# Research Papers — 2025-10 · bundle page 107 of 217 > Full-text markdown of papers #5301–5350 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/107 [← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/106.md) [Next bundle →](https://aipod.dev/papers/archive/2025-10/page/108.md) ### MUSE: Model-based Uncertainty-aware Similarity Estimation for zero-shot 2D Object Detection and Segmentation Authors: Sungmin Cho, Sungbum Park, Insoo Oh Published: 2025-10-15 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2510.17866v1 In this work, we introduce MUSE (Model-based Uncertainty-aware Similarity Estimation), a training-free framework designed for model-based zero-shot 2D object detection and segmentation. MUSE leverages 2D multi-view templates rendered from 3D unseen objects and 2D object proposals extracted from input query images. In the embedding stage, it integrates class and patch embeddings, where the patch embeddings are normalized using generalized mean pooling (GeM) to capture both global and local representations efficiently. During the matching stage, MUSE employs a joint similarity metric that combines absolute and relative similarity scores, enhancing the robustness of matching under challenging scenarios. Finally, the similarity score is refined through an uncertainty-aware object prior that adjusts for proposal reliability. Without any additional training or fine-tuning, MUSE achieves state-of-the-art performance on the BOP Challenge 2025, ranking first across the Classic Core, H3, and Industrial tracks. These results demonstrate that MUSE offers a powerful and generalizable framework for zero-shot 2D object detection and segmentation. --- ### InsideOut: Integrated RGB-Radiative Gaussian Splatting for Comprehensive 3D Object Representation Authors: Jungmin Lee, Seonghyuk Hong, Juyong Lee, Jaeyoon Lee, Jongwon Choi Published: 2025-10-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.17864v1 We introduce InsideOut, an extension of 3D Gaussian splatting (3DGS) that bridges the gap between high-fidelity RGB surface details and subsurface X-ray structures. The fusion of RGB and X-ray imaging is invaluable in fields such as medical diagnostics, cultural heritage restoration, and manufacturing. We collect new paired RGB and X-ray data, perform hierarchical fitting to align RGB and X-ray radiative Gaussian splats, and propose an X-ray reference loss to ensure consistent internal structures. InsideOut effectively addresses the challenges posed by disparate data representations between the two modalities and limited paired datasets. This approach significantly extends the applicability of 3DGS, enhancing visualization, simulation, and non-destructive testing capabilities across various domains. --- ### Robotic Classification of Divers' Swimming States using Visual Pose Keypoints as IMUs Authors: Demetrious T. Kutzke, Ying-Kun Wu, Elizabeth Terveen, Junaed Sattar Published: 2025-10-15 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2510.17863v1 Traditional human activity recognition uses either direct image analysis or data from wearable inertial measurement units (IMUs), but can be ineffective in challenging underwater environments. We introduce a novel hybrid approach that bridges this gap to monitor scuba diver safety. Our method leverages computer vision to generate high-fidelity motion data, effectively creating a ``pseudo-IMU'' from a stream of 3D human joint keypoints. This technique circumvents the critical problem of wireless signal attenuation in water, which plagues conventional diver-worn sensors communicating with an Autonomous Underwater Vehicle (AUV). We apply this system to the vital task of identifying anomalous scuba diver behavior that signals the onset of a medical emergency such as cardiac arrest -- a leading cause of scuba diving fatalities. By integrating our classifier onboard an AUV and conducting experiments with simulated distress scenarios, we demonstrate the utility and effectiveness of our method for advancing robotic monitoring and diver safety. --- ### DMTrack: Deformable State-Space Modeling for UAV Multi-Object Tracking with Kalman Fusion and Uncertainty-Aware Association Authors: Zenghuang Fu, Xiaofeng Han, Mingda Jia, Jin ming Yang, Qi Zeng, Muyang Zahng, Changwei Wang, Weiliang Meng, Xiaopeng Zhang Published: 2025-10-15 Categories: eess.SY, cs.CV arXiv: https://arxiv.org/abs/2510.17860v1 Multi-object tracking (MOT) from unmanned aerial vehicles (UAVs) presents unique challenges due to unpredictable object motion, frequent occlusions, and limited appearance cues inherent to aerial viewpoints. These issues are further exacerbated by abrupt UAV movements, leading to unreliable trajectory estimation and identity switches. Conventional motion models, such as Kalman filters or static sequence encoders, often fall short in capturing both linear and non-linear dynamics under such conditions. To tackle these limitations, we propose DMTrack, a deformable motion tracking framework tailored for UAV-based MOT. Our DMTrack introduces three key components: DeformMamba, a deformable state-space predictor that dynamically aggregates historical motion states for adaptive trajectory modeling; MotionGate, a lightweight gating module that fuses Kalman and Mamba predictions based on motion context and uncertainty; and an uncertainty-aware association strategy that enhances identity preservation by aligning motion trends with prediction confidence. Extensive experiments on the VisDrone-MOT and UAVDT benchmarks demonstrate that our DMTrack achieves state-of-the-art performance in identity consistency and tracking accuracy, particularly under high-speed and non-linear motion. Importantly, our method operates without appearance models and maintains competitive efficiency, highlighting its practicality for robust UAV-based tracking. --- ### Mixed Monotonicity Reachability Analysis of Neural ODE: A Trade-Off Between Tightness and Efficiency Authors: Abdelrahman Sayed Sayed, Pierre-Jean Meyer, Mohamed Ghazel Published: 2025-10-15 Categories: eess.SY, cs.LG arXiv: https://arxiv.org/abs/2510.17859v2 Neural ordinary differential equations (neural ODE) are powerful continuous-time machine learning models for depicting the behavior of complex dynamical systems, but their verification remains challenging due to limited reachability analysis tools adapted to them. We propose a novel interval-based reachability method that leverages continuous-time mixed monotonicity techniques for dynamical systems to compute an over-approximation for the neural ODE reachable sets. By exploiting the geometric structure of full initial sets and their boundaries via the homeomorphism property, our approach ensures efficient bound propagation. By embedding neural ODE dynamics into a mixed monotone system, our interval-based reachability approach, implemented in TIRA with single-step, incremental, and boundary-based approaches, provides sound and computationally efficient over-approximations compared with CORA's zonotopes and NNV2.0 star set representations, while trading tightness for efficiency. This trade-off makes our method particularly suited for high-dimensional, real-time, and safety-critical applications. Applying mixed monotonicity to neural ODE reachability analysis paves the way for lightweight formal analysis by leveraging the symmetric structure of monotone embeddings and the geometric simplicity of interval boxes, opening new avenues for scalable verification. This novel approach is illustrated on two numerical examples of a spiral system and a fixed-point attractor system modeled as a neural ODE. --- ### Shortcutting Pre-trained Flow Matching Diffusion Models is Almost Free Lunch Authors: Xu Cai, Yang Wu, Qianli Chen, Haoran Wu, Lichuan Xiang, Hongkai Wen Published: 2025-10-15 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2510.17858v1 We present an ultra-efficient post-training method for shortcutting large-scale pre-trained flow matching diffusion models into efficient few-step samplers, enabled by novel velocity field self-distillation. While shortcutting in flow matching, originally introduced by shortcut models, offers flexible trajectory-skipping capabilities, it requires a specialized step-size embedding incompatible with existing models unless retraining from scratch$\unicode{x2013}$a process nearly as costly as pretraining itself. Our key contribution is thus imparting a more aggressive shortcut mechanism to standard flow matching models (e.g., Flux), leveraging a unique distillation principle that obviates the need for step-size embedding. Working on the velocity field rather than sample space and learning rapidly from self-guided distillation in an online manner, our approach trains efficiently, e.g., producing a 3-step Flux less than one A100 day. Beyond distillation, our method can be incorporated into the pretraining stage itself, yielding models that inherently learn efficient, few-step flows without compromising quality. This capability also enables, to our knowledge, the first few-shot distillation method (e.g., 10 text-image pairs) for dozen-billion-parameter diffusion models, delivering state-of-the-art performance at almost free cost. --- ### CMIS-Net: A Cascaded Multi-Scale Individual Standardization Network for Backchannel Agreement Estimation Authors: Yuxuan Huang, Kangzhong Wang, Eugene Yujun Fu, Grace Ngai, Peter H. F. Ng Published: 2025-10-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.17855v1 Backchannels are subtle listener responses, such as nods, smiles, or short verbal cues like "yes" or "uh-huh," which convey understanding and agreement in conversations. These signals provide feedback to speakers, improve the smoothness of interaction, and play a crucial role in developing human-like, responsive AI systems. However, the expression of backchannel behaviors is often significantly influenced by individual differences, operating across multiple scales: from instant dynamics such as response intensity (frame-level) to temporal patterns such as frequency and rhythm preferences (sequence-level). This presents a complex pattern recognition problem that contemporary emotion recognition methods have yet to fully address. Particularly, existing individualized methods in emotion recognition often operate at a single scale, overlooking the complementary nature of multi-scale behavioral cues. To address these challenges, we propose a novel Cascaded Multi-Scale Individual Standardization Network (CMIS-Net) that extracts individual-normalized backchannel features by removing person-specific neutral baselines from observed expressions. Operating at both frame and sequence levels, this normalization allows model to focus on relative changes from each person's baseline rather than absolute expression values. Furthermore, we introduce an implicit data augmentation module to address the observed training data distributional bias, improving model generalization. Comprehensive experiments and visualizations demonstrate that CMIS-Net effectively handles individual differences and data imbalance, achieving state-of-the-art performance in backchannel agreement detection. --- ### Provenance of AI-Generated Images: A Vector Similarity and Blockchain-based Approach Authors: Jitendra Sharma, Arthur Carvalho, Suman Bhunia Published: 2025-10-15 Categories: cs.CV, cs.CR, cs.LG arXiv: https://arxiv.org/abs/2510.17854v1 Rapid advancement in generative AI and large language models (LLMs) has enabled the generation of highly realistic and contextually relevant digital content. LLMs such as ChatGPT with DALL-E integration and Stable Diffusion techniques can produce images that are often indistinguishable from those created by humans, which poses challenges for digital content authentication. Verifying the integrity and origin of digital data to ensure it remains unaltered and genuine is crucial to maintaining trust and legality in digital media. In this paper, we propose an embedding-based AI image detection framework that utilizes image embeddings and a vector similarity to distinguish AI-generated images from real (human-created) ones. Our methodology is built on the hypothesis that AI-generated images demonstrate closer embedding proximity to other AI-generated content, while human-created images cluster similarly within their domain. To validate this hypothesis, we developed a system that processes a diverse dataset of AI and human-generated images through five benchmark embedding models. Extensive experimentation demonstrates the robustness of our approach, and our results confirm that moderate to high perturbations minimally impact the embedding signatures, with perturbed images maintaining close similarity matches to their original versions. Our solution provides a generalizable framework for AI-generated image detection that balances accuracy with computational efficiency. --- ### A Storm-Centric 250 m NEXRAD Level-II Dataset for High-Resolution ML Nowcasting Authors: Andy Shi Published: 2025-10-15 Categories: physics.ao-ph, cs.LG arXiv: https://arxiv.org/abs/2510.16031v2 Machine learning-based precipitation nowcasting relies on high-fidelity radar reflectivity sequences to model the short-term evolution of convective storms. However, the development of models capable of predicting extreme weather has been constrained by the coarse resolution (1-2 km) of existing public radar datasets, such as SEVIR, HKO-7, and GridRad-Severe, which smooth the fine-scale structures essential for accurate forecasting. To address this gap, we introduce Storm250-L2, a storm-centric radar dataset derived from NEXRAD Level-II and GridRad-Severe data. We algorithmically crop a fixed, high-resolution (250 m) window around GridRad-Severe storm tracks, preserve the native polar geometry, and provide temporally consistent sequences of both per-tilt sweeps and a pseudo-composite reflectivity product. The dataset comprises thousands of storm events across the continental United States, packaged in HDF5 tensors with rich context metadata and reproducible manifests. --- ### TAO: Tolerance-Aware Optimistic Verification for Floating-Point Neural Networks Authors: Jianzhu Yao, Hongxu Su, Taobo Liao, Zerui Cheng, Huan Zhang, Xuechao Wang, Pramod Viswanath Published: 2025-10-15 Categories: cs.CR, cs.AI, cs.LG, eess.SY arXiv: https://arxiv.org/abs/2510.16028v4 Neural networks increasingly run on hardware outside the user's control (cloud GPUs, inference marketplaces). Yet ML-as-a-Service reveals little about what actually ran or whether returned outputs faithfully reflect the intended inputs. Users lack recourse against service downgrades (model swaps, quantization, graph rewrites, or discrepancies like altered ad embeddings). Verifying outputs is hard because floating-point(FP) execution on heterogeneous accelerators is inherently nondeterministic. Existing approaches are either impractical for real FP neural networks or reintroduce vendor trust. We present TAO: a Tolerance Aware Optimistic verification protocol that accepts outputs within principled operator-level acceptance regions rather than requiring bitwise equality. TAO combines two error models: (i) sound per-operator IEEE-754 worst-case bounds and (ii) tight empirical percentile profiles calibrated across hardware. Discrepancies trigger a Merkle-anchored, threshold-guided dispute game that recursively partitions the computation graph until one operator remains, where adjudication reduces to a lightweight theoretical-bound check or a small honest-majority vote against empirical thresholds. Unchallenged results finalize after a challenge window, without requiring trusted hardware or deterministic kernels. We implement TAO as a PyTorch-compatible runtime and a contract layer currently deployed on Ethereum Holesky testnet. The runtime instruments graphs, computes per-operator bounds, and runs unmodified vendor kernels in FP32 with negligible overhead (0.3% on Qwen3-8B). Across CNNs, Transformers and diffusion models on A100, H100, RTX6000, RTX4090, empirical thresholds are $10^2-10^3$ times tighter than theoretical bounds, and bound-aware adversarial attacks achieve 0% success. Together, TAO reconciles scalability with verifiability for real-world heterogeneous ML compute. --- ### A tutorial on discovering and quantifying the effect of latent causal sources of multimodal EHR data Authors: Marco Barbero-Mota, Eric V. Strobl, John M. Still, William W. Stead, Thomas A. Lasko Published: 2025-10-15 Categories: cs.LG, stat.AP arXiv: https://arxiv.org/abs/2510.16026v2 We provide an accessible description of a peer-reviewed generalizable causal machine learning pipeline to (i) discover latent causal sources of large-scale electronic health records observations, and (ii) quantify the source causal effects on clinical outcomes. We illustrate how imperfect multimodal clinical data can be processed, decomposed into probabilistic independent latent sources, and used to train taskspecific causal models from which individual causal effects can be estimated. We summarize the findings of the two real-world applications of the approach to date as a demonstration of its versatility and utility for medical discovery at scale. --- ### On-Chain Decentralized Learning and Cost-Effective Inference for DeFi Attack Mitigation Authors: Abdulrahman Alhaidari, Balaji Palanisamy, Prashant Krishnamurthy Published: 2025-10-15 Categories: cs.CR, cs.AI, cs.DC, cs.LG arXiv: https://arxiv.org/abs/2510.16024v1 Billions of dollars are lost every year in DeFi platforms by transactions exploiting business logic or accounting vulnerabilities. Existing defenses focus on static code analysis, public mempool screening, attacker contract detection, or trusted off-chain monitors, none of which prevents exploits submitted through private relays or malicious contracts that execute within the same block. We present the first decentralized, fully on-chain learning framework that: (i) performs gas-prohibitive computation on Layer-2 to reduce cost, (ii) propagates verified model updates to Layer-1, and (iii) enables gas-bounded, low-latency inference inside smart contracts. A novel Proof-of-Improvement (PoIm) protocol governs the training process and verifies each decentralized micro update as a self-verifying training transaction. Updates are accepted by \textit{PoIm} only if they demonstrably improve at least one core metric (e.g., accuracy, F1-score, precision, or recall) on a public benchmark without degrading any of the other core metrics, while adversarial proposals get financially penalized through an adaptable test set for evolving threats. We develop quantization and loop-unrolling techniques that enable inference for logistic regression, SVM, MLPs, CNNs, and gated RNNs (with support for formally verified decision tree inference) within the Ethereum block gas limit, while remaining bit-exact to their off-chain counterparts, formally proven in Z3. We curate 298 unique real-world exploits (2020 - 2025) with 402 exploit transactions across eight EVM chains, collectively responsible for \$3.74 B in losses. --- ### A Conformation-Centric Generative Foundation Model for Linear Polymer Modeling and Design Authors: Fanmeng Wang, Ruochao Wang, Shan Mei, Wentao Guo, Hongshuai Wang, Qi Ou, Zhifeng Gao, Hongteng Xu Published: 2025-10-15 Categories: cs.LG, cond-mat.mtrl-sci arXiv: https://arxiv.org/abs/2510.16023v2 Linear polymers, macromolecules formed from monomers covalently bonded into continuous chains, underpin countless technologies and are indispensable to modern life. While deep learning is advancing polymer science, existing methods typically represent the whole linear polymer solely through monomer-level descriptors, overlooking the global structural information inherent in polymer conformations, which ultimately limits their practical performance. Moreover, this important field still lacks a dedicated foundation model that can effectively support diverse downstream tasks, thereby severely constraining progress. To address these challenges, we introduce PolyConFM, a foundation model tailored for modeling and designing linear polymers through conformation-centric generative pretraining. Recognizing that each linear polymer is essentially a continuous chain whose conformation can be naturally decomposed into a sequence of local conformations (i.e., those of its repeating units), we pretrain PolyConFM under the conditional generation paradigm, reconstructing these local conformations via masked autoregressive (MAR) modeling and further generating their orientation transformations to recover the corresponding polymer conformation. Meanwhile, we construct a linear polymer conformation dataset via molecular dynamics simulations to mitigate data sparsity, thereby enabling conformation-centric pretraining. Experiments demonstrate that PolyConFM consistently outperforms representative task-specific methods across diverse downstream tasks, thereby equipping polymer science with a powerful tool targeting linear polymers. --- ### Breaking Memorization Barriers in LLM Code Fine-Tuning via Information Bottleneck for Improved Generalization Authors: Changsheng Wang, Xin Chen, Sijia Liu, Ke Ding Published: 2025-10-15 Categories: cs.LG, cs.SE arXiv: https://arxiv.org/abs/2510.16022v1 Adapting pretrained large language models (LLMs) to code domains via supervised fine-tuning (FT) has been commonly used for code generation. However, we identify a previously underappreciated failure mode, the memorization barrier, where strong memorization of downstream code data in the base model could trap optimization and prevent the standard FT from effectively acquiring new, generalizable code knowledge. To overcome this barrier, we propose the information bottleneck (IB)-guided fine-tuning, termed IB-FT, which applies an IB penalty on hidden representations of the code data to compress spurious, memorized features while preserving task-relevant information. Extensive experiments on two code benchmarks (OriGen and Evol-CodeAlpaca-V1) show that IB-FT substantially alleviates the memorization barrier, improves top-1 performance (Pass@$1$), and yields far more stable gains under the stricter multi-sample metric Pass@$k^{(m)}$ (a problem counts as solved only if at least $m$ of $k$ samples pass unit tests) compared with conventional FT. --- ### Feature-driven reinforcement learning for photovoltaic in continuous intraday trading Authors: Arega Getaneh Abate, Xiao-Bing Zhang, Xiufeng Liu, Ruyu Liu Published: 2025-10-15 Categories: cs.LG, econ.GN arXiv: https://arxiv.org/abs/2510.16021v3 Sequential intraday electricity trading allows photovoltaic (PV) operators to reduce imbalance settlement costs as forecasts improve throughout the day. Yet deployable trading policies must jointly handle forecast uncertainty, intraday prices, liquidity, and the asymmetric economics of PV imbalance exposure. This paper proposes a feature-driven reinforcement learning (FDRL) framework for intraday PV trading in the Nordic market. Its main methodological contribution is a corrected reward that evaluates performance relative to a no-trade baseline, removing policy-independent noise that can otherwise push reinforcement learning toward inactive policies in high-price regimes. The framework combines this objective with a predominantly linear policy and a closed-form execution surrogate for efficient, interpretable training. In a strict walk-forward evaluation over 2021-2024 across four Nordic bidding zones (DK1, DK2, SE3, SE4), the method delivers statistically significant profit improvements over the spot-only baseline in every zone. Portfolio experiments show that a pooled cross-zone policy can match zone-specific models, while transfer-learning results indicate a two-cluster market structure and effective deployment in new zones with limited local data. The proposed framework offers an interpretable and computationally practical way to reduce imbalance costs, while the transfer results provide guidance for scaling strategies across bidding zones with different market designs. --- ### Airfoil optimization using Design-by-Morphing with minimized design-space dimensionality Authors: Sangjoon Lee, Haris Moazam Sheikh Published: 2025-10-15 Categories: cs.LG, physics.flu-dyn arXiv: https://arxiv.org/abs/2510.16020v2 Effective airfoil geometry optimization requires exploring a diverse range of designs using as few design variables as possible. This study introduces AirDbM, a Design-by-Morphing (DbM) approach specialized for airfoil optimization that systematically reduces design-space dimensionality. AirDbM selects an optimal set of 12 baseline airfoils from the UIUC airfoil database, which contains over 1,600 shapes, by sequentially adding the baseline that most increases the design capacity. With these baselines, AirDbM reconstructs 99 % of the database with a mean absolute error below 0.005, which matches the performance of a previous DbM approach that used more baselines. In multi-objective aerodynamic optimization, AirDbM demonstrates rapid convergence and achieves a Pareto front with a greater hypervolume than that of the previous larger-baseline study, where new Pareto-optimal solutions are discovered with enhanced lift-to-drag ratios at moderate stall tolerances. Furthermore, AirDbM demonstrates outstanding adaptability for reinforcement learning (RL) agents in generating airfoil geometry when compared to conventional airfoil parameterization methods, implying the broader potential of DbM in machine learning-driven design. --- ### InfraGPT Smart Infrastructure: An End-to-End VLM-Based Framework for Detecting and Managing Urban Defects Authors: Ibrahim Sheikh Mohamed, Abdullah Yahya Abdullah Omaisan Published: 2025-10-15 Categories: cs.CV, cs.AI, cs.CL, cs.RO arXiv: https://arxiv.org/abs/2510.16017v1 Infrastructure in smart cities is increasingly monitored by networks of closed circuit television (CCTV) cameras. Roads, bridges and tunnels develop cracks, potholes, and fluid leaks that threaten public safety and require timely repair. Manual inspection is costly and hazardous, and existing automatic systems typically address individual defect types or provide unstructured outputs that cannot directly guide maintenance crews. This paper proposes a comprehensive pipeline that leverages street CCTV streams for multi defect detection and segmentation using the YOLO family of object detectors and passes the detections to a vision language model (VLM) for scene aware summarization. The VLM generates a structured action plan in JSON format that includes incident descriptions, recommended tools, dimensions, repair plans, and urgent alerts. We review literature on pothole, crack and leak detection, highlight recent advances in large vision language models such as QwenVL and LLaVA, and describe the design of our early prototype. Experimental evaluation on public datasets and captured CCTV clips demonstrates that the system accurately identifies diverse defects and produces coherent summaries. We conclude by discussing challenges and directions for scaling the system to city wide deployments. --- ### Transfer learning strategies for accelerating reinforcement-learning-based flow control Authors: Saeed Salehi Published: 2025-10-15 Categories: cs.LG, physics.flu-dyn arXiv: https://arxiv.org/abs/2510.16016v1 This work investigates transfer learning strategies to accelerate deep reinforcement learning (DRL) for multifidelity control of chaotic fluid flows. Progressive neural networks (PNNs), a modular architecture designed to preserve and reuse knowledge across tasks, are employed for the first time in the context of DRL-based flow control. In addition, a comprehensive benchmarking of conventional fine-tuning strategies is conducted, evaluating their performance, convergence behavior, and ability to retain transferred knowledge. The Kuramoto-Sivashinsky (KS) system is employed as a benchmark to examine how knowledge encoded in control policies, trained in low-fidelity environments, can be effectively transferred to high-fidelity settings. Systematic evaluations show that while fine-tuning can accelerate convergence, it is highly sensitive to pretraining duration and prone to catastrophic forgetting. In contrast, PNNs enable stable and efficient transfer by preserving prior knowledge and providing consistent performance gains, and are notably robust to overfitting during the pretraining phase. Layer-wise sensitivity analysis further reveals how PNNs dynamically reuse intermediate representations from the source policy while progressively adapting deeper layers to the target task. Moreover, PNNs remain effective even when the source and target environments differ substantially, such as in cases with mismatched physical regimes or control objectives, where fine-tuning strategies often result in suboptimal adaptation or complete failure of knowledge transfer. The results highlight the potential of novel transfer learning frameworks for robust, scalable, and computationally efficient flow control that can potentially be applied to more complex flow configurations. --- ### Decision-focused Sensing and Forecasting for Adaptive and Rapid Flood Response: An Implicit Learning Approach Authors: Qian Sun, Graham Hults, Susu Xu Published: 2025-10-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.16015v1 Timely and reliable decision-making is vital for flood emergency response, yet it remains severely hindered by limited and imprecise situational awareness due to various budget and data accessibility constraints. Traditional flood management systems often rely on in-situ sensors to calibrate remote sensing-based large-scale flood depth forecasting models, and further take flood depth estimates to optimize flood response decisions. However, these approaches often take fixed, decision task-agnostic strategies to decide where to put in-situ sensors (e.g., maximize overall information gain) and train flood forecasting models (e.g., minimize average forecasting errors), but overlook that systems with the same sensing gain and average forecasting errors may lead to distinct decisions. To address this, we introduce a novel decision-focused framework that strategically selects locations for in-situ sensor placement and optimize spatio-temporal flood forecasting models to optimize downstream flood response decision regrets. Our end-to-end pipeline integrates four components: a contextual scoring network, a differentiable sensor selection module under hard budget constraints, a spatio-temporal flood reconstruction and forecasting model, and a differentiable decision layer tailored to task-specific objectives. Central to our approach is the incorporation of Implicit Maximum Likelihood Estimation (I-MLE) to enable gradient-based learning over discrete sensor configurations, and probabilistic decision heads to enable differentiable approximation to various constrained disaster response tasks. --- ### STAR: Boosting Time Series Foundation Models for Anomaly Detection through State-aware Adapter Authors: Hanyin Cheng, Ruitong Zhang, Yuning Lu, Peng Chen, Meng Wang, Yang Shu, Bin Yang, Chenjuan Guo Published: 2025-10-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.16014v1 While Time Series Foundation Models (TSFMs) have demonstrated remarkable success in Multivariate Time Series Anomaly Detection (MTSAD), however, in real-world industrial scenarios, many time series comprise not only numerical variables such as temperature and flow, but also numerous discrete state variables that describe the system status, such as valve on/off or day of the week. Existing TSFMs often overlook the distinct categorical nature of state variables and their critical role as conditions, typically treating them uniformly with numerical variables. This inappropriate modeling approach prevents the model from fully leveraging state information and even leads to a significant degradation in detection performance after state variables are integrated. To address this critical limitation, this paper proposes a novel STate-aware AdapteR (STAR). STAR is a plug-and-play module designed to enhance the capability of TSFMs in modeling and leveraging state variables during the fine-tuning stage. Specifically, STAR comprisesthree core components: (1) We design an Identity-guided State Encoder, whicheffectively captures the complex categorical semantics of state variables through a learnable State Memory. (2) We propose a Conditional Bottleneck Adapter, which dynamically generates low-rank adaptation parameters conditioned on the current state, thereby flexibly injecting the influence of state variables into the backbone model. (3) We also introduce a Numeral-State Matching module to more effectively detect anomalies inherent to the state variables themselves. Extensive experiments conducted on real-world datasets demonstrate that STAR can improve the performance of existing TSFMs on MTSAD. --- ### AGNES: Adaptive Graph Neural Network and Dynamic Programming Hybrid Framework for Real-Time Nanopore Seed Chaining Authors: Jahidul Arafat, Sanjaya Poudel Published: 2025-10-15 Categories: q-bio.GN, cs.LG arXiv: https://arxiv.org/abs/2510.16013v3 Nanopore sequencing enables real-time long-read DNA sequencing with reads exceeding 10 kilobases, but inherent error rates of 12-15 percent present significant computational challenges for read alignment. The critical seed chaining step must connect exact k-mer matches between reads and reference genomes while filtering spurious matches, yet state-of-the-art methods rely on fixed gap penalty functions unable to adapt to varying genomic contexts including tandem repeats and structural variants. This paper presents RawHash3, a hybrid framework combining graph neural networks with classical dynamic programming for adaptive seed chaining that maintains real-time performance while providing statistical guarantees. We formalize seed chaining as graph learning where seeds constitute nodes with 12-dimensional feature vectors and edges encode 8-dimensional spatial relationships including gap consistency. Our architecture employs three-layer EdgeConv GNN with confidence-based method selection that dynamically switches between learned guidance and algorithmic fallback. Comprehensive evaluation on 1,000 synthetic nanopore reads with 5,200 test seeds demonstrates RawHash3 achieves 99.94 percent precision and 40.07 percent recall, representing statistically significant 25.0 percent relative improvement over baseline with p less than 0.001. The system maintains median inference latency of 1.59ms meeting real-time constraints, while demonstrating superior robustness with 100 percent success rate under 20 percent label corruption versus baseline degradation to 30.3 percent. Cross-validation confirms stability establishing graph neural networks as viable approach for production genomics pipelines. --- ### VaultGemma: A Differentially Private Gemma Model Authors: Amer Sinha, Thomas Mesnard, Ryan McKenna, Daogao Liu, Christopher A. Choquette-Choo, Yangsibo Huang, Da Yu, George Kaissis, Zachary Charles, Ruibo Liu, Lynn Chua, Pritish Kamath et al. Published: 2025-10-15 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2510.15001v2 We introduce VaultGemma 1B, a 1 billion parameter model within the Gemma family, fully trained with differential privacy. Pretrained on the identical data mixture used for the Gemma 2 series, VaultGemma 1B represents a significant step forward in privacy-preserving large language models. We openly release this model to the community --- ### Estimand framework and intercurrent events handling for clinical trials with time-to-event outcomes Authors: Yixin Fang, Man Jin Published: 2025-10-15 Categories: stat.ME, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2510.15000v1 The ICH E9(R1) guideline presents a framework of estimand for clinical trials, proposes five strategies for handling intercurrent events (ICEs), and provides a comprehensive discussion and many real-life clinical examples for quantitative outcomes and categorical outcomes. However, in ICH E9(R1) the discussion is lacking for time-to-event (TTE) outcomes. In this paper, we discuss how to define estimands and how to handle ICEs for clinical trials with TTE outcomes. Specifically, we discuss six ICE handling strategies, including those five strategies proposed by ICH E9(R1) and a new strategy, the competing-risk strategy. Compared with ICH E9(R1), the novelty of this paper is three-fold: (1) the estimands are defined in terms of potential outcomes, (2) the methods can utilize time-dependent covariates straightforwardly, and (3) the efficient estimators are discussed accordingly. --- ### Optimal Control Theoretic Neural Optimizer: From Backpropagation to Dynamic Programming Authors: Guan-Horng Liu, Tianrong Chen, Evangelos A. Theodorou Published: 2025-10-15 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2510.14168v1 Optimization of deep neural networks (DNNs) has been a driving force in the advancement of modern machine learning and artificial intelligence. With DNNs characterized by a prolonged sequence of nonlinear propagation, determining their optimal parameters given an objective naturally fits within the framework of Optimal Control Programming. Such an interpretation of DNNs as dynamical systems has proven crucial in offering a theoretical foundation for principled analysis from numerical equations to physics. In parallel to these theoretical pursuits, this paper focuses on an algorithmic perspective. Our motivated observation is the striking algorithmic resemblance between the Backpropagation algorithm for computing gradients in DNNs and the optimality conditions for dynamical systems, expressed through another backward process known as dynamic programming. Consolidating this connection, where Backpropagation admits a variational structure, solving an approximate dynamic programming up to the first-order expansion leads to a new class of optimization methods exploring higher-order expansions of the Bellman equation. The resulting optimizer, termed Optimal Control Theoretic Neural Optimizer (OCNOpt), enables rich algorithmic opportunities, including layer-wise feedback policies, game-theoretic applications, and higher-order training of continuous-time models such as Neural ODEs. Extensive experiments demonstrate that OCNOpt improves upon existing methods in robustness and efficiency while maintaining manageable computational complexity, paving new avenues for principled algorithmic design grounded in dynamical systems and optimal control theory. --- ### Towards Reversible Model Merging For Low-rank Weights Authors: Mohammadsajad Alipour, Mohammad Mohammadi Amiri Published: 2025-10-15 Categories: cs.LG, cs.AI, cs.CL, cs.CV arXiv: https://arxiv.org/abs/2510.14163v1 Model merging aims to combine multiple fine-tuned models into a single set of weights that performs well across all source tasks. While prior work has shown that merging can approximate the performance of individual fine-tuned models for each task, it largely overlooks scenarios where models are compressed into low-rank representations, either through low-rank adaptation (LoRA) or post-training singular value decomposition (SVD). We first demonstrate that applying conventional merging methods to low-rank weights leads to severe performance degradation in the merged model. Motivated by this phenomenon, we propose a fundamentally different approach: instead of collapsing all adapters into one set of weights, we construct a compact basis (e.g., an equivalent of holding two or more models) from which original task-specific models can be recovered via linear combination. This reframes merging as generating a reconstruction-capable model space rather than producing a single merged model. Crucially, this allows us to ``revert'' to each individual model when needed, recognizing that no merged model can consistently outperform one specialized for its task. Building on this insight, we introduce our method, Reversible Model Merging (RMM), an efficient, data-free, and flexible method that provides a closed-form solution for selecting the optimal basis of model weights and task-specific coefficients for linear combination. Extensive experiments across diverse datasets and model scales demonstrate that RMM consistently outperforms existing merging approaches, preserving the performance of low-rank compressed models by a significant margin. --- ### FinAI Data Assistant: LLM-based Financial Database Query Processing with the OpenAI Function Calling API Authors: Juhyeong Kim, Yejin Kim, Youngbin Lee, Hyunwoo Byun Published: 2025-10-15 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2510.14162v2 We present FinAI Data Assistant, a practical approach for natural-language querying over financial databases that combines large language models (LLMs) with the OpenAI Function Calling API. Rather than synthesizing complete SQL via text-to-SQL, our system routes user requests to a small library of vetted, parameterized queries, trading generative flexibility for reliability, low latency, and cost efficiency. We empirically study three questions: (RQ1) whether LLMs alone can reliably recall or extrapolate time-dependent financial data without external retrieval; (RQ2) how well LLMs map company names to stock ticker symbols; and (RQ3) whether function calling outperforms text-to-SQL for end-to-end database query processing. Across controlled experiments on prices and fundamentals, LLM-only predictions exhibit non-negligible error and show look-ahead bias primarily for stock prices relative to model knowledge cutoffs. Ticker-mapping accuracy is near-perfect for NASDAQ-100 constituents and high for S\&P~500 firms. Finally, FinAI Data Assistant achieves lower latency and cost and higher reliability than a text-to-SQL baseline on our task suite. We discuss design trade-offs, limitations, and avenues for deployment. --- ### Data Understanding Survey: Pursuing Improved Dataset Characterization Via Tensor-based Methods Authors: Matthew D. Merris, Tim Andersen Published: 2025-10-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.14161v1 In the evolving domains of Machine Learning and Data Analytics, existing dataset characterization methods such as statistical, structural, and model-based analyses often fail to deliver the deep understanding and insights essential for innovation and explainability. This work surveys the current state-of-the-art conventional data analytic techniques and examines their limitations, and discusses a variety of tensor-based methods and how these may provide a more robust alternative to traditional statistical, structural, and model-based dataset characterization techniques. Through examples, we illustrate how tensor methods unveil nuanced data characteristics, offering enhanced interpretability and actionable intelligence. We advocate for the adoption of tensor-based characterization, promising a leap forward in understanding complex datasets and paving the way for intelligent, explainable data-driven discoveries. --- ### On Evaluating Loss Functions for Stock Ranking: An Empirical Analysis With Transformer Model Authors: Jan Kwiatkowski, Jarosław A. Chudziak Published: 2025-10-15 Categories: cs.LG, q-fin.PM arXiv: https://arxiv.org/abs/2510.14156v1 Quantitative trading strategies rely on accurately ranking stocks to identify profitable investments. Effective portfolio management requires models that can reliably order future stock returns. Transformer models are promising for understanding financial time series, but how different training loss functions affect their ability to rank stocks well is not yet fully understood. Financial markets are challenging due to their changing nature and complex relationships between stocks. Standard loss functions, which aim for simple prediction accuracy, often aren't enough. They don't directly teach models to learn the correct order of stock returns. While many advanced ranking losses exist from fields such as information retrieval, there hasn't been a thorough comparison to see how well they work for ranking financial returns, especially when used with modern Transformer models for stock selection. This paper addresses this gap by systematically evaluating a diverse set of advanced loss functions including pointwise, pairwise, listwise for daily stock return forecasting to facilitate rank-based portfolio selection on S&P 500 data. We focus on assessing how each loss function influences the model's ability to discern profitable relative orderings among assets. Our research contributes a comprehensive benchmark revealing how different loss functions impact a model's ability to learn cross-sectional and temporal patterns crucial for portfolio selection, thereby offering practical guidance for optimizing ranking-based trading strategies. --- ### Combining Reinforcement Learning and Behavior Trees for NPCs in Video Games with AMD Schola Authors: Tian Liu, Alex Cann, Ian Colbert, Mehdi Saeedi Published: 2025-10-15 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.14154v1 While the rapid advancements in the reinforcement learning (RL) research community have been remarkable, the adoption in commercial video games remains slow. In this paper, we outline common challenges the Game AI community faces when using RL-driven NPCs in practice, and highlight the intersection of RL with traditional behavior trees (BTs) as a crucial juncture to be explored further. Although the BT+RL intersection has been suggested in several research papers, its adoption is rare. We demonstrate the viability of this approach using AMD Schola -- a plugin for training RL agents in Unreal Engine -- by creating multi-task NPCs in a complex 3D environment inspired by the commercial video game ``The Last of Us". We provide detailed methodologies for jointly training RL models with BTs while showcasing various skills. --- ### CodeEvolve: an open source evolutionary coding agent for algorithmic discovery and optimization Authors: Henrique Assumpção, Diego Ferreira, Leandro Campos, Fabricio Murai Published: 2025-10-15 Categories: cs.AI, cs.LG, cs.NE arXiv: https://arxiv.org/abs/2510.14150v6 We introduce CodeEvolve, an open-source framework that couples large language models with island-based evolutionary search for end-to-end algorithmic discovery. CodeEvolve integrates inspiration-based crossover, meta-prompting, and depth-based refinement on top of a CVT-MAP-Elites archive and a weighted LLM ensemble to generate optimized solutions for complex problems. On the AlphaEvolve benchmark suite, CodeEvolve matches or surpasses the reported AlphaEvolve results on 5 of 9 problems and, under matched conditions, outperforms the open-source frameworks OpenEvolve and ShinkaEvolve on 6 of 9. With the open-weight Qwen3-Coder-30B backbone, it surpasses the reported AlphaEvolve score on both CirclePackingSquare instances at roughly an order of magnitude lower cost than a frontier closed-source ensemble, and remains competitive with EoH on heuristic-design tasks without retuning. Ablations show that the interaction between CodeEvolve's components, rather than any single operator, drives these results. We release the framework, experimental data, and practical hyperparameter guidelines at https://github.com/inter-co/science-codeevolve. --- ### PoissonNet: A Local-Global Approach for Learning on Surfaces Authors: Arman Maesumi, Tanish Makadia, Thibault Groueix, Vladimir G. Kim, Daniel Ritchie, Noam Aigerman Published: 2025-10-15 Categories: cs.GR, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2510.14146v1 Many network architectures exist for learning on meshes, yet their constructions entail delicate trade-offs between difficulty learning high-frequency features, insufficient receptive field, sensitivity to discretization, and inefficient computational overhead. Drawing from classic local-global approaches in mesh processing, we introduce PoissonNet, a novel neural architecture that overcomes all of these deficiencies by formulating a local-global learning scheme, which uses Poisson's equation as the primary mechanism for feature propagation. Our core network block is simple; we apply learned local feature transformations in the gradient domain of the mesh, then solve a Poisson system to propagate scalar feature updates across the surface globally. Our local-global learning framework preserves the features's full frequency spectrum and provides a truly global receptive field, while remaining agnostic to mesh triangulation. Our construction is efficient, requiring far less compute overhead than comparable methods, which enables scalability -- both in the size of our datasets, and the size of individual training samples. These qualities are validated on various experiments where, compared to previous intrinsic architectures, we attain state-of-the-art performance on semantic segmentation and parameterizing highly-detailed animated surfaces. Finally, as a central application of PoissonNet, we show its ability to learn deformations, significantly outperforming state-of-the-art architectures that learn on surfaces. --- ### High-Dimensional BWDM: A Robust Nonparametric Clustering Validation Index for Large-Scale Data Authors: Mohammed Baragilly, Hend Gabr Published: 2025-10-15 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2510.14145v1 Determining the appropriate number of clusters in unsupervised learning is a central problem in statistics and data science. Traditional validity indices such as Calinski-Harabasz, Silhouette, and Davies-Bouldin-depend on centroid-based distances and therefore degrade in high-dimensional or contaminated data. This paper proposes a new robust, nonparametric clustering validation framework, the High-Dimensional Between-Within Distance Median (HD-BWDM), which extends the recently introduced BWDM criterion to high-dimensional spaces. HD-BWDM integrates random projection and principal component analysis to mitigate the curse of dimensionality and applies trimmed clustering and medoid-based distances to ensure robustness against outliers. We derive theoretical results showing consistency and convergence under Johnson-Lindenstrauss embeddings. Extensive simulations demonstrate that HD-BWDM remains stable and interpretable under high-dimensional projections and contamination, providing a robust alternative to traditional centroid-based validation criteria. The proposed method provides a theoretically grounded, computationally efficient stopping rule for nonparametric clustering in modern high-dimensional applications. --- ### cubic: CUDA-accelerated 3D Bioimage Computing Authors: Alexandr A. Kalinin, Anne E. Carpenter, Shantanu Singh, Matthew J. O'Meara Published: 2025-10-15 Categories: cs.CV, q-bio.QM arXiv: https://arxiv.org/abs/2510.14143v1 Quantitative analysis of multidimensional biological images is useful for understanding complex cellular phenotypes and accelerating advances in biomedical research. As modern microscopy generates ever-larger 2D and 3D datasets, existing computational approaches are increasingly limited by their scalability, efficiency, and integration with modern scientific computing workflows. Existing bioimage analysis tools often lack application programmable interfaces (APIs), do not support graphics processing unit (GPU) acceleration, lack broad 3D image processing capabilities, and/or have poor interoperability for compute-heavy workflows. Here, we introduce cubic, an open-source Python library that addresses these challenges by augmenting widely used SciPy and scikit-image APIs with GPU-accelerated alternatives from CuPy and RAPIDS cuCIM. cubic's API is device-agnostic and dispatches operations to GPU when data reside on the device and otherwise executes on CPU, seamlessly accelerating a broad range of image processing routines. This approach enables GPU acceleration of existing bioimage analysis workflows, from preprocessing to segmentation and feature extraction for 2D and 3D data. We evaluate cubic both by benchmarking individual operations and by reproducing existing deconvolution and segmentation pipelines, achieving substantial speedups while maintaining algorithmic fidelity. These advances establish a robust foundation for scalable, reproducible bioimage analysis that integrates with the broader Python scientific computing ecosystem, including other GPU-accelerated methods, enabling both interactive exploration and automated high-throughput analysis workflows. cubic is openly available at https://github$.$com/alxndrkalinin/cubic --- ### Inferred global dense residue transition graphs from primary structure sequences enable protein interaction prediction via directed graph convolutional neural networks Authors: Islam Akef Ebeid, Haoteng Tang, Pengfei Gu Published: 2025-10-15 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.14139v1 Introduction Accurate prediction of protein-protein interactions (PPIs) is crucial for understanding cellular functions and advancing drug development. Existing in-silico methods use direct sequence embeddings from Protein Language Models (PLMs). Others use Graph Neural Networks (GNNs) for 3D protein structures. This study explores less computationally intensive alternatives. We introduce a novel framework for downstream PPI prediction through link prediction. Methods We introduce a two-stage graph representation learning framework, ProtGram-DirectGCN. First, we developed ProtGram. This approach models a protein's primary structure as a hierarchy of globally inferred n-gram graphs. In these graphs, residue transition probabilities define edge weights. Each edge connects a pair of residues in a directed graph. The probabilities are aggregated from a large corpus of sequences. Second, we propose DirectGCN, a custom directed graph convolutional neural network. This model features a unique convolutional layer. It processes information through separate path-specific transformations: incoming, outgoing, and undirected. A shared transformation is also applied. These paths are combined via a learnable gating mechanism. We apply DirectGCN to ProtGram graphs to learn residue-level embeddings. These embeddings are pooled via attention to generate protein-level embeddings for prediction. Results We first established the efficacy of DirectGCN on standard node classification benchmarks. Its performance matches established methods on general datasets. The model excels at complex, directed graphs with dense, heterophilic structures. When applied to PPI prediction, the full ProtGram-DirectGCN framework delivers robust predictive power. This strong performance holds even with limited training data. --- ### Learning Wireless Interference Patterns: Decoupled GNN for Throughput Prediction in Heterogeneous Multi-Hop p-CSMA Networks Authors: Faezeh Dehghan Tarzjani, Bhaskar Krishnamachari Published: 2025-10-15 Categories: cs.LG, eess.SY arXiv: https://arxiv.org/abs/2510.14137v2 The p-persistent CSMA protocol is central to random-access MAC analysis, but predicting saturation throughput in heterogeneous multi-hop wireless networks remains a hard problem. Simplified models that assume a single, shared interference domain can underestimate throughput by 48-62% in sparse topologies. Exact Markov-chain analyses are accurate but scale exponentially in computation time, making them impractical for large networks. These computational barriers motivate structural machine learning approaches like GNNs for scalable throughput prediction in general network topologies. Yet off-the-shelf GNNs struggle here: a standard GCN yields 63.94% normalized mean absolute error (NMAE) on heterogeneous networks because symmetric normalization conflates a node's direct interference with higher-order, cascading effects that pertain to how interference propagates over the network graph. Building on these insights, we propose the Decoupled Graph Convolutional Network (D-GCN), a novel architecture that explicitly separates processing of a node's own transmission probability from neighbor interference effects. D-GCN replaces mean aggregation with learnable attention, yielding interpretable, per-neighbor contribution weights while capturing complex multihop interference patterns. D-GCN attains 3.3% NMAE, outperforms strong baselines, remains tractable even when exact analytical methods become computationally infeasible, and enables gradient-based network optimization that achieves within 1% of theoretical optima. --- ### A Multimodal Approach to Heritage Preservation in the Context of Climate Change Authors: David Roqui, Adèle Cormier, nistor Grozavu, Ann Bourges Published: 2025-10-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.14136v1 Cultural heritage sites face accelerating degradation due to climate change, yet tradi- tional monitoring relies on unimodal analysis (visual inspection or environmental sen- sors alone) that fails to capture the complex interplay between environmental stres- sors and material deterioration. We propose a lightweight multimodal architecture that fuses sensor data (temperature, humidity) with visual imagery to predict degradation severity at heritage sites. Our approach adapts PerceiverIO with two key innovations: (1) simplified encoders (64D latent space) that prevent overfitting on small datasets (n=37 training samples), and (2) Adaptive Barlow Twins loss that encourages modality complementarity rather than redundancy. On data from Strasbourg Cathedral, our model achieves 76.9% accu- racy, a 43% improvement over standard multimodal architectures (VisualBERT, Trans- former) and 25% over vanilla PerceiverIO. Ablation studies reveal that sensor-only achieves 61.5% while image-only reaches 46.2%, confirming successful multimodal synergy. A systematic hyperparameter study identifies an optimal moderate correlation target (τ =0.3) that balances align- ment and complementarity, achieving 69.2% accuracy compared to other τ values (τ =0.1/0.5/0.7: 53.8%, τ =0.9: 61.5%). This work demonstrates that architectural sim- plicity combined with contrastive regularization enables effective multimodal learning in data-scarce heritage monitoring contexts, providing a foundation for AI-driven con- servation decision support systems. --- ### Formalizing the Safety, Security, and Functional Properties of Agentic AI Systems Authors: Edoardo Allegrini, Ananth Shreekumar, Z. Berkay Celik Published: 2025-10-15 Categories: cs.AI, cs.CR, cs.MA arXiv: https://arxiv.org/abs/2510.14133v2 Agentic AI systems, which leverage multiple autonomous agents and large language models (LLMs), are increasingly used to address complex, multi-step tasks. The safety, security, and functionality of these systems are critical, especially in high-stakes applications. However, the current ecosystem of inter-agent communication is fragmented, with protocols such as the Model Context Protocol (MCP) for tool access and the Agent-to-Agent (A2A) protocol for coordination being analyzed in isolation. This fragmentation creates a semantic gap that prevents the rigorous analysis of system properties and introduces risks such as architectural misalignment and exploitable coordination issues. To address these challenges, we introduce a modeling framework for agentic AI systems composed of two central models: (1) the host agent model formalizes the top-level entity that interacts with the user, decomposes tasks, and orchestrates their execution by leveraging external agents and tools; (2) the task lifecycle model details the states and transitions of individual sub-tasks from creation to completion, providing a fine-grained view of task management and error handling. Together, these models provide a unified semantic framework for reasoning about the behavior of multi-AI agent systems. Grounded in this framework, we define 16 properties for the host agent and 14 for the task lifecycle, categorized into liveness, safety, completeness, and fairness. Expressed in temporal logic, these properties enable formal verification of system behavior, detection of coordination edge cases, and prevention of deadlocks and security vulnerabilities. Through this effort, we introduce the first rigorously grounded, domain-agnostic framework for the analysis, design, and deployment of correct, reliable, and robust agentic AI systems. --- ### Demystifying the Mechanisms Behind Emergent Exploration in Goal-conditioned RL Authors: Mahsa Bastankhah, Grace Liu, Dilip Arumugam, Thomas L. Griffiths, Benjamin Eysenbach Published: 2025-10-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.14129v1 In this work, we take a first step toward elucidating the mechanisms behind emergent exploration in unsupervised reinforcement learning. We study Single-Goal Contrastive Reinforcement Learning (SGCRL), a self-supervised algorithm capable of solving challenging long-horizon goal-reaching tasks without external rewards or curricula. We combine theoretical analysis of the algorithm's objective function with controlled experiments to understand what drives its exploration. We show that SGCRL maximizes implicit rewards shaped by its learned representations. These representations automatically modify the reward landscape to promote exploration before reaching the goal and exploitation thereafter. Our experiments also demonstrate that these exploration dynamics arise from learning low-rank representations of the state space rather than from neural network function approximation. Our improved understanding enables us to adapt SGCRL to perform safety-aware exploration. --- ### Building a Macedonian Recipe Dataset: Collection, Parsing, and Comparative Analysis Authors: Darko Sasanski, Dimitar Peshevski, Riste Stojanov, Dimitar Trajanov Published: 2025-10-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.14128v2 Computational gastronomy increasingly relies on diverse, high-quality recipe datasets to capture regional culinary traditions. Although there are large-scale collections for major languages, Macedonian recipes remain under-represented in digital research. In this work, we present the first systematic effort to construct a Macedonian recipe dataset through web scraping and structured parsing. We address challenges in processing heterogeneous ingredient descriptions, including unit, quantity, and descriptor normalization. An exploratory analysis of ingredient frequency and co-occurrence patterns, using measures such as Pointwise Mutual Information and Lift score, highlights distinctive ingredient combinations that characterize Macedonian cuisine. The resulting dataset contributes a new resource for studying food culture in underrepresented languages and offers insights into the unique patterns of Macedonian culinary tradition. --- ### Neural Network-enabled Domain-consistent Robust Optimisation for Global CO$_2$ Reduction Potential of Gas Power Plants Authors: Waqar Muhammad Ashraf, Talha Ansar, Abdulelah S. Alshehri, Peipei Chen, Ramit Debnath, Vivek Dua Published: 2025-10-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.14125v1 We introduce a neural network-driven robust optimisation framework that integrates data-driven domain as a constraint into the nonlinear programming technique, addressing the overlooked issue of domain-inconsistent solutions arising from the interaction of parametrised neural network models with optimisation solvers. Applied to a 1180 MW capacity combined cycle gas power plant, our framework delivers domain-consistent robust optimal solutions that achieve a verified 0.76 percentage point mean improvement in energy efficiency. For the first time, scaling this efficiency gain to the global fleet of gas power plants, we estimate an annual 26 Mt reduction potential in CO$_2$ (with 10.6 Mt in Asia, 9.0 Mt in the Americas, and 4.5 Mt in Europe). These results underscore the synergetic role of machine learning in delivering near-term, scalable decarbonisation pathways for global climate action. --- ### Laser Fault Injection in Memristor-Based Accelerators for AI/ML and Neuromorphic Computing Authors: Muhammad Faheemur Rahman, Wayne Burleson Published: 2025-10-15 Categories: cs.ET, cs.NE, eess.SY arXiv: https://arxiv.org/abs/2510.14120v1 Memristive crossbar arrays (MCA) are emerging as efficient building blocks for in-memory computing and neuromorphic hardware due to their high density and parallel analog matrix-vector multiplication capabilities. However, the physical properties of their nonvolatile memory elements introduce new attack surfaces, particularly under fault injection scenarios. This work explores Laser Fault Injection as a means of inducing analog perturbations in MCA-based architectures. We present a detailed threat model in which adversaries target memristive cells to subtly alter their physical properties or outputs using laser beams. Through HSPICE simulations of a large MCA on 45 nm CMOS tech. node, we show how laser-induced photocurrent manifests in output current distributions, enabling differential fault analysis to infer internal weights with up to 99.7% accuracy, replicate the model, and compromise computational integrity through targeted weight alterations by approximately 143%. --- ### David vs. Goliath: A comparative study of different-sized LLMs for code generation in the domain of automotive scenario generation Authors: Philipp Bauerfeind, Amir Salarpour, David Fernandez, Pedram MohajerAnsari, Johannes Reschke, Mert D. Pesé Published: 2025-10-15 Categories: cs.SE, cs.LG arXiv: https://arxiv.org/abs/2510.14115v1 Scenario simulation is central to testing autonomous driving systems. Scenic, a domain-specific language (DSL) for CARLA, enables precise and reproducible scenarios, but NL-to-Scenic generation with large language models (LLMs) suffers from scarce data, limited reproducibility, and inconsistent metrics. We introduce NL2Scenic, an open dataset and framework with 146 NL/Scenic pairs, a difficulty-stratified 30-case test split, an Example Retriever, and 14 prompting variants (ZS, FS, CoT, SP, MoT). We evaluate 13 models: four proprietary (GPT-4o, GPT-5, Claude-Sonnet-4, Gemini-2.5-pro) and nine open-source code models (Qwen2.5Coder 0.5B-32B; CodeLlama 7B/13B/34B), using text metrics (BLEU, ChrF, EDIT-SIM, CrystalBLEU) and execution metrics (compilation and generation), and compare them with an expert study (n=11). EDIT-SIM correlates best with human judgments; we also propose EDIT-COMP (F1 of EDIT-SIM and compilation) as a robust dataset-level proxy that improves ranking fidelity. GPT-4o performs best overall, while Qwen2.5Coder-14B reaches about 88 percent of its expert score on local hardware. Retrieval-augmented prompting, Few-Shot with Example Retriever (FSER), consistently boosts smaller models, and scaling shows diminishing returns beyond mid-size, with Qwen2.5Coder outperforming CodeLlama at comparable scales. NL2Scenic and EDIT-COMP offer a standardized, reproducible basis for evaluating Scenic code generation and indicate that mid-size open-source models are practical, cost-effective options for autonomous-driving scenario programming. --- ### Briding Diffusion Posterior Sampling and Monte Carlo methods: a survey Authors: Yazid Janati, Alain Durmus, Jimmy Olsson, Eric Moulines Published: 2025-10-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.14114v1 Diffusion models enable the synthesis of highly accurate samples from complex distributions and have become foundational in generative modeling. Recently, they have demonstrated significant potential for solving Bayesian inverse problems by serving as priors. This review offers a comprehensive overview of current methods that leverage \emph{pre-trained} diffusion models alongside Monte Carlo methods to address Bayesian inverse problems without requiring additional training. We show that these methods primarily employ a \emph{twisting} mechanism for the intermediate distributions within the diffusion process, guiding the simulations toward the posterior distribution. We describe how various Monte Carlo methods are then used to aid in sampling from these twisted distributions. --- ### Toward Cybersecurity-Expert Small Language Models Authors: Matan Levi, Daniel Ohayon, Ariel Blobstein, Ravid Sagi, Ian Molloy, Yair Allouche Published: 2025-10-15 Categories: cs.CL, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2510.14113v2 Large language models (LLMs) are transforming everyday applications, yet deployment in cybersecurity lags due to a lack of high-quality, domain-specific models and training datasets. To address this gap, we present CyberPal 2.0, a family of cybersecurity-expert small language models (SLMs) ranging from 4B-20B parameters. To train CyberPal 2.0, we generate an enriched chain-of-thought cybersecurity instruction dataset built with our data enrichment and formatting pipeline, SecKnowledge 2.0, which integrates expert-in-the-loop steering of reasoning formats alongside LLM-driven multi-step grounding, yielding higher-fidelity, task-grounded reasoning traces for security tasks. Across diverse cybersecurity benchmarks, CyberPal 2.0 consistently outperforms its baselines and matches or surpasses various open and closed-source frontier models, while remaining a fraction of their size. On core cyber threat intelligence knowledge tasks, our models outperform almost all tested frontier models, ranking second only to Sec-Gemini v1. On core threat-investigation tasks, such as correlating vulnerabilities and bug tickets with weaknesses, our best 20B-parameter model outperforms GPT-4o, o1, o3-mini, and Sec-Gemini v1, ranking first, while our smallest 4B-parameter model ranks second. --- ### STEMS: Spatial-Temporal Enhanced Safe Multi-Agent Coordination for Building Energy Management Authors: Huiliang Zhang, Di Wu, Arnaud Zinflou, Benoit Boulet Published: 2025-10-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.14112v2 Building energy management is essential for achieving carbon reduction goals, improving occupant comfort, and reducing energy costs. Coordinated building energy management faces critical challenges in exploiting spatial-temporal dependencies while ensuring operational safety across multi-building systems. Current multi-building energy systems face three key challenges: insufficient spatial-temporal information exploitation, lack of rigorous safety guarantees, and system complexity. This paper proposes Spatial-Temporal Enhanced Safe Multi-Agent Coordination (STEMS), a novel safety-constrained multi-agent reinforcement learning framework for coordinated building energy management. STEMS integrates two core components: (1) a spatial-temporal graph representation learning framework using a GCN-Transformer fusion architecture to capture inter-building relationships and temporal patterns, and (2) a safety-constrained multi-agent RL algorithm incorporating Control Barrier Functions to provide mathematical safety guarantees. Extensive experiments on real-world building datasets demonstrate STEMS's superior performance over existing methods, showing that STEMS achieves 21% cost reduction, 18% emission reduction, and dramatically reduces safety violations from 35.1% to 5.6% while maintaining optimal comfort with only 0.13 discomfort proportion. The framework also demonstrates strong robustness during extreme weather conditions and maintains effectiveness across different building types. --- ### DROID: Dual Representation for Out-of-Scope Intent Detection Authors: Wael Rashwan, Hossam M. Zawbaa, Sourav Dutta, Haytham Assem Published: 2025-10-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.14110v1 Detecting out-of-scope (OOS) user utterances remains a key challenge in task-oriented dialogue systems and, more broadly, in open-set intent recognition. Existing approaches often depend on strong distributional assumptions or auxiliary calibration modules. We present DROID (Dual Representation for Out-of-Scope Intent Detection), a compact end-to-end framework that combines two complementary encoders -- the Universal Sentence Encoder (USE) for broad semantic generalization and a domain-adapted Transformer-based Denoising Autoencoder (TSDAE) for domain-specific contextual distinctions. Their fused representations are processed by a lightweight branched classifier with a single calibrated threshold that separates in-domain and OOS intents without post-hoc scoring. To enhance boundary learning under limited supervision, DROID incorporates both synthetic and open-domain outlier augmentation. Despite using only 1.5M trainable parameters, DROID consistently outperforms recent state-of-the-art baselines across multiple intent benchmarks, achieving macro-F1 improvements of 6--15% for known and 8--20% for OOS intents, with the most significant gains in low-resource settings. These results demonstrate that dual-encoder representations with simple calibration can yield robust, scalable, and reliable OOS detection for neural dialogue systems. --- ### Generating Fair Consensus Statements with Social Choice on Token-Level MDPs Authors: Carter Blair, Kate Larson Published: 2025-10-15 Categories: cs.AI, cs.CL, cs.GT arXiv: https://arxiv.org/abs/2510.14106v1 Current frameworks for consensus statement generation with large language models lack the inherent structure needed to provide provable fairness guarantees when aggregating diverse free-form opinions. We model the task as a multi-objective, token-level Markov Decision Process (MDP), where each objective corresponds to an agent's preference. Token-level rewards for each agent are derived from their policy (e.g., a personalized language model). This approach utilizes the finding that such policies implicitly define optimal Q-functions, providing a principled way to quantify rewards at each generation step without a value function (Rafailov et al., 2024). This MDP formulation creates a formal structure amenable to analysis using principles from social choice theory. We propose two approaches grounded in social choice theory. First, we propose a stochastic generation policy guaranteed to be in the ex-ante core, extending core stability concepts from voting theory to text generation. This policy is derived from an underlying distribution over complete statements that maximizes proportional fairness (Nash Welfare). Second, for generating a single statement, we target the maximization of egalitarian welfare using search algorithms within the MDP framework. Empirically, experiments using language models to instantiate agent policies show that search guided by the egalitarian objective generates consensus statements with improved worst-case agent alignment compared to baseline methods, including the Habermas Machine (Tessler et al., 2024). --- ### Extracting latent representations from X-ray spectra. Classification, regression, and accretion signatures of Chandra sources Authors: Nicolò Oreste Pinciroli Vago, Juan Rafael Martínez-Galarza, Roberta Amato Published: 2025-10-15 Categories: astro-ph.IM, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.14102v2 Spectral signatures are crucial in the era of large X-ray surveys. Automatic machine learning methods have proven useful in this respect, but so far they have not been applied to large spectral datasets, such as the Chandra Source Catalog (CSC). This work aims to develop a compact and physically meaningful representation of Chandra X-ray spectra using deep learning. To verify that the learned representation captures relevant information, we evaluate it through classification, regression, and interpretability analyses, and measure the mutual information between spectral and time-domain properties of these sources, aiding in the future identification of transient events. We use a transformer-based autoencoder to compress X-ray spectra into representations in an 8-dimensional latent space. Astrophysical source types and physical summary statistics are compiled from external catalogs. We evaluate the learned representation in terms of spectral reconstruction accuracy, clustering performance on 8 known astrophysical source classes, and correlation with physical quantities such as hardness ratios and hydrogen column densities ($N_H$). Upon reconstruction, clustering in the latent space yields a balanced classification accuracy of $\sim$40% across the 8 source classes, increasing to $\sim$69% when restricted to AGNs and stellar-mass compact objects exclusively. Moreover, latent features correlate with spectral and temporal properties, suggesting that the compressed representation captures physically relevant information. Features learned directly from X-ray spectra capture relevant physical information as effectively as human-extracted features that require additional computations. They can be used for both classification and regression in large surveys, and also share mutual information with time-domain properties. The method can be adapted to existing and upcoming X-ray catalogs. --- ### Near-Optimal Regret-Queue Length Tradeoff in Online Learning for Two-Sided Markets Authors: Zixian Yang, Sushil Mahavir Varma, Lei Ying Published: 2025-10-15 Categories: cs.LG, cs.GT, math.OC, math.PR arXiv: https://arxiv.org/abs/2510.14097v1 We study a two-sided market, wherein, price-sensitive heterogeneous customers and servers arrive and join their respective queues. A compatible customer-server pair can then be matched by the platform, at which point, they leave the system. Our objective is to design pricing and matching algorithms that maximize the platform's profit, while maintaining reasonable queue lengths. As the demand and supply curves governing the price-dependent arrival rates may not be known in practice, we design a novel online-learning-based pricing policy and establish its near-optimality. In particular, we prove a tradeoff among three performance metrics: $\tilde{O}(T^{1-γ})$ regret, $\tilde{O}(T^{γ/2})$ average queue length, and $\tilde{O}(T^γ)$ maximum queue length for $γ\in (0, 1/6)$, significantly improving over existing results (1). Moreover, barring the permissible range of $γ$, we show that this trade-off between regret and average queue length is optimal up to logarithmic factors under a class of policies, matching the optimal one as in (2) which assumes the demand and supply curves to be known. Our proposed policy has two noteworthy features: a dynamic component that optimizes the tradeoff between low regret and small queue lengths; and a probabilistic component that resolves the tension between obtaining useful samples for fast learning and maintaining small queue lengths. --- ### TENDE: Transfer Entropy Neural Diffusion Estimation Authors: Simon Pedro Galeano Munoz, Mustapha Bounoua, Giulio Franzese, Pietro Michiardi, Maurizio Filippone Published: 2025-10-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.14096v3 Transfer entropy measures directed information flow in time series, and it has become a fundamental quantity in applications spanning neuroscience, finance, and complex systems analysis. However, existing estimation methods suffer from the curse of dimensionality, require restrictive distributional assumptions, or need exponentially large datasets for reliable convergence. We address these limitations in the literature by proposing TENDE (Transfer Entropy Neural Diffusion Estimation), a novel approach that leverages score-based diffusion models to estimate transfer entropy through conditional mutual information. By learning score functions of the relevant conditional distributions, TENDE provides flexible, scalable estimation while making minimal assumptions about the underlying data-generating process. We demonstrate superior accuracy and robustness compared to existing neural estimators and other state-of-the-art approaches across synthetic benchmarks and real data. ---