade-off. We release our benchmark to help accelerate the development of truly efficient dLLMs.

---

### LMM-Incentive: Large Multimodal Model-based Incentive Design for User-Generated Content in Web 3.0

Authors: Jinbo Wen, Jiawen Kang, Linfeng Zhang, Xiaoying Tang, Jianhang Tang, Yang Zhang, Zhaohui Yang, Dusit Niyato
Published: 2025-10-06
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.04765v1

Web 3.0 represents the next generation of the Internet, which is widely recognized as a decentralized ecosystem that focuses on value expression and data ownership. By leveraging blockchain and artificial intelligence technologies, Web 3.0 offers unprecedented opportunities for users to create, own, and monetize their content, thereby enabling User-Generated Content (UGC) to an entirely new level. However, some self-interested users may exploit the limitations of content curation mechanisms and generate low-quality content with less effort, obtaining platform rewards under information asymmetry. Such behavior can undermine Web 3.0 performance. To this end, we propose \textit{LMM-Incentive}, a novel Large Multimodal Model (LMM)-based incentive mechanism for UGC in Web 3.0. Specifically, we propose an LMM-based contract-theoretic model to motivate users to generate high-quality UGC, thereby mitigating the adverse selection problem from information asymmetry. To alleviate potential moral hazards after contract selection, we leverage LMM agents to evaluate UGC quality, which is the primary component of the contract, utilizing prompt engineering techniques to improve the evaluation performance of LMM agents. Recognizing that traditional contract design methods cannot effectively adapt to the dynamic environment of Web 3.0, we develop an improved Mixture of Experts (MoE)-based Proximal Policy Optimization (PPO) algorithm for optimal contract design. Simulation results demonstrate the superiority of the proposed MoE-based PPO algorithm over representative benchmarks in the context of contract design. Finally, we deploy the designed contract within an Ethereum smart contract framework, further validating the effectiveness of the proposed scheme.

---

### Are BabyLMs Deaf to Gricean Maxims? A Pragmatic Evaluation of Sample-efficient Language Models

Authors: Raha Askari, Sina Zarrieß, Özge Alacam, Judith Sieker
Published: 2025-10-06
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.04764v2

Implicit meanings are integral to human communication, making it essential for language models to be capable of identifying and interpreting them. Grice (1975) proposed a set of conversational maxims that guide cooperative dialogue, noting that speakers may deliberately violate these principles to express meanings beyond literal words, and that listeners, in turn, recognize such violations to draw pragmatic inferences. Building on Surian et al. (1996)'s study of children's sensitivity to violations of Gricean maxims, we introduce a novel benchmark to test whether language models pretrained on less than 10M and less than 100M tokens can distinguish maxim-adhering from maxim-violating utterances. We compare these BabyLMs across five maxims and situate their performance relative to children and a Large Language Model (LLM) pretrained on 3T tokens. We find that overall, models trained on less than 100M tokens outperform those trained on less than 10M, yet fall short of child-level and LLM competence. Our results suggest that modest data increases improve some aspects of pragmatic behavior, leading to finer-grained differentiation between pragmatic dimensions.

---

### Fisher-Bingham-like normalizing flows on the sphere

Authors: Thorsten Glüsenkamp
Published: 2025-10-06
Categories: stat.ML, astro-ph.IM, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.04762v1

A generic D-dimensional Gaussian can be conditioned or projected onto the D-1 unit sphere, thereby leading to the well-known Fisher-Bingham (FB) or Angular Gaussian (AG) distribution families, respectively. These are some of the most fundamental distributions on the sphere, yet cannot straightforwardly be written as a normalizing flow except in two special cases: the von-Mises Fisher in D=3 and the central angular Gaussian in any D. In this paper, we describe how to generalize these special cases to a family of normalizing flows that behave similarly to the full FB or AG family in any D. We call them "zoom-linear-project" (ZLP)-Fisher flows. Unlike a normal Fisher-Bingham distribution, their composition allows to gradually add complexity as needed. Furthermore, they can naturally handle conditional density estimation with target distributions that vary by orders of magnitude in scale - a setting that is important in astronomical applications but that existing flows often struggle with. A particularly useful member of the new family is the Kent analogue that can cheaply upgrade any flow in this situation to yield better performance.

---

### Agile Software Effort Estimation using Regression Techniques

Authors: Sisay Deresa Sima, Ayalew Belay Habtie
Published: 2025-10-06
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2510.04760v1

Software development effort estimation is one of the most critical aspect in software development process, as the success or failure of the entire project depends on the accuracy of estimations. Researchers are still conducting studies on agile effort estimation. The aim of this research is to develop a story point based agile effort estimation model using LASSO and Elastic Net regression techniques. The experimental work is applied to the agile story point approach using 21 software projects collected from six firms. The two algorithms are trained using their default parameters and tuned grid search with 5-fold cross-validation to get an enhanced model. The experiment result shows LASSO regression achieved better predictive performance PRED (8%) and PRED (25%) results of 100.0, MMRE of 0.0491, MMER of 0.0551, MdMRE of 0.0593, MdMER of 0.063, and MSE of 0.0007. The results are also compared with other related literature.

---

### Progressive Gaussian Transformer with Anisotropy-aware Sampling for Open Vocabulary Occupancy Prediction

Authors: Chi Yan, Dan Xu
Published: 2025-10-06
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.04759v2

The 3D occupancy prediction task has witnessed remarkable progress in recent years, playing a crucial role in vision-based autonomous driving systems. While traditional methods are limited to fixed semantic categories, recent approaches have moved towards predicting text-aligned features to enable open-vocabulary text queries in real-world scenes. However, there exists a trade-off in text-aligned scene modeling: sparse Gaussian representation struggles to capture small objects in the scene, while dense representation incurs significant computational overhead. To address these limitations, we present PG-Occ, an innovative Progressive Gaussian Transformer Framework that enables open-vocabulary 3D occupancy prediction. Our framework employs progressive online densification, a feed-forward strategy that gradually enhances the 3D Gaussian representation to capture fine-grained scene details. By iteratively enhancing the representation, the framework achieves increasingly precise and detailed scene understanding. Another key contribution is the introduction of an anisotropy-aware sampling strategy with spatio-temporal fusion, which adaptively assigns receptive fields to Gaussians at different scales and stages, enabling more effective feature aggregation and richer scene information capture. Through extensive evaluations, we demonstrate that PG-Occ achieves state-of-the-art performance with a relative 14.3% mIoU improvement over the previous best performing method. Code and pretrained models will be released upon publication on our project page: https://yanchi-3dv.github.io/PG-Occ

---

### Provable Affine Identifiability of Nonlinear CCA under Latent Distributional Priors

Authors: Zhiwei Han, Stefan Matthes, Hao Shen
Published: 2025-10-06
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.04758v3

In this work, we establish the sufficient conditions under which nonlinear Canonical Correlation Analysis (CCA) recovers ground-truth latent factors up to an affine transformation. By transporting the analysis from the observation space to the source space, we extend classical statistical results on orthogonal polynomial expansions of bivariate distributions to representation learning, proving affine identifiability under specific distributional priors. We formally demonstrate that whitening is strictly necessary to ensure the boundedness and well-conditioning of the learned mappings. Furthermore, we bridge the gap between theory and practice by proving that ridge-regularized empirical CCA converges to its population counterpart in the finite-sample regime. Finally, our findings provide a rigorous theoretical foundation explaining the empirical success of recent correlation-based non-contrastive learning methods. Experiments on synthetic and rendered image datasets, alongside systematic ablations, validate the predicted recovery behavior and illustrate the failure modes that arise when the assumptions are violated.

---

### ModernBERT + ColBERT: Enhancing biomedical RAG through an advanced re-ranking retriever

Authors: Eduardo Martínez Rivera, Filippo Menolascina
Published: 2025-10-06
Categories: cs.CL, q-bio.QM
arXiv: https://arxiv.org/abs/2510.04757v1

Retrieval-Augmented Generation (RAG) is a powerful technique for enriching Large Language Models (LLMs) with external knowledge, allowing for factually grounded responses, a critical requirement in high-stakes domains such as healthcare. However, the efficacy of RAG systems is fundamentally restricted by the performance of their retrieval module, since irrelevant or semantically misaligned documents directly compromise the accuracy of the final generated response. General-purpose dense retrievers can struggle with the nuanced language of specialised domains, while the high accuracy of in-domain models is often achieved at prohibitive computational costs. In this work, we aim to address this trade-off by developing and evaluating a two-stage retrieval architecture that combines a lightweight ModernBERT bidirectional encoder for efficient initial candidate retrieval with a ColBERTv2 late-interaction model for fine-grained re-ranking. We conduct comprehensive evaluations of our retriever module performance and RAG system performance in the biomedical context, fine-tuning the IR module using 10k question-passage pairs from PubMedQA. Our analysis of the retriever module confirmed the positive impact of the ColBERT re-ranker, which improved Recall@3 by up to 4.2 percentage points compared to its retrieve-only counterpart. When integrated into the biomedical RAG, our IR module leads to a state-of-the-art average accuracy of 0.4448 on the five tasks of the MIRAGE question-answering benchmark, outperforming strong baselines such as MedCPT (0.4436). Our ablation studies reveal that this performance is critically dependent on a joint fine-tuning process that aligns the retriever and re-ranker; otherwise, the re-ranker might degrade the performance.

---

### A New Digital Divide? Coder Worldviews, the Slop Economy, and Democracy in the Age of AI

Authors: Jason Miklian, Kristian Hoelscher
Published: 2025-10-06
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2510.04755v4

Digital technologies are transforming democratic life in conflicting ways. This article bridges two perspectives to unpack these tensions. First, we present an original survey of software developers in Silicon Valley, interrogating how coder worldviews, ethics, and workplace cultures shape the democratic potential and social impact of the technologies they build. Results indicate that while most developers recognize the power of their products to influence civil liberties and political discourse, they often face ethical dilemmas and top-down pressures that can lead to design choices undermining democratic ideals. Second, we critically investigate these findings in the context of an emerging new digital divide, not of internet access but of information quality. We interrogate the survey findings in the context of the Slop Economy, in which billions of users unable to pay for high-quality content experience an internet dominated by low-quality, AI-generated ad-driven content. We find a reinforcing cycle between tech creator beliefs and the digital ecosystems they spawn. We discuss implications for democratic governance, arguing for more ethically informed design and policy interventions to help bridge the digital divide to ensure that technological innovation supports rather than subverts democratic values in the next chapter of the digital age.

---

### Beyond Appearance: Transformer-based Person Identification from Conversational Dynamics

Authors: Masoumeh Chapariniya, Teodora Vukovic, Sarah Ebling, Volker Dellwo
Published: 2025-10-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.04753v1

This paper investigates the performance of transformer-based architectures for person identification in natural, face-to-face conversation scenario. We implement and evaluate a two-stream framework that separately models spatial configurations and temporal motion patterns of 133 COCO WholeBody keypoints, extracted from a subset of the CANDOR conversational corpus. Our experiments compare pre-trained and from-scratch training, investigate the use of velocity features, and introduce a multi-scale temporal transformer for hierarchical motion modeling. Results demonstrate that domain-specific training significantly outperforms transfer learning, and that spatial configurations carry more discriminative information than temporal dynamics. The spatial transformer achieves 95.74% accuracy, while the multi-scale temporal transformer achieves 93.90%. Feature-level fusion pushes performance to 98.03%, confirming that postural and dynamic information are complementary. These findings highlight the potential of transformer architectures for person identification in natural interactions and provide insights for future multimodal and cross-cultural studies.

---

### A Low-Resource Speech-Driven NLP Pipeline for Sinhala Dyslexia Assistance

Authors: Peshala Perera, Deshan Sumanathilaka
Published: 2025-10-06
Categories: cs.CL, cs.SE
arXiv: https://arxiv.org/abs/2510.04750v1

Dyslexia in adults remains an under-researched and under-served area, particularly in non-English-speaking contexts, despite its significant impact on personal and professional lives. This work addresses that gap by focusing on Sinhala, a low-resource language with limited tools for linguistic accessibility. We present an assistive system explicitly designed for Sinhala-speaking adults with dyslexia. The system integrates Whisper for speech-to-text conversion, SinBERT, an open-sourced fine-tuned BERT model trained for Sinhala to identify common dyslexic errors, and a combined mT5 and Mistral-based model to generate corrected text. Finally, the output is converted back to speech using gTTS, creating a complete multimodal feedback loop. Despite the challenges posed by limited Sinhala-language datasets, the system achieves 0.66 transcription accuracy and 0.7 correction accuracy with 0.65 overall system accuracy. These results demonstrate both the feasibility and effectiveness of the approach. Ultimately, this work highlights the importance of inclusive Natural Language Processing (NLP) technologies in underrepresented languages and showcases a practical

---

### Anomaly-Aware YOLO: A Frugal yet Robust Approach to Infrared Small Target Detection

Authors: Alina Ciocarlan, Sylvie Le Hégarat-Mascle, Sidonie Lefebvre
Published: 2025-10-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.04741v1

Infrared Small Target Detection (IRSTD) is a challenging task in defense applications, where complex backgrounds and tiny target sizes often result in numerous false alarms using conventional object detectors. To overcome this limitation, we propose Anomaly-Aware YOLO (AA-YOLO), which integrates a statistical anomaly detection test into its detection head. By treating small targets as unexpected patterns against the background, AA-YOLO effectively controls the false alarm rate. Our approach not only achieves competitive performance on several IRSTD benchmarks, but also demonstrates remarkable robustness in scenarios with limited training data, noise, and domain shifts. Furthermore, since only the detection head is modified, our design is highly generic and has been successfully applied across various YOLO backbones, including lightweight models. It also provides promising results when integrated into an instance segmentation YOLO. This versatility makes AA-YOLO an attractive solution for real-world deployments where resources are constrained. The code will be publicly released.

---

### ExposureEngine: Oriented Logo Detection and Sponsor Visibility Analytics in Sports Broadcasts

Authors: Mehdi Houshmand Sarkhoosh, Frøy Øye, Henrik Nestor Sørlie, Nam Hoang Vu, Dag Johansen, Cise Midoglu, Tomas Kupka, Pål Halvorsen
Published: 2025-10-06
Categories: cs.CV, cs.MM
arXiv: https://arxiv.org/abs/2510.04739v1

Quantifying sponsor visibility in sports broadcasts is a critical marketing task traditionally hindered by manual, subjective, and unscalable analysis methods. While automated systems offer an alternative, their reliance on axis-aligned Horizontal Bounding Box (HBB) leads to inaccurate exposuremetrics when logos appear rotated or skewed due to dynamic camera angles and perspective distortions. This paper introduces ExposureEngine, an end-to-end system designed for accurate, rotation-aware sponsor visibility analytics in sports broadcasts, demonstrated in a soccer case study. Our approach predicts Oriented Bounding Box (OBB) to provide a geometrically precise fit to each logo regardless of the orientation on-screen. To train and evaluate our detector, we developed a new dataset comprising 1,103 frames from Swedish elite soccer, featuring 670 unique sponsor logos annotated with OBBs. Our model achieves a mean Average Precision (mAP@0.5) of 0.859, with a precision of 0.96 and recall of 0.87, demonstrating robust performance in localizing logos under diverse broadcast conditions. The system integrates these detections into an analytical pipeline that calculates precise visibility metrics, such as exposure duration and on-screen coverage. Furthermore, we incorporate a language-driven agentic layer, enabling users to generate reports, summaries, and media content through natural language queries. The complete system, including the dataset and the analytics dashboard, provides a comprehensive solution for auditable and interpretable sponsor measurement in sports media. An overview of the ExposureEngine is available online: https://youtu.be/tRw6OBISuW4 .

---

### Speak, Edit, Repeat: High-Fidelity Voice Editing and Zero-Shot TTS with Cross-Attentive Mamba

Authors: Baher Mohammad, Magauiya Zhussip, Stamatios Lefkimmiatis
Published: 2025-10-06
Categories: cs.SD, cs.AI, cs.CL, cs.LG, eess.AS
arXiv: https://arxiv.org/abs/2510.04738v1

We introduce MAVE (Mamba with Cross-Attention for Voice Editing and Synthesis), a novel autoregressive architecture for text-conditioned voice editing and high-fidelity text-to-speech (TTS) synthesis, built on a cross-attentive Mamba backbone. MAVE achieves state-of-the-art performance in speech editing and very competitive results in zero-shot TTS, while not being explicitly trained on the latter task, outperforming leading autoregressive and diffusion models on diverse, real-world audio. By integrating Mamba for efficient audio sequence modeling with cross-attention for precise text-acoustic alignment, MAVE enables context-aware voice editing with exceptional naturalness and speaker consistency. In pairwise human evaluations on a random 40-sample subset of the RealEdit benchmark (400 judgments), 57.2% of listeners rated MAVE - edited speech as perceptually equal to the original, while 24.8% prefered the original and 18.0% MAVE - demonstrating that in the majority of cases edits are indistinguishable from the source. MAVE compares favorably with VoiceCraft and FluentSpeech both on pairwise comparisons and standalone mean opinion score (MOS) evaluations. For zero-shot TTS, MAVE exceeds VoiceCraft in both speaker similarity and naturalness, without requiring multiple inference runs or post-processing. Remarkably, these quality gains come with a significantly lower memory cost and approximately the same latency: MAVE requires ~6x less memory than VoiceCraft during inference on utterances from the RealEdit database (mean duration: 6.21s, A100, FP16, batch size 1). Our results demonstrate that MAVE establishes a new standard for flexible, high-fidelity voice editing and synthesis through the synergistic integration of structured state-space modeling and cross-modal attention.

---

### EVaR-Optimal Arm Identification in Bandits

Authors: Mehrasa Ahmadipour, Aurélien Garivier
Published: 2025-10-06
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.04728v1

We study the fixed-confidence best arm identification (BAI) problem within the multi-armed bandit (MAB) framework under the Entropic Value-at-Risk (EVaR) criterion. Our analysis considers a nonparametric setting, allowing for general reward distributions bounded in (0,1). This formulation addresses the critical need for risk-averse decision-making in high-stakes environments, such as finance, moving beyond simple expected value optimization. We propose a $δ$-correct, Track-and-Stop based algorithm and derive a corresponding lower bound on the expected sample complexity, which we prove is asymptotically matched. The implementation of our algorithm and the characterization of the lower bound both require solving a complex convex optimization problem and a related, simpler non-convex one.

---

### Directional Sheaf Hypergraph Networks: Unifying Learning on Directed and Undirected Hypergraphs

Authors: Emanuele Mule, Stefano Fiorini, Antonio Purificato, Federico Siciliano, Stefano Coniglio, Fabrizio Silvestri
Published: 2025-10-06
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.04727v2

Hypergraphs provide a natural way to represent higher-order interactions among multiple entities. While undirected hypergraphs have been extensively studied, the case of directed hypergraphs, which can model oriented group interactions, remains largely under-explored despite its relevance for many applications. Recent approaches in this direction often exhibit an implicit bias toward homophily, which limits their effectiveness in heterophilic settings. Rooted in the algebraic topology notion of Cellular Sheaves, Sheaf Neural Networks (SNNs) were introduced as an effective solution to circumvent such a drawback. While a generalization to hypergraphs is known, it is only suitable for undirected hypergraphs, failing to tackle the directed case. In this work, we introduce Directional Sheaf Hypergraph Networks (DSHN), a framework integrating sheaf theory with a principled treatment of asymmetric relations within a hypergraph. From it, we construct the Directed Sheaf Hypergraph Laplacian, a complex-valued operator by which we unify and generalize many existing Laplacian matrices proposed in the graph- and hypergraph-learning literature. Across 7 real-world datasets and against 13 baselines, DSHN achieves relative accuracy gains from 2% up to 20%, showing how a principled treatment of directionality in hypergraphs, combined with the expressive power of sheaves, can substantially improve performance.

---

### Predictive economics: Rethinking economic methodology with machine learning

Authors: Miguel Alves Pereira
Published: 2025-10-06
Categories: econ.GN, cs.LG
arXiv: https://arxiv.org/abs/2510.04726v1

This article proposes predictive economics as a distinct analytical perspective within economics, grounded in machine learning and centred on predictive accuracy rather than causal identification. Drawing on the instrumentalist tradition (Friedman), the explanation-prediction divide (Shmueli), and the contrast between modelling cultures (Breiman), we formalise prediction as a valid epistemological and methodological objective. Reviewing recent applications across economic subfields, we show how predictive models contribute to empirical analysis, particularly in complex or data-rich contexts. This perspective complements existing approaches and supports a more pluralistic methodology - one that values out-of-sample performance alongside interpretability and theoretical structure.

---

### Benchmark on Monocular Metric Depth Estimation in Wildlife Setting

Authors: Niccolò Niccoli, Lorenzo Seidenari, Ilaria Greco, Francesco Rovero
Published: 2025-10-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.04723v1

Camera traps are widely used for wildlife monitoring, but extracting accurate distance measurements from monocular images remains challenging due to the lack of depth information. While monocular depth estimation (MDE) methods have advanced significantly, their performance in natural wildlife environments has not been systematically evaluated. This work introduces the first benchmark for monocular metric depth estimation in wildlife monitoring conditions. We evaluate four state-of-the-art MDE methods (Depth Anything V2, ML Depth Pro, ZoeDepth, and Metric3D) alongside a geometric baseline on 93 camera trap images with ground truth distances obtained using calibrated ChARUCO patterns. Our results demonstrate that Depth Anything V2 achieves the best overall performance with a mean absolute error of 0.454m and correlation of 0.962, while methods like ZoeDepth show significant degradation in outdoor natural environments (MAE: 3.087m). We find that median-based depth extraction consistently outperforms mean-based approaches across all deep learning methods. Additionally, we analyze computational efficiency, with ZoeDepth being fastest (0.17s per image) but least accurate, while Depth Anything V2 provides an optimal balance of accuracy and speed (0.22s per image). This benchmark establishes performance baselines for wildlife applications and provides practical guidance for implementing depth estimation in conservation monitoring systems.

---

### BrokenMath: A Benchmark for Sycophancy in Theorem Proving with LLMs

Authors: Ivo Petrov, Jasper Dekoninck, Martin Vechev
Published: 2025-10-06
Categories: cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.04721v1

Large language models (LLMs) have recently shown strong performance on mathematical benchmarks. At the same time, they are prone to hallucination and sycophancy, often providing convincing but flawed proofs for incorrect mathematical statements provided by users. This significantly limits the applicability of LLMs in theorem proving, as verification of these flawed proofs must be done manually by expert mathematicians. However, existing benchmarks that measure sycophancy in mathematics are limited: they focus solely on final-answer problems, rely on very simple and often contaminated datasets, and construct benchmark samples using synthetic modifications that create ill-posed questions rather than well-posed questions that are demonstrably false. To address these issues, we introduce BrokenMath, the first benchmark for evaluating sycophantic behavior in LLMs within the context of natural language theorem proving. BrokenMath is built from advanced 2025 competition problems, which are perturbed with an LLM to produce false statements and subsequently refined through expert review. Using an LLM-as-a-judge framework, we evaluate state-of-the-art LLMs and agentic systems and find that sycophancy is widespread, with the best model, GPT-5, producing sycophantic answers 29% of the time. We further investigate several mitigation strategies, including test-time interventions and supervised fine-tuning on curated sycophantic examples. These approaches substantially reduce, but do not eliminate, sycophantic behavior.

---

### JSON Whisperer: Efficient JSON Editing with LLMs

Authors: Sarel Duanis, Asnat Greenstein-Messica, Eliya Habba
Published: 2025-10-06
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.04717v1

Large language models (LLMs) can modify JSON documents through natural language commands, but current approaches regenerate entire structures for each edit, resulting in computational inefficiency. We present JSON Whisperer, a framework that enables LLMs to generate RFC 6902 diff patches-expressing only the necessary modifications-rather than complete documents. We identify two key challenges in patch-based editing: (1) LLMs often miss related updates when generating isolated patches, and (2) array manipulations require tracking index shifts across operations, which LLMs handle poorly. To address these issues, we introduce EASE (Explicitly Addressed Sequence Encoding), which transforms arrays into dictionaries with stable keys, eliminating index arithmetic complexities. Our evaluation shows that patch generation with EASE reduces token usage by 31% while maintaining edit quality within 5% of full regeneration with particular gains for complex instructions and list manipulations. The dataset is available at: https://github.com/emnlp2025/JSON-Whisperer/

---

### Curved Boolean Logic: A Contextual Generalization of Propositional Logic with Algorithmic Consequences

Authors: Maximilian R. P. von Liechtenstein
Published: 2025-10-06
Categories: cs.LO, cs.AI, cs.CC, quant-ph
arXiv: https://arxiv.org/abs/2510.04716v3

Curved Boolean Logic (CBL) generalizes propositional logic by allowing local truth assignments that do not extend to a single global valuation, analogous to curvature in geometry. We give equivalent sheaf and exclusivity-graph semantics and a context-aware proof calculus that is conservative in the flat limit. We formalize CBL-SAT and basic complexity (NP-complete in general) and present operational operators (CBL-AC and CBL-CONS) that prune contradictions earlier on classical hardware. We model noise with iid, AR(1)-correlated, and adversarial bounded perturbations and provide permutation-based significance with Benjamini-Hochberg FDR control. A Colab-ready notebook (ancillary files) regenerates all figures and statistics. We position CBL relative to KCBS, CSW, and sheaf frameworks and outline links to SAT/CSP and robustness/adapter stability in large language models.

---

### Object-Centric Representation Learning for Enhanced 3D Semantic Scene Graph Prediction

Authors: KunHo Heo, GiHyun Kim, SuYeon Kim, MyeongAh Cho
Published: 2025-10-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.04714v5

3D Semantic Scene Graph Prediction aims to detect objects and their semantic relationships in 3D scenes, and has emerged as a crucial technology for robotics and AR/VR applications. While previous research has addressed dataset limitations and explored various approaches including Open-Vocabulary settings, they frequently fail to optimize the representational capacity of object and relationship features, showing excessive reliance on Graph Neural Networks despite insufficient discriminative capability. In this work, we demonstrate through extensive analysis that the quality of object features plays a critical role in determining overall scene graph accuracy. To address this challenge, we design a highly discriminative object feature encoder and employ a contrastive pretraining strategy that decouples object representation learning from the scene graph prediction. This design not only enhances object classification accuracy but also yields direct improvements in relationship prediction. Notably, when plugging in our pretrained encoder into existing frameworks, we observe substantial performance improvements across all evaluation metrics. Additionally, whereas existing approaches have not fully exploited the integration of relationship information, we effectively combine both geometric and semantic features to achieve superior relationship prediction. Comprehensive experiments on the 3DSSG dataset demonstrate that our approach significantly outperforms previous state-of-the-art methods. Our code is publicly available at https://github.com/VisualScienceLab-KHU/OCRL-3DSSG-Codes.

---

### ReactDiff: Fundamental Multiple Appropriate Facial Reaction Diffusion Model

Authors: Luo Cheng, Song Siyang, Yan Siyuan, Yu Zhen, Ge Zongyuan
Published: 2025-10-06
Categories: cs.CV, cs.HC, cs.MM
arXiv: https://arxiv.org/abs/2510.04712v1

The automatic generation of diverse and human-like facial reactions in dyadic dialogue remains a critical challenge for human-computer interaction systems. Existing methods fail to model the stochasticity and dynamics inherent in real human reactions. To address this, we propose ReactDiff, a novel temporal diffusion framework for generating diverse facial reactions that are appropriate for responding to any given dialogue context. Our key insight is that plausible human reactions demonstrate smoothness, and coherence over time, and conform to constraints imposed by human facial anatomy. To achieve this, ReactDiff incorporates two vital priors (spatio-temporal facial kinematics) into the diffusion process: i) temporal facial behavioral kinematics and ii) facial action unit dependencies. These two constraints guide the model toward realistic human reaction manifolds, avoiding visually unrealistic jitters, unstable transitions, unnatural expressions, and other artifacts. Extensive experiments on the REACT2024 dataset demonstrate that our approach not only achieves state-of-the-art reaction quality but also excels in diversity and reaction appropriateness.

---